To see the other types of publications on this topic, follow the link: Smart Assistant.
Dissertations / Theses on the topic 'Smart Assistant'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 dissertations / theses for your research on the topic 'Smart Assistant.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse dissertations / theses on a wide variety of disciplines and organise your bibliography correctly.
1
Dhang, Prakriti, and Manaswini Kolluru. "Interaction with Smart Assistant." Thesis, Malmö universitet, Fakulteten för teknik och samhälle (TS), 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:mau:diva-20337.
Full textAbstract:
Newer technologies are being developed all the time in order to help us in our daily tasks. Smart Assistant (SA) is one such broad category of devices which, when instructed through speech or command, perform certain tasks. Most SAs have two primary tasks: identify the user, and perform the taskcommunicated by the user. The task of identification can be achieved in severalways and one such method involves face recognition interface integrated within SA. Further interaction with the user is achieved via either a touch screen or a speech-based interface integrated within SA. Since the primary objective of a SA involves interaction with an individual user, it is necessary to identify users' concerns related to the usability of SA.In this thesis, the goal is to perform a usability study of Smart Assistant(SA) in the context of providing assistance in scheduling meetings at the workplace. Adopting a qualitative approach and we performed the usability study by designing a questionnaire to document public perception of new technologies like a smart assistant. We performed an online survey and collected responses from a section of the population. We also performed a similar survey with employees at Cybercom who have experience in interacting with the SAbeing developed in their company, and which is meant for providing assistance in scheduling meetings.In the process, we also provide relevant background literatureon human-computer interaction to contextualize the results of our survey. Themain outcome of this work is a list of guidelines to be followed for developing asocially interactive speech-based SA.The results of our survey indicate that there are several privacy and security related concerns that users have when using a face recognition interface and speech-based interaction. Although some of the concerns require technological advancements, a few of the concerns can be addressed by adopting certain suggested strategies.
2
Kuang, Hao. "SSA: Smart Surveillance Assistant for Mobile Devices." Thesis, Université d'Ottawa / University of Ottawa, 2015. http://hdl.handle.net/10393/32535.
Full textAbstract:
Over the past few years, the capability of smart devices has grown incessantly, and is showing no sign of slowing down. Along with the decreasing cost of manufacturing high definition surveillance cameras, this has led to the increased ease and convenience of installing surveillance cameras at or in private places. Various applications focus on home surveillance, however simply sending a high definition image does not satisfy all of the users’ needs. On a site that is monitored by a surveillance camera, the high-resolution surveillance camera streams its video to a user's handheld device. Unfortunately, such devices are unable to make use of the high-resolution video due to their limited display size and bandwidth, and the visual range is also a key problem.
In this thesis, we propose a method to assist the mobile operator of the surveillance camera in focusing on sensitive regions of the videos.
Our system automatically identifies relevant regions, combined with foreground detection and human body detection, which is referred to as object detection. A sensitivity map that represents those informative regions returned by the detection methods is accumulated over number of frames. It shows the collection of the sensitivity data in the video over a period of time. We then introduce a zoom strategy to ensure that the operator is able to see the fine details in these areas, while maintaining contextual knowledge.
Regions of interest are identified using foreground detection as well as body detection.
In order to accelerate the processing speed, we propose two optimization methods.
The efficacy of the proposed methods is demonstrated through a user study, the results of which show that this approach is more successful than three comparable approaches used to get an understanding of the activities in a surveillance scene while maintaining context.
3
Krishnamoorthy, Shyam 1978. "Minerva : a smart video assistant for the kitchen." Thesis, Massachusetts Institute of Technology, 2001. http://hdl.handle.net/1721.1/62041.
Full textAbstract:
Thesis (S.M.)--Massachusetts Institute of Technology, School of Architecture and Planning, Program in Media Arts and Sciences, 2001.<br>Includes bibliographical references (p. 63-65).<br>Minerva, a video assistant for cooking, is controlled by the actions of the user. Specifically, the content and format of the video shown on Minerva's display are decided by the food that one places on the kitchen counter. Thus, it aims to develop new ways of interactivity and control for media that solve the problem of content choice in an innovative and useful manner. In parallel, it is a study of the applicability of a generalized image-matching algorithm [1] [21 and into reflecting a program's awareness of the context of its execution in its behavior. Minerva is, for the user, a personalized kitchen assistant, a culinary knowledge-base and a cooking tutor, all built into it by design rather than by accident. Minerva tackles problems faced by current computer systems, including trade-offs between automatic program execution and user control, access mechanisms for media from large databases, retrieval techniques for recipes and cooking information, and embedding computing systems in the home environment with useful features without compromising on non-obtrusiveness. The system has a camera that looks at the kitchen counter and a recognition engine that analyses the ingredient placed under the camera. Together, they form part of the input that decides the choice for the content of the media displayed. Contextual variables, including the user's identity and preferences form the other part of this input. A database look-up program that returns the location of the video and recipe image appropriate for these input forms the retrieval sub-system and a player for the cooking video retrieved displays the media chosen. Automatic control for the media is enabled wherever possible, allowing for prior information about the user to affect the choice and format of the cooking video displayed. This thesis describes the motivations, concept and implementation of Minerva, ending with an evaluation of its performance and impact, as well as directions for future work.<br>by Shyam Krishnamoorthy.<br>S.M.
4
Di, Tuccio Gianluca. "Smart Hospital Assistant: studio ed implementazione di un assistente vocale ospedaliero tramite tecnologie semantiche." Bachelor's thesis, Alma Mater Studiorum - Università di Bologna, 2021. http://amslaurea.unibo.it/24006/.
Full textAbstract:
In questo elaborato è stata proposta l’implementazione di un assistente vocale ospedaliero, denominato Mario, fondato su tecnologie semantiche. La sua realizzazione è stata possibile grazie alla creazione di un’ontologia e all’implementazione dell’assistente vocale basato sul linguaggio Python. Per l’inserimento dei dati diagnostici è stato realizzato un software usato sia per la registrazione della parte anagrafica di operatori sanitari e pazienti, sia per l’inserimento o la modifica dei dati di una cartella clinica elettronica. Verranno discussi i vantaggi di queste tecnologie, tra cui l’interoperabilità tra sistemi diversi ed il poter realizzare queries personalizzate ad hoc per l’assistente vocale.
5
ANDERSSON, PHILIP, and EDVIN KUGELBERG. "Home Assistant Navigation - Smart Optical and Laser Orientation : H.A.N.S.O.L.O." Thesis, KTH, Mekatronik, 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-233139.
Full textAbstract:
With the market for autonomous home assistants steadily growing, reasons for the development of new ways of communicating with the robot assistants have emerged. This thesis aims to develop a system wherein a human can draw instructions for the robot to interpret and follow or perform. An autonomous robot based on an Arduino board was built. Software for pattern recognition through a camera was developed and tested for precision and efficiency. The device was able to read a command drawn on a sheet of paper by the user, analyze it to extract a route for the four wheeled robot to follow and transmit operations wirelessly via Bluetooth. The intent was not to create a marketable product, but rather to build a proof of concept for a viable alternative to existing communication systems for home assistants. The resulting product was able to interact with a human operator, ask it to circle an area to sweep and successfully do as commanded. When the camera captured what had been drawn the system needed 70 seconds to sweep an area of 0.8m2. Errors for forward motion and rotation were calculated to 2% - 3.5% and 0.98% - 0.99% respectively.<br>Med en växande marknad för hemnära robotar finns utrymme för utveckling av ett nytt sätt att kommuniceramed robotassistenter. Denna avhandling kommer behandla framställandet av ett system där en användare har möjligheten att, med grafiska kommandon, instruera vad den vill att roboten ska utföra. En autonom Arduino-baserad robot byggdes och mjukvara för mönsterigen känning med en kamera utveckladesoch testades för precision och tidseffektivitet. Enheten kunde läsa av en instruktion som användare ritat på ett papper, analysera detta och extrahera en rutt för roboten att följa. Kommunikationen mellan kamera enheten och roboten skedde trådlöst via Bluetooth. Syftet var inte att bygga en kommersiellt färdig produkt, avsikten varatt konstruera ett system som skulle kunna visas upp somett alternativ till redan existerande kommunikationssystem för hemnära robotar. Resultatet blev en produkt som kunde interagera meden användare, be den ringa in en area att svepa över och med framgång utföra detta. Efter att kameran tagit bild över den ritade instruktionen behövde systemet totalt 70 sekunder för att utföra det och täcka en area på 0,8m2. Felmarginaler för körning rakt fram och rotation uppmättestill 2% - 3,5% respektive 0,98% - 0,99%.
6
Tarabelli, Jari. "ViVi: Progettazione e realizzazione di un voice powered retail assistant nella realtà virtuale." Bachelor's thesis, Alma Mater Studiorum - Università di Bologna, 2019. http://amslaurea.unibo.it/19635/.
Full textAbstract:
La realtà virtuale, negli ultimi anni, ha riscosso un crescente successo dovuto alla diminuzione dei costi, e all'aumentare della disponibilità di applicazioni in qualsiasi campo, dall'intrattenimento all'istruzione.
In particolare nell'ambito in oggetto, le applicazioni di shopping immersive sono ancora nello stato sperimentale, e i grandi nomi del settore si stanno preparando all'ingresso della VR nel mercato mainstream.
Un'altra tecnologia che ha raggiunto una discreta utenza e che ha guadagnato una fetta molto ampia di mercato, è lo Smart Assistant.
L'impiego di un assistente virtuale, con cui si interagisce attraverso la voce, che riconosce l'utente, esegue comandi e raccoglie informazioni sulla base delle preferenze dell'utente, è entrato nel quotidiano: molte realtà hanno infatti deciso di integrarlo tra i loro servizi.
Lo scopo di questa tesi è di cercare di migliorare diversi aspetti dell'esperienza utente, applicando un approccio che mira ad unire le due tecnologie. Si vedrà come, sfruttando le potenzialità date dall'esperienza d'uso dell'assistente (quali semplicità d'uso e gestione/reperimento delle informazioni), e quelle visive della VR (espressività visiva, immersione ed engagement), sia possibile lasciare più libertà creativa in molti aspetti del retailing ed al contempo alleggerire il contesto visivo, delegando funzioni che normalmente sarebbero a carico dell'interfaccia, direttamente all'assistant.
L'utente verrà agevolato nell'esperienza, come già abituato nei negozi fisici, dove il personale è formato per essere l'addetto a chiarimenti, assistenza e sopratutto suggerimenti.
Nello svolgimento dello studio verranno presentati ideazione, sviluppo, test con partecipanti, e relativa valutazione dell'approccio proposto.
7
Thakur, Nirmalya. "Framework for a Context Aware Adaptive Intelligent Assistant for Activities of Daily Living." University of Cincinnati / OhioLINK, 2019. http://rave.ohiolink.edu/etdc/view?acc_num=ucin1553528536685873.
Full text
8
Vizcarra, Christopher, Gabriel Medina, and Alfredo Barrientos. "Implementation of a Fashion Virtual Assistant with the Use of a Kinect v2 Camera and Image Processing." Universidad Peruana de Ciencias Aplicadas (UPC), 2021. http://hdl.handle.net/10757/653792.
Full textAbstract:
El texto completo de este trabajo no está disponible en el Repositorio Académico UPC por restricciones de la casa editorial donde ha sido publicado.<br>This article is about the problem and development of a fashion virtual assistant proposed by using a Kinect v2 camera and image processing, for fashion retail stores. It comes up mainly as a response to the inability of providing unique experiences during the shopping process through the use of diverse devices. Because of this, similar virtual assistant solutions, oriented to provide clothing recommendations, were analyzed to be able to provide software that could give a more personalized suggestion for the users based on their physical characteristics.<br>Revisión por pares
9
Kallab, Karel. "Návrh mobilní aplikace Yourcut a její nasazení." Master's thesis, Vysoké učení technické v Brně. Fakulta podnikatelská, 2021. http://www.nusl.cz/ntk/nusl-444617.
Full textAbstract:
The master's thesis focuses on the creation of the Yourcut application for streamlining the services of barbering. The main goal of this work is to create an application and deploy it in a smart mirror, built directly to the needs of the application. The whole work can be divided into three parts. In the first part, the reader gets acquainted with all the technological prerequisites that need to be known in order to understand the whole work. The second part describes and analyzes. It summarizes the problems associated with creating an application and all the technical and technological prerequisites for the application to be created correctly. In the last part there is a description of the application creating, along with the construction of a smart mirror and their deployment.
10
Pellegrini, Lorenzo. "Integrazione Architetturale di Personal Assistant Agent basati su modello BDI con Servizi Cognitivi: Un Caso di Studio in Ambito Ospedaliero." Master's thesis, Alma Mater Studiorum - Università di Bologna, 2018. http://amslaurea.unibo.it/15625/.
