Thèses sur le sujet « Smartphone-based »

Human Activity Recognition (HAR) is a multidisciplinary research field that aims to gather data regarding people's behavior and their interaction with the environment in order to deliver valuable context-aware information. It has nowadays contributed to develop human-centered areas of study such as Ambient Intelligence and Ambient Assisted Living, which concentrate on the improvement of people's Quality of Life. The first stage to accomplish HAR requires to make observations from ambient or wearable sensor technologies. However, in the second case, the search for pervasive, unobtrusive, low-powered, and low-cost devices for achieving this challenging task still has not been fully addressed. In this thesis, we explore the use of smartphones as an alternative approach for performing the identification of physical activities. These self-contained devices, which are widely available in the market, are provided with embedded sensors, powerful computing capabilities and wireless communication technologies that make them highly suitable for this application. This work presents a series of contributions regarding the development of HAR systems with smartphones. In the first place we propose a fully operational system that recognizes in real-time six physical activities while also takes into account the effects of postural transitions that may occur between them. For achieving this, we cover some research topics from signal processing and feature selection of inertial data, to Machine Learning approaches for classification. We employ two sensors (the accelerometer and the gyroscope) for collecting inertial data. Their raw signals are the input of the system and are conditioned through filtering in order to reduce noise and allow the extraction of informative activity features. We also emphasize on the study of Support Vector Machines (SVMs), which are one of the state-of-the-art Machine Learning techniques for classification, and reformulate various of the standard multiclass linear and non-linear methods to find the best trade off between recognition performance, computational costs and energy requirements, which are essential aspects in battery-operated devices such as smartphones. In particular, we propose two multiclass SVMs for activity classification:one linear algorithm which allows to control over dimensionality reduction and system accuracy; and also a non-linear hardware-friendly algorithm that only uses fixed-point arithmetic in the prediction phase and enables a model complexity reduction while maintaining the system performance. The efficiency of the proposed system is verified through extensive experimentation over a HAR dataset which we have generated and made publicly available. It is composed of inertial data collected from a group of 30 participants which performed a set of common daily activities while carrying a smartphone as a wearable device. The results achieved in this research show that it is possible to perform HAR in real-time with a precision near 97\% with smartphones. In this way, we can employ the proposed methodology in several higher-level applications that require HAR such as ambulatory monitoring of the disabled and the elderly during periods above five days without the need of a battery recharge. Moreover, the proposed algorithms can be adapted to other commercial wearable devices recently introduced in the market (e.g. smartwatches, phablets, and glasses). This will open up new opportunities for developing practical and innovative HAR applications.
El Reconocimiento de Actividades Humanas (RAH) es un campo de investigación multidisciplinario que busca recopilar información sobre el comportamiento de las personas y su interacción con el entorno con el propósito de ofrecer información contextual de alta significancia sobre las acciones que ellas realizan. Recientemente, el RAH ha contribuido en el desarrollo de áreas de estudio enfocadas a la mejora de la calidad de vida del hombre tales como: la inteligència ambiental (Ambient Intelligence) y la vida cotidiana asistida por el entorno para personas dependientes (Ambient Assisted Living). El primer paso para conseguir el RAH consiste en realizar observaciones mediante el uso de sensores fijos localizados en el ambiente, o bien portátiles incorporados de forma vestible en el cuerpo humano. Sin embargo, para el segundo caso, aún se dificulta encontrar dispositivos poco invasivos, de bajo consumo energético, que permitan ser llevados a cualquier lugar, y de bajo costo. En esta tesis, nosotros exploramos el uso de teléfonos móviles inteligentes (Smartphones) como una alternativa para el RAH. Estos dispositivos, de uso cotidiano y fácilmente