Dissertations / Theses on the topic 'Smartphone sensing'

Lo scopo di questa tesi è di usare i sensori dello smartphone per cercare di rilevare alcune tra le attività umane più frequenti, come il salire una scala. Si presenta quindi lo smartphone in termini di hardware elencando i possibili sensori contenuti in esso e descrivendone le qualità. Vengono presentati i principali sistemi operativi mobili adottati per questi tipi di dispositivi mostrando un confronto tra di essi in termini di pregi e difetti e viene narrata un minimo di storia relativa ai dispositivi mobili in generale spiegando come lo smartphone abbia sostituito il classico telefono cellulare. Nel documento di tesi verranno poi presentati i principali strumenti con cui verrà sviluppata l'applicazione di rilevamento e verranno presi in considerazione due programmi di sviluppo per due linguaggi e tipologie di smartphone differenti: Windows Phone e Android. Tuttavia per lo sviluppo del progetto di tesi verrà impiegata solo la strumentazione relativa a Windows Phone. In seguito verrà presentata l'applicazione d'ausilio alla progettazione dei metodi, Scilab. Per il rilevamento dell'attività verranno esposti due diversi metodi e ne verranno mostrati il codice per l'implementazione e i relativi risultati. Questi verranno poi discussi e confrontati per analizzare l'affidabilità di entrambi i metodi.

Thesis: S.M. in Transportation, Massachusetts Institute of Technology, Department of Civil and Environmental Engineering, 2018.
Cataloged from PDF version of thesis.
Includes bibliographical references (pages 77-85).
Understanding the travel routine of the individuals is important in many domains. In transport research understanding daily travel routine is crucial for modeling the travel behavior of the individuals. Such models help predict the travel demand and develop strategies for managing that demand. Understanding travel patterns of the individuals is also important to develop effective incentive mechanisms. Location-based services like personal digital assistants and journey planners use historical travel routine to build preferences of the user and make useful recommendations. In health sciences logging the routine travel behavior is important to monitor health of the patients and make recommendations wherever necessary. Several fitness tracking applications available on smartphones utilize the travel activity diary to evaluate the fitness of the individuals and make recommendations. The proliferation of sensing-enabled smartphone devices engendered the development of tools for logging travel routine of individuals. The research in this thesis uses the sensor data collected from smartphone devices to develop a travel activity inference algorithm. Presently, the research into travel activity inference has been focused on developing supervised learning algorithms. These algorithms require a large amount of labeled data for training algorithms that generalize well. Generalization in personalized travel activity inference is a challenging problem due to the concept drift. The problem of concept drift is magnified as the more personalized information is introduced in the input variables. Once the users start using the applications they are constantly generating new data. Expecting the users to label all the data generated by them is impractical. Instead, it would be useful to identify only those examples which would help most improve the algorithm and have the user label such instance. This reduces the burden on the user and does not discourage them from participating in the data collection process. In other words, we need a model that is identifies concept drift in data and adapts accordingly. There has been advances in the deep learning research in last few years. The deep learning algorithms provide a framework for learning feature representation from raw data. The convolutional neural networks have been particularly effective in learning feature representations on many datasets. These models have achieved significant improvement on many complex problems over other machine learning approaches. For the sequential classification problems like the travel activity inference, the recurrent neural network like long short term memory networks are particularly suitable. This thesis proposes to use the deep learning algorithms for travel activity inference. To develop an end-to-end deep learning algorithm that learns feature representations from raw sensor data and incorporates different sensors with differing frequencies. The research proposes using a combination of convolutional neural network for feature representation learning in both time and frequency domain and long short term memory network for sequential classification. In practical situations, the users of the smartphones cannot be asked to carry their smartphones in a fixed position every time. The proposed algorithm for travel activity inference need to be robust to changes in orientation of the smartphones. We compared the performance of the proposed deep learning algorithm against a baseline model based on the current supervised machine learning approaches. The deep learning algorithm achieved an overall average accuracy of 95.98% compared to the baseline method which achieved an overall average accuracy of 89%. We also show that the proposed deep learning algorithm is robust to changes in the orientation of the smartphone.
by Ajinkya Ghorpade.
S.M. in Transportation

Field-portable instruments for ubiquitous detection and analysis of biological, environmental and agricultural items are becoming ever more popular over their traditional non-portable benchtop counterparts as a means to ensure hazard minimization in many fields. One significantly more convenient approach that has emerged in recent years is the harnessing of smartphone capabilities to create field-deployable scientific instruments, allowing measurements to be made onsite and in real-time. In this thesis, a number of self-contained lab-in-a-phone devices have been presented with the particular focus on spectroscopic measurements. In the first work to be presented, a smartphone-based intensity fluorimeter has been developed by using the in-built white flash LED as an optical source and the CMOS camera as a detector. For spectroscopic measurements, a low-cost dispersive element fabricated by nano-imprinted technology has been added into the system within a 3D-printed enclosure to smartphone camera. By adding an optical fibre bundle, the functionality of the device was extended further to make possible spectral acquisitions from solid surfaces in hard-to-reach places. In advance to the steady-state measurements, time-resolved fluorescence intensity measurements at various temperatures is demonstrated. Finally, the utilisation of smartphone-based devices has also gone beyond chemical analysis by demonstrating a simple, low-cost, portable smartphone-based laser beam profiler. Performances of all these instruments have been analysed by some proof-of-principle demonstrations. With the IoT compatibility, the instrumentation on a smartphone can be integrated into a large network of other instruments. As such, data can be monitored, shared, and processed to build real-time regional and global maps for a range of phenomena.

