To see the other types of publications on this topic, follow the link: Intelligent machine.
Dissertations / Theses on the topic 'Intelligent machine'
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 'Intelligent machine.'
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
Henderson, Graham Barry. "The intelligent camera system." Thesis, Lancaster University, 1992. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.239905.
Full text
2
Ma, Ye M. Eng Massachusetts Institute of Technology. "Human-machine teaming for intelligent demand planning." Thesis, Massachusetts Institute of Technology, 2020. https://hdl.handle.net/1721.1/127102.
Full textAbstract:
Thesis: M. Eng. in Supply Chain Management, Massachusetts Institute of Technology, Supply Chain Management Program, May, 2020<br>Cataloged from the official PDF of thesis.<br>Includes bibliographical references (pages 66-70).<br>The second machine age is reshaping the way we work, do business, and collaborate. Today collaboration is switching from just among humans to between humans and machines. Mundane and repetitive tasks will be done by machines automatically, while humans can develop insights and make wise decisions supported by data streaming from intelligent machines. If and how different human-machine teaming decision-making structures would influence the organization's performance is important to understand, so that human-machine teaming capabilities could contribute the most to business outcomes. By using the augmented inverse propensity weight estimator method, this research empirically analyzes the average treatment effects of three different human-machine decision-making structures: Full human to AI delegation, Hybrid AI-Human with adequate human intervention, and Hybrid AI-Human with all steps of demand planning overrides.<br>These three decision-making structures are defined as treatment groups, and the traditional manual demand-adjustment process is defined as the control group. Effects of switching human-machine teaming decisionmaking structures from one to another are also analyzed. The performance of each treatment and control group is measured by the long-term forecast accuracy, short-term forecast accuracy, and customer inventory level. The project is based on an IT collaboration project between a large fast-moving consumer goods company and one of its largest e-commerce customers. The project implemented an AI-enabled demand-adjustment process to incorporate the external e-commerce customer demand signals into existing demand-planning process. Demand planners engage in the demand-adjustment process via web-based interfaces, to apply human judgment-based decisions. All the stock keeping units are randomly assigned to treatment and control groups.<br>The results show that after the implementation of human-machine teaming decision-making structures, both demand-forecast accuracy and inventory level are strongly improved by at least 47%. Overall, the Hybrid AI-Human with adequate human intervention model is the optimal decision-making structures between human and machine, which improves the short-term forecast accuracy by 53%, long-term forecast accuracy by 64%, and inventory level by 70%. The Hybrid AI-Human with all steps of demand planning overrides model performed worse than the previous model, because of the heavy human overrides. Additionally, those AI enabled decisionmaking structures works better for low-turnover products than high-turnover ones.<br>by Ye Ma.<br>M. Eng. in Supply Chain Management<br>M.Eng.inSupplyChainManagement Massachusetts Institute of Technology, Supply Chain Management Program
3
Sathyan, Anoop. "Intelligent Machine Learning Approaches for Aerospace Applications." University of Cincinnati / OhioLINK, 2017. http://rave.ohiolink.edu/etdc/view?acc_num=ucin1491558309625214.
Full text
4
Rashid, Zahin Azher. "Intelligent Scheduling for Yarn : Using Online Machine Learning." Thesis, KTH, Skolan för informations- och kommunikationsteknik (ICT), 2017. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-219607.
Full textAbstract:
Many big companies who provide cloud infrastructure, platforms and services have to face a lot of challenges in dealing with big data and execution of thousands of tasks that run on servers. Thousands of servers running in cloud consume a large amount of energy which increases operating cost to a great extent for companies hosting infrastructures and platforms as services. Hundreds of thousands of applications are submitted every day on these servers by users. On submission of applications, somehow the total resources are not properly utilized which cause the overall operating cost to increase. A distribution of Apache Hadoop called HOPS is developed at SICS Swedish ICT and efforts are made to make it a better platform for institutions and companies. Yarn is used as the resource management and scheduling framework which is responsible for allocating resources such as memory and CPU cores to submitted applications. Yarn simply allocate resources based on the default set of values or what user has demanded. Yarn has no prior information about the submitted applications so it is very much possible that allocated resources are more or less than required. Energy is being wasted if fewer resources are required or application will probably not succeed if required more. In this research project, different techniques and methods are looked into for the collection of useful metrics related to applications and resources from Yarn, Spark and other sources. Machine Learning is becoming a very popular technique nowadays for the optimization of systems dealing with big data in a cloud environment. The goal is to collect these vital metrics and build a machine learning model to commission smart allocation of resources to submitted applications. This can help to increase the efficiency of the servers in the cloud and reduce the operating cost. Finally, a machine learning model was developed and memory and vCores were successfully predicted to be allocated to applications.<br>Många stora företag som tillhandahåller molninfrastruktur, plattformar och tjänster måste möta många utmaningar när det handlar om stora data och utförandeav tusentals uppgifter som körs på servrar. Tusentals servrar som kör i molnetförbrukar en stor mängd energi vilket i hög grad ökar driftskostnaden för företag som tillhandahåller infrastrukturer och plattformar som tjänster. Hundratusentals applikationer skickas varje dag på dessa servrar av användare. Vid inlämning av ansökningar på något sätt utnyttjas inte de totala resurserna korrekt, vilket medför att de totala driftskostnaderna ökar. En distribution av Apache Hadoop, kallad HOPS, är utvecklad hos SICS Swedish ICT, och det görs ansträngningar för att göra den till en bättre plattform för institutioner och företag. Garn används som resurshanteringsoch schemaläggningsramen som är ansvarig för att allokera resurser som minne och CPU-kärnor till inlämnade applikationer. Garn fördelar helt enkelt resurser utifrån standardvärdet av värden eller vilken användare som har krävt. Garn har ingentidigare information om de inlämnade ansökningarna så det är mycket möjligtatt tilldelade resurser är mer eller mindre än vad som krävs. Energi slösas bort om färre resurser krävs eller ansökan kommer sannolikt inte att lyckas om det behövs mer. I detta forskningsprojekt undersöks olika tekniker och metoder för insamling av användbara mätvärden relaterade till applikationer och resurser från Garn, Spark och andra källor. Machine Learning blir idag en mycket populär teknik för optimering av systemsom hanterar stora data i en molnmiljö.Målet är att samla in dessa viktigamätvärden och bygga en maskininlärningsmodell för att beställa smart fördelning av resurser till inlämnade applikationer. Detta kan hjälpa till att öka effektiviteten hos servrarna i molnet och minska driftskostnaden. Slutligen utvecklades en maskininlärningsmodell och minnet och vCores hade framgångsrikt förutsagt att tilldelas applikationer.
5
Angelikaki, C. "An intelligent sample changer." Thesis, University of Reading, 1988. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.234786.
Full text
6
Lee, Siu-keung, and 李少強. "Reinforcement learning for intelligent assembly automation." Thesis, The University of Hong Kong (Pokfulam, Hong Kong), 2002. http://hub.hku.hk/bib/B31244397.
Full text
7
Youn, Bong-Soo. "Intelligent knowledge acquisition system /." Online version of thesis, 1989. http://hdl.handle.net/1850/10444.