Full textAbstract:
L’ambito sanitario è oggetto di cambiamenti legati alla pervasiva adozione di tecnologie informatiche in grado di supportare i processi legati alla gestione della sanità. Su questa strada vanno le iniziative inerenti agli Smart Hospital, che prevedono una informatizzazione degli ospedali e dei sistemi per la loro gestione. Questa pionieristica visione prevede che vengano messe in campo le più disparate tecniche informatiche con l’obiettivo di supportare l’operato del personale sanitario, specialmente per quanto concerne il processo decisionale e la gestione del flusso di lavoro. La tesi si inserisce nel contesto di Trauma Tracker, un progetto di Smart Hospital nato dalla collaborazione tra il Trauma Center dell’ospedale Maurizio Bufalini e la facoltà di Ingegneria e Scienze Informatiche dell’Università di Bologna, sede di Cesena. Scopo del progetto è quello di sviluppare un Personal Assistant Agent in grado di supportare i medici durante la gestione dei traumi. Tra di queste è presente la generazione di avvisi e suggerimenti il cui obiettivo è quello di guidare l’operato del Trauma Team richiamandone l’attenzione qualora venissero individuate situazioni anomale oppure opportunità circa azioni che è possibile intraprendere. In Trauma Tracker è attualmente presente un sistema per la generazione di avvisi basata su regole. Questo presenta una espressività limitata per cui si intende ampliare le capacità di ragionamento dell’Assistant al fine di considerare informazioni storiche mantenute nell’archivio delle pratiche. Tra le tecniche considerate a tal fine figurano il Machine Learning e il Cognitive Computing. L'obiettivo della tesi è quello di identificare e sviluppare un'estensione architetturale del Trauma Assistant Agent (TAA) in modo che possa integrare la generazione di avvisi basati su regole definite dagli esperti del dominio con la generazione di suggerimenti elaborati e forniti in modo asincrono da servizi cognitivi in rete, in continua interazione con il TAA.
11
Zomer, Manuel. "Shaping proactivity : Designing interactions with proactive ambient artefacts." Thesis, Malmö universitet, Institutionen för konst, kultur och kommunikation (K3), 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:mau:diva-43699.
Full textAbstract:
This thesis aims to explore how to shape proactive interactions between ambient artefacts and humans. Where ambient artefacts are represented by smart personal assistants and interactive tabletop robots. The conducted research is of explorative nature, relying on a critical and speculative design approach. Key aspects and their influence in shaping proactivity were identified. Insights upon different means of feedback, namely coloured light, motion and sound are discussed in connection with the spatial placement of a proactive artefact and the provided user experience. The notion of gaining versus losing control to an artefact is presented and a reflection on the concept of annoyance as a design material. A proactive system featuring a collection of physical and digital interactive artefacts was created as part of this research. Insights and conclusions are based on conducted interviews after user-testing those artefacts.
12
Vizcarra, Casas Christopher Alonso, and Quevedo Gabriel Alejandro Medina. "Implementación de un asistente virtual de modas con el uso de una cámara Kinect v2 y procesamiento de imágenes." Bachelor's thesis, Universidad Peruana de Ciencias Aplicadas (UPC), 2020. http://hdl.handle.net/10757/653659.
Full textAbstract:
Este artículo trata sobre la problemática y el desarrollo de un asistente virtual de moda propuesto mediante el uso de una cámara Kinect v2 y procesamiento de imágenes, para tiendas minoristas de moda. Surge principalmente como una respuesta a la incapacidad de proporcionar experiencias únicas durante el proceso de compra mediante el uso de diversos dispositivos. Debido a esto, se analizaron soluciones de asistente virtual similares orientadas a proporcionar recomendaciones de vestimenta para poder proporcionar un software que podría dar una sugerencia más personalizada para los usuarios basándose en sus características físicas. La validación del modelo se realizará a través de la experiencia de un grupo de usuarios en el momento del uso del asistente virtual y expertos en el área de evaluación de moda.<br>This article is about the problematic and development of a fashion virtual assistant proposed by using a Kinect v2 camera and image processing, for fashion retail stores. It comes up mainly as a response to the inability of providing unique experiences during the shopping process through the use of diverse devices. Because of this, similar virtual assistant solutions oriented to provide clothing recommendations were analysed to be able to provide a software that could give a more personalized suggestion for the users basing in their physical characteristics. The model validation will be done through the experience of a group of users at the moment of use of the virtual assistant and experts in the fashion assessment area.<br>Trabajo de investigación
13
Rasch, Katharina. "Smart assistants for smart homes." Doctoral thesis, KTH, Programvaruteknik och Datorsystem, SCS, 2013. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-129171.
Full textAbstract:
The smarter homes of tomorrow promise to increase comfort, aid elderly and disabled people, and help inhabitants save energy. Unfortunately, smart homes today are far from this vision – people who already live in such a home struggle with complicated user interfaces, inflexible home configurations, and difficult installation procedures. Under these circumstances, smart homes are not ready for mass adoption. This dissertation addresses these issues by proposing two smart assistants for smart homes. The first assistant is a recommender system that suggests useful services (i.e actions that the home can perform for the user). The recommended services are fitted to the user’s current situation, habits, and preferences. With these recommendations it is possible to build much simpler user interfaces that highlight the most interesting choices currently available. Configuration becomes much more flexible: since the recommender system automatically learns user habits, user routines no longer have to be manually described. Evaluations with two smart home datasets show that the correct service is included in the top five recommendations in 90% of all cases. The second assistant addresses the difficult installation procedures. The unique feature of this assistant is that it removes the need for manually describing device functionalities (such descriptions are needed by the recommender system). Instead, users can simply plug in a new device, begin using it, and let the installation assistant identify what the device is doing. The installation assistant has minimal requirements for manufacturers of smart home devices and was successfully integrated with an existing smart home. Evaluations performed with this smart home show that the assistant can quickly and reliably learn device functionalities.<br><p>QC 20130924</p>
14
Hashemi, Arshan. "Fingerprinting the Smart Home: Detection of Smart Assistants Based on Network Activity." DigitalCommons@CalPoly, 2018. https://digitalcommons.calpoly.edu/theses/1958.
Full textAbstract:
As the concept of the Smart Home is being embraced globally, IoT devices such as the Amazon Echo, Google Home, and Nest Thermostat are becoming a part of more and more households. In the data-driven world we live in today, internet service providers (ISPs) and companies are collecting large amounts of data and using it to learn about their customers. As a result, it is becoming increasingly important to understand what information ISPs are capable of collecting. IoT devices in particular exhibit distinct behavior patterns and specific functionality which make them especially likely to reveal sensitive information. Collection of this data provides valuable information and can have some serious privacy implications. In this work I present an approach to fingerprinting IoT devices behind private networks while only examining last-mile internet traffic . Not only does this attack only rely on traffic that would be available to an ISP, it does not require changes to existing infrastructure. Further, it does not rely on packet contents, and therefore works despite encryption. Using a database of 64 million packets logged over 15 weeks I was able to train machine learning models to classify the Amazon Echo Dot, Amazon Echo Show, Eufy Genie, and Google Home consistently. This approach combines unsupervised and supervised learning and achieves a precision of 99.95\%, equating to one false positive per 2,000 predictions. Finally, I discuss the implication of identifying devices within a home.
15
Carohl, Qvist Amanda. "IOT inom hemautomation : Jämförande av open-source kontrollers." Thesis, Högskolan i Skövde, Institutionen för informationsteknologi, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:his:diva-18922.
Full textAbstract:
Internet Of Things (IoT) och hemautomation innebär möjligheten att koppla upp diverse enheter i ett hem gentemot internet, som därefter har som mål att underlätta och göra konsumenters vardag mer bekvämt. Hemautomation kan exempelvis handla om att låsa dörrar och tända lampor från en enda enhet (kontrollern), vilket underlättar då konsumenten inte behöver gå till vardera enhet för att utföra önskade aktiviteter. Kontrollers är den del av ett IoT-system inom hemautomation som agerar gränssnittet mellan konsumenten och enheterna.Open-source erbjuder konsumenter ett mer fritt nyttjande av produkter pga. dess öppna källkod. Många problem och frågor som uppstår i samband med dessa produkter härstammar inom området av säkerhet, samt vad som skiljer produkterna åt avseende säkerhet.Denna studie har samlat ihop sex open-source kontrollers och genomfört en jämförelse för att identifiera vilka kontrollers som uppnår säkerhet avseende konfidentialitet, integritet och tillgänglighet. Detta har utförts genom att identifiera vilka värden som förekommer i tidigare artiklar där säkerheten utvärderas för IoT och hemautomation, och för kontrollers.Studien kopplar ihop identifierade värden med CIA modellen, vilket står för confidentiality, integrity och availability (konfidentialitet, integritet och tillgänglighet). I samband med CIA modellen presenteras ett resultat där studiens aktuella kontrollers visar till vilken nivå de upprätthåller CIA modellen, baserat på det identifierade värden som fastställts. De kontrollers som förekommer i studien är Home Genie, OpenHAB, Home Assistant, Domoticz, Calaos och Pimatic.Studiens resultat erhålls via en litterär undersökning av 25 tidigare studier samt 12st tillkommande tekniska dokumentationer och forum för samtliga tillhörande kontrollers. Samtliga studier har blivit hämtade från databaserna Google Scholar, IEEE Xplore och ACM Digital Library och har därefter blivit analyserade och tematiskt kodade för vidare information. Totalt har studiens material genomgått urval i fem steg för att garantera relevant material som stämmer överens med studiens kriterier och mål för innehåll. Studiens resultat presenterar en ögonblicksbild som ger kunskap om jämförda kontrollers, specifikt i samband med CIA modellen, vilket belyser produkterna i samband för området av säkerhet avseende konfidentialitet, integritet och tillgänglighet.<br>Internet of Things (IoT) and home automation means the opportunity to connect various devices in a home to the Internet, which has the goal of facilitating and making consumers’ everyday lives more comfortable. For example, home automation could be about locking doors and lighting lamps from a single device (the controller), which may make it easier for the consumer since the consumer does not have to go to each device to perform the desired activity. Controllers are the part of a home automation IoT-system that acts as an interface between the consumer and the devices.Open-source offers consumers a freer use of products, due to its open-source code. Many problems and issues that arise in connection with these products originate in the field of security, as well as what distinguishes the products in terms of security.This study has collected six open-source controllers and conducted a comparison to identify which controllers achieve security regarding confidentiality, integrity and availability. This has been done by identifying the values that appear in previous articles where security is evaluated for IoT and home automation, and controllers.This study links identified values with the CIA model, which stands for confidentiality, integrity, and availability. In accordance with the CIA model, a result is presented where the study’s current controllers show to what level they maintain the CIA model, based on the identifies values established. The controllers that appears in this study are Home Genie, OpenHAB, Home Assistant, Domoticz, Calaos, and Pimatic.This study’s results are obtained through a literary study of 25 studies, and 12 additional technical documentations and information through forums for all the associated controllers. All studies have been retrieved from the Google Scholar database, IEEE Xplore, and ACM Digital Library, and subsequently analyzed and thematically coded for further information. In total, the material of this study has been selected in five steps to ensure relevant material that meets this study’s criteria and objectives for content. This study’s results present an overview that provides knowledge about compared controllers, specifically in connection with the CIA model which highlights the products in the field of security, regarding confidentiality, integrity, and availability.
16
Björkman, Adam, and Max Kardos. "Threat Analysis of Smart Home Assistants Involving Novel Acoustic Based Attack-Vectors." Thesis, Blekinge Tekniska Högskola, Institutionen för datavetenskap, 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:bth-18329.