asequibles en el mercado, están dotados de sensores embebidos, potentes capacidades de cómputo y diversas tecnologías de comunicación inalámbrica que los hacen apropiados para esta aplicación. Nuestro trabajo presenta una serie de contribuciones en relación al desarrollo de sistemas para el RAH con Smartphones. En primera instancia proponemos un sistema que permite la detección de seis actividades físicas en tiempo real y que, además, tiene en cuenta las transiciones posturales que puedan ocurrir entre ellas. Con este fin, hemos contribuido en distintos ámbitos que van desde el procesamiento de señales y la selección de características, hasta algoritmos de Aprendizaje Automático (AA). Nosotros utilizamos dos sensores inerciales (el acelerómetro y el giroscopio) para la captura de las señales de movimiento de los usuarios. Estas han de ser procesadas a través de técnicas de filtrado para la reducción de ruido, segmentación y obtención de características relevantes en la detección de actividad. También hacemos énfasis en el estudio de Máquinas de soporte vectorial (MSV) que son uno de los algoritmos de AA más usados en la actualidad. Para ello reformulamos varios de sus métodos estándar (lineales y no lineales) con el propósito de encontrar la mejor combinación de variables que garanticen un buen desempeño del sistema en cuanto a precisión, coste computacional y requerimientos de energía, los cuales son aspectos esenciales en dispositivos portátiles con suministro de energía mediante baterías. En concreto, proponemos dos MSV multiclase para la clasificación de actividad: un algoritmo lineal que permite el balance entre la reducción de la dimensionalidad y la precisión del sistema; y asimismo presentamos un algoritmo no lineal conveniente para dispositivos con limitaciones de hardware que solo utiliza aritmética de punto fijo en la fase de predicción y que permite reducir la complejidad del modelo de aprendizaje mientras mantiene el rendimiento del sistema. La eficacia del sistema propuesto es verificada a través de una experimentación extensiva sobre la base de datos RAH que hemos generado y hecho pública en la red. Esta contiene la información inercial obtenida de un grupo de 30 participantes que realizaron una serie de actividades de la vida cotidiana en un ambiente controlado mientras tenían sujeto a su cintura un smartphone que capturaba su movimiento. Los resultados obtenidos en esta investigación demuestran que es posible realizar el RAH en tiempo real con una precisión cercana al 97%. De esta manera, podemos emplear la metodología propuesta en aplicaciones de alto nivel que requieran el RAH tales como monitorizaciones ambulatorias para personas dependientes (ej. ancianos o discapacitados) durante periodos mayores a cinco días sin la necesidad de recarga de baterías.

This thesis consists of four research papers presenting a microdata analysis approach to assess and evaluate the Parkinson’s disease (PD) motor symptoms using smartphone-based systems. PD is a progressive neurological disorder that is characterized by motor symptoms. It is a complex disease that requires continuous monitoring and multidimensional symptom analysis. Both patients’ perception regarding common symptom and their motor function need to be related to the repeated and time-stamped assessment; with this, the full extent of patient’s condition could be revealed. The smartphone enables and facilitates the remote, long-term and repeated assessment of PD symptoms. Two types of collected data from smartphone were used, one during a three year, and another during one-day clinical study. The data were collected from series of tests consisting of tapping and spiral motor tests. During the second time scale data collection, along smartphone-based measurements patients were video recorded while performing standardized motor tasks according to Unified Parkinson’s disease rating scales (UPDRS). At first, the objective of this thesis was to elaborate the state of the art, sensor systems, and measures that were used to detect, assess and quantify the four cardinal and dyskinetic motor symptoms. This was done through a review study. The review showed that smartphones as the new generation of sensing devices are preferred since they are considered as part of patients’ daily accessories, they are available and they include high-resolution activity data. Smartphones can capture important measures such as forces, acceleration and radial displacements that are useful for assessing PD motor symptoms. Through the obtained insights from the review study, the second objective of this thesis was to investigate whether a combination of tapping and spiral drawing tests could be useful to quantify