Full text
8
Kang, Seong Pal Mechanical & Manufacturing Engineering Faculty of Engineering UNSW. "Virtual human-machine interfaces and intelligent navigation of wheelchairs." Awarded by:University of New South Wales. School of Mechanical and Manufacturing Engineering, 2006. http://handle.unsw.edu.au/1959.4/24359.
Full textAbstract:
This thesis is concerned with the development of virtual Human-Machine Interfaces (HMI) and navigation method for wheelchair systems. For virtual HMI, hand gesture recognition is employed, and two different hand gesture recognition algorithms have been developed. One is based on the geometric properties of a hand shape, and the other algorithm is based on the curvature of a hand shape contour. In the hand gesture recognition algorithm using geometric properties of a hand shape, eight non-dimensional parameters are computed and identifies hand shapes by comparing the ranges of the parameters to the statistical range information. This algorithm is invariant at scale, but does not work properly if the forearm of a hand shape is cluttered. The curvature based hand gesture recognition algorithm recognizes hand gestures using a combination of hand shape contour geometry and a non-dimensional quantity derived using the curvatures of the hand shape contour. The algorithm produces a set of signatures of the contour and identifies each hand gesture by finding matched template signatures. This algorithm is not affected by the forearm of a hand shape, but the scaling procedure is required. The developed gesture recognition system is implemented on a wheelchair in two different modes of operations, namely, the manual mode and the map (autonomous) mode. In the manual mode, the user continuously interacts with the wheelchair and controls the speed and the steering using the position and the orientation of hand gestures. In the map mode, the user selects a desired destination by pointing with a hand gesture onto a known map, and then the wheelchair initiates autonomous navigation. For wheelchair navigation, a doorway recognition algorithm and an obstacle avoidance algorithm have been developed. The wheelchair is localised by finding the doorway template in the specified zone. If the doorway recognition algorithm does not detect the doorway, it navigates to find the doorway using the obstacle avoidance algorithm. The obstacle avoidance algorithm finds obstacle edge points using range data and decides a safe passage for wheelchair navigation to find the doorway. Results obtained by implementing the above mentioned algorithms are presented.
9
Fang, Yajun Ph D. Massachusetts Institute of Technology. "Fusion-layer-based machine vision for intelligent transportation systems/." Thesis, Massachusetts Institute of Technology, 2010. http://hdl.handle.net/1721.1/60143.
Full textAbstract:
Thesis (Ph. D.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2010.<br>Cataloged from PDF version of thesis.<br>Includes bibliographical references (p. 307-317).<br>Environment understanding technology is very vital for intelligent vehicles that are expected to automatically respond to fast changing environment and dangerous situations. To obtain perception abilities, we should automatically detect static and dynamic obstacles, and obtain their related information, such as, locations, speed, collision/occlusion possibility, and other dynamic current/historic information. Conventional methods independently detect individual information, which is normally noisy and not very reliable. Instead we propose fusion-based and layered-based information-retrieval methodology to systematically detect obstacles and obtain their location/timing information for visible and infrared sequences. The proposed obstacle detection methodologies take advantage of connection between different information and increase the computational accuracy of obstacle information estimation, thus improving environment understanding abilities, and driving safety.<br>by Yajun Fang.<br>Ph.D.
10
CONTIGIANI, MARCO. "Machine vision and IoT applications in intelligent retail environments." Doctoral thesis, Università Politecnica delle Marche, 2017. http://hdl.handle.net/11566/245516.
Full textAbstract:
Il settore retail negli ultimi anni ha visto crescere sempre di più la necessità di acquisire informazioni sul comportamento dei clienti e come si muovono all’interno degli store. Queste informazioni consentono di ottimizzare il layout del punto vendita, migliorare l'offerta, innovare prodotti e massimizzare i profitti monitorando in realtime i comportamenti e le scelte dei clienti. Il punto vendita non è più ormai l'unico luogo dove avviene l'acquisto e per questo motivo deve essere in grado di allinearsi velocemente con l'esigenze dei clienti, trasformando gli spazi e l'esperienza di acquisto. Grazie all’utilizzo di soluzioni IoT basate sulla visione artificiale, sistemi di tracking indoor e sensori distribuiti per il monitoraggio ambientale è possibile raggiungere questo obiettivo. L’attività di ricerca ha avuto pertanto come focus principale lo studio ed il test di soluzioni basate sull’utilizzo di camere RGBD, sistemi UWB di tracking indoor e lo studio di reti distribuite di sensori capacitivi posizionati all’interno di pavimenti per il monitoraggio degli spostamenti. La validità dei sistemi di misura utilizzati e degli applicativi software implementati hanno permesso di realizzare un sistema completo di monitoraggio del punto vendita che, grazie all'uso di protocolli IoT di comunicazione, consente di sapere in tempo reale: quante persone entrano, come si muovano, come interagiscono, cosa comprano e quanto tempo impiegano a svolgere ciascuna delle precedenti azioni. Il percorso di ricerca è stato condotto in collaborazione con l’azienda Grottini Lab. Grazie a questa sinergia sono state effettuate numerose installazioni in ambienti di retail reali che hanno consentito di testare la validità delle soluzioni tecnologiche sviluppate ed allo stesso tempo di raccogliere numerosi dati utili all’analisi del comportamento di singoli e gruppi di individui negli ambienti retail.<br>In the retail sector, in recent years, has grown the need to acquire information about customer behavior. This information allows to optimize stores, improve the commercial offer, innovate products and maximize profits by monitoring in real time the behavior and choices of customers. The physical sales point is now no longer the only place where the purchase takes place and for this reason should be able to rapidly align with the needs of customers transforming the spaces and the shopping experience using the data collected. This aim can be achieved through the use of IoT solutions based on machine vision, indoor tracking systems and distributed sensors for environmental parameters monitoring.
In this context the research activity had as its main focus the study and development of solutions based on RGB-D cameras, UWB indoor tracking systems and the analysis of distributed networks of capacitive sensors placed inside floor for human movement control. The effectiveness of these measuring systems and the analysis software developed have allowed to realize a complete monitoring system for retail environments that thanks to IoT communication protocols allows to analyze in detail and in real time in a store: how many people, how they move, how interact, what they buy and how long it takes to perform each of the above actions.
The research path has been conducted in full collaboration and cooperation with the Grottini Lab company. Through this synergy several installations have been made in real stores that have allowed to test the validity of technological solutions designed and at the same time to collect many data useful for the behavior analys of individual and groups of customers.
The data produced with these analysis systems are collected on IoT cloud platforms and once stored, can be processed and made visible in appropriate dashboards in terms of charts and key performance indicator to make a careful analysis of the human behavior in a retail space.
11
Lubbe, H. G., and B. J. Kotze. "Machine learning through self generating programs." Interim : Interdisciplinary Journal, Vol 6, Issue 2: Central University of Technology Free State Bloemfontein, 2007. http://hdl.handle.net/11462/407.