Full textAbstract:
Background. Smart home assistants are becoming more common in our homes. Often taking the form of a speaker, these devices enable communication via voice commands. Through this communication channel, users can for example order a pizza, check the weather, or call a taxi. When a voice command is given to the assistant, the command is sent to cloud services over the Internet, enabling a multitude of functions associated with risks regarding security and privacy. Furthermore, with an always active Internet connection, smart home assistants are a part of the Internet of Things, a type of historically not secure devices. Therefore, it is crucial to understand the security situation and the risks that a smart home assistant brings with it. Objectives. This thesis aims to investigate and compile threats towards smart home assistants in a home environment. Such a compilation could be used as a foundation during the creation of a formal model for securing smart home assistants and other devices with similar properties. Methods. Through literature studies and threat modelling, current vulnerabilities towards smart home assistants and systems with similar properties were found and compiled. A few vulnerabilities were tested against two smart home assistants through experiments to verify which vulnerabilities are present in a home environment. Finally, methods for the prevention and protection of the vulnerabilities were found and compiled. Results. Overall, 27 vulnerabilities towards smart home assistants and 12 towards similar systems were found and identified. The majority of the found vulnerabilities focus on exploiting the voice interface. In total, 27 methods to prevent vulnerabilities in smart home assistants or similar systems were found and compiled. Eleven of the found vulnerabilities did not have any reported protection methods. Finally, we performed one experiment consisting of four attacks against two smart home assistants with mixed results; one attack was not successful, while the others were either completely or partially successful in exploiting the target vulnerabilities. Conclusions. We conclude that vulnerabilities exist for smart home assistants and similar systems. The vulnerabilities differ in execution difficulty and impact. However, we consider smart home assistants safe enough to usage with the accompanying protection methods activated.<br>Bakgrund. Smarta hemassistenter blir allt vanligare i våra hem. De tar ofta formen av en högtalare och möjliggör kommunikation via röstkommandon. Genom denna kommunikationskanal kan användare bland annat beställa pizza, kolla väderleken eller beställa en taxi. Röstkommandon som ges åt enheten skickas till molntjänster över internet och möjliggör då flertalet funktioner med associerade risker kring säkerhet och integritet. Vidare, med en konstant uppkoppling mot internet är de smarta hemassistenterna en del av sakernas internet; en typ av enhet som historiskt sett är osäker. Således är det viktigt att förstå säkerhetssituationen och riskerna som medföljer användningen av smarta hemassistenter i en hemmiljö. Syfte. Syftet med rapporten är att göra en bred kartläggning av hotbilden mot smarta hemassistenter i en hemmiljö. Dessutom kan kartläggningen fungera som en grund i skapandet av en modell för att säkra både smarta hemassistenter och andra enheter med liknande egenskaper. Metod. Genom literaturstudier och hotmodellering hittades och sammanställdes nuvarande hot mot smarta hemassistenter och system med liknande egenskaper. Några av hoten testades mot två olika smarta hemassistenter genom experiment för att säkerställa vilka hot som är aktuella i en hemmiljö. Slutligen hittades och sammanställdes även metoder för att förhindra och skydda sig mot sårbarheterna. Resultat. Totalt hittades och sammanställdes 27 stycken hot mot smarta hemassistenter och 12 mot liknande system. Av de funna sårbarheterna fokuserar majoriteten på manipulation av röstgränssnittet genom olika metoder. Totalt hittades och sammanställdes även 27 stycken metoder för att förhindra sårbarheter i smarta hemassistenter eller liknande system, varav elva sårbarheter inte förhindras av någon av dessa metoder. Slutligen utfördes ett experiment där fyra olika attacker testades mot två smarta hemassistenter med varierande resultat. En attack lyckades inte, medan resterande antingen helt eller delvis lyckades utnyttja sårbarheterna. Slutsatser. Vi konstaterar att sårbarheter finns för smarta hemassistenter och för liknande system. Sårbarheterna varierar i svårighet att uföra samt konsekvens. Dock anser vi att smarta hemassistenter är säkra nog att använda med medföljande skyddsmetoder aktiverade.
17
Tamatsu, Yukimasa, Hiroshi Murase, Ichiro Ide, et al. "Estimation of Traffic Sign Visibility Toward Smart Driver Assistance." IEEE, 2010. http://hdl.handle.net/2237/14486.
Full text
18
Camboim, Hugo Barros. "Cloud computing assisted smart surveillance based safe transportation system to improve crime assistance on smart cities." PROGRAMA DE P?S-GRADUA??O EM SISTEMAS E COMPUTA??O, 2015. https://repositorio.ufrn.br/jspui/handle/123456789/22077.
Full textAbstract:
Submitted by Automa??o e Estat?stica (sst@bczm.ufrn.br) on 2017-02-20T21:14:31Z
No. of bitstreams: 1
HugoBarrosCamboim_DISSERT.pdf: 2235324 bytes, checksum: ebcb1e19c35ba48ea27d27d8fce0b644 (MD5)<br>Approved for entry into archive by Arlan Eloi Leite Silva (eloihistoriador@yahoo.com.br) on 2017-02-23T20:04:37Z (GMT) No. of bitstreams: 1
HugoBarrosCamboim_DISSERT.pdf: 2235324 bytes, checksum: ebcb1e19c35ba48ea27d27d8fce0b644 (MD5)<br>Made available in DSpace on 2017-02-23T20:04:37Z (GMT). No. of bitstreams: 1
HugoBarrosCamboim_DISSERT.pdf: 2235324 bytes, checksum: ebcb1e19c35ba48ea27d27d8fce0b644 (MD5)
Previous issue date: 2015-12-17<br>Vigil?ncia Inteligente desempenha um papel fundamental na assist?ncia tecnol?gica em cen?rios
de seguran?a p?blica atrav?s de seu potencial em detectar objetos e eventos em tempo real. Essa
tecnologia tem atra?do aten??o especial no campo de seguran?a p?blica, particularmente em
ambientes veiculares pela habilidade em assistir cen?rios de miss?o cr?tica atrav?s de detec??o
autom?tica por v?deo em tempo real(ex. assaltos, sequestros, atos de viol?ncia, etc.). Consequentemente,
? poss?vel permitir que autoridades realizem uma compensa??o entre reativa e
pr?-ativa na tomada de a??es, buscando manter sistemas de alertas customizados, realizando
um planejamento mais eficiente, e prover melhor qualidade de vida ? sociedade. Al?m disso, a
associa??o de recursos de Computa??o em Nuvem ? suscept?vel de proporcionar perspectivas
avan?adas para aplica??es de Vigil?ncia Inteligente, em termos de aprovisionamento refor?ado:
(i) processamento, para permitir implanta??o de t?cnicas de computa??o inteligente para melhorar
a precis?o; (ii) armazenamento, para adotar uma grande variedade de templates; (iii) e,
acesso ub?quo para que qualquer dispositivo permane?a conectado em qualquer lugar. A investiga??o
realizada neste trabalho ? focada na abordagem de Vigil?ncia Inteligente baseada
em Computa??o em Nuvem conduzida para permitir execu??o de aplica??es m?veis baseadas
em eventos no dom?nio de seguran?a p?blica. O objetivo ? permitir que aplica??es m?veis
otimizadas, as quais explorando um esquema baseado em eventos, possam prover perspectivas
de baixo consumo de recursos(energia, CPU e rede) em compra??o ? abordagem reativa cl?ssica.
Uma avalia??o ? feita atrav?s de um conjunto de experimentos realizados em um testbed
real, os quais demonstram que o trabalho proposto supera o esquema de computa??o m?vel
cl?ssico.<br>Smart video surveillance plays a key role in offering technological assistance in public safety
scenarios, due to its potential to allow events and objects to be automatically detected in realtime.
The Smart video surveillance technology has attracted special attention in the field of
public safety, particularly in vehicular environments by the ability in assisting mission critical
scenarios through real-time video processing based automatic detections (e.g., assaults, kidnaps,
acts of violence etc.). Hence, it is possible to enable a tradeoff to be made between reactive and
pro-active authorities when taking action, seeking to keep customized alert systems, carry out
more efficient planning, and thus provide society with a better quality of life. Moreover, the association
to Cloud Computing capabilities, is likely to provide advanced perspectives to smart
surveillance applications, in terms to provisioning enhanced: (i) processing, to allow for deploying
smart computing techniques for improved accuracy; (ii) storage, to adopt a wide variety of
templates; (iii), and ubiquitous access, to keep connected everywhere and to any device. The
investigation carried in this work focus in deploying a smart surveillance driven cloud-enabled
approach to allow for event-based mobile applications in the public safety field. The objective
is to allow optimized mobile applications, by which exploiting event-based scheme to provide
to low resource consumption (energy, CPU and network usage) perspectives in comparison
to the classic reactive approach. The evaluation is carried out in a set of experiments over a
real testbed, which demonstrates that the proposal outperforms the classical mobile computing
scheme.
19
Seifert, Fanny. "Smart Maintenance." Fraunhofer-Institut für Verfahrenstechnik und Verpackung IVV, 2018. https://slub.qucosa.de/id/qucosa%3A32446.
Full text
20
Wang, Hans S. M. Massachusetts Institute of Technology. "Voice wars : smart speakers, voice assistants, and strategies for building a successful voice ecosystem." Thesis, Massachusetts Institute of Technology, 2019. https://hdl.handle.net/1721.1/122259.
Full textAbstract:
Thesis: S.M. in Engineering and Management, Massachusetts Institute of Technology, System Design and Management Program, 2019<br>Page 99 blank. Cataloged from PDF version of thesis.<br>Includes bibliographical references (pages 96-98).<br>In recent years, voice-powered digital assistants have exploded into the consumer mainstream as an important new form of human-computer interaction. Powered by dramatic improvements in speech recognition and artificial intelligence (Al) technologies over the last decade, digital voice assistants are now abundantly prevalent in modem consumer electronic devices ranging from mobile phones, to smart speakers, to wearables. As the technology matures and the availability of big data used by digital assistants proliferates, voice will soon become a primary modality by which people interact and accomplish tasks. Many of these tasks will be accomplished in consumer homes and digital voice assistants present a significant new opportunity where voice and the physical home intersect to dramatically reshape how consumers live in their home.<br>This also represents a tremendous opportunity for companies in the digital assistant industry, and, in order to successfully leverage this nascent technology, they will need to understand both their own strategic goals as well as their direct and indirect competitors' strategies in building a business ecosystem around voice-first digital assistants. A fierce struggle has begun - not just amongst current technology titans (i.e. Google, Amazon, Apple, Microsoft), but also involving key incumbent players in the home media and electronics industry (e.g. Samsung, Sonos, Bang & Olufsen).<br>The goals of this thesis, with respect to the current industry leaders in the digital assistant and smart home space, are to 1) understand the current landscape of the digital assistant voice ecosystem, 2) elucidate each major players' current voice-powered digital assistant platform strategy, 3) analyze the consumer adoption, selection, and diffusion mechanisms for digital voice assistants in the consumer smart home, and 4) determine what the likely outcomes are for each major player as well as the likelihood of success and associated risks with the current ecosystem and platforming strategies employed. Finally, through additional market analysis and industry projections, strategic recommendations will be presented to guide each key player over the next decade. Following these recommendations will be key to winning the digital assistant voice wars and for creating a successful and sustainable voice technology ecosystem in the personal digital assistant market.<br>by Hans Wang.<br>S.M. in Engineering and Management<br>S.M.inEngineeringandManagement Massachusetts Institute of Technology, System Design and Management Program
21
Oriwoh, Edewede. "A smart home anomaly detection framework." Thesis, University of Bedfordshire, 2015. http://hdl.handle.net/10547/622486.
Full textAbstract:
Smart Homes (SHs), as subsets of the Internet of Things (IoT), make use of Machine Learning and Arti cial Intelligence tools to provide technology-enabled solutions which assist their occupants and users with their Activities of Daily Living (ADL). Some SH provide always-present, health management support and care services. Having these services provided at home enables SH occupants such as the elderly and disabled to continue to live in their own homes and localities thus aiding Ageing In Place goals and eliminating the need for them to be relocated in order to be able to continue receiving the same support and services. Introducing and interconnecting smart, autonomous systems in homes to enable these service provisions and Assistance Technologies (AT) requires that certain interfaces in, and connections to, SH are exposed to the Internet, among other public-facing networks. This introduces the potential for cyber-physical attacks to be perpetrated through, from and against SH. Apart from the actual threats posed by these attacks to SH occupants and their homes, the potential that these attacks might occur can adversely a ect the adoption or uptake of SH solutions. This thesis identi es key attributes of the di erent elements (things or nodes and rooms or zones) in SHs and the relationships that exist between these elements. These relationships can be used to build SH security baselines for SHs such that any deviations from this baseline is described as anomalous. The thesis demonstrates the application of these relationships to Anomaly Detection (AD) through the analysis of several hypothetical scenarios and the decisions reached about whether they are normal or anomalous. This thesis also proposes an Internet of Things Digital Forensics Framework (IDFF), a Forensics Edge Management System (FEMS), a FEMS Decision-Making Algorithm (FDMA) and an IoT Incident Response plan. These tools can be combined to provide proactive (autonomous and human-led) Digital Forensics services within cyber-physical environments like the Smart Home.
22
gupta, Devansh. "Smart-Scooter Rider Assistance System using Internet of Wearable Things and Computer Vision." Case Western Reserve University School of Graduate Studies / OhioLINK, 2021. http://rave.ohiolink.edu/etdc/view?acc_num=case1619611136736967.
Full text
23
Lotankar, Akshay Naresh. "Development of a smart-phone based augmented reality view application for driver assistance systems." Master's thesis, Universitätsbibliothek Chemnitz, 2017. http://nbn-resolving.de/urn:nbn:de:bsz:ch1-qucosa-229312.
Full textAbstract:
The goal of this thesis is to develop a smartphone application for augmented reality view; it is an initial attempt to realize a driver assistance functionality using just a smartphone and an external lens. Initially it depicts a brief analysis about the most feasible development technologies for mobile application development, selecting a proper lens and positioning of the smartphone in the car. Later, it discusses the strategies for real-time object detection using OpenCV; the video frames are processed using the strategies to find patterns in the videos. Different techniques like Hough-line transform, watershed, contour detection, color segmentation, color thresholding and HAAR cascades are implemented and compared in terms of real time detection of the desired objects. Then a unified algorithm is implemented for the given scenario which overcomes the challenges faced during the conceptualization phase. Finally, the results are depicted with the snapshots of the real time detection done from the smartphone and then evaluated against the vision of the application and the achieved tasks. This thesis is concluded by stating the prospects of this mobile application in the future.