This article reviews the Electronically Activated Recorder (EAR) as an ambulatory ecological momentary assessment tool for the real-world observation of daily behavior. Technically, the EAR is an audio recorder that intermittently records snippets of ambient sounds while participants go about their lives. Conceptually, it is a naturalistic observation method that yields an acoustic log of a person’s day as it unfolds. The power of the EAR lies in unobtrusively collecting authentic real-life observational data. In preserving a high degree of naturalism at the level of the raw recordings, it resembles ethnographic methods; through its sampling and coding, it enables larger empirical studies. This article provides an overview of the EAR method; reviews its validity, utility, and limitations; and discusses it in the context of current developments in ambulatory assessment, specifically the emerging field of mobile sensing.

Context. Both smartphones and PC games are increasingly commonplace nowadays. There are more and more people who own smartphones and – at the same time – like playing video games. Since the smartphones are becoming widely affordable and offer more and more advanced features (such as multi-touch screens, a variety of sensors, vibration feedback, and others), it is justifiable to study their potential in new application areas. The aim of this thesis is to adapt the smartphone for the use as a game controller in PC racing games and evaluate this solution taking into account such aspects as race results and user experience. Objectives. To this end, two applications were developed - a game controller application for Android‑based smartphones (i.e. the client application) and a PC server application. The applications support a selected open-source PC racing game called SuperTuxKart. The evaluation of the smartphone encompasses both race results (whether the smartphone enables players to achieve comparable results to the keyboard – a standard game controller) and user experience (whether this game controller may be satisfying to players). Methods. An experiment was conducted where 20 participants controlled the SuperTuxKart game using first the smartphone, and then the keyboard or vice versa. The experiment was followed by a questionnaire-based survey of the user experience. Results. The experiment results indicate that the smartphone may achieve results which are comparable to those achieved by the keyboard. The race times corresponding to the smartphone were somewhat longer than those obtained with the keyboard, but the average relative difference was below 18%. The questionnaire results show that more than half of the participants enjoyed the smartphone more than the keyboard, despite the fact that the smartphone turned out to be a more challenging game controller for many players and did not provide so good control of the racing game as the keyboard. Conclusions. Overall, this study shows that the smartphone has a potential to be a suitable, satisfying and enjoyable controller for PC racing games.

Les réseaux sans fils et mobiles se sont énormément développés au cours de ces dernières années. Loin d'être réservés aux pays industrialisés, ces réseaux nécessitant une infrastructure fixe limitée se sont aussi imposés dans les pays émergents et les pays en voie de développement. En effet, avec un investissement structurel relativement très faible en comparaison de celui nécessaire à l'implantation d'un réseau filaire, ces réseaux permettent aux opérateurs d'offrir une couverture du territoire très large, avec un coût d'accès au réseau (prix du téléphone et des communications) tout à fait acceptable pour les utilisateurs. Aussi, il n'est pas surprenant qu'aujourd'hui, dans la majorité des pays, le nombre de téléphones sans fil soit largement supérieur à celui des téléphones fixes. Ce grand nombre de terminaux disséminé sur l'ensemble de la planète est un réservoir inestimable d'information dont une infime partie seulement est aujourd'hui exploitée. En effet, en combinant la position d'un mobile et sa vitesse de déplacement, il devient possible d'en déduire la qualité des routes ou du trafic routier. Dans un autre registre, en intégrant un thermomètre et/ou un hygromètre dans chaque terminal, ce qui à grande échelle impliquerait un coût unitaire dérisoire, ces terminaux pourraient servir de relai pour une météo locale plus fiable. Dans ce contexte, l'objectif de cette thèse consiste à étudier et analyser les opportunités offertes par l'utilisation des données issues des terminaux mobiles, de proposer des solutions originales pour le traitement de ces grands masses de données, en insistant sur les optimisations (fusion, agrégation, etc.) pouvant être réalisées de manière intermédiaire dans le cadre de leur transport vers les(s) centre(s) de stockage et de traitement, et éventuellement d'identifier les données non disponibles aujourd'hui sur ces terminaux mais qui pourraient avoir un impact fort dans les années à venir. Un prototype présentant un exemple typique d'utilisation permettra de valider les différentes approches
Mobile and wireless networks have developed enormously over the recent years. Far from being restricted to industrialized countries, these networks which require a limited fixed infrastructure, have also imposed in emerging countries and developing countries. Indeed, with a relatively low structural investment as compared to that required for the implementation of a wired network, these networks enable operators to offer a wide coverage of the territory with a network access cost (price of devices and communications) quite acceptable to users. Also, it is not surprising that today, in most countries, the number of wireless phones is much higher than landlines. This large number of terminals scattered across the planet is an invaluable reservoir of information that only a tiny fraction is exploited today. Indeed, by combining the mobile position and movement speed, it becomes possible to infer the quality of roads or road traffic. On another level, incorporating a thermometer and / or hygrometer in each terminal, which would involve a ridiculous large-scale unit cost, these terminals could serve as a relay for more reliable local weather. In this context, the objective of this thesis is to study and analyze the opportunities offered by the use of data from mobile devices to offer original solutions for the treatment of these big data, emphasizing on optimizations (fusion, aggregation, etc.) that can be performed as an intermediate when transferred to center(s) for storage and processing, and possibly identify data which are not available now on these terminals but could have a strong impact in the coming years. A prototype including a typical sample application will validate the different approaches