Full textAbstract:
Published Article<br>People have tried different ways to make machines intelligent. One option is to use a simulated neural net as a platform for Genetic Algorithms. Neural nets are a combination of neurons in a certain pattern. Neurons in a neural net system are a simulation of neurons in an organism's brain. Genetic Algorithms represent an emulation of evolution in nature. The question arose as to why write a program to simulate neurons if a program can execute the functions a combination of neurons would generate. For this reason a virtual robot indicated in Figure 1 was made "intelligent" by developing a process where the robot creates a program for itself. Although Genetic Algorithms might have been used in the past to generate a program, a new method called Single-Chromosome-Evolution-Algorithms (SCEA) was introduced and compared to Genetic Algorithms operation. Instructions in the program were changed by using either Genetic Algorithms or alternatively with SCEA where only one simulation was needed per generation to be tested by the fitness of the system.
12
Song, Sukhan. "Intelligent machining control for turning process /." Digital version accessible at:, 1998. http://wwwlib.umi.com/cr/utexas/main.
Full text
13
Onyiagha, Chyke Godfrey. "Intelligent neural network access control of ATM network." Thesis, King's College London (University of London), 2002. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.271321.
Full text
14
St-Martin, Cormier Olivier. "Visual tracking of computer numerical control machine for intelligent controllers." Thesis, McGill University, 2013. http://digitool.Library.McGill.CA:80/R/?func=dbin-jump-full&object_id=114377.
Full textAbstract:
The purpose of this thesis is to determine the applicability of computer vision tracking as a source of feed-back in the development of an intelligent computer numerical (CNC) controller potentially capable of detecting problems and eventually correcting them. For this task, three types of visual tracking methods are quantitatively evaluated to determine which approach is more suited to the development of the visual tracker. Emphasis will also be placed on camera calibration.The three classes of visual methods chosen are a marker-based detector, a template matching algorithm, and a model-based tracker. From these, it is found that the marker-based detector is the most accurate for the CNC tracking task by providing sub-pixel accuracy and robustness to visual contaminants such as noise. A visual simulator is developed to provide a fully controllable testing environment to determine optimal system parameters. The simulator also provides precise ground-truth used to quantify the tracking error and obtain an accuracy baseline before applying the tracker on real data. The tracking algorithm is then applied to image sequences of a physical machine to evaluate the real performance of the system. The accuracy of the system is found to be limited mostly by image resolution.<br>Le but du présent mémoire est de déterminer si la vision par ordinateur peut être utilisée comme source d'information, afin de réaliser un contrôleur intelligent pour une machine contrôlée numériquement. Un tel contrôleur pourrait être capable de détecter les problèmes et ultérieurement être capable de les corriger. Pour cette tâche, trois types de traqueurs visuels sont évalués quantitativement afin de déterminer quelle approche est la plus adéquate. L'accent sera également mis sur la calibration de la caméra. Les trois classes de méthodes visuelles choisies sont: un détecteur de marqueurs, un algorithme de correspondance de gabarit et un traqueur de modèle. À partir de ces méthodes, il est constaté que le détecteur basé sur les marqueurs est le plus précis pour la tâche qui est de suivre une machine opérée par commande numérique, car il fournit une précision sous-pixel et est robuste aux contaminants visuels tel que le bruit.Un simulateur visuel est conçu pour fournir un environnement de test entièrement contrôlable afin de déterminer les paramètres optimaux du système. Le simulateur fournit aussi des données précises utilisées pour quantifier l'erreur du traqueur et obtenir un niveau de référence de précision avant d'appliquer le traqueur sur des données réelles. Le traqueur est ensuite appliqué à des séquences d'images d'une machine physique pour évaluer la performance réelle du système. La précision du système se trouve être limitée principalement par la résolution d'image.
15
Jia, Pei. "Audio-visual based human machine interface for an intelligent wheelchair." Thesis, University of Essex, 2011. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.531551.
Full text
16
Marzi, M. Hosein. "An intelligent condition monitoring system with applications to machine tools." Thesis, Cardiff University, 1994. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.265591.
Full text
17
Adhikari, Bhisma. "Intelligent Simulink Modeling Assistance via Model Clones and Machine Learning." Miami University / OhioLINK, 2021. http://rave.ohiolink.edu/etdc/view?acc_num=miami1627040347560589.
Full text
18
Teltz, Richard W. "Open architecture control for intelligent machining systems." Thesis, National Library of Canada = Bibliothèque nationale du Canada, 1998. http://www.collectionscanada.ca/obj/s4/f2/dsk1/tape11/PQDD_0006/NQ42883.pdf.
Full text
19
Wang, Ying. "Cooperative and intelligent control of multi-robot systems using machine learning." Thesis, University of British Columbia, 2008. http://hdl.handle.net/2429/905.
Full textAbstract:
This thesis investigates cooperative and intelligent control of autonomous multi-robot systems in a dynamic, unstructured and unknown environment and makes significant original contributions with regard to self-deterministic learning for robot cooperation, evolutionary optimization of robotic actions, improvement of system robustness, vision-based object tracking, and real-time performance.
A distributed multi-robot architecture is developed which will facilitate operation of a cooperative multi-robot system in a dynamic and unknown environment in a self-improving, robust, and real-time manner. It is a fully distributed and hierarchical architecture with three levels. By combining several popular AI, soft computing, and control techniques such as learning, planning, reactive paradigm, optimization, and hybrid control, the developed architecture is expected to facilitate effective autonomous operation of cooperative multi-robot systems in a dynamically changing, unknown, and unstructured environment.
A machine learning technique is incorporated into the developed multi-robot system for self-deterministic and self-improving cooperation and coping with uncertainties in the environment. A modified Q-learning algorithm termed Sequential Q-learning with Kalman Filtering (SQKF) is developed in the thesis, which can provide fast multi-robot learning. By arranging the robots to learn according to a predefined sequence, modeling the effect of the actions of other robots in the work environment as Gaussian white noise and estimating this noise online with a Kalman filter, the SQKF algorithm seeks to solve several key problems in multi-robot learning.
As a part of low-level sensing and control in the proposed multi-robot architecture, a fast computer vision algorithm for color-blob tracking is developed to track multiple moving objects in the environment. By removing the brightness and saturation information in an image and filtering unrelated information based on statistical features and domain knowledge, the algorithm solves the problems of uneven illumination in the environment and improves real-time performance.
In order to validate the developed approaches, a Java-based simulation system and a physical multi-robot experimental system are developed to successfully transport an object of interest to a goal location in a dynamic and unknown environment with complex obstacle distribution. The developed approaches in this thesis are implemented in the prototype system and rigorously tested and validated through computer simulation and experimentation.
20
Wei, Lai. "Face movement based multi-modality human machine interface for intelligent wheelchairs." Thesis, University of Essex, 2012. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.571498.
Full textAbstract:
This thesis is dedicated to the development of advanced human machine interfaces (HMIs) for elderly people and people with motor disabilities such as spinal cord injury, quadriplegia and amputation. Based on an intelligent wheelchair system developed at the University of Essex, several new face movement based control interfaces are unveiled and utilized to substitute traditional joystick controllers. Color face video from a web camera is applied to track face, head and eye movements of the user. Meanwhile, the concept of multi-modality human machine interface (MMHMI) is introduced to integrate face video data with facial muscle and eye activities recorded from electromyography (EMG) and electrooculography (EOG) signals. The control interface presented in this thesis covers the state-of-the-art research progress carried out under the intelligent wheelchair project at the robot arena for the last five years. In order to test the mechanism between different wheelchair control methods, three face movement based control interfaces are deployed in indoor navigation tasks in which users are asked to drive a wheelchair following designated routes, avoid obstacle and barriers one by one. The control results are compared with traditional joystick and touch screen control methods. The performance of individual control methods is analyzed based on recorded user behavior, wheelchair trajectory, task completion duration,' and user feedback. User driving experience is collected in the form of feedback questionnaires in terms of the wheelchair control such as user comfort, interface response, control accuracy and control reliability. These can be are used to improve future wheelchair control interface design.