24
Bottazzi, Manuel. "Il Progetto Smart Shock Room: Studio e sviluppo di un ambiente ospedaliero intelligente basato sull'integrazione di approcci ad agenti, assistenti vocali e digital twin." Master's thesis, Alma Mater Studiorum - Università di Bologna, 2020. http://amslaurea.unibo.it/20862/.
Full textAbstract:
Le moderne tecnologie informatiche trovano oggi applicazione in svariati ambiti ed entrano sempre più nella vita quotidiana delle persone offrendo nuove possibilità. Nuove tecnologie di comunicazione, dispositivi IoT avanzati e i loro sensori, algoritmi di Machine Learning ed AI vengono sempre più utilizzati nel supporto attivo di persone nello svolgimento del lavoro, migliorandone efficacia ed efficienza e riducendo il tempo necessario. Questo aspetto assume un'importanza ancora maggiore nell'ambito del supporto sanitario ospedaliero, in cui il tempo è una risorsa critica. Il gran numero di applicazioni di tecnologie avanzate in questo settore, come agenti conversazionali per il supporto ai pazienti o modelli di supporto alle decisioni dei medici, ne sono la prova.
In questo contesto si colloca il lavoro di questa tesi, che concerne il progetto "Smart Shock Room". Esso consiste nella realizzazione di un sistema per il controllo di un ambiente intelligente in ambito ospedaliero. Tramite questo sistema è possibile visualizzare, in automatico o in seguito ad una richiesta tramite un assistente vocale o un'apposita applicazione, informazioni mediche di varia natura, provenienti da diverse sorgenti e dagli strumenti diagnostici presenti, relative a pazienti in cura e gestire operazioni specifiche sull'ambiente stesso e relative al trauma in corso. Il documento descrive tutti i passaggi relativi alla progettazione e modellazione di tale sistema partendo dalla raccolta ed analisi dei requisiti. È stata inoltre proposta ed applicata al progetto una modalità di integrazione tra approcci tecnologici innovativi (sistemi multiagente, digital twin ed assistenti vocali), tale da poter ottenere un'architettura integrata, capace di semplificare la rappresentazione del modello del dominio e di garantire disaccoppiamento ed interoperabilità tra i componenti del sistema. Infine è stato realizzato un prototipo del sistema in modo da poter validare il risultato con l'equipe medica.
25
Kovařík, Viktor. "IoT systém pro domácnost." Master's thesis, Vysoké učení technické v Brně. Fakulta informačních technologií, 2020. http://www.nusl.cz/ntk/nusl-417285.
Full textAbstract:
The aim of this thesis was to learn and summarize basic information about IoT systems, which protocols are used and introduction of Google Home system. The first part of the thesis describes the individual parts of the system --- microcontrollers, sensors, light elements and possible systems for backend. In the implementation part of the thesis was designed a solution for smart home controling using Google Home technology. Based on data from the weather station, the system controls and adjusts the intensity of outdoor lighting and controls the blinds. Furthermore, a control module for gate and garage door control is implemented. The system also takes care of vacuum cleaning in the house using iRobot Roomba vacuum cleaners with custom Wi-Fi module. The final part of the thesis summarizes the achieved results.
26
Akhlaq, Muhammad. "A Smart-Dashboard : Augmenting safe & smooth driving." Thesis, Blekinge Tekniska Högskola, Sektionen för datavetenskap och kommunikation, 2010. http://urn.kb.se/resolve?urn=urn:nbn:se:bth-6162.
Full textAbstract:
Annually, road accidents cause more than 1.2 million deaths, 50 million injuries, and US$ 518 billion of economic cost globally. About 90% of the accidents occur due to human errors such as bad awareness, distraction, drowsiness, low training, fatigue etc. These human errors can be minimized by using advanced driver assistance system (ADAS) which actively monitors the driving environment and alerts a driver to the forthcoming danger, for example adaptive cruise control, blind spot detection, parking assistance, forward collision warning, lane departure warning, driver drowsiness detection, and traffic sign recognition etc. Unfortunately, these systems are provided only with modern luxury cars because they are very expensive due to numerous sensors employed. Therefore, camera-based ADAS are being seen as an alternative because a camera has much lower cost, higher availability, can be used for multiple applications and ability to integrate with other systems. Aiming at developing a camera-based ADAS, we have performed an ethnographic study of drivers in order to find what information about the surroundings could be helpful for drivers to avoid accidents. Our study shows that information on speed, distance, relative position, direction, and size & type of the nearby vehicles & other objects would be useful for drivers, and sufficient for implementing most of the ADAS functions. After considering available technologies such as radar, sonar, lidar, GPS, and video-based analysis, we conclude that video-based analysis is the fittest technology that provides all the essential support required for implementing ADAS functions at very low cost. Finally, we have proposed a Smart-Dashboard system that puts technologies – such as camera, digital image processor, and thin display – into a smart system to offer all advanced driver assistance functions. A basic prototype, demonstrating three functions only, is implemented in order to show that a full-fledged camera-based ADAS can be implemented using MATLAB.<br>Phone# 00966-56-00-56-471
27
Ekenberg, William, André Ekström, and Hannes Töyrä. "''Hey Google, jag är hemma!'' : En studie om smarta hem och hur tekniken skapar värde för konsumenten." Thesis, Umeå universitet, Institutionen för informatik, 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:umu:diva-183227.
Full textAbstract:
Smart homes are based on connecting different parts and components of the household through sensors and the use of the internet. The interconnection of the household enables control and remote control of the home. The factors behind consumer adoption of the smart home have been studied but there are still questions regarding the value propositions of smart homes. This study presents material that can provide insights into what value propositions young adults demand in smart home products. The methods used to produce the study results were, a survey and a questionnaire. The results from the survey showed that smart voice assistants were appreciated by the participants. However, all the participants believed the functional value of the smart voice assistants was limited. After participating in the survey, they felt no real need for the smart voice assistant in their home. The results from the questionnaire’s 112 answers showed that a large majority of the respondents did not own a smart voice assistant. Many did however, express a positive opinion towards voice assistants and were open to the purchase of a smart voice assistant in the future. The small number of respondents that did own a smart voice assistant were all satisfied with their purchase of a smart voice assistant
28
Kodys, Martin. "Raisonnement sémantique pour une plateforme d’assistance intelligente orienté bien-être et santé numérique." Thesis, Université Grenoble Alpes, 2020. http://www.theses.fr/2020GRALM033.
Full textAbstract:
Les objets connectés de la vie courante ont trouvé leur chemin dans notre quotidien. Connu sous le terme d'Internet des choses, une pluralité de technologies inspire une vaste variété des cas d'utilisation. Une des applications innovatrices est le concept et le développement de la maison intelligente. Actuellement, ce concept est en train de s'étendre vers l'extérieur ; il rend futés des véhicules, bâtiments et même des villes entières. De plus, la technologie devient aussi plus personnelle - comme le port des vêtements futés et d'autres appareils pour l'autosurveillance personnelle devient de plus en plus courant et populaire. Ce phénomène est souvent appelée le soi quantifié.Un cas particulier de l'environnement futé est l'assistance à l'autonomie à domicile (ambient assisted living) conçue pour améliorer la qualité de la vie quotidienne des personnes âgées. Un tel système informatique, omniprésent et discret, peut être porté dans d'autres domaines et tranches d'âge. Par exemple, le suivi des activités du quotidien peut aider jeune adultes à améliorer leur mode de vie. Tout le monde peut être encouragé à maintenir un mode de vie sain, à exercer une activité physique suffisante et prendre les décisions fondées quant à la mobilité. Ce sont les facteurs direct contribuant à la prévention des risques de santé, tel que les maladies métaboliques comme le diabète de type 2 ; et permettent un meilleur maîtrise des maladies respiratoires comme l'asthme.Dirigée par ces idées, cette thèse explore les possibilités d'une plate-forme web avec un raisonnement sémantique basé sur les règles. La thèse détaille le travail sur les améliorations techniques, avancements dans la reconnaissance d'activités, les extensions pour l'analyse des données et une application orientée mobilité.Suivant l'approche centrée utilisateur, un déploiement dans les conditions réelles est necessary. Deux cas d'utilisation sont abordés. Le premier est l'amélioration du système existant, consistant des capteurs et d'une passerelle tous placés dans le domicile de la personne âgée. Le deuxième cas est le déploiement d'une application pour téléphones portables pour l'assistance à la mobilité active. En collectant les donnés relevantes et actuelles, l'application affiche un niveau de recommandation personnalisée pour chaque type de mobilité. Ces recommandations sont basées sur l'appareil de soi quantifié qui incorpore les objectifs personnels, le profil et autres données librement accessible, tel que la météo ou la qualité d'air.Cette thèse décrit les sorties et les leçons tirées des déploiements de ces technologies. Cette thèse apporte une discussion et des analyses des résultats de ces déploiements<br>Connected objects of everyday living have made their way into our lives. Known as Internet of Things, the various technologies inspire a vast variety of applications. One of the pioneer applications is the concept and development of a smart home. This is now spreading outdoors; making vehicles, buildings, and even large cities smart. Moreover, the technology is getting more personal as well – as wearing smart clothes and other self-tracking devices become increasingly common and popular. This is often referred to as the quantified self.One particular case of a smart environment is ambient assisted living, which is designed to enhance elderly people’s day-to-day life. Such a ubiquitous and unobtrusive computer system can also be ported to other domains and age groups. For instance, the tracking of daily activities can also help younger adults to improve their lifestyle. Everyone can be encouraged to maintain a healthy lifestyle, perform sufficient physical activity, and make more informed decisions about their mobility. These are direct factors in preventing health risks, such as metabolic diseases like the type 2 diabetes, and allow a better control over respiratory diseases like the asthma.Driven by these ideas, this thesis explores the possibilities of a web-based platform with a semantic rule-based reasoning. The thesis details the work on technical improvements, enhancements in activity recognition, extensions for data analysis, and a mobility-oriented application.Following a user-centric approach, a real life deployment of the described technologies is necessary. Two use cases are examined. First, I enhanced and built upon a pre-existing system, which consists of sensors and a gateway placed into elderly participants' homes. The second use case is the deployment of a mobile phone application for active mobility assistance. Collecting relevant and timely data, the application then outputs a level of recommendation for every type of mobility. The recommendations are based on each user’s exercise tracking device, which incorporates their goals, their profiles, and other publicly available data sources such as weather and air quality.This thesis describes the outcomes and lessons learnt from these deployments. In addition, this thesis provides an in-depth discussion as well as analytical insights on the results of the deployments
29
Ben, Hadj Mohamed Asma. "Réseau de capteurs sans fil comportementaux pour l'aide au maintien à domicile par la surveillance en habitat intelligent." Thesis, Toulouse 2, 2015. http://www.theses.fr/2015TOU20077/document.
Full textAbstract:
Ces dernières années, les réseaux de capteurs sans fil ont vu leurs champs d'applications s'élargir pour toucher plusieurs domaines dont celui de surveillance. En parallèle, le domaine à vocation médicale pour l'assistance aux personnes n’a pas manqué de s'intéresser lui aussi à cette technologie émergente face aux nombreux attraits qu'elle représente. C'est dans ce contexte que se situe notre travail de thèse. Nous nous intéressons à l'utilisation des réseaux de capteurs de type vidéo non intrusif pour la surveillance continue de personnes âgées évoluant dans leur environnement naturel. L’objectif est la proposition d’un système associant capteur vidéo et analyse intelligente locale, à un système de communication sans fil permettant la surveillance de personnes dans son habitat ou en milieu spécialisé. Nous désirons avant tout être capable d’identifier la personne surveillée et détecter son comportement, ses actions, ses mouvements afin d’agir sur son environnement via un système de communication sans fil et domotique, détecter une chute et émettre une alerte à travers le réseau. Une telle proposition, représente une solution avantageuse pour plusieurs raisons. Sur le plan économique, surveiller une personne âgée tout en la gardant dans son environnement normal permettrait de diminuer les charges d'assistance aux personnes en les traitant par un personnel spécialisé à l'hôpital ou à une maison de retraite. Un apport non négligeable est celui lié aux aspects psychiques et sociaux de la personne âgée, à qui cette surveillance discrète et imperceptible lui assure à la fois le sentiment de sécurité, de respect de la vie privée et d'autonomie<br>In recent years, wireless sensor networks have seen their fields of application expand to affect several areas, including monitoring. In parallel, the field medical projects to assist people did not fail to be interested in this emerging technology thanks to the attractions it represents. It is in this context that our thesis is subscribed. We are interested in the use of a non-intrusive video sensors network to monitor elderly people continuously in their natural environment. The objective is the proposal of a video sensor system combining local and intelligent analysis, a wireless communication system for monitoring people in their habitat or specialized environment. We want above all, to be able to identify and detect the monitored person's behavior as well as his actions and his movements to act on his environment via a wireless communication system and home automation. Then we aim to detect a fall and communicate an alert through the network. This proposal represents an advantageous solution for several reasons. Economically, monitor an elderly person while keeping it in his normal environment would reduce the charges of assistance to people by treating them with specialized staff at the hospital or a nursing home. A significant contribution is the one related to the psychological and social aspects of the elderly, to whom this discreet and invisible monitoring ensures both the feeling of security, respect for privacy and autonomy
30
Gudmundsson, Magdalena. "Aging-in-place with ICT : A qualitative study of senior citizen users’ perception and acceptance towards Smart home technology." Thesis, Linnéuniversitetet, Institutionen för informatik (IK), 2017. http://urn.kb.se/resolve?urn=urn:nbn:se:lnu:diva-67074.