dexterity in PD. More specifically, the aim was to develop data-driven methods to quantify and characterize dexterity in PD. The results from this study showed that tapping and spiral drawing tests that were collected by smartphone can detect movements reasonably well related to under- and over-medication. The thesis continued by developing an Approximate Entropy (ApEn)-based method, which aimed to measure the amount of temporal irregularity during spiral drawing tests. One of the disabilities associated with PD is the impaired ability to accurately time movements. The increase in timing variability among patients when compared to healthy subjects, suggests that the Basal Ganglia (BG) has a role in interval timing. ApEn method was used to measure temporal irregularity score (TIS) which could significantly differentiate the healthy subjects and patients at different stages of the disease. This method was compared to two other methods which were used to measure the overall drawing impairment and shakiness. TIS had better reliability and responsiveness compared to the other methods. However, in contrast to other methods, the mean scores of the ApEn-based method improved significantly during a 3-year clinical study, indicating a possible impact of pathological BG oscillations in temporal control during spiral drawing tasks. In addition, due to the data collection scheme, the study was limited to have no gold standard for validating the TIS. However, the study continued to further investigate the findings using another screen resolution, new dataset, new patient groups, and for shorter term measurements. The new dataset included the clinical assessments of patients while they performed tests according to UPDRS. The results of this study confirmed the findings in the previous study. Further investigation when assessing the correlation of TIS to clinical ratings showed the amount of temporal irregularity present in the spiral drawing cannot be detected during clinical assessment since TIS is an upper limb high frequency-based measure.

Mestrado em Engenharia Electrónica e de Telecomunicações
Attendance control systems are associated with labour legislation for the protection of employees and employers. School attendances' issues may be directly connected to academic achievements at the same time it is di cult to control by children's parents. To solve these problems, there are several systems available and the di erence between them is essentially the technology adopted to make them work. Nowadays, mobile equipment market has a great diversity with smartphone equipments having the highest demands and high growth rates. Due to the huge capacities of their operating systems and hardware, smartphones have now the possibility to be used as part of an attendance control system. In this dissertation, it is developed an attendance control system based on smarphone and virtual doors composed of two Access Points (APs). This system has the advantage of being inexpensive and, since the application runs in the background of the operating system, attendance detection becomes a fully automatic process. Moreover, since a smartphone is a personal equipment which is hardly shared with other person, attempts to defraud the control system are very unlikely to happen.
Os sistemas de registo de assiduidade estão associados a legislação laboral para defender os interesses dos empregados e dos empregadores. O controlo de presenças em escolas adquiriu também extrema importância estando cada vez mais associado ao sucesso académico. Atualmente existe uma panóplia de sistemas deste tipo cujas diferenças estão essencialmente ao nível da tecnologia utilizada como base de funcionamento do sistema. O mercado de equipamentos m oveis apresenta igualmente grande diversidade e um rápido e sustentado crescimento, sendo mesmo um dos mercados com maiores taxas de crescimento ano ap os ano na área das tecnologias de informação. A venda de smartphones representa j a mais de metade da venda deste tipo de equipamentos. Devido as enormes potencialidades dos seus sistemas operativos e do seu hardware, estes equipamentos abriram a possibilidade da sua utilização como parte integrante de um sistema de registo de assiduidade. Nesta dissertação e proposto um sistema de registo de assiduidade baseado em smartphone e em portarias virtuais compostas por dois Access Point. O sistema apresenta como principais vantagens o facto de ser barato, a aplicação correr em segundo plano no sistema operativo tornando o processo de picagem um processo automático, e também por ser um dispositivo que o utilizador tem dificuldade em ceder a terceiros, reduzindo por isso tentativas de fraude ao sistema de controlo de assiduidade.