21
Charnnarong, Jain. "The design of an intelligent machine for upper-limb physical therapy." Thesis, Massachusetts Institute of Technology, 1991. http://hdl.handle.net/1721.1/13026.
Full text
22
Jarvis, Matthew P. "Applying machine learning techniques to rule generation in intelligent tutoring systems." Link to electronic thesis, 2004. http://www.wpi.edu/Pubs/ETD/Available/etd-0429104-112724.
Full textAbstract:
Thesis (M.S.)--Worcester Polytechnic Institute.<br>Keywords: Intelligent Tutoring Systems; Model Tracing; Machine Learning; Artificial Intelligence; Programming by Demonstration. Includes bibliographical references.
23
Wu, Jaichun. "The development and implementation of an intelligent, semantic machine control system with specific reference to human-machine interface design." Thesis, Cape Peninsula University of Technology, 2005. http://hdl.handle.net/20.500.11838/2292.
Full textAbstract:
Thesis (MTech (Information Technology))--Cape Peninsula University of Technology, 2005.<br>This thesis explores the design and implementation of an intelligent semantic machine
control system with specific reference to human-machine interface design. The term
"intelligent" refers to machines that can execute some level of decision taking in
context. The term "semantic" refers to a structured language that allows user and
machine to communicate.
This study will explore all the key concepts about an intelligent semantic machine
control system with human-machine interface. The key concepts to be investigated
will include Artificial Intelligence, Intelligent Control, Semantics, Intelligent Machine
Architecture, Human-Machine Interaction, Information systems and Graphical User
Interface. The primary purpose of this study is to develop a methodology for
designing a machine control system and its related human-machine interface.
24
Kostias, Aristotelis, and Georgios Tagkoulis. "Development of an Artificial Intelligent Software Agent using Artificial Intelligence and Machine Learning Techniques to play Backgammon Variants." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-251923.
Full textAbstract:
Artificial Intelligence has seen enormous progress in many disciplines in the recent years. Particularly, digitalized versions of board games require artificial intelligence application due to their complex decision-making environment. Game developers aim to create board game software agents which are intelligent, adaptive and responsive. However, the process of designing and developing such a software agent is far from straight forward due the nature and diversity of each game. The thesis examines and presents a detailed procedure of constructing a software agent for backgammon variants, using temporal difference, artificial neural networks and backpropagation. Different artificial intelligence and machine learning algorithms used in board games, are overviewed and presented. Finally, the thesis describes the development and implementation of a software agent for the backgammon variant called Swedish Tables and evaluates its performance.<br>Artificiell intelligens har sett enorma framsteg inom många discipliner de senare åren. Speciellt, digitaliserade brädspel kräver implementering av Artificiell intelligens då deras beslutfattande logik är väldigt komplex. Dataspelutvecklarnas syfte och mål är att skapa programvaror som är intelligenta, adaptiva och lyhörda. Dock konstruktionsoch utvecklingsprocess för att kunna skapa en sådan mjukvara är långtifrån att vara faställd, mest på grund av diversitet av naturen av varje spel. Denna avhandlingen forskar och föreslår en detaljerad procedur för att bygga en "Software Agent" för olika slags Backagammon, genom att använda AI neurala nätvärk och back-propagation metoder. Olika artificiell intelligensoch maskininlärningsalgoritmer som används i brädspel forskas och presenteras. Slutligen denna avhandling beskriver implementeringen och utvecklingen av ett mjukvaru agent för en backgammonvariant, närmare bestämt av "Svenska Tabeller" samt utvärderar dess prestanda.
25
Doumit, Sarjoun S. "IONA: Intelligent Online News Analysis." University of Cincinnati / OhioLINK, 2018. http://rave.ohiolink.edu/etdc/view?acc_num=ucin1544001149153864.
Full text
26
Bertholds, Alexander, and Emil Larsson. "An intelligent search for feature interactions using Restricted Boltzmann Machines." Thesis, Uppsala universitet, Institutionen för informationsteknologi, 2013. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-202208.
Full textAbstract:
Klarna uses a logistic regression to estimate the probability that an e-store customer will default on its given credit. The logistic regression is a linear statistical model which cannot detect non-linearities in the data. The aim of this project has been to develop a program which can be used to find suitable non-linear interaction-variables. This can be achieved using a Restricted Boltzmann Machine, an unsupervised neural network, whose hidden nodes can be used to model the distribution of the data. By using the hidden nodes as new variables in the logistic regression it is possible to see which nodes that have the greatest impact on the probability of default estimates. The contents of the hidden nodes, corresponding to different parts of the data distribution, can be used to find suitable interaction-variables which will allow the modelling of non-linearities. It was possible to find the data distribution using the Restricted Boltzmann Machine and adding its hidden nodes to the logistic regression improved the model's ability to predict the probability of default. The hidden nodes could be used to create interaction-variables which improve Klarna's internal models used for credit risk estimates.<br>Klarna använder en logistisk regression för att estimera sannolikheten att en e-handelskund inte kommer att betala sina fakturor efter att ha givits kredit. Den logistiska regressionen är en linjär modell och kan därför inte upptäcka icke-linjäriteter i datan. Målet med detta projekt har varit att utveckla ett program som kan användas för att hitta lämpliga icke-linjära interaktionsvariabler. Genom att införa dessa i den logistiska regressionen blir det möjligt att upptäcka icke-linjäriteter i datan och därmed förbättra sannolikhetsestimaten. Det utvecklade programmet använder Restricted Boltzmann Machines, en typ av oövervakat neuralt nätverk, vars dolda noder kan användas för att hitta datans distribution. Genom att använda de dolda noderna i den logistiska regressionen är det möjligt att se vilka delar av distributionen som är viktigast i sannolikhetsestimaten. Innehållet i de dolda noderna, som motsvarar olika delar av datadistributionen, kan användas för att hitta lämpliga interaktionsvariabler. Det var möjligt att hitta datans distribution genom att använda en Restricted Boltzmann Machine och dess dolda noder förbättrade sannolikhetsestimaten från den logistiska regressionen. De dolda noderna kunde användas för att skapa interaktionsvariabler som förbättrar Klarnas interna kreditriskmodeller.
27
Strickland, Ted John Jr. "Dynamic management of multichannel interfaces for human interaction with computer-based intelligent assistants." Diss., The University of Arizona, 1989. http://hdl.handle.net/10150/184793.