Full textAbstract:
This is a qualitative, interpretive research study of how six senior citizens’ aged 70-85 describe their use and need of Smart home technology for their independent living and welfare. Data was collected through technology probing and interviews. Data analysis was done using a thematic method. The research was underpinned by the theoretical model Unified Theory of Acceptance and Use of Technology (UTAUT2). The research setting was senior citizens’ living in Care housing rented out by the municipality owned company. The findings show that technology is perceived by the senior citizens’ to be something must be taught and takes effort. Senior housing need to be better designed for its senior tenants. It was also found that if technology is used to ensure safety, fall detection for instance, trust and sufficient support is crucial. The findings suggest it could be difficult to assess your own need and to realize when assistance technology is needed. It also found that the use of technology was perceived as being individual and as something that cannot be treated collectively. It was suggested that health professionals do have some influence on the senior citizen and their use of technology. The findings of this study was compared to previous studies and how it relates to the determinants and moderating factors suggested by the theoretical model UTAUT2.
31
McFerren, Mary Margaret. "Incentives and Barriers to Participation in Community Nutrition Education Programs for Recipients of Food Stamps and Temporary Assistance to Needy Families." Diss., Virginia Tech, 2007. http://hdl.handle.net/10919/27013.
Full textAbstract:
The purpose of this study was to explore the incentives and barriers perceived by low-income women of child-bearing age related to their participation in nutrition education programs. The specific programs of concern in this study are the Expanded Food and Nutrition Education Program (EFNEP) and the Food Stamp Nutrition Education (FSNE) program. This qualitative study sought to hear the voices of the women so that nutrition programs can be made more successful in reaching this population. Personal interviews were conducted with 23 women in their homes or appropriate local sites, and transcripts were analyzed to identify categories and themes.
People of low socioeconomic status and those with the least education have higher rates of obesity and overweight and suffer disproportionately from poor health. Women receiving Temporary Assistance to Needy Families (TANF) also receive Medicaid. Medicaid costs have escalated due to the obesity rate, which is currently estimated at 64% of the adult population. In addition, 30% of American children are experiencing obesity or are overweight. It is important for parents to understand the causes of obesity and the effects of the chronic diseases related to obesity. Prevention programs are more cost effective than medical treatment of the diseases associated with obesity, and proper nutrition can reduce the incidence of chronic diseases.
Findings of this study suggest that isolation is the main impediment to participating in nutrition education programs. Missing from the interviewed women's circumstances are social capital, human capital, and economic capital. Social capital relates to the connections and relationships that are important in life. Human capital involves the knowledge and skills acquired through life experiences. Economic capital refers to individual wealth or economic resources available to an individual or community.
Nutrition education programs should be refined to incorporate opportunities for socialization that will develop trust and reciprocity, as well as nutrition knowledge. Based on the results of this study, Virginia Cooperative Extension programs will be adapted to incorporate weight control and cooking classes with nutritious recipes. The learning environment will be safe, learner-centered, and fun. New marketing tools that are more appealing to the prospective clients will be developed.<br>Ed. D.
32
Devigne, Louise. "Solutions robotiques bas coût pour l’aide à la navigation en fauteuil roulant électrique : vers une contribution dans le champ de la rééducation neurologique." Thesis, Rennes, INSA, 2018. http://www.theses.fr/2018ISAR0024/document.
Full textAbstract:
Alors que l’utilisation d’un fauteuil roulant permet aux personnes en situation de handicap de compenser une perte de la mobilité, certaines personnes se voient privées de l’utilisation d’un fauteuil roulant électrique. En effet, la présence de troubles cognitifs ou de la perception visuelle altère la capacité à conduire sans danger. Dans ce contexte, l’accès à la mobilité peut être amélioré par l’apport d’aides techniques adaptées permettant de compenser la perte de mobilité dans tous types d’environnements. Alors que les premiers travaux sur les fauteuils roulants intelligents datent du début des années 80, aucune solution n’est à ce jour sur le marché ou dans les centres de rééducation. Ce travail vise à proposer un ensemble de solutions d’aide à la conduite de fauteuil roulant électrique conçu en collaboration. Le développement de telles aides techniques constitue de multiples défis robotiques mêlant techniques de détection innovantes et méthodes de contrôle partagé avec l’utilisateur. Dans ce travail, un simulateur de conduite visant à appuyer la recherche et le développement de nouvelles solutions robotiques est proposé. Puis des solutions bas coût d’assistance semiautonome à la conduite en intérieur et en extérieur sont détaillées. L’évaluation avec des participants sains nous permet de valider les méthodes mathématiques mises en oeuvre et de fournir des preuves de concept des solutions proposées. Enfin, les premières évaluations cliniques avec des usagers au Pôle MPR Saint Hélier montrent la validation de de la méthode proposée en termes de satisfaction des utilisateurs<br>While the use of a wheelchair allows people with disabilities to compensate for a loss of mobility, people with severe disabilities are denied the use of a power wheelchair. Indeed, cognitive or visual perception impairments can affect the ability to drive safely. In this context, access to mobility can be improved by providing appropriate assistive technologies to compensate for loss of mobility in all types of environments. While the first research on smart wheelchairs dates back to the early 1980s, no solutions have yet been proposed on the market or in rehabilitation centers and other specialized structures. This work aims to propose a set of solutions for power wheelchair navigation assistance designed in close collaboration with users and therapists. The development of such assistive solutions faces multiple robotic challenges combining innovative detection techniques, shared control with the user. In this work, a driving simulator supporting research and development of new robotic solutions for wheelchair navigation assistance is proposed. Then low-cost semi-autonomous assistance solutions for navigation assistance in indoor and outdoor environments are detailed. The evaluation with able-bodied participants allows to validate the mathematical methods and provide proof of concept of the proposed solutions. Finally, the first clinical evaluations with regular users at Pôle MPR Saint Hélier show the validation of the proposed framework in terms of user satisfaction
33
Brenot, François. "Application d'une méthodologie de co-design à la définition et à l'implémentation d'une chaîne SLAM opérationnelle." Phd thesis, Toulouse, INPT, 2016. http://oatao.univ-toulouse.fr/18588/1/BRENOT_Francois.pdf.
Full textAbstract:
Dans le domaine de la détection et du suivi d'obstacles pour les systèmes ADAS (Advanced Driver Assistance System) basés vision, il est nécessaire d'assurer la localisation à court terme du véhicule. Le SLAM (Simultaneous Localization and Mapping) basé vision propose de résoudre ce problème en combinant l’estimation de l’état du véhicule (pose dans un repère local et vitesses) et une modélisation incrémentale de l’environnement. Ce dernier est perçu par l'extraction de caractéristiques locales (points d'intérêt) dans une séquence d'images et leur suivi au cours du temps pour permettre la construction incrémentale d'une carte d'amers. Cette tâche de perception engendre une importante charge de calcul qui affecte très significativement la latence et la cadence du système. Les méthodologies de co-design permettent de concevoir une architecture mixte de calcul pour l“exécution d'une application particulière. Dans ce type d'architecture, l'utilisation d'accélérateurs matériels permet d'améliorer significativement les performances (temps d'exécution, encombrement, consommation). Le ZynQ (Xilinx) propose une architecture de prototypage mixte comprenant un processeur dual-core associé à des ressources matérielles configurables. L'objectif de cette thèse est donc de proposer une implémentation co-design d'un SLAM basé vision par la conception d'accélérateurs pour les opérations de vision afin de satisfaire les contraintes en performances des systèmes ADAS embarqués. La première contribution des travaux est la conception de cette chaîne complète 3D EKF-SLAM à l'aide une approche co-design. Nous avons défini et validé, selon notre méthodologie de conception, le choix d'une architecture Hardware-in-theloop (HIL) afin de valider les différentes itérations de conception. La seconde contribution est l'intégration de modules matériels dédiés pour accélérer les traitements de perception visuelle de cette chaîne (détection, description et mise en correspondance de points d’intérêt).
34
Belloum, Rafik. "Méthodologies outillées de développement de services dédiés à l'assistance domiciliaire." Thesis, Bordeaux, 2020. http://www.theses.fr/2020BORD0091.
Full textAbstract:
L’accroissement du vieillissement de la population entraîne l’émergence de technologies informatiques pervasives au service de l’aide à domicile, afin de réduire le nombre de personnes transférées dans des établissements de soins coûteux. L’objectif de l’informatique d’assistance est de fournir des services adaptés au contexte qui aident les personnes âgées dans tous les aspects de la vie quotidienne, par exemple en surveillant des activités telles que la préparation des repas et en leur rappelant leurs rendez-vous ou leurs médicaments. Malgré de nombreux progrès, le développement des services d’assistance reste un défi, en raison du manque d’approches et d’outils de soutien au développement. Ce défi implique : (1) tenir compte des variations interindividuelles (e.g., les caractéristiques du domicile et les habitudes et préférences des utilisateurs), (2) surveiller les activités sur de longues périodes et (3) permettre aux experts du vieillissement de personnaliser les services d’assistance. Cette thèse présente plusieurs contributions à ce sujet. Les principales contributions sont deux méthodes itératives dédiées au soutien du développement de services d’assistance. Chacune de ces méthodes est soutenue par un ensemble d’outils pour la collecte, l’analyse et la visualisation des données de suivi. Ces outils assurent le développement agile de détecteurs d’activité précis grâce à un affinement progressif de l’analyse des données des capteurs. La première méthode, pour la reconnaissance des activités, utilise les déclarations de routines rapportées par les utilisateurs. Au-delà de la reconnaissance des activités, la deuxième méthode s’attaque aux difficultés de la surveillance à long terme (e.g., les défaillances des capteurs) et donne aux professionnels de la santé des indications utiles sur les activités des utilisateurs. Enfin, une approche pour l’utilisateur final est présentée, qui fournit un outil permettant aux experts du vieillissement de définir facilement les services d’assistance domiciliaire dans les maisons intelligentes. Les méthodologies présentées ont été appliquées à une plateforme d’assistance, déployée au domicile de 140 utilisateurs. Les résultats expérimentaux montrent l’efficacité de toutes les méthodes proposées<br>The growing population of older adults gives rise to a need for assistive computing systems that support independent living, to reduce the number of people being transferred to costly care facilities. The goal of assistive computing is to provide context-aware services that assist older adults in all aspects of daily life, for example, monitoring activities such as meal preparation and providing appointment or medication reminders. Despite much progress, the development of assistive services remains a challenge, because of a lack of supporting approaches and tools. This challenge involves: (1) coping with inter-individual variabilities (e.g., home features and user routines and preferences) to deliver tailored services, (2) monitoring activities over long periods of time and (3) enabling care providers and/or professionals in aging to contribute their expert knowledge towardsservice development. This dissertation presents several contributions to this topic. The primary contributions are two iterative methods dedicated to supporting the development of services that monitor activities of daily living (ADLs). Each of these methods is supported by a set of tools for collecting, analyzing and visualizing monitoring data. These tools ensure the agile development of accurate activity recognizers via a stepwise refinement of the analysis of sensor data. The first method, for recognizing ADLs, encompasses the main variations of a target activity by abstracting over descriptions reported by users. Beyond recognizing ADLs, the second method addresses long-term monitoring shortcomings (e.g., sensor failures) and gives health professionals actionable insights into user activities. A final end-user approach is presented, which provides a tool to enable experts in aging to easily define assisted living services in smart homes. The presented methodologies have been applied to an assisted living platform for aging in place, deployed in the home of 140 users. Experimental results show the effectiveness of all the proposed methods. First, the recognition methodology has achieved an accuracy of 80%, rising to 88% when considering the more routinized participants of the experiment. Second, the method for long-term monitoring of ADLs mostly produced the same interpretations as an expert in activity analysis, who manually analyzed the longitudinal sensor datasets. Finally, the findings reveal good usability of the end-user tool, which has been tested by occupational therapists
35
Merdivan, Erinc. "Ambient Assisted Living with Deep Learning." Electronic Thesis or Diss., CentraleSupélec, 2019. http://www.theses.fr/2019CSUP0006.