Les réseaux sans fils et mobiles se sont énormément développés au cours de ces dernières années. Loin d'être réservés aux pays industrialisés, ces réseaux nécessitant une infrastructure fixe limitée se sont aussi imposés dans les pays émergents et les pays en voie de développement. En effet, avec un investissement structurel relativement très faible en comparaison de celui nécessaire à l'implantation d'un réseau filaire, ces réseaux permettent aux opérateurs d'offrir une couverture du territoire très large, avec un coût d'accès au réseau (prix du téléphone et des communications) tout à fait acceptable pour les utilisateurs. Aussi, il n'est pas surprenant qu'aujourd'hui, dans la majorité des pays, le nombre de téléphones sans fil soit largement supérieur à celui des téléphones fixes. Ce grand nombre de terminaux disséminé sur l'ensemble de la planète est un réservoir inestimable d'information dont une infime partie seulement est aujourd'hui exploitée. En effet, en combinant la position d'un mobile et sa vitesse de déplacement, il devient possible d'en déduire la qualité des routes ou du trafic routier. Dans un autre registre, en intégrant un thermomètre et/ou un hygromètre dans chaque terminal, ce qui à grande échelle impliquerait un coût unitaire dérisoire, ces terminaux pourraient servir de relai pour une météo locale plus fiable. Dans ce contexte, l'objectif de cette thèse consiste à étudier et analyser les opportunités offertes par l'utilisation des données issues des terminaux mobiles, de proposer des solutions originales pour le traitement de ces grands masses de données, en insistant sur les optimisations (fusion, agrégation, etc.) pouvant être réalisées de manière intermédiaire dans le cadre de leur transport vers les(s) centre(s) de stockage et de traitement, et éventuellement d'identifier les données non disponibles aujourd'hui sur ces terminaux mais qui pourraient avoir un impact fort dans les années à venir. Un prototype présentant un exemple typique d'utilisation permettra de valider les différentes approches
Mobile and wireless networks have developed enormously over the recent years. Far from being restricted to industrialized countries, these networks which require a limited fixed infrastructure, have also imposed in emerging countries and developing countries. Indeed, with a relatively low structural investment as compared to that required for the implementation of a wired network, these networks enable operators to offer a wide coverage of the territory with a network access cost (price of devices and communications) quite acceptable to users. Also, it is not surprising that today, in most countries, the number of wireless phones is much higher than landlines. This large number of terminals scattered across the planet is an invaluable reservoir of information that only a tiny fraction is exploited today. Indeed, by combining the mobile position and movement speed, it becomes possible to infer the quality of roads or road traffic. On another level, incorporating a thermometer and / or hygrometer in each terminal, which would involve a ridiculous large-scale unit cost, these terminals could serve as a relay for more reliable local weather. In this context, the objective of this thesis is to study and analyze the opportunities offered by the use of data from mobile devices to offer original solutions for the treatment of these big data, emphasizing on optimizations (fusion, aggregation, etc.) that can be performed as an intermediate when transferred to center(s) for storage and processing, and possibly identify data which are not available now on these terminals but could have a strong impact in the coming years. A prototype including a typical sample application will validate the different approaches