Full textAbstract:
For complex man-machine tasks where multi-media interaction with computer-based assistants is appropriate, a portion of the assistant's intelligence must be devoted to managing its communication processes with the user. Since people often serve the role of assistants, the conventions of human communication provide a basis for designing the communication processes of the computer-based assistant. Human decision making for communication requires knowledge of the user's style, the task demands, and communication practices, and knowledge of the current situation. Decisions necessary for effective communication, when, how, and what to communicate, can be expressed using these knowledge sources. A system based on human communication rules was developed to manage the communication decisions of an intelligent assistant. The Dynamic Communication Management (DCM) system consists of four components, three models and a manager. The model of the user describes the user's communication preferences for different task situations. The model of the task is used to establish the user's current activity and to describe how communication should be conducted for this activity. The communication model provides the rules needed to make decisions: when to communicate the message, how to present the message to the user, and what information should be communicated. The Communication Manager controls and coordinates these models to conduct all communication with the user. Performance with DCM as the interface to a simulated Flexible Manufacturing System (FMS) control task was established to learn about the potential benefits of the concept. An initial comparison showed no improvement over a keyboard and monitor interface, but provided performance data which exposed the differences in information needed for decision making using auditory and visual communication. This knowledge and related performance data were used to redesign features of the DCM. The redesigned DCM significantly improved all aspects of system performance compared to the keyboard and monitor interface. The FMS performance measures and performance on a secondary task improved, user communication behavior was changed favorably, and users preferred the advanced features of DCM. These types of benefits can potentially accrue for a variety of tasks where multi-media communication with computer-based intelligent assistants is managed with DCM.
28
Liu, Yi. "An evaluation system for intelligent smart badges." Thesis, University of Canterbury. Computer Science and Software Engineering, 2006. http://hdl.handle.net/10092/1111.
Full textAbstract:
In this thesis we develop and test a software algorithm for an electronic smart badge system. The smart badge system we have developed has the ability to figure out the interests of people who wear the badge by using time and position information collected by the badge. The badge can also present feedback to the wearer, so that users may be guided to people will similar interests and so may have more effective conversations. The smart badge system is based on an inference system which uses a Bayesian network. Evaluation of the system was challenging because there were no completed badges that could be used. To overcome this, we developed a simulation of crowd behaviour in a conference setting. We tuned the parameters of the model using several test situations and the final simulated behavior appeared realistic. Compared to other smart badge systems, our work is unique because it is able to enhance conversation by the real time inference of common ideas or interests of the conversion participants.
29
Fletcher, Simon. "Computer aided system for intelligent implementation of machine tool error reduction methodologies." Thesis, University of Huddersfield, 2001. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.368312.
Full text
30
Zhou, Shang-Ming. "Machine learning and intelligent data analysis for interpretable neuro-fuzzy system modelling." Thesis, University of Essex, 2006. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.426019.
Full text
31
Gheyas, Iffat A. "Novel computationally intelligent machine learning algorithms for data mining and knowledge discovery." Thesis, University of Stirling, 2009. http://hdl.handle.net/1893/2152.
Full textAbstract:
This thesis addresses three major issues in data mining regarding feature subset selection in large dimensionality domains, plausible reconstruction of incomplete data in cross-sectional applications, and forecasting univariate time series. For the automated selection of an optimal subset of features in real time, we present an improved hybrid algorithm: SAGA. SAGA combines the ability to avoid being trapped in local minima of Simulated Annealing with the very high convergence rate of the crossover operator of Genetic Algorithms, the strong local search ability of greedy algorithms and the high computational efficiency of generalized regression neural networks (GRNN). For imputing missing values and forecasting univariate time series, we propose a homogeneous neural network ensemble. The proposed ensemble consists of a committee of Generalized Regression Neural Networks (GRNNs) trained on different subsets of features generated by SAGA and the predictions of base classifiers are combined by a fusion rule. This approach makes it possible to discover all important interrelations between the values of the target variable and the input features. The proposed ensemble scheme has two innovative features which make it stand out amongst ensemble learning algorithms: (1) the ensemble makeup is optimized automatically by SAGA; and (2) GRNN is used for both base classifiers and the top level combiner classifier. Because of GRNN, the proposed ensemble is a dynamic weighting scheme. This is in contrast to the existing ensemble approaches which belong to the simple voting and static weighting strategy. The basic idea of the dynamic weighting procedure is to give a higher reliability weight to those scenarios that are similar to the new ones. The simulation results demonstrate the validity of the proposed ensemble model.
32
He, Yuesheng. "The intelligent behavior of 3D graphical avatars based on machine learning methods." HKBU Institutional Repository, 2012. https://repository.hkbu.edu.hk/etd_ra/1404.
Full text
33
Hasan, Irfan. "Machine learning techniques for automated knowledge acquisition in intelligent knowledge-based systems." Instructions for remote access. Click here to access this electronic resource. Access available to Kutztown University faculty, staff, and students only, 1991. http://www.kutztown.edu/library/services/remote_access.asp.
Full textAbstract:
Thesis (M.S.)--Kutztown University of Pennsylvania, 1991.<br>Source: Masters Abstracts International, Volume: 45-06, page: 3187. Abstract precedes thesis as [2] preliminary leaves. Typescript. Includes bibliographical references (leaves 102-104).
34
Foster, Kate Yvonne, and kate foster@dsto defence gov au. "An investigation of the use of past experience in single and multiple agent learning classifier systems." Swinburne University of Technology. Centre for Intelligent Systems & Complex Processes, 2005. http://adt.lib.swin.edu.au./public/adt-VSWT20051117.112922.
Full textAbstract:
The field of agent control is concerned with the design and implementation of components that form an agent's control architecture. The interaction between these components determines how an agent?s sensor data and internal state combine to direct how the agent will act. Rule-based systems couple sensing and action in the form of condition-action rules and one class of such systems, learning classifier systems, has been extensively used in the design of adaptive agents. An adaptive agent explores an often unknown environment and uses its experience in its environment with the aim of improving its performance over time. The data an adaptive agent receives regarding the current state of its environment might be limited and ambiguous. In learning classifier systems, three different approaches to the problem of limited and ambiguous data from the environment have been: (1) to enable the agent to learn from its past experience, (2) to develop sequences of rules (in which rules may be linked implicitly or explicitly) and (3) multiagent LCSs.
This thesis investigates the use of an adaptive agent?s past experience as a resource with which to perform a number of functions internal to the agent. These functions involve developing explicit sequences of rules, detecting and escaping from infinite loops, and firing and reinforcing rules.
The first part of this thesis documents the design, implementation and evaluation of a control system that incorporates these functions. The control system is realised as a learning classifier system and is evaluated through experiments in a number of environments that provide limited and ambiguous stimuli. These experiments test the impact of explicit sequences of rules on the performance of a learning classifier system more thoroughly than previous research achieved. The use of explicit sequences of rules results in mixed performance in these environments and it is shown that while the use of these sequences in simple environments enables the rule space to be more effectively explored, in complex environments the behaviours developed by these sequences result in the agent stagnating more often in corners of the environment.
Rather than endowing the rule-base with more rules, as in previous research with explicit sequences of rules, it is proposed that multiple interacting agents may enhance the exploration of the rule space in more complex environments. This approach is taken in the second part of this thesis, where the control system is used with multiple agents that interact by sharing rules. The aim of this interaction is to enhance the rule discovery process through cooperation between agents and thus improve the performance of the agents in their respective environments. It is shown that the benefit obtained from rule sharing is dependent on the environment and the type and amount of rule sharing used and that rule sharing is generally more beneficial in complex environments compared to simple environments. The properties of the rule-bases developed in these environments are examined in order to account for these results and it is shown that the type and amount of rule sharing most useful in each environment are dependent on these properties.