The fields of navigation and motion inference have rapidly been transformed by advances in computing, connectivity, and sensor design. As a result, unprecedented amounts of data are today being collected by cheap and small navigation sensors residing in our surroundings. Often, these sensors will be embedded into personal mobile devices such as smartphones and tablets. To transform the collected data into valuable information, one must typically formulate and solve a statistical inference problem. This thesis is concerned with inference problems that arise when trying to use smartphone sensors to extract information on driving behavior and traffic conditions. One of the fundamental differences between smartphone-based driver behavior profiling and traditional analysis based on vehicle-fixed sensors is that the former is based on measurements from sensors that are mobile with respect to the vehicle. Thus, the utility of data from smartphone-embedded sensors is diminished by not knowing the relative orientation and position of the smartphone and the vehicle. The problem of estimating the relative smartphone-to-vehicle orientation is solved by extending the state-space model of a global navigation satellite system-aided inertial navigation system. Specifically, the state vector is augmented to include the relative orientation, and the measurement vector is augmented with pseudo observations describing well-known characteristics of car dynamics. To estimate the relative positions of multiple smartphones, we exploit the kinematic relation between the accelerometer measurements from different smartphones. The characteristics of the estimation problem are examined using the Cramér-Rao bound, and the positioning method is evaluated in a field study using concurrent measurements from seven smartphones. The characteristics of smartphone data vary with the smartphone's placement in the vehicle. To investigate this, a large set of vehicle trip segments are clustered based on measurements from smartphone-embedded sensors and vehicle-fixed accelerometers. The clusters are interpreted as representing the smartphone being rigidly mounted on a cradle, placed on the passenger seat, held by hand, etc. Finally, the problem of fusing speed measurements from the on-board diagnostics system and a global navigation satellite system receiver is considered. Estimators of the vehicle’s speed and the scale factor of the wheel speed sensors are derived under the assumptions of synchronous and asynchronous samples.

QC 20171123

Mestrado em Engenharia Electrónica e Telecomunicações
Intelligent Transportation Systems are emerging, to increase safety, e - ciency and comfort on roads. This intelligence is due to the fact that new technologies are being introduced in the most recent automobiles. As a result of this technological evolution, vehicular communication systems are being developed, to provide drivers with more information about the interventionists present in the roads they circulate. Predictions point that this information can increase safety and e ciency on roads. Presently, the Instituto de Telecomunica c~oes de Aveiro, is developing its own vehicular communication system, named HEADWAY, as a solution. HEADWAY DSRC 5.9 GHz vehicular communication system currently under development. Smartphones nowadays are very popular devices. This is due to the fact that they pack incredible hardware resources in a small and portable device and the possibility to third party developers, develop applications for them. This enables these devices to be used in di erent areas, depending only from the creativity of the developers. To diminish the number of fatalities due to road accidents, the European Commission has mandated the implementation of eCall in every new vehicle by 2015. In vehicles, the eCall aim to detect accidents and request accidents automatically. This dissertation targets, on the one hand, the development of an accident detection mechanism with eCall implementation. On the other hand it targets the integration of smartphones with HEADWAY, by developing an application that takes advantage of the system characteristics and demonstrates it. To achieve the proposed goals, an Android application was developed which acts as an HMI for HEADWAY, enables message exchange between vehicles, automatically detects accidents and proceeds with a help request. Most of the proposed goals where achieved, except the eCall implementation, which an alternative method was developed.
Os Sistemas de Transporte Inteligentes estão a emergir, de forma a introduzir mais segurança, eficiência e conforto nas estradas. Esta inteligência deve-se ao facto de novas tecnologias estarem a ser introduzidas nos automóveis recentes. Como resultado da evolução tecnológica os sistemas de comunicação veiculares estão a ser desenvolvidos, com o objectivo de munir os condutores com informações relativas aos diferentes intervenientes da estrada onde circulam. Prevê-se que este tipo de informação leve a uma maior segurança e eficiência nas estradas. Actualmente no Instituto de Telecomunicações de Aveiro, está a decorrer um projecto que visa fornecer uma alternativa como sistema de comunicações veiculares. Este projecto tem o nome de HEADWAY. O HEADWAY é um sistema de comunicações veiculares DSRC 5.9 GHz, atualmente em desenvolvimento. Os smartphones hoje em dia já são dispositivos estabelecidos no mercado. Isto deve-se ao facto destes apresentarem um grande potencial, ao integrarem recursos de hardware incríveis num pequeno dispositivo e de permitirem o desenvolvimento de aplicações por terceiros. A criatividade dos programadores tem permitido a utilização destes dispositivos em diversas áreas. De forma a diminuir o número de mortes causadas por acidentes rodoviários, a Comissão Europeia, tornou obrigatório que em 2015 todos os novos carros estejam equipados com o sistema eCall, que visa a deteção de acidentes e pedido de ajuda ao 112 automáticos. Esta dissertação tem por um lado, o objectivo de desenvolver um detector de acidentes com implementação de eCall, e, por outro lado, integrar um smartphone com o HEADWAY, através do desenvolvimento de uma aplicação que tire partido das características deste sistema e assim o demonstre. Para cumprir os objectivos foi desenvolvida uma aplicação para Android que atua como HMI para o HEADWAY, facilita a troca de mensagens entre veículos, deteta automaticamente acidentes e procede com pedidos de ajuda. Na conclusão do projecto, verificou-se que os objectivos propostos foram na sua maioria concluídos, exceptuando a implementação da eCall ao 112, sendo desenvolvido um método alternativo.