To encourage and support physical activity in increasingly sedentary lifestyles, many are turning to mobile technology. Modern smartphones are equipped with a wealth of sensors, including Global Positioning Systems (GPS) and accelerometers, suggesting great potential to be integrated with fitness and exercise applications. So far, GPS-enabled devices have been used to support running, cycling, or even exercise games that encourage people to be physically active, but GPS- enabled devices lack fine-grained information about the user’s activity. Accelerometers have been used to some effect to detect step count and walking cadence (step rate), and even to classify activity (distinguishing walking from cycling, for example), but require a known carrying location and orientation. In this work, we examine the role of location in two application areas - real-time cadence estimation and gait classification - and develop algorithms to accommodate diverse carrying locations. In the first application area, real-time cadence estimation, our algorithm (Robust Real-time Algorithm for Cadence Estimation, or RRACE) uses a frequency- domain analysis to perform well without training or tuning, and is robust to changes in carrying locations. We demonstrate RRACE’s performance and robustness to be an improvement over existing algorithms with data collected from a user study. In the second application area, gait classification, we present a novel set of 15 gaits suitable for exercise games and other fitness applications. Using a minimal amount of training for participants, we can achieve a mean of 78.1% classification for all 15 gaits and all locations, an accuracy which may be usable now in some applications and warrants further investigation of this approach. We present findings of how our classification scheme confuses these gaits, and encapsulate insights in guidelines for designers. We also demonstrate that our classification performance varies dramatically for each individual even when trained and tested on that individual, suggesting strong individual differences in performing gaits. Our innovative methodology for simple and quick collection of accelerometer data is also described in detail. Future work includes planned improvements to both algorithms, further investigation of individual differences, and extension of this work to other application areas.