Full textAbstract:
L'aide ambiante à la personne (ambiant assisted living) a pour objectif d'accompagner le vieillissement de la population. Cela s'instancie notamment par les maisons intelligentes (smart homes), équipées de multiples capteurs connectés, dont un des objectifs est de prolonger le maintien à domicile des personnes âgées. Le manuscrit s'attache d'abord à introduire la problématique générale des maisons intelligentes, avant de présenter plus avant les trois sous-thématiques qui font plus particulièrement l'objet de la thèse, à savoir la reconnaissance d'activités, la confidentialité et les systèmes de dialogue.La reconnaissance d'activités consiste à déterminer les activités courantes d'une personne ou d'un groupe de personnes, à partir des données (brutes) des capteurs dont est équipée la maison. On peut citer comme exemple la détection de la chute d'une personne. Une maison intelligent repose typiquement sur l'internet des objets (Internet of Things, ou IoT). De nombreuses données sont produites, pouvant contenir des informations privées ou sensibles. Une partie de ces données doit être partagée avec l'extérieur, ce qui peut poser des problèmes de confidentialité. Enfin, pour interragir avec la maison intelligente, un moyen naturel pour l'utilisateur est d'utiliser le dialogue, sujet traité par les systèmes de dialogue.Ce travail de thèse propose des contributions sur ces trois versants, la plupart basées sur l'apprentissage profond<br>Ambient assisted living aims to support the aging population. This is particularly the case with smart homes, equipped with multiple connected sensors, which enables to extend home care for the elderly. The manuscript begins by introducing the general problem of smart homes, after presenting further the three sub-themes that are the subject of the thesis, namely the activity recognition, privacy and dialogue systems.Activity recognition is the process of determining the day-to-day activities of a person or a group of people from the (raw) sensor data that the home is equipped with. An example of this is the detection of a person's fall. A smart home is typically based on the Internet of Things (IoT). Many data are produced, which may contain private or sensitive information. Some of this data must be shared externally, which may pose privacy issues. Finally, a natural way of communication for the user is to use the dialogue to interact with the smart home via dialogue manager.This thesis proposes contributions on these three sides, most of them based on deep learning
36
Bouaziz, Ghazi. "Développement et mise en œuvre d'un système de détection de l'isolement social basé sur la reconnaissance des activités en matière de repas et de mobilité chez les personnes âgées à domicile." Electronic Thesis or Diss., Université de Toulouse (2023-....), 2024. http://www.theses.fr/2024TLSES137.
Full textAbstract:
La reconnaissance d'activités de vie quotidienne (AVQs) fait l'objet, depuis des années, de recherches pour proposer des solutions performantes. Elle s'appuie sur l'analyse spatio-temporelle de situations, de comportements, etc. dont les données d'entrée sont les informations fournies par des capteurs ambiants ou par des capteurs portés par la personne. Cette thèse se focalise sur l'instrumentation du lieu de vie par des capteurs ambiants et sur la détection d'un état d'isolement social chez les personnes âgées. Deux approches sont utilisées pour évaluer l'isolement social. La première se base sur des questionnaires. La deuxième approche s'appuie sur l'utilisation de technologies pour la récupération objective de données représentatives d'un état ou d'un comportement. En particulier, l'activité " se nourrir " est liée à une séquence d'actions telles que faire les courses, cuisiner, manger et faire la vaisselle. L'activité " se déplacer " est liée à la mobilité au sein du domicile et au fait de sortir du logement. La littérature montre que ces deux activités semblent pertinentes pour évaluer un risque potentiel d'isolement social chez les aînés. Les travaux de thèse portent sur quatre contributions principales : Un état bibliographique des recherches sur la détection des AVQs afin d'en identifier les apports et les limites et tracer des voies de recherches pertinentes. Des critères spécifiques ont été choisis pour inclure les articles dans lesquels des systèmes de détection d'activités sont présentés. Une démarche de conception système appliquée à la reconnaissance d'AVQs. Cette démarche s'intègre dans un processus d'Ingénierie Système. Elle décrit l'analyse des exigences, leur modélisation au travers de diagrammes SysML et la mise en place d'une architecture matérielle et logicielle basée sur un réseau IoT. L'analyse des AVQs, dans notre étude, utilise les données de détecteurs de mouvement et de capteurs de contacts. Un affichage sur une application web permet de visualiser les résultats obtenus à destination de l'aide-soignant ou de la famille. L'utilisation originale de quatre méthodes de classification des AVQs à savoir "préparer le repas", "prendre le repas", "faire la vaisselle", "dormir/se relaxer", "hygiène", "la personne à l'extérieur du logement", "un visiteur à l'intérieur de la maison" et "autres activités". Les trois premières méthodes utilisées sont K-means, le modèle de mélange gaussien et BIRCH auxquelles on applique une pondération aux données. Les activités liées au repas n'ont ainsi pas le même poids que le reste des données, ce qui a permis d'améliorer la détection des AVQs. Le quatrième algorithme est basé sur une méthode logique à la suite de la détermination d'une matrice de corrélation prenant en entrée l'ensemble des capteurs disponibles. En utilisant les données de la matrice de corrélation, l'algorithme personnalise la détection des activités liées au repas en différenciant une personne qui prépare seule son repas d'une personne qui bénéficie d'un service de portage de repas. Nous validons nos méthodes en se référant aux formulaires remplis par les participants au début et à la fin de l'expérimentation dans lesquels ils indiquent le déroulement de leur journée-type. Ces algorithmes ont été appliqués sur une base de données annotée ouverte pour confirmer la précision de nos approches. La proposition d'un score du niveau d'isolement social chez la personne suivie. Ce score est établi sur la base de l'identification des activités pour extraire les habitudes quotidiennes au travers d'indicateurs du comportement (Le temps passé à l'extérieur de la maison et à l'intérieur de la cuisine, etc.). Six aînées ont été suivies pendant plus de 3 mois. L'algorithme régression logistique a été utilisé pour l'extraction du niveau d'isolement social qui a été comparé à celui identifié grâce au questionnaire " Lubben Social Network Scale " rempli avec chaque participant au début et à la fin de l'étude<br>The recognition of daily life activities has been the subject of research for years to provide effective solutions. It is based on the spatio-temporal analysis of situations and behaviors whose input data is information provided by ambient sensors or by sensors worn by the person. This thesis focuses on the instrumentation of the living space by ambient sensors and on the detection of a state of social isolation in elderly people. Two approaches are used to assess social isolation. The first one is based on questionnaires. The second approach is based on the use of technologies for the objective acquisition of data representative of a state, behavior, etc. In particular, the activity "eating" is linked to a sequence of actions such as shopping, cooking, eating and washing dishes. The activity "moving" is linked to mobility within the home and leaving the home. The literature shows that these two activities seem to be relevant for assessing a potential risk of social isolation among older people. The thesis work focuses on four main contributions: A bibliographic review of ADLs detection research to identify its contributions and limitations, and to outline relevant research directions. Specific criteria were chosen to include articles presenting activity detection systems. A system design approach applied to the detection of ADLs. This approach is part of a system engineering process. It describes the analysis of requirements, their modeling through SysML diagrams and the implementation of a hardware and software architecture based on an IoT network. The analysis of ADLs, in our study, uses data from motion detectors and contact sensors. A display on a web application allows you to visualize the results obtained for the caregiver or the family. The original use of four methods to classify ADLs, namely "preparing the meal", "eating the meal", "washing the dishes", "sleeping/relaxing", "hygiene", "the person outside the home", "a visitor inside the home" and "other activities". The first three methods used are K-means, the Gaussian mixture model and BIRCH, which applies weights to the data. Meal-related activities therefore do not have the same weight as the rest of the data, which made it possible to improve the detection of ADLs. The fourth algorithm is based on a logical method following the determination of a correlation matrix using all the available sensors as input. Using the data from the correlation matrix, the algorithm personalizes the detection of meal-related activities by distinguishing a person preparing their meal from a person using a meal delivery service. We validate our methods by referring to the forms filled in by the participants at the beginning and end of the experiment, in which they describe the course of their typical day. These algorithms were applied to an open annotated database to confirm the accuracy of our approaches. The proposal of a score for the level of social isolation of the person being monitored. This score is based on the identification of activities to extract daily habits through behavioral indicators (time spent outside the house and in the kitchen, etc.). Six elderly people were followed for more than 3 months. The logistic regression algorithm was used to extract the level of social isolation, which was compared with the level of social isolation identified using the "Lubben Social Network Scale" questionnaire, which was completed by each participant at the beginning and end of the study
37
Hsiao, Chung-Yan, and 蕭君妍. "Application of School Administrative Assistant on Smart Speaker." Thesis, 2019. http://ndltd.ncl.edu.tw/handle/34th7r.
Full textAbstract:
碩士<br>義守大學<br>資訊工程學系<br>107<br>In this thesis, the campus administrative service using deep learning to be implemented on Linebot and Google Voice kit. The purpose of system is automatic voice or text response so that students can ask questions and get answers via voice or text. In this Chotbot system, the natural language understanding (NLP) is by training and testing to compare with the differences of the three methods: convolutional neural network (CNN), long short-term memory neural network (LSTM) and Google’s Dialogflow. Simulation result showed that the CNN and the LSTM training got more than 96%, and Google''s Dialogflow was only about 60% correct rate. It is known that the training model using deep learning is better than the Google’s Dialogflow using intents and entities.
38
Lai, Hsin-Yi, and 賴欣怡. "Exploring Antecedents to Consumers’ Intention to Adopt Smart Home Voice Assistant." Thesis, 2019. http://ndltd.ncl.edu.tw/handle/8tpc8z.
Full textAbstract:
碩士<br>國立臺灣科技大學<br>資訊管理系<br>107<br>The internet is an inevitably necessary technology nowadays, in particular, the worldwide development of internet of things (IoT) continues to grow strongly. The IoT technology connects and communicates almost every object. The application of the IoT technology for individual includes smart wrist bands and smart watches, to name a few, and smart home, a controlling hub connecting other home devices and equipment, for family. The smart home hub developed by Google, namely Google Home, allows users to control their smart home devices, for example, smart light bulbs, smart audio speakers…etc, through voice control. The business competitors of Google on the smart home hubs include Amazon, Xiao Mi, Samsung…etc. The developers of the smart home devices collaborate with these smart home hub companies to launch new IoT products. These products are now able to bring marvelous convenience and pleasance to the consumers and therefore bloom quite rapidly. Despite is widely adopted in many countries already, the smart home system also causes privacy concern to the consumers. This thesis is to investigate the impact of the privacy risk and the perceived benefit caused by the smart home voice assistant to the potential consumers’ intention of adoption. This study concludes that the privacy concern is the major risk to the potential consumers, whereas the perceived benefit is what they expect and gain. This study further explored the factors influencing the privacy concern and the perceived benefit. Furthermore, despite people worry about their privacy, they are so tired of managing their privacy and will still adopt these products that could infringe their privacy. We think that this is going to be a major issue in our community and will influence the privacy control particularly on the privacy concern and their intention of adoption.
This research was performed by collecting the questionnaire from the potential consumers who have never used any smart home voice assistant in Taiwan. A total of 300 effective questionnaires were received and analyzed by the Smart PLS 3 analytic tool. Our research showed that the privacy concern and the perceived benefit are both correlated with the potential consumers’ intention of adoption. The consummate privacy policy will reduce the consumers’ privacy concern. However, the privacy control and the consumer trust are irrelevant with the privacy concern. The consumer trust, as well as their adoption of innovative technology, will increase the perceived benefit of the products and services. Besides, the privacy fatigue significantly moderates the privacy concern of potential consumers and their intention of adoption.
39
Chen, Chien-Chou, and 陳建州. "Applying Smart Phone and Personal Digital Assistant in the Diagnosis of Insomnia." Thesis, 2011. http://ndltd.ncl.edu.tw/handle/58272989899514413019.
Full textAbstract:
碩士<br>國立陽明大學<br>醫學工程研究所<br>99<br>Insomnia is a common health issue. According to research findings, insomnia had higher prevalence rate year by year. Sleep disturbance is associated with major psychiatric disorders and some chronic diseases such as diabetes mellitus, hypertension, hyperlipidemia, etc.
Diagnosis of insomnia is mainly by the method of diagnostic interview, few using instruments. The rate of misdiagnosis of insomnia and misuse of hypnotics is high if diagnosis is made only by interviewing. Examination of insomnia by instrument is difficult due to lack of resources and too expensive in Taiwan. So it is time to develop new tools which are cheap and effective to discover the real problem of insomnia.
In our research, computer programs were developed for hand-held equipment to collect data of sleep. Sleep-related questionnaire and diagnostic interview was also done. Data of these diagnostic tools were analyzed and compared.
Twenty three subjects, consisting of 11 non-insomnia participants and 12 psychiatric outpatients completed the experiment. The results showed the data of equipment and questionnaire had good consistence in time of go to bed, wake up, visual analog scale. Data of equipment showed superior information about sleep efficiency and some detailed data. But it showed inconsistence in evaluating about difference of difficulty in falling asleep and fragmented sleep. This method could provide more information for diagnosis of insomnia and resolution of problems.