Smartphones have facilitated tasks in private and work life for its users. In business, employees often should manage sensitive data that unauthorised people cannot access, so some user authentication is needed to perform. Besides the normal user authentication, some employers give the right to access to the sensitive data only if the employees stay in specific locations. That makes sense for those businesses that have various construction sites and offices that are not necessarily located in the same geographical region. In those companies, the employees must be able to perform their tasks from different locations regardless of the available network infrastructure. To protect the data from intruders, this research presents a secure location-based user authentication scheme for mobile application that works offline. This research considers to enable access to the sensitive data using off-the-shelf mobile devices without adding any extra hardware and with no additional information from a fixed infrastructure. This Thesis firstly describes the architecture and attributes of the proposed solution. Then, the techniques used for the design and functionality of the solution are presented. The results of this study reveal that the proposed solution is more suitable for the applications that is used in outdoor locations. Finally, to alleviate the shortcoming of the presented technique for indoor locations, a new method has been discussed and tested. This report is a final Thesis in collaboration with SAAB. The purpose of this research is to examine the best way to protect sensitive data managed by the employees using their smartphones in different workplaces.

Mobile phone usage is constantly increasing, as a result we are becoming more reliant on services provided for mobile devices. Mobile devices and especially smartphones can be used for a variety of purposes and has especially made location based services (LBS) mainstream, where outdoor usage has been the primary scope of use. However, by leveraging the positioning abilities of the Assisted Global Positioning System (A-GPS) and location-sensing techniques based on e.g. cellular towers and WiFi access points (AP), mobile phones can be used to determine a position in indoor environments. As indoor positioning has evolved, early stage systems designed for indoor navigation have been developed. With positioning accuracy set aside, other areas (e.g. usability and design) of indoor positioning and navigation have been sparsely explored, both regarding user behaviour and adaptation of the provided solutions. This study encompasses an experimental deployment of two smartphone-based indoor navigation systems that were evaluated using two methods: self-guided exploration and end-user evaluation. The subject of indoor navigation were approached from two separate viewpoints - Administrator and End-user - with usability as a common denominator. The results from our study clearly showed that systems designed for smartphone-based indoor navigation, have yet to reach their full potential from both viewpoints. Functionality embedded in the systems proved to be very error sensitive, due to a minimal usability margin concerning end-user abilities to orient and navigate indoors. Administrators have to make a thorough assessment of the intended environment, in order to ensure that the system will operate properly and to minimise the time for deployment. Administrators also have to consider the controllability of the provided system, as dependencies towards the creator of the system infer undesired lack of control. If pre-existing infrastructure is to be utilised, such as a WiFi installation, the prerequisites of indoor positioning needs to be ensured by the administrators of the system. Lastly in this paper, our common recommendations are compiled as six guidelines, which are: 1. Functionality and features for orientation and navigation are error sensitive, 2. Positioning technique should be determined based on the environment, 3. Precise positioning is less crucial than stable positioning, 4. Live-tracing is of great importance in terms of orientational feedback, 5. Dynamic floor plans are fundamental for a dynamic navigational system, and 6. Controllability is valuable, dependance should be kept to a minimum.