La contaminación ambiental es uno de los principales problemas que afecta a nuestro planeta. El crecimiento industrial y los aglomerados urbanos, entre otros, están contribuyendo a que dicho problema se diversifique y se cronifique. La presencia de contaminantes ambientales en niveles elevados afecta la salud humana, siendo la calidad del aire y los niveles de ruido ejemplos de factores que pueden causar efectos negativos en las personas tanto psicológicamente como fisiológicamente. Sin embargo, la ubiquidad de los microcomputadores, y el aumento de los sensores incorporados en nuestros smartphones, han hecho posible la aparición de nuevas estrategias para medir dicha contaminación. Así, el Mobile Crowdsensing se ha convertido en un nuevo paradigma mediante el cual los teléfonos inteligentes emergen como tecnología habilitadora, y cuya adopción generalizada proporciona un enorme potencial para su crecimiento, permitiendo operar a gran escala, y con unos costes asumibles para la sociedad. A través del crowdsensing, los teléfonos inteligentes pueden convertirse en unidades de detección flexibles y multiuso que, a través de los sensores integrados en dichos dispositivos, o combinados con nuevos sensores, permiten monitorizar regiones de interés con una buena granularidad tanto espacial como temporal. En esta tesis nos centramos en el diseño de soluciones de crowdsensing usando smartphones donde abordamos problemas de contaminación ambiental, específicamente del ruido y de la contaminación del aire. Con este objetivo, se estudian, en primer lugar, las propuestas de crowdsensing que han surgido en los últimos años. Los resultados de nuestro estudio demuestran que todavía hay mucha heterogeneidad en términos de tecnologías utilizadas y métodos de implementación, aunque los diseños modulares en el cliente y en el servidor parecen ser dominantes. Con respecto a la contaminación del aire, proponemos una arquitectura que permita medir la contaminación del aire, concretamente del ozono, dentro de entornos urbanos. Nuestra propuesta utiliza smartphones como centro de la arquitectura, siendo estos dispositivos los encargados de leer los datos de un sensor móvil externo, y de luego enviar dichos datos a un servidor central para su procesamiento y tratamiento. Los resultados obtenidos demuestran que la orientación del sensor y el período de muestreo, dentro de ciertos límites, tienen muy poca influencia en los datos capturados. Con respecto a la contaminación acústica, proponemos una arquitectura para medir los niveles de ruido en entornos urbanos basada en crowdsensing, y cuya característica principal es que no requiere intervención del usuario. En esta tesis detallamos aspectos tales como la calibración de los smartphones, la calidad de las medidas obtenidas, el instante de muestreo, el diseño del servidor, y la interacción cliente-servidor. Además, hemos validado nuestra solución en escenarios reales para demostrar el potencial de la solución alcanzada. Los resultados experimentales muestran que, con nuestra propuesta, es posible medir niveles de ruido en diferentes zonas urbanas o rurales con un grado de precisión comparable al de los dispositivos profesionales, todo ello sin requerir intervención del usuario, y con un consumo reducido en cuanto a recursos del sistema. En general, las diferentes contribuciones de esta tesis doctoral ofrecen un punto de partida para nuevos desarrollos, ofreciendo estrategias de calibración y algoritmos eficientes de cara a realizar medidas representativas. Además, una importante ventaja de nuestra propuesta es que puede ser implementada de forma directa tanto en instituciones públicas como no gubernamentales en poco tiempo, ya que utiliza tecnología accesible y soluciones basadas en código abierto.
La contaminació ambiental és un dels principals problemes que afecten el nostre planeta. El creixement industrial i els aglomerats urbans, entre altres, estan contribuint al fet que aquest problema es diversifique i es cronifique. La presència de contaminants ambientals en nivells elevats afecta la salut humana, sent la qualitat de l'aire i els nivells de soroll exemples de factors que poden causar efectes negatius en les persones, tant psicològicament com fisiològicament. No obstant això, la ubiqüitat de les microcomputadores i l'augment dels sensors incorporats als nostres telèfons intel·ligents han fet possible l'aparició de noves estratègies per a mesurar aquesta contaminació. Així, el mobile crowdsensing s'ha convertit en un nou paradigma mitjançant el qual els telèfons intel·ligents emergeixen com a tecnologia habilitadora, i l'adopció generalitzada d'aquest proporciona un enorme potencial per al seu creixement, ja que permet operar a gran escala i amb uns costos assumibles per a la societat. A través del crowdsensing, els telèfons intel·ligents poden convertir-se en unitats de detecció flexibles i multiús que, a través dels sensors integrats en els esmentats dispositius, o combinats amb nous sensors, permeten monitoritzar regions d'interès amb una bona granularitat, tant espacial com temporal. En aquesta tesi ens centrem en el disseny de solucions de crowdsensing usant telèfons intel·ligents, on abordem problemes de contaminació ambiental, específicament del soroll i de la contaminació de l'aire. Amb aquest objectiu, s'estudien, en primer lloc, les propostes de crowdsensing que han sorgit en els últims anys. Els resultats del nostre estudi demostren que encara hi ha molta heterogeneïtat en termes de tecnologies utilitzades i mètodes d'implementació, encara que els dissenys modulars en el client i en el servidor semblen ser dominants. Pel que fa a la contaminació de l'aire, proposem una arquitectura que permeta mesurar la contaminació d'aquest, concretament de l'ozó, dins d'entorns urbans. La nostra proposta utilitza telèfons intel·ligents com a centre de l'arquitectura, sent aquests dispositius els encarregats de llegir les dades d'un sensor mòbil extern, i d'enviar després aquestes dades a un servidor central per al seu processament i tractament. Els resultats obtinguts demostren que l'orientació del sensor i el període de mostratge, dins de certs límits, tenen molt poca influència en les dades capturades. Pel que fa a la contaminació acústica, proposem una arquitectura per a mesurar els nivells de soroll en entorns urbans basada en crowdsensing, i la característica principal de la qual és que no requereix intervenció de la persona usuària. En aquesta tesi detallem aspectes com ara el calibratge dels telèfons intel·ligents, la qualitat de les mesures obtingudes, l'instant de mostratge, el disseny del servidor i la interacció client-servidor. A més, hem validat la nostra solució en escenaris reals per a demostrar el potencial de la solució assolida. Els resultats experimentals mostren que, amb la nostra proposta, és possible mesurar nivells de soroll en diferents zones urbanes o rurals amb un grau de precisió comparable al dels dispositius professionals, tot això sense requerir intervenció de l'usuari o usuària, i amb un consum reduït quant a recursos del sistema. En general, les diferents contribucions d'aquesta tesi doctoral ofereixen un punt de partida per a nous desenvolupaments, i ofereixen estratègies de calibratge i algorismes eficients amb vista a realitzar mesures representatives. A més, un important avantatge de la nostra proposta és que pot ser implementada de forma directa tant en institucions públiques com no governamentals en poc de temps, ja que utilitza tecnologia accessible i solucions basades en el codi obert.
Environmental pollution is one of the main problems that affect our planet. Industrial growth and urban agglomerations, among others, are contributing to the diversification and chronification of this problem. The presence of environmental pollutants at high levels affect human health, with air quality and noise levels being examples of factors that can cause negative effects on people both psychologically and physiologically. Traditionally, environmental pollution is measured through monitoring centers, which are usually fixed and have a high cost. However, the ubiquity of microcomputers and the increase in the number of sensors embedded in our smartphones, have paved the way for the appearance of new strategies to measure such pollution. Thus, Mobile Crowdsensing has become a new paradigm through which smartphones emerge as an enabling technology, and whose widespread adoption provides enormous potential for growth, allowing large-scale operations, and with costs acceptable to our society. Through crowdsensing, smartphones can become flexible and multipurpose detection units that, through the sensors integrated into these devices, or combined with new sensors, allow monitoring regions of interest with good spatial and temporal granularity. In this thesis, we focus on the design of crowdsensing solutions using smartphones. We deal with environmental pollution problems, specifically noise and air pollution. With this objective, the crowdsensing proposals that have emerged in recent years are studied in the first place. The results of our study show that there is still a lot of heterogeneity in terms of technologies used and implementation methods, although modular designs at both client and server seem to be dominant. Concerning air pollution, we propose an architecture that allows measuring air pollution, specifically ozone, in urban environments. Our proposal uses smartphones as the center of the architecture, being these devices responsible for reading the data obtained by an external mobile sensor, and then sending such data to a central server for processing and analysis. In this proposal, several problems have been analyzed with regard to the orientation of the external sensor and the sampling time, and the proposed solution has been validated in real scenarios. The results obtained show that the orientation of the sensor and the sampling period, within certain limits, have very little influence on the captured data. Also, by comparing the heat maps generated by our solution with the data from the existing monitoring stations in the city of Valencia, we demonstrate that our approach is capable of providing greater data granularity. Concerning noise pollution, we propose an architecture to measure noise levels in urban environments based on crowdsensing, and whose main characteristic is that it does not require user intervention. In this thesis, we detail aspects such as the calibration of smartphones, the quality of the measurements obtained, the sampling instant, the server design, and the client-server interaction. Besides, we have validated our solution in real scenarios to demonstrate the potential of the proposed solution. Experimental results show that, with our proposal, it is possible to measure noise levels in different urban or rural areas with a degree of precision comparable to that of professional devices, all without requiring the intervention of the user, and with reduced consumption of system resources. In general, the different contributions of this doctoral thesis provide a starting point for new developments, offering efficient calibration strategies and algorithms to make representative measurements. Besides, a significant advantage of our proposal is that it can be implemented straightforwardly by both public and non-governmental institutions in a short time, as it relies on accessible technology and open source software
Zamora Mero, WJ. (2018). Crowdsensing solutions for urban pollution monitoring using smartphones [Tesis doctoral no publicada]. Universitat Politècnica de València. https://doi.org/10.4995/Thesis/10251/115483
TESIS