35
Ozbey, Halil. "A Genetic-based Intelligent Intrusion Detection System." Master's thesis, METU, 2005. http://etd.lib.metu.edu.tr/upload/2/12606636/index.pdf.
Full textAbstract:
In this study we address the problem of detecting new types of intrusions to computer systems which cannot be handled by widely implemented knowledge-based mechanisms. The solutions offered by behavior-based prototypes either suffer low accuracy and low completeness or require use data eplaining abnormal behavior which actually is not available. Our aim is to develop an algorithm which can produce a satisfactory model of the target system&rsquo<br>s behavior in the absence of negative data.
First, we design and develop an intelligent and behavior-based detection mechanism using genetic-based machine learning techniques with subsidies in the Bucket Brigade Algorithm. It classifies the possible system states to be normal and abnormal and interprets the abnormal state observations as evidences for the presence of an intrusion.
Next we provide another algorithm which focuses on capturing normal behavior of the target system to detect intrusions again by identifying anomalies. A compact and highly complete rule set is generated by continuously inserting observed states as rules into the rule set and combining similar rule pairs in each step.
Experiments conducted using the KDD-99 data set have produced fairly good results for both of the algorihtms.
36
Zyner, Alex Grzegorz. "Naturalistic Driver Intention and Path Prediction using Machine Learning." Thesis, The University of Sydney, 2018. http://hdl.handle.net/2123/20505.
Full textAbstract:
Autonomous vehicles are still yet to be available to the public. This is because there are a number of challenges that have not been overcome to ensure that autonomous vehicles can safely and efficiently drive on public roads. Accurate prediction of other vehicles is vital for safe driving, as interacting with other vehicles is unavoidable on public streets. This thesis explores reasons why this problem of scene understanding is still unsolved, and presents methods for driver intention and path prediction. The thesis focuses on intersections, as this is a very complex scenario in which to predict the actions of human drivers. There is very limited data available for intersection studies from the perspective of an autonomous vehicle. This thesis presents a very large dataset of over 23,000 vehicle trajectories, used to validate the algorithms presented in this thesis. This dataset was collected using a lidar based vehicle detection and tracking system onboard a vehicle. Analytics of this data is presented. To determine the intent of vehicle at an intersection, a method for manoeuvre classification through the use of recurrent neural networks is presented. This allows accurate predictions of which destination a vehicle will take at an unsignalised intersection, based on that vehicle's approach. The final contribution of this thesis presents a method for driver path prediction, based on recurrent neural networks. It produces a multi-modal prediction for the vehicle’s path with uncertainty assigned to each mode. The output modes are not hand labelled, but instead learned from the data. This results in there not being a fixed number of output modes. Whilst the application of this method is vehicle prediction, this method shows significant promise to be used in other areas of robotics.
37
Shafqat, Adnan. "Mobile Usability of Intelligent Electronic Devices." Thesis, Blekinge Tekniska Högskola, Institutionen för datalogi och datorsystemteknik, 2015. http://urn.kb.se/resolve?urn=urn:nbn:se:bth-10526.
Full textAbstract:
Context: The Human Machine Interface (HMI) for Intelligent Electronic Devices (IEDs) is limited in its capability and is often the most common cause of failure when interacting with devices. A new approach to interact with these devices is needed with focus on improving interaction and effective visualization of information. Objectives: In this thesis, we investigate and propose a solution to visualize data of existing IED in interactive way. A mobile based prototype is proposed to list alarms, events and disturbances. Further single line diagram shown with capability to switch controls. Objective of proposed solution is to investigate specific use of mobile device from the perspective of usability and compare the new prototype with existing use of IED monochrome screen interface. Methods: Mixed approach based on qualitative and quantitative methods is conducted for analysis of the problem, method and approach to solve the problems in the domain of Substation automation. Analysis of the problem was carried out with the literature review of the technical documentation of IEDs. Experiments are performed in real environment to test and verify the usability of prototype. Results: Experiments results of proposed solution indicate that new approach is acceptable. The interfaces developed in mobile provide better results than traditional interfaces of IED. The difference between them is significant. Conclusions: We conclude that mobile usability gives better interaction, freedom, visualization of information and enhance the users’ experience by providing context specific information as compared to the existing Local Human Machine Interface of Intelligent Electronic Devices. The study provides strong results that recent developments of mobile technologies have revolutionized users’ possibilities to access information in an easy and better way.
38
CHEN, YEN-HSUN, and 陳彥勳. "Intelligent Air Conditioning Switch Machine." Thesis, 2018. http://ndltd.ncl.edu.tw/handle/5eab8u.
Full textAbstract:
碩士<br>逢甲大學<br>資訊電機工程碩士在職學位學程<br>106<br>The purpose of this research is to construct a smart oxygen air conditioning switching system integrating various environmental sensors. Sensors include temperature and humidity sensors, carbon dioxide sensors, aerosol (PM2.5) sensors with an instantaneous and accurate intelligent system to monitor the quality of indoor air.
In a sealed indoor environment, generally cold air is activated and so-called internal circulation and indoor exhaust in which indoor air naturally exchanges indoor and outdoor air can be considered, but in reality both the internal circulation and the external exhaust can only be used. In order to improve the indoor air quality of the indoor environment, fresh air outside the room can be introduced into the room. The intelligent oxygen-operated air conditioning switch system designs the air filter at the inlet and outlet fan ports for indoor air cleaning, indoor cloudy air emission, and high oxygen content replacement of fresh gas.
39
Yiying-Chen and 陳奕穎. "Intelligent Design in Automatic Drilling Machine." Thesis, 2010. http://ndltd.ncl.edu.tw/handle/33936946933943019730.
Full textAbstract:
碩士<br>建國科技大學<br>自動化工程系暨機電光系統研究所<br>98<br>ABSTRAT
The current traditional drilling machines are usually unable to identify the different kind of material hardness during the drilling action. Therefore, the drills are easily abraded or damaged which may cause the increase of cost. Due to these problems and disadvantages of the drills, this paper designs an intelligent automatic drilling machine to improve the disadvantages of traditional fixed speed drilling machines.
The purpose of this design is to avoid the collision of hard material and cause the drill collapse or breaking. On the contrary, when the material’s hardness is lower, such as plastic materials, it can become a high-speed execution. After the penetrating, it will retreat from the subject in low-speed rotation. While using high-speed in drilling, faster speed can avoid the high temperature of drilling the materials. The high temperature will lead to the problem of deformation of aperture or low accuracy.
The system integrates a touch screen and a PLC controller to automatically select and judge the materials for the drilling machine. The experiment proves the design can actually improve the drilling efficiency and extend the usage of drills.
Keywords: Drill pressd, rilling machine, touch screen, PLC controller
40
Tsai, Shang-Wen, and 蔡尚紋. "Developments of an Intelligent Honing Machine." Thesis, 2010. http://ndltd.ncl.edu.tw/handle/44707513970331603484.