40
LIN, KAN-FU, and 林侃賦. "The Research and Implementation of Artificial Intelligence-Based Smart Door Bell Assistant." Thesis, 2017. http://ndltd.ncl.edu.tw/handle/234mx5.
Full textAbstract:
碩士<br>國立臺北科技大學<br>電機工程研究所<br>105<br>This thesis aims to present an artificial intelligence-based smart-doorbell assistant (AISA), which can enormously enhance the extra functions of traditional doorbell as well as integrate with smart home and intelligence surveillance system to increase residential security. By using battery-based webcam as the terminal server, AISA combines client-to-client (C2C) communication protocol with Amazon Web Services (AWS), such as cloud computing (AWS EC2), image recognition (AWS Rekognition), and speech synthesis (AWS Polly).
When AISA detects a visitor, the system automatically recognizes the identity of the visitor and sends the message to the users smartphone. The user and the visitor are able to communicate mutually with each other via AISA and C2C communication protocol. Therefore, compared with the traditional doorbell, this project undertakes a detailed analysis of AISA—featuring instant reaction to any creatures or humankind whenever receiving their visiting.
41
Chen, Po-Kai, and 陳柏愷. "Development and application of IoT smart home products integrated in voice assistant interface." Thesis, 2018. http://ndltd.ncl.edu.tw/handle/72c592.
Full textAbstract:
碩士<br>元智大學<br>機械工程學系<br>106<br>Many smart home products still use graphic user interface operation such as mobile phone remote control or displaying the usage status based on display-based. The number of smart home IoT devices that added to the voice user interface are still small.
The purpose of the research is to integrate Google Assistant in the cloud infrastructure of “WhizSeries” smart home IoT products then achieve voice control function and expand the cloud infrastructure. Create design process and cloud infrastructure for integrating smart home IoT products in Google Assistant, including the design process of voice controlled IoT devices, format of devices properties and transmission data, establishing a standard cloud docking function on AWS server supported voice assistant cloud services, and create an exclusive Google Assistant service for “WhizSeries”.
42
"Domain-Agnostic Context-Aware Assistant Framework for Task-Based Environment." Master's thesis, 2020. http://hdl.handle.net/2286/R.I.57245.
Full textAbstract:
abstract: Smart home assistants are becoming a norm due to their ease-of-use. They employ spoken language as an interface, facilitating easy interaction with their users. Even with their obvious advantages, natural-language based interfaces are not prevalent outside the domain of home assistants. It is hard to adopt them for computer-controlled systems due to the numerous complexities involved with their implementation in varying fields. The main challenge is the grounding of natural language base terms into the underlying system's primitives. The existing systems that do use natural language interfaces are specific to one problem domain only.
In this thesis, a domain-agnostic framework that creates natural language interfaces for computer-controlled systems has been developed by making the mapping between the language constructs and the system primitives customizable. The framework employs ontologies built using OWL (Web Ontology Language) for knowledge representation purposes and machine learning models for language processing tasks. It has been evaluated within a simulation environment consisting of objects and a robot. This environment has been deployed as a web application, providing anonymous user testing for evaluation, and generating training data for machine learning components. Performance evaluation has been done on metrics such as time taken for a task or the number of instructions given by the user to the robot to accomplish a task. Additionally, the framework has been used to create a natural language interface for a database system to demonstrate its domain independence.<br>Dissertation/Thesis<br>Masters Thesis Software Engineering 2020
43
Kao, Harriel Pei-Yu, and 高珮瑜. "Contextual Design and Innovative Applications of Chatbot Assistant for the Smart Aging Home in Place." Thesis, 2018. http://ndltd.ncl.edu.tw/handle/53dq9d.
Full textAbstract:
碩士<br>國立臺北科技大學<br>互動設計系<br>106<br>More resources have been put on the ageing people of incapacitation or dementia in Taiwan in the past. Nowadays our government has been promoting long-term care 1.0 and the advanced edition long-term care 2.0 for many years. It focuses on the senior citizens “who are getting old but still healthy” and the places where can accept the local ageing as the main goals. Through the focusing group interviewing of the pilot study, most elderly people like to be aging under their familiar circumstances. With such study conclusion and active promotion of our government, we can predict the business opportunity of “Aging in Place” will grow obviously. The present young adults and middle adults (30~49 years old) who come in contact with various novel technology products will need cross-industry integration and innovative service when they stride into middle and elderly age in the future. This is not a problem which can be solved by single enterprise or industry.
Euromonitor (2017) providing market research reports on Consumer Market Surveys, with trends market analysis and consumer preferences. The meaning “Old is the New Young” is the future youngster senior people. With more and more brand-new technological products flooded around at present, the elderly consumers will be influenced by more intelligent and user-friendly products in the very near future. They certainly will be more familiar with higher technology and can be more acceptable with technological products than the elderly nowadays. Therefore the future elderly definition will be changed little by little. The consumers’ demand will turn out to be more multiple to create the youngster seniors consuming trend. Their consuming style will be different from the past senior citizens as we know.
The present research mainly stresses on the future youngster senior people who are unable to hold or touch the cellphone screen, but through the sound-control orders of language distinguished conduct, they can still be offered more convenient and wiser operation than the operation convenience offered by the interaction dimension between man and machines. Such convenience can build up the smart home equipment to remember the users’ characteristics, habits and expected contextual design of users’ demand. Then it can set up the smart home installment which is suitable for the future youngster senior citizens. Furthermore it can also offer users’ usability and experience with integration.
In the pilot study, the researchers aim at the Smart Care, Aging in Place, Contextual Design, Smart Home and Intelligent Voice Assistant to understand wholly. They are divided into three stages: The first stage is the experimental study. They proceed to the experimental test with the present intelligent voice assistant to evaluate how the elderly operate and control the voice control of intelligent voice assistant and find out the technical restrictions. The second stage targets 50~65 year-old senior citizens and 30~49 year-old middle age people to hold focus group interviews. Thus the researchers can figure out how the senior citizens and different age groups understand or accept the smart technical products and the smart family to find out their exact demands. Hopefully the intelligent voice assistant can offer the demanding contextual design and converge the results on the operation and control of intelligent voice assistant. The third stage focuses on the users’ using situation about intelligent voice assistant to make the preliminary investigation of contextual design.
The frameworks of the present research can be divided into two parts: creative design application environment analysis and creative design function analysis. First, through the focus interview of the elderly and the middle groups, the researchers can find out what they really need and define the biographical notes and data. After that, the researchers present creative users’ journey map and contextual design plan. Then they can direct at creative application interactive contextual design of intelligent voice assistant to proceed to intelligent voice and environmental function design analysis through the method of Kano Model questionnaire. In the meanwhile the researchers should take the users’ satisfaction into consideration. Furthermore they should sketch out the importance order of the environmental application function through QFD (Quality Function Deployment) analysis to evaluate the whole environment and function application to be more comprehensive. Eventually, using intelligent voice assistant, the researchers can aim at smart home intelligent voice assistant system to proceed to the users’ experience evaluation, Through the design of the users’ demands, satisfaction and experience, they can also explore the overall usages and the integrated effects of environmental application design and the value of developmental dimension.
To sum up the above analysis and conclusion, the contextual design in the present study can show the positive effects to promote the future smart aging in place’ elderly resident voice assistant users the operating experience and to solve the aging in place problems. We can learn from the examinees’ interviews that the voice control assistant completes anything assigned is a new and convenient function. However, back to the first place, the examinees suggest that the smart installment App and the real assistance of button are still indispensable. After all the voice control can’t reach the users’ demand completely. Keeping the practical button or cellphone/Tablet PC App to control operation mode of the smart home installment can make the function more complete. The final results indicate that the examinees have the positive response toward the future smart aging in place resident voice control contextual design. There is full feasibility and design developmental potentiality. The present study can offer those academic fields or enterprises which want to develop smart voice assistance contextual design for reference.
44
Sheng, Yen Lee, and 李昇衍. "Developing a Multimedia APP on Smart Phone Served as a Teaching Assistant for Early Childhood Abacus and Mental Arithmetic Education." Thesis, 2013. http://ndltd.ncl.edu.tw/handle/22084630601807794996.
Full textAbstract:
碩士<br>中州科技大學<br>工程技術研究所<br>101<br>With the advancement of technology, using smart phones has become a popular trend. It is already very common that people use smart phones to surf the Internet, check the map, book tickets and do other daily work .Also, many people use smart phone APPs to download games for killing time. As a result, more and more people become the “smart phone addicts”. Because of the trend of smart phones, the widely use of multimedia teaching aids in the early childhood education, and researcher’s passion for abacus and mental arithmetic education, the researcher uses Android SDK software and JAVA programming languages on the Android system platforms. He also joins the abacus, mental and decimal arithmetic with lovely patterns and adjective multimedia teaching materials, and develops a multimedia app on smart phone served as a teaching assistant - "Bear teach you abacus" for early childhood abacus and mental arithmetic education. The researcher hopes to raise interest in learning abacus and mental arithmetic for preschool children. Also, he hopes that it can become useful electronic multimedia aids for kindergarten teachers and parents which can help them save the expenses of entity abacus and exercises.
Keyword:Abacus and Mental Arithmetic , APP(Application) , Multimedia Teaching Aids
45
Moreira, Wanessa de Andrade. "Smart speakers and the news in Portuguese: consumption pattern and challenges for content producers." Master's thesis, 2021. http://hdl.handle.net/10071/23092.
Full textAbstract:
The voice assistants popularized by smartphones are now the driving force behind a device that is making its way into homes in recent years: smart speakers. Since 2018, these devices are available in Brazilian Portuguese. These devices are also a new platform for news distribution and consumption. How does the platform define the content that will be delivered to the user? What challenges do content producers face? How does the user access this news? To try to find the answers to these questions, we conducted a literature review, a market situation point through business reports, developed an online survey with smart speaker users and also interviewed content producers. The answers show that there is influence of algorithms and the business model. An extra challenge for Portuguese content producers is the language itself. The voice assistant systems still have difficulty understanding words and expressions in Portuguese for users. This work may be helpful for content producers, especially Portuguese-speaking ones, to find ways to reach their audience.<br>Os assistentes de voz popularizados pelos smartphones são agora o motor de um aparelho que está entrando nas casas nos últimos anos: os smart speakers. Desde 2018, Esses equipamentos estão disponíveis em português do Brasil. Tais aparelhos são também uma nova plataforma para distribuição e consumo de notícias. Como a plataforma define o conteúdo que será entregue ao usuário? Quais os desafios que os produtores de conteúdo enfrentam? Como o usuário acessa essas notícias? Para tentar encontrar as respostas a essas questões, fizemos uma revisão de literatura, um ponto de situação do mercado através de relatórios empresariais, desenvolvemos um inquérito online com usuários de smart speakers e também entrevistamos produtores de conteúdo. As respostas mostram que há influência dos algoritmos e do modelo de negócio. Um desafio extra para os produtores de conteúdo em português é a própria língua. Os sistemas dos assistentes de voz ainda apresentam dificuldade de compreensão de palavras e expressões em português para os usuários. Este trabalho poderá ser útil para produtores de conteúdo, especialmente de língua portuguesa, encontrarem maneiras de chegar ao público.
46
Гоцко, Єлизавета Олегівна, та Yelyzaveta Olehivna Hotsko. "Дослідження європейського досвіду впровадження соціальних комунікацій у розумні будинки". Master's thesis, 2021. http://elartu.tntu.edu.ua/handle/lib/36768.
Full textAbstract:
Проведено аналіз наукових статей та публікацій по темі кваліфікаційної роботи.
У кваліфікаційній роботі розглянуто концепцію соціальних комунікацій та вплив соціальних мереж на думку людей та їх зв'язок з розумним містом.
Розглянуто різні протоколи розумного будинку. Безпровідні протоколи стають все більш поширеними, але провідні варіанти також залишаються надійними.
Проведено глибинний аналіз дослідження, в якому брали участь респонденти з чотирьох Європейських міст. В результатах дослідження перераховані найбільш значні соціальні проблеми в розумних будинках. Запропоновано дії щодо зменшення негативного ефекту на життя в розумному будинку.
The analysis of scientific articlesand publications on the top icof qualification the sisiscarried out.
The qualification the sisconsiders the concept of social communication sand the influence of social networks on people'sopinionand their connection with a smar tcity.
Various protocols of a smart house are considered. Wirelessprotocolsarebecomingmorecommon, butwiredoptionsalsoremainreliable.