Abstract This thesis explores different ways of leveraging mobile sensing to understand how end users use and interact with their smart technologies, namely smartphones and smartwatches. These topics are extensively explored in other parallel research; however, numerous gaps still exist within the literature. The use of mobile sensing to collect quantified ground-truth information of device use in-the-wild is critical to collect unbiased experiences and usage traces. This thesis covers three main themes: (a) the way our affect influences our smartphone use, and how our smartphone usage can also be analysed from our usage habits; (b) revealing quantified exploration of smartwatch usage traits, and how these relate to smartphone use, and (c) novel ways to mitigate interruptions during smartphone or smartwatch use. The thesis begins by explaining the related work and the overall theme of mobile sensing and how device usage influences attention; it then proceeds to elaborate on the contribution of each included article to the overall scope of the thesis. The thesis then concludes with a summary of how the presented articles tie together in a broader scope. Considering the vast amount of research in this field by this thesis’ author as well as other researchers, this type of work can potentially improve the use of novel wearable technologies in the future. By the end of the thesis, the reader should have a broad understanding of what mobile sensing is, and how it can be applied to comprehensively uncover technology use as well as leveraging mobile sensing to enhance the use of technology
Tiivistelmä Tässä väitöskirjassa tarkastellaan erilaisia tapoja hyödyntää mobiilikäytön tunnistamista ymmärtääkseen, miten loppukäyttäjät käyttävät ja ovat vuorovaikutuksessa älykkäiden teknologioidensa, esimerkiksi älypuhelimien ja älykellojen kanssa. Näitä aiheita tutkitaan laajasti muissa rinnakkaisissa tutkimuksissa, mutta kirjallisuudessa on vielä lukuisia aukkoja. Matkaviestinnän käytöstä kerätään kvantitatiiviset tiedot, jotka koskevat laitteen käyttöä luonnossa. Tämän tiedon kerääminen on kriittistä jotta voidaan kerätä puolueettomia kokemuksia ja käyttöjälkiä. Tässä työssä käsitellään kolmea pääteemaa; i) miten älypuhelinkäyttöömme vaikuttaa meidän mielialamme ja miten älypuhelinkäyttöämme voidaan analysoida käyttötapojen perusteella, ii) paljastaa älykellon käyttöominaisuuksien määrälliset tutkimukset ja miten nämä tulokset heijastuvat älypuhelimen käyttöön ja iii) uusia tapoja lieventää katkoksia älypuhelimen tai älykellon käytön aikana. Työ aloittaa selittämällä siihen liittyvää työtä ja mobiilin tunnistamisen yleistä teemaa ja sitä, miten laitteen käyttö vaikuttaa huomiokykyyn, ja jatkuu sitten yksityiskohtaisesti jokaisen mukana tulevan artikkelin osuuden yleiseen käsittelyyn. Työssä päädytään yhteenvetoon siitä, miten esitetyt artikkelit sitovat yhteen laajemman kokonaisuuden ja ottavat huomioon tämän alan tekijän ja muiden tutkijoiden tämän alan tutkimukset, ja miten tällaista työtä voitaisiin mahdollisesti parantaa edelleen tulevaisuudessa käyttämällä uusia tekniikoita. Työn päätyttyä lukijalla on laaja käsitys siitä, mitä mobiili-tunnistaminen on ja miten sitä voidaan soveltaa sekä teknologian käytön kattavaan paljastamiseen että mobiilidatan tunnistuksen hyödyntämiseen teknologian käytön tehostamiseksi