Full textAbstract:
碩士<br>聖約翰科技大學<br>自動化及機電整合研究所<br>98<br>The traditional honing machine is operated by manual model for hole processing. Due to rotational speed and different feed rate on actuator motion, the superficial hole is not very smoothness so that it can influence mechanical performance for micro-nano series machine. The low cost intelligent honing machine is designed and manufactured. In this paper, the system includes :(1)hydraulic control system, (2)PC-Based human-machine interface, (3)interface signal processing, (4) data library. In addition. The adaptive fuzzy sliding mode control is used to improve precision and superficial roughness of hole for honing machine. AFSMC includes fuzzy sliding mode surface, adaptive fuzzy rules and adaptive scale factors. The fuzzy sliding mode surface can reduce the numbers of fuzzy rule, an adaptive fuzzy rules can adjust on-line fuzzy rules, and scale factors are modified by mode-matching techuique. Experimental results indicate that the AFSMC and FSMC has achive excellent performant for honing maching.
41
Yen, Chao-Shiung, and 嚴昭雄. "Business Model for Intelligent Vending Machine." Thesis, 2018. http://ndltd.ncl.edu.tw/handle/hfrc72.
Full textAbstract:
碩士<br>國立東華大學<br>管理學院高階經營管理碩士在職專班<br>106<br>The logistic network of Taiwan is mature now. And Online to Offline (O2O) is a flourish retailing model. The impact of e-commerce and increasing cost of running a store bothers retailers a lot. Vending machines were invented far before the O2O patter appears, and intelligent vending machine was proposed to further improving the selling service level. Combining with different technologies, Parcel Locker, Smart Sales, New Retail, and Self-Service stores are new ideas that changes the retailing big. In this research, we considered an application pattern of smart sale, which focused on the makeup industry. We set a scenario and analyzed it. If the operation fits our assumption, a profit is expectable.
42
WANG, LI-WEI, and 王力偉. "Process Control of Intelligent Coffee Coaster Machine." Thesis, 2016. http://ndltd.ncl.edu.tw/handle/14860195895179681411.
Full textAbstract:
碩士<br>中華科技大學<br>電子工程研究所碩士班<br>104<br>For a success coffee roasting, one has to deal with a complex process which controls pre-heat temperature, bean loading temperature, roasting procedure profile, drying and steaming steps, venting adjustment, temperature regulation (as of gas flow rate or electrical power control), first and second crack control, coffee unloading, and cooling, and all of those steps are often achieved by utilizing two knobs to control the heating and venting of a roaster. In order to retain the delicate flavor and aroma of the coffee, very often, having to rely on experienced experts; and as a consequence, it may be a difficult task to make a good coffee for a beginner. The purpose of this paper is to construct a fully automatic control coffee roasting device to replace the conventional counter one which may heavily rely on the manual adjustment, so that one can enjoy gourmet coffee at home in a relative easy fashion by just pressing a control bottom. For that reason, an intelligent coffee bean roasting system and method with expert’s experiences have been proposed accordingly. In this paper, two control modes including keypad panel and touch panel are designed as human interface respectively. By using rs232 serial communication or Bluetooth wireless transmission to receive coffee beans roasting parameters and the temperature profile of the roasting process is displayed on the PC screen or touch panel. Due to roasting profile or curve is collection of temperature variation or fluctuation during the entire roasting process, and for different coffee varieties or regions of production, different roasting profiles have been investigated and defined in several different roasting modes. Also, one can selectively adjust the profile at particular interest. The proposed system uses chip (PIC18F452) as a micro controller, implementing temperature profile from the top notched expert and embedded as a basis with unique characteristics, and that includes roasting procedures as follow: (1) roasting profile optimization, which is aimed for some well-known coffee beans up to eight varieties, such as Blue Mountain, Mandheling, and Mocha, etc.; (2) customized parameters, which allows one to input and define individually up to ten data sets, the data sets can be save to E2PROM of microcontroller or WEINTEK’s touch panel(MT6071iE); (3) complete manually operation, which allows one to explore freely at one’s own interest by manipulating two knobs to control the power and air dissipation; and (4) roasting process data recording, which allow one to print, log, and on-line editing roasting parameters, via USB linkage, back and forth between a computer and the controller.
43
Ke, Yen-Ting, and 柯彥廷. "Machine Learning Based Intelligent Healthcare Assistance System." Thesis, 2017. http://ndltd.ncl.edu.tw/handle/tw738u.
Full textAbstract:
碩士<br>遠東科技大學<br>機械工程研究所<br>105<br>It is proposed to develop a machine learning based intelligent healthcare assistance system in the thesis. It works with quantitative measurement and intelligent analysis in the cloud system for somatic fitness. Automatic measurement will reduce labor costs and enhance the customization of the system for web-based healthcare assistance.
The automatic measurement of the system is consist of electrocardiography (ECG), electroencephalography (EEG), electro meridian analysis system (EMAS). And it measures for the physiological, psychological and meridian energy state by sensors. The website of the cloud system with records, assessment, prediction, diagnosis, and prescription function was built by using ASP.NET tool and machine learning methods.
By experimental results, The accuracy of intelligent healthcare assistance system using machine learning method is pretty good. The accuracy of the assessment system using multiclass decision forest method is over 88%. The accuracy of the prediction system using decision forest regression method is over 95%. The accuracy of the diagnosis system using multiclass decision jungle method is over 92%. And the accuracy of the prescription system using boosted decision tree regression method is over 100%. These experimental results show the good performance of the machine learning based intelligent healthcare assistance system.
44
Lin, Wei-Hung, and 林韋宏. "The Design of Intelligent Simulated Hippotherapy Machine." Thesis, 2015. http://ndltd.ncl.edu.tw/handle/51676202286907615046.
Full textAbstract:
碩士<br>淡江大學<br>機械與機電工程學系碩士班<br>103<br>Hippotherapy is limited to less legal racecourse and higher charge. These inconvenient factors disturb hippotherapy to popularize. Therefore, base on the basic movements of hippotherapy, this research is intended to design and product an intelligent simulated hippotherapy (equine-assisted) machine which is useful to enhance the hands, legs, waist body strength and balance training during the rehabilitation treatment in a single machine simultaneously. In order to bring benefits to patients and to reduce the cost of medical and health care, this machine makes physical disabled friends have more affordable and more convenient way to achieve the effects of hippotherapy.
The research works include mechanical design. Patients are able to sit on the seat which is similar to a saddle, and put foot on toe clips to tread. The kinetic energy of tread will be transmitted by gearwheel and belt. This machine is designed to make the saddle move up and down, and resemble a walking-horse. In order to simulate the movement of hippotherapy to do balance training and to strength the muscular movement of patients’ arms, legs and waist, the swing system which is under the saddle will coordinate the frequency of patients to produce movements from side to side.
The research word starts from hand-painted machine parts. The second step is to build models by using ProEngineer, and then designs, calculates and draws the size of machine parts particularly, so as to facilitate the processing and the mechanical design. The third step is analyzing and checking the results of the simulation are consistent with the goal or not through the simulated track. The final step is testing in a particularly way to observe the rehabilitation situation of users on the Intelligent Simulated Hippotherapy Machine.
45
Chan, Shih-Lang, and 詹世朗. "System design of an intelligent Human-Machine Interface on NC machine tools." Thesis, 2005. http://ndltd.ncl.edu.tw/handle/13941083524194010235.