I takt med den konstant växande globala mobilanvändningen blir vi allt mer beroende av mobila tjänster. Smartphones har numera ett brett spektrum av användningsområden, där platsspecifika tjänster blivit en del av vår vardag. Tjänsterna har dock hitintills främst kommit att omfatta utomhusmiljöer. Genom att utnyttja mobiltelefonens inbyggda Assisted Global Positioning System (A-GPS) i kombination med tekniker för platsigenkänning, som baseras på exempelvis mobilmaster eller WiFi-noder, kan dock mobiltelefoner numera användas för att bestämma en position även i inomhusmiljöer. Då utvecklingen av inomhuspositionering fortskridit har förstadium-system, avsedda för inomhusnavigering med hjälp av smartphones, tagits fram. Bortsett från noggrannheten i den resulterade positionen så har andra områden inom inomhusnavigering och -positionering blivit åsidosatta, såsom användarbeteende och implementering av de framtagna systemen. Denna studie innefattar två faser, varav första fasen var att upprätta två inomhusnavigeringssystem samt parallellt utvärdera dessa system ur ett utvecklarperspektiv. I den andra fasen, kallad slutanvändarperspektivet, genomfördes användartester, vilket gjordes i form av fälttest i kombination med intervjuer. Gemensamt för bägge faser var användbarhet, där två olika perspektiv och därmed två olika betydelser gestaltades. Resultatet från vår studie visar tydligt att system utformade för inomhusnavigering med hjälp av smartphones, ännu inte nått sin fulla potential - varken för slutanvändare eller administratörer. Den inbäddade funktionaliteten visade sig vara väldigt felkänslig, där små användbarhetsproblem fick stora konsekvenser för slutanvändares förmåga att orientera och navigera sig inomhus. Administratörer/utvecklare måste göra en grundlig utvärdering av den ämnade inomhusmiljön, för att säkerställa att systemet kommer fungera samt för att minimera den totala tiden för implementeringen. Administratörer bör även överväga kontrollerbarheten av tillgängliga system, då beroenden till aktörer som tillhandahåller systemet innebär en oönskad brist av kontroll. Om existerande infrastruktur ämnas användas, såsom WiFi-noder, bör nödvändiga förutsättningar för inomhuspositionering säkerställas på förhand. Avslutningsvis i denna rapport listas våra (författarnas) gemensamma rekommendationer, där de mest omfattande slutsatserna lyfts fram i form av sex riktlinjer. Riktlinjerna som tagits fram är: 1 Funktionalitet för orientering och navigering är felkänslig, 2. Positioneringsmetod bör väljas baserat på den tilltänkta miljön, 3. Stabil positionering är viktigare än exakt positionering, 4. Live-spårning ger omedelbar återkoppling på förflyttning, 5. Dynamiska planlösningar är grundläggande för ett dynamiskt navigeringssytem, samt 6. Kontrollerbarhet är värdefullt, beroenden bör vara minimala.

Here we present a novel Smartphone-based colorimeter and demonstrate its application to the measurements of glucose and protein concentrations in biological samples. The key innovation of our approach was to combine powerful image processing encoded into a mobile phone application with a low cost 3D printed sample holder that allowed to control lighting conditions and significantly improved sensitivity. Different solutions with protein and glucose concentrations ranging from 0 to 2000 mg/dL were prepared and analyzed using our system. The Smartphone-based colorimeter always correctly classified the corresponding reagent strip pads, what confirms that it can be used as a low cost alternative for commercial test strip analyzers.