碩士
國立交通大學
網路工程研究所
102
Recently, smartphones provide a promising platform for cooperative computation and inference among social groups. Microphone is a common sensor on a smartphone that can be used for acoustic sensing. A lot of personal daily contexts and activities may be inferred by analyzing the recorded acoustic data. In this work, we consider the inference of conversation partners, which is an important context of social interaction. We design an efficient smartphone-based conversation inference system, which can quickly derive the conversation partners of a phone user in a real-time manner. By considering the continuity and overlap of speeches, we propose two novel inference methods to distinguish the conversational relationship among co-located speakers. Via direct wireless communications, smartphones cooperatively conduct speaker turn recognition by processing acoustic data. The speaker turn recognition of a conversation consists of when a user speaks and how long he/she speaks. Furthermore, to improve inference accuracy, our system also derives speakers’ emotion of utterances and uses the consistency of emotions of a conversation group to make inference. To evaluate our system, we collect conversation data from movie clips and real life with the number of speakers ranging from 2 to 9. The result shows that our system achieves promising performance in both quiet indoor and noisy outdoor environments. In addition, we have also demonstrated a prototype on Android smartphones to verify the feasibility of our approach from off-the-shelf devices.

With the proliferation of sensor-enabled smartphones, significant attention has been attracted to develop sensing-driven mobile systems. Current research on sensing-driven mobile systems can be classified into two categories, based on the purpose of sensing. In the first category, smartphones are used to sense personal context information, such as locations, activities, and daily habits to enable applications such as location-aware systems and virtual reality systems. In the second category, smartphones are exploited to collect sensing data of the physical world and enable applications including traffic monitoring, environmental monitoring, and others. As smartphones become blossomed in popularity and ubiquity, new problems have emerged in both categories of mobile sensing systems. In this thesis, we investigate three core challenges by answering the following fundamental questions: first, how can we utilize user context to improve the operating system performance? Second, how can we process sensing data, especially images, with high accuracy? Third, how can we enable distributed sensing while satisfy resource constraints of smartphones? The first part of this thesis studies how to exploit user context to improve the responsiveness of mobile operating systems. We propose a context-aware application-preloading engine named FALCON. The core of FALCON is a decision engine that learns application usage patterns of mobile users and preloads applications ahead of time to improve the responsiveness of mobile OS. Compared with other approaches such as caching schemes like Least Recently Used (LRU), Falcon improves the application responsiveness by two times. The second part of this thesis focuses on image search for mobile phones. We first explore how to improve image search accuracy on centralized servers, and propose an image search engine named CrowdSearch. The core idea of CrowdSearch is to incorporate crowdsourced human validation into the system for removing erroneous results from automated image search engines, while still provide realtime response for mobile users. Compared with existing automated image search engines, CrowdSearch achieves over 95% accuracy consistently across multiple categories of images with response time in a minute. We then extend image search to distributed mobile phones, and emphasis resource constraint problems, especially on energy and bandwidth. We propose a distributed image search system named SenSearch, which turns smartphones into micro image search engines. Images are collected, indexed, and transmitted using compact features that are two magnitudes smaller than their raw format. SenSearch improves the energy and bandwidth cost by five times compared with centralized image search engines.

abstract: Abnormally low or high blood iron levels are common health conditions worldwide and can seriously affect an individual’s overall well-being. A low-cost point-of-care technology that measures blood iron markers with a goal of both preventing and treating iron-related disorders represents a significant advancement in medical care delivery systems. Methods: A novel assay equipped with an accurate, storable, and robust dry sensor strip, as well as a smartphone mount and (iPhone) app is used to measure total iron in human serum. The sensor strip has a vertical flow design and is based on an optimized chemical reaction. The reaction strips iron ions from blood-transport proteins, reduces Fe(III) to Fe(II), and chelates Fe(II) with ferene, with the change indicated by a blue color on the strip. The smartphone mount is robust and controls the light source of the color reading App, which is calibrated to obtain output iron concentration results. The real serum samples are then used to assess iron concentrations from the new assay and validated through intra-laboratory and inter-laboratory experiments. The intra-laboratory validation uses an optimized iron detection assay with multi-well plate spectrophotometry. The inter-laboratory validation method is performed in a commercial testing facility (LabCorp). Results: The novel assay with the dry sensor strip and smartphone mount, and App is seen to be sensitive to iron detection with a dynamic range of 50 - 300 µg/dL, sensitivity of 0.00049 µg/dL, coefficient of variation (CV) of 10.5%, and an estimated detection limit of ~15 µg/dL These analytical specifications are useful for predicting iron deficiency and overloads. The optimized reference method has a sensitivity of 0.00093 µg/dL and CV of 2.2%. The correlation of serum iron concentrations (N=20) between the optimized reference method and the novel assay renders a slope of 0.95, and a regression coefficient of 0.98, suggesting that the new assay is accurate. Lastly, a spectrophotometric study of the iron detection reaction kinetics is seen to reveal the reaction order for iron and chelating agent. Conclusion: The new assay is able to provide accurate results in intra- and inter- laboratory validations and has promising features of both mobility and low-cost.
Dissertation/Thesis
Doctoral Dissertation Chemical Engineering 2020