Full textAbstract:
碩士<br>國立高雄應用科技大學<br>模具工程系碩士班<br>93<br>Currently in the drastic competitive era for the Machine tool industry, the demand towards multi-function development such as function integration, specialization, high speed, and lightweight has been inevitable trend. That is to say, multifunctional intelligent machine tool is the trend in the future to enhance the product value.
The objective of research is to integrate the CAM (Computer Aided Manufacture) function with the human machine interface (HMI) of the machine tool via the development of an intelligent machine HMI that has 2-1/2 axis (2.5D) capability. The Microsoft Windows-Based were adopted as the development platform. The pocket machining function in this research was developed through the contour offset algorithm based on the proposed new adjacent pair-intersection method. The color-filling notion was used to decide if there were removable over-cutting loop firstly; tool path planning was then followed. The representation of sequence tree was applied in tool path planning and independent machining loop was merged by using its hierarchical relations so as to generate the comprehensive tool path. An integrated pocketing loop was defined in this research based on the common G code to ease the programming for the used to create machining cycle.
The Unified Modeling Language (UML) was utilized in the development of the HMI system for the system function analysis and planning so as to create the HMI that can satisfy the user’s need. The CAM kernel module was then integrated finally into the HMI to accomplish the intelligent NC machine tool HMI system design and implementation of Cam module.
With the developed intelligent NC machine tool HMI system, a user can input directly a general profile containing islands (in DXF format) or the proposed G code-based pocketing program parametrically, and the machining tool path can be immediately displayed and simulated for real machining. The developed methodology has been tested and implemented successfully for reliable application.
46
Abou, Saleh Jamil. "Integrated Framework Design for Intelligent Human Machine Interaction." Thesis, 2008. http://hdl.handle.net/10012/3726.
Full textAbstract:
Human-computer interaction, sometimes referred to as Man-Machine Interaction, is a concept that emerged simultaneously with computers, or more generally machines. The methods by which humans have been interacting with computers have traveled a long way. New designs and technologies appear every day. However, computer systems and complex machines are often only technically successful, and most of the time users may find them confusing to use; thus, such systems are never used efficiently. Therefore, building sophisticated machines and robots is not the only thing someone has to address; in fact, more effort should be put to make these machines simpler for all kind of users, and generic enough to accommodate different types of environments. Thus, designing intelligent human computer interaction modules come to emerge. In this work, we aim to implement a generic framework (referred to as CIMF framework) that allows the user to control the synchronized and coordinated cooperative type of work that a set of robots can perform. Three robots are involved so far: Two manipulators and one mobile robot. The framework should be generic enough to be hardware independent and to allow the easy integration of new entities and modules. We also aim to implement the different building blocks for the intelligent manufacturing cell that communicates with the framework via the most intelligent and advanced human computer interaction techniques. Three techniques shall be addressed: Interface-, audio-, and visual-based type of interaction.
47
Lu, Chien Hao, and 呂健豪. "The Development of Intelligent Virtual Coordinate Measuring Machine." Thesis, 2000. http://ndltd.ncl.edu.tw/handle/84237133108915657934.
Full textAbstract:
碩士<br>國立中正大學<br>機械系<br>88<br>The development of CAD/CAM system has made the design and manufacture process more effective, but the inspection process still much relies on the traditional manual operations and techniques. To improve the development of automatic inspection technique, an effective system that incorporates computer-aided inspection (CAI) and computer-aided analysis (CAA) subsystems into CAD/CAM system for industrial use is urgently needed. In this paper, a new concept is proposed for dimensional inspection and geometry error analysis by introducing the idea of Virtual-CMM.
In recent years, because of the improvement in measurement hardware, it is easier to get huge and high precision measuring data than before. But the general solution to handle this large and random data had not been found. To solve this problem, the Intelligent Virtual-CMM system is developed. The developed Virtual-CMM system is a computational analysis software kernel aiming at analyzing the “virtual part”, which is a collection of scanning points of products created by any type of dimensional measuring equipment (DME), such as laser scanner or CMM. In this measuring system, it provides common analysis tools such as alignment, best-fit of standard and free-form geometric features, intersection of geometric entities, form error evaluation and tolerance analysis.
It is tedious and slow to inspect a complex part using the manual operations or simple CNC measuring methods. To solve this problem, the CAD directed inspection module included in the Virtual-CMM system is proposed. This module includes the automatic generation of inspection points, the simulation of the inspection process, and the creation of a DMIS CNC inspection program that will automate the CMM inspection. In addition, the inspection result from the DMIS CNC inspection codes can be returned in the DMIS format, and can feed back into the Virtual-Part analysis module to analyze the inspection results by registration and best-fit methods.
48
Qiu, Zhen-Xuan, and 邱振軒. "The Intelligent Control System for Cloth Spreader Machine." Thesis, 2017. http://ndltd.ncl.edu.tw/handle/a29sfn.
Full textAbstract:
碩士<br>明志科技大學<br>電機工程系碩士班<br>105<br>Recent years have seen growing interest in In INDUSTRY 4.0 technologies and INTERNET of THINGS (IoT). A number of companies in Taiwan are already researching and developing INDUSTRY 4.0 technologies for use. In this thesis, we propose a system that combines Embedded System and Web Server to replace Programmable Logic Controller system in the Cloth Spreader Machine by Embedded System which is widely used in IoT. We also provide statistical analysis of sensor data of and graphical analysis of production so as to make system smart and intelligent.
In this thesis, using webapp as the User Interface and webserver as the cloud platform system. To implementation cloud computing and cloud data storage. Both of System are built in Raspberry Pi 3. The webapp can point out the necessary working information of machine to enable data analysis for manager to promote better productivity. It can bring in its term unlimited economic opportunities.
49
Hung, JiRung, and 洪紀榮. "Development of an Intelligent Inspection Machine for PCB Microdrills." Thesis, 2001. http://ndltd.ncl.edu.tw/handle/61710430240540062266.
Full textAbstract:
碩士<br>國立臺灣科技大學<br>機械工程系<br>89<br>The purpose of this project is to develop an intelligent microdrills inspection machine. The inspection path can be programmed with a great flexibility and also controlled with a high accuracy. The required specifications for measuring can be managed by inner database system. The geometries of microdrills are obtained by using a machine vision system and the features of microdrills are inspected by using image processing and analysis techniques. As a result, the qualities of microdrills can be determined and classified. Finally, the complete inspection results can be sent to an automatic packing machine by RS-232 communication, and then the good microdrills are packed in this machine.
50
Tai, Au-Zou, and 戴傲儒. "Study on Intelligent Vending Machine for Visual Control System." Thesis, 2017. http://ndltd.ncl.edu.tw/handle/mz5396.
Full textAbstract:
碩士<br>逢甲大學<br>機械與電腦輔助工程學系<br>105<br>In order to improve the lack of systematic management of traditional vending machines, and a lot of idle time and poor sales situation, this paper will try to develop a new type of intelligent vending machine and with real-time face recognition use the facial features the collection of consumer spending Habits, become intelligent self-service store. In order to verify the shortcomings of this new type of vending machine to improve the old machine, the difference between the two will be measured experimentally. The experimental results show that the new type of intelligent vending machine does achieve the purpose of increasing the sales of goods and saving the cost. Can be used as a reference for vending machine design, it is expected that there will be commercialization.