Ingeniero Civil Industrial
Las redes de pagos electrónicos constituyen uno de los pilares del comercio moderno. El acceso a estos servicios permite al usuario mejorar su calidad de vida al enfrentar menos inseguridad cuando el manejo del dinero, el acceso a nuevos productos y servicios que sólo están disponibles a través de plataformas de comercio electrónico y reducir el tiempo dedicado a la realización de pagos y el retiro de dinero en efectivo. La alta penetración de teléfonos inteligentes en América Latina, donde los pronósticos predicen que para el año 2017 más del 44% de la población será el propietario de un Smartphone con internet móvil, presenta una oportunidad desafiante para proporcionar nuevos servicios basados en la tecnología de una manera más accesible y ubicua. Por otro lado, las redes de pago electrónico actuales presentan altos cargos para los comerciantes, que van desde 1,5% a más del 5%, mientras que se subvenciona el lado comprador. Por otra parte, la baja capilaridad de las redes existentes empuja una gran demanda de dinero en efectivo que llega a más de USD $ 40 mil millones por año en Chile y USD $ 30 mil millones al año en Perú. Ambos factores han incentivado el creciente interés de los usuarios en los servicios financieros móviles, ya sea para cuentas personales, pagos de facturas o servicios de prepago. El reciente desarrollo de protocolos criptográficos como Bitcoin y Ripple permite a los desarrolladores crear servicios financieros móviles de bajo coste derivados de la utilización de protocolos de transacciones distribuidas. Este trabajo presenta Dine: un Servicio Financiero Móvil basado en Smartphones y habilitado por el protocolo de monedas criptográficas Ripple. En base a un enfoque centrado en el Delta Model, Customer Discovery y Lean Startup se presenta un análisis del mercado y las hipótesis de desarrollo de servicio que guiarán el modelo de negocios del emprendimiento. Un plan de negocios es presentado junto con la primera implementación de un prototipo funcional limitado para la aplicación Smartphone y plataforma web.

Dissertação para obtenção do Grau de Mestrado em Engenharia de Informática
The use of persuasive technologies can induce changes in attitudes or behaviours, even in individuals that other strategies of persuasion can not reach effectively. In addition, this type of technology can be applied in numerous areas such as health, education, finance, e-business, among others. Although persuasion can be seen as something negative, being used to serve the interests of the persuader rather than the interests of the persuaded, this work aims to achieve a common and shared goal: to change people's behaviour towards the environment. A significant part of the population is still not aware of the sustainability problems that our planet is facing, so it is important to inform people about the theme while persuading them to change their behaviour and acquire proenvironmental attitudes. In this dissertation, work was conducted to alert citizens to this issue in a fun and immersive way using mobile devices, more specifically smartphones, and augmented reality technology that was used to create an environmental scanner. This scanner provided the user with informative insight about the surrounding environment, while highlighting the environmental threats. In addition to augmented reality, pro-environmental actions were positively reinforced using a reward system and a virtual character that interacted and motivated the user. A form of rapid spread through social networks was also created, allowing the persuasive effect to quickly reach a large number of users. Finally was performed a study to assess the success of the work done in changing behaviour towards environmental issues, and to study the influence of augmented reality and positive reinforcement in the changing of behaviours and acquisition of pro-environmental attitudes.

Mobile devices are increasingly used for self-monitoring in areas of health, mood, and exercise tracking. The capabilities of modern devices also enable automation of this monitoring on a brand new scale. This thesis outlines the design, implementation, and evaluation via two-month long deployment of a system aimed to help both individual users and researchers to efficiently gather self-reported data. The name of the presented system is LifeTracker. LifeTracker is a two-tier system consisting of an Android application, used to gather data for personal or academic use, and a web dashboard, used to define parameters for studies. The main focus of the application is a novel input mechanism for self-reported data, leveraging notification popups as reactive input methods, that are presented to the user at opportune times. The thesis explains the design process of the system in detail in terms of use cases, requirements, and interface wireframes and the implementation process for both the web dashboard as well as the Android application. The Android application is evaluated in terms of usability and data gathering efficiency using interviews and the Standard Usability Survey. We also perform quantitative analysis of the machine learning classifiers used to predict user interruptibility. The results of the deployment show that users with prior experience with life logging applications appreciate the novel