碩士
國立臺灣大學
化學工程學研究所
106
This work presented the development of a smartphone-based spectrometer for acquisition of plasma optical emission to detect the ambient atmosphere. Through a combination of a low-cost microplasma generation device and a smartphone-based spectrometer, a portable gas detector will be designed. The smartphone-based spectrometer contains a slit, a grating, and utilizes the camera of a cellphone for spectra acquisition. The main structure of this device, a 5.0×2×7.8 cm3 cuboid, is constructed using a 3D-printer. Due to the limitation of the smartphone camera, this smartphone-based spectrometer is able to perform spectral analysis with the wavelengths from 400 to 700 nm. The full width at half maximum of this smartphone-based spectrometer is well below 10 nm, which is comparable with commercial spectrometers. The microplasma generation device used in this work is a type of dielectric barrier discharge. It is mainly made of a copper clad laminate through a toner transfer process and wet etching, and has the advantages of low cost, simple fabrication, and customization. Combining with the above device, the spectral image from smartphone can be efficiently converted into a useful spectrum by Matlab. This device not only distinguishes the background ambient, but also observes its most important emission bands in the atmosphere of volatile organic compounds: CH (431 nm, A2Δ–X2Π), C2 (469 nm, d3Πg–a3Πa) and C2 (516 nm, 563 nm and 605 nm, A3Πg–X''3Πu). The possibility of stability and quantification of plasma is also explored through smartphone camera recording mode and commercial spectrometers.

Relatório Final de Estágio do Mestrado em Engenharia Informática apresentado à Faculdade de Ciências e Tecnologia da Universidade de Coimbra.
In the past few years, the idea of the “Internet of Things” has been developing rapidly, with sensors and machines communicating with each other through the Internet. These new technologies can be used to support new types of Cyber-Physical systems(CPS). Even though CPS consider humans as a part of itself, they still treat them as external element, with unpredictable behavior. In order to serve human needs better, they have to take into account all sorts of psychological and emotional states. Smartphones present an excellent opportunity to do so, seen as they contain several sensors that allow us to collect information about user movement, location, their environment, and interaction with other people. This type of mobile device usually accompanies the user anywhere he goes throughout the day. We have taken this opportunity and tried to create apps that can infer human emotions and help people by giving them suggestions that may improve their mood. These apps are HappySPEAK and WeDoCare. We also tested and analyzed the system on which these were built upon: HappyWalk. All of these apps are based on the Happy System architecture. HappySPEAK aims to further improve this platform by detecting if the user is isolated and give suggestions that may help him overcome it. Migrants are the perfect candidates to use this, seeing that it is common for them to come alone to a new country in order to provide for their families. WeDoCare aims to detect violent attacks against users, and aims to help them by alerting other people that an attack is happening, show danger zones and alternate paths to avoid them. The rest of the report will focus on the Software Engineering part, implementation of these apps and what we can do to further improve them. We will also present all of the performance and emotion detection test results and analyze them thoroughly to expose our findings. Everything described in this report reflects the work done in the 2015/2016 school year.

碩士
國立清華大學
資訊系統與應用研究所
102
With the vast developments of microelectronics, a multitude of sensors can now be packed into a smart phone. This has enabled many context-aware applications that utilize the rich set of sensors to sense the environmental contexts, system status, and user activities. For a smart phone, it is common that different applications may request the same context, while a context may be inferred by different combinations of sensors. Current phone systems do not coordinate the use of sensors by the context-aware applications, leading to redundant sensors activated and unnecessary energy consumption. In this thesis, we propose an Energy/Accuracy-Optimized Framework (EAOF), which sits between the applications and the low-level sensors to provide a coordinated and optimized use of sensors to satisfy the context-sensing requirements of the applications. The use of sensors may be optimized based on two criteria: energy-optimized, which minimizes the total energy consumption while maintaining a target accuracy, and accuracy-optimized, which maximizes the overall accuracy under a given energy budget. Our experimental results show that the power consumption can be reduced by 30.45% in the energy-optimized mode and 19.91% in the accuracy-optimized mode, compared with the original, uncoordinated sensor management on Android.

Indiana University-Purdue University Indianapolis (IUPUI)
With the advances in embedded technology and the omnipresence of smartphones, tracking systems do not need to be confined to a specific tracking environment. By introducing mobile devices into a tracking system, we can leverage their mobility and the availability of multiple sensors such as camera, Wi-Fi, Bluetooth and Inertial sensors. This thesis proposes to improve the existing tracking systems, enhanced Distributed Tracking System (e-DTS 2.0) [19] and enhanced Distributed Object Tracking System (eDOTS)[26], in the form of e-DTS 3.0 and provides an empirical analysis of these improvements. The enhancements proposed are to introduce Android-based mobile devices into the tracking system, to use multiple sensors on the mobile devices such as the camera, the Wi-Fi and Bluetooth sensors and inertial sensors and to utilize possible resources that may be available in the environment to make the tracking opportunistic. This thesis empirically validates the proposed enhancements through the experiments carried out on a prototype of e-DTS 3.0.