Anin-depth analysis of study in which respondents from four European cities participated was performed. The results of the study list the most significant social problem sin smart homes. Action store duce the negative effecton life in a smart home are proposed.<br>Вступ 8
1 Аналіз предметної області 10
1.1 Соціальна комунікація в інформаційному суспільстві 10
1.1.1 Постановка проблеми 11
1.1.2Аналіз проблеми 11
1.1.3 Зв'язок соціальної комунікації та розумного міста 14
1.1.4 Використання великих даних у розумному місті 15
1.2 Концепція розумного будинку 17
1.3 Комунікація людей в соціальних мережах 19
1.4 Віртуальні голосові помічники 22
1.4.1 Технологіївеликихкомпаній 23
1.4.2 Розширення на основі голосового помічника 24
1.4.3 Штучний інтелект як основа розпізнавання мови 24
1.4.4 Можливості електронної комерції 25
1.5 Висновки до першогорозділу 25
2 Взаємодія пристроїв розумного будинку 27
2.1 Необхідністьствореннязагального протоколу іот. 27
2.2 Користь протоколів іот для виробників та користувачів 28
2.3 Компоненти для зв’язку пристроїв іот 29
2.3.1 Пристрої інтернету речей 30
2.3.2 Підключення бездротових пристроїв 31
2.3.3 Методи і протоколи локального зв’язку 32
2.3.4 Шлюзи 36
2.3.5 Мережеві сервери і хмарні додатки 38
2.3.6 Інтерфейс користувача 39
2.4 Приклад на основі вимикача світла 40
2.5 Висновки до другого розділу 41
3 Соціальні проблеми розумного будинку: огляд досвіду чотирьох
європейських міст………………………………………………………….......42
3.1 Переваги та недоліки розумного будинку. 42
3.2 Соціальні бар’єри розумних будинків 44
3.3 Концептуальна модель 45
3.4 Тематичне дослідження 47
3.5 Висновки до третього розділу 55
4 Охорона праці та безпека в надзвичайних ситуаціях 56
4.1 Міжнародний досвід та світові методики оцінки ризиків для
здоров’я працівників 56
4.1.1 Рекомендації для представників unison з охорони праці та
Техніки безпеки. 57
4.1.2 Оцінка ризиків covid-19 58
4.2 Проведення рятувальних та інших невідкладних робіт на об’єкті
Господарської діяльності в осередку ураження (зараження) 60
4.3 Висновки до четвертого розділу 64
Висновки 65
Перелік використаних джерел 66
Додатки
47
Koffler, Viola. "Voice user interfaces : a consumer behavior perspective in the perception and intention to adopt smart speakers in German households." Master's thesis, 2021. http://hdl.handle.net/10400.14/35355.
Full textAbstract:
Voice user interfaces have become increasingly popular, and many consumer-level products containing this technology have been launched to the market. One of these products is the smart speaker, which shows high potential for consumer adoption. Companies will be interested in entering this lucrative market, simplifying people’s life and making the smart speaker a mainstream product.
However, not many studies focus on the consumer behavior perspective.
This dissertation aims to explore factors that influence the perception and intention to use smart speakers in German households, by proposing and analyzing an extended technology acceptance model (TAM).
Data includes secondary data as well as primary data, from qualitative and quantitative analysis.
The result showed that the factors attitude, household size for users and non-users and perceived usefulness, social influence and interest in innovation influences the intention to use smart speaker, whereas the perception and attitude is influenced by perceived usefulness (PU) and privacy concerns.
Following these study results, companies should try to optimize the features of smart speaker to guarantee a higher perceived usefulness, tackle privacy concerns and investing in right targeted consumer group marketing campaigns.
This study gives a solid basis for further research in the field of voice user interfaces and gives managerial implications for companies.<br>As interfaces de voz de utilizador têm-se tornado cada vez mais populares, e muitos produtos a nível do consumidor que contêm esta tecnologia têm sido lançados no mercado. Um destes produtos é a coluna inteligente, que mostra um elevado potencial para a adopção pelo consumidor. Empresas estarão interessadas em entrar neste mercado lucrativo, simplificando a vida das pessoas e tornando o altifalante inteligente num produto padrão.
No entanto, não há muitos estudos que se concentrem na perspectiva do comportamento do consumidor.
Esta dissertação visa explorar factores que influenciam a percepção e intenção de utilizar colunas inteligentes em lares alemães, propondo e analisando um modelo de aceitação de tecnologia alargada (TAM).
Os dados incluem dados secundários, bem como dados primários, de análises qualitativas e quantitativas.
O resultado mostrou que os aspetos atitude do usuário, o tamanho do agregado familiar de utilizadores e não-utilizadores e a percepção da utilidade, influência social e interesse na inovação influenciam a intenção de utilizar falantes inteligentes, enquanto que a percepção e atitude é influenciada pela percepção da utilidade (PU) e preocupações de privacidade.
Na sequência destes resultados do estudo, as empresas devem tentar optimizar as características do "smart speaker" para garantir uma maior percepção da utilidade, lidar com as preocupações de privacidade e investir em campanhas de marketing de grupos de consumidores bem direccionadas.
Este estudo fornece uma base sólida para uma maior investigação no campo das interfaces de voz de utilizador e dá implicações de gestão para empresas.
48
Calaça, Jorge Duarte Lomelino. "Smartly water: rede de águas Inteligente." Master's thesis, 2019. http://hdl.handle.net/10400.13/2379.
Full textAbstract:
A água é um recurso essencial para a nossa sobrevivência, mas é cada vez mais escassa. Estima-se que daqui a 32 anos não existirão reservas suficientes de água para a produção alimentar.
Este projeto tem como objetivo o desenvolvimento de um sistema que permita consciencializar as pessoas para uma redução do consumo de água. Tendo esse objetivo em vista, desenvolveu-se um sistema que inclui sensores e atuadores dispersos pela rede de águas. Os sensores permitem a recolha de dados do consumo de água, da temperatura e da pressão. No que toca aos atuadores, estes permitem o controlo/corte de água. Toda a informação recolhida é armazenada numa base de dados.
O sistema tem ao seu dispor vários meios para a promoção da consciencialização do utilizador. Em primeiro lugar, possui uma aplicação móvel que permite ao utilizador estar ao corrente dos seus consumos. Em segundo lugar, conta com um website que tem como objetivo ilustrar os consumos do utilizador. Em terceiro lugar, usufrui de um assistente virtual que permite ao utilizador estar ao corrente dos seus consumos, controlar a rede de água por comandos de voz e auxiliá-lo nas tarefas diárias relacionadas com a água. O auxílio nas tarefas diárias permite a promoção de um comportamento responsável no consumo de água. Um exemplo desse auxílio é o ajudar na tarefa da lavagem dos dentes, em que o assistente ao longo da tarefa vai mantendo o utilizador ao corrente do tempo decorrido e controla a rotina de abertura e fecho da torneira.
Neste projeto implementou-se o sistema em 3 casas e um edifício. Estas implementações permitiram avaliar o funcionamento do sistema e a recolha de consumo de diversos utilizadores. Avaliando os dados recolhidos, estes permitiram a deteção de padrões de consumo nas rotinas de tomar duche, lavar os dentes e a recarga do autoclismo.<br>Water is an essencial resource for our survival, but it is becoming increasingly scarce. It is estimated that in 32 years, there will not be enough water reserves for food production. The objective of this project is the development of a system to increase peoples awareness to water consumption reduction. For that, a system comprised of sensors and actuators throughout the water network was developed. The sensors gather information regarding water consumption, temperature and pressure. As for the actuators, these allow the control of water flow. Then, all the gathered information is stored in a database. The system has at its disposal several means to promote water usage awareness to the user. Firstly, it has a mobile app which allows the user to keep track of the consumptions, as well as to monitor the goal of achieving ideal consumptions. Secondly, it also has a website, which illustrates the consumptions to the user. Finally, it has a virtual assistant, which allows the user to keep track of its consumptions, control the water network with voice activated commands and to aid in the daily chores related with water. This aid allows the promotion of a responsible behaviour with regards to water consumption. An exemple of this, is the aid in the task of brushing the teeth, wherein the virtual assistant keeps the user up to date on the elapsed time throughout the task and, at the end of it, controls the opening and closing of the tap. In this project the system was implemented in 3 houses and in one building. These implementations allowed the evaluation of system’s operations, as well as the gathering of the consumption data of several users. By analysing the gathered information, it was possible to detect consumption patterns, specific to the routines of showering, brushing the teeth and toilet flushing.
49
Martins, Maria M. "Online control of a mobility assistance smart walker." Master's thesis, 2011. http://hdl.handle.net/1822/19924.
Full textAbstract:
Dissertação de mestrado integrado em Engenharia Biomédica<br>This work presents the NeoASAS project that was developed at the Bioengineering Group, Consejo Superior de Investigaciones Cientificas (CSIC) in Madrid. Further, it continued with adaptations and improvements at Minho University with the Adaptive System Behavior Group (ASBG) in Guimarães, being designated by ASBGo Project.
These developments include the conceptual design, implementation and validation of Smart Walkers with a new interface approach integrated into these devices. This interface is based on a joystick and it is intended to extract the user’s movement intentions. It was designed to be user-friendly and efficient, meeting usability aspects and focused on a commercial implementation, but not being demanding at the user cognitive level. Considering the ASBGo walker, the overall assemblage, mechanical adjustments, electronics and computing have been performed.
First, a review about the mobility assistive devices is presented, specially focused on Smart Walkers. Despite the intensive research, in current literature, there are not many works providing a "point of the situation", and explaining the role that robotics can play in this domain.
Healthy users performed preliminary sets of experiments with each walker, which showed the sensibility of the joystick to extract command intentions from the user. These signals presented a higher frequency component that was attenuated by a Benedict-Bordner g-h filter, considering the NeoASAS walker and by a Butterworth circuit, considering the ASBGo walker. These methodologies offer a cancelation of the undesired components from joystick data, allowing the system to extract in real-time user’s commands. Based on this identification, an approach to the control architecture based on a fuzzy logic algorithm was developed, in order to allow the control of the walkers’ motors. In addition, a set of sensors were integrated on the walker for safety reasons: an infrared sensor to detect if the user is falling forwards; two force sensors to make sure that the user is properly grabbing the hand support; and two force sensors in the support forearms to verify if the user is with his forearms properly supported. This will make sure that the device stops when one of these situations happens.
Thus, an assistive device to provide safety and natural manoeuvrability was conceived and offers a certain degree of intelligence in assistance and decision-making. These results will be used to advance towards a commercial product with an affordable cost, but presenting high reliability and safety. The motivation is that this will contribute to improve rehabilitation purposes by promoting ambulatory daily exercises and thus extend users’ independent living.<br>Este trabalho apresenta o projecto NeoASAS desenvolvido no Grupo de Bioengenharia, do Consejo Superior de Investigaciones Cientificas (CSIC) em Madrid. Este teve continuidade com adaptações e melhorias na Universidade do Minho com o grupo Adaptative System Behaviour (ASBG) em Guimarães, sendo designado por projecto ASBGo.
Estes desenvolvimentos incluem o projecto concetual, implementação e validação de andarilhos inteligentes com uma nova interface integrada nestes dispositivos. Esta interface é baseada num joystick e tem como objetivo a extração de intenções de comando do utilizador, sendo intuitiva e eficiente. Atende a aspectos de usabilidade e está focada numa aplicação comercial, não sendo exigente a nível cognitivo. Considerando o andarilho ASBGo, foi realizada a construção deste, bem como, ajustes mecânicos, eletrónicos e programação.
É apresentada uma revisão sobre os dispositivos de assistência à marcha, tendo especial enfoque os andarilhos. Apesar da intensa investigação, na literatura não existem trabalhos que apresentem o ponto de situação desta área, bem como o seu papel na robótica de reabilitação.
Depois foram realizados testes com utilizadores, mostrando a sensibilidade que o joytick tem na identificação de inteções de comando do utilizador. Além disso, os sinais apresentam uma componente de alta frequência que foi atenuada, no caso do NeoASAS, com um filtro g-h Benedict-Bordner, e no caso do ASBGo, através de um filtro Butterworth implementado em hardware.
As metodologias apresentadas oferecem um cancelamento componentes indesejáveis, permitindo ao sistema a extração das intenções de comando do utilizador em tempo real. Desta forma, uma arquitetura de controlo baseada em fuzzy logic foi desenvolvida de maneira a fornecer uma assistência segura ao utilizador, através do controlo dos motores. Foram também integrados um conjunto de sensores no andarilho por razões de segurança: um sensor infravermelho para detetar a queda frontal do utilizador, dois sensores de força nos apoios de mão para detetar se o utilizador está a agarrá-los, e dois sensores de força nos suportes de antebraço para certificar que o utilizador está devidamente apoiado.
Assim, foi concebido um dispositivo que garante a segurança do utilizador e oferece um certo grau de inteligência e tomada de decisão. Estes resultados serão utilizados para a criação de um produto comercial com custo acessível, mas com alta confiabilidade. A motivação deste trabalho reflete-se na contribuição que este dispositivo terá na melhoria da reabilitação e desenvolvimento de dispositivos ambulatórios para promover exercicios diários, e melhorar a vida dos utilizadores.
50
Liao, Lu-Xun, and 廖祿勛. "Development of Smart Assistance System for Patients with Blepharoptosis." Thesis, 2018. http://ndltd.ncl.edu.tw/handle/3556du.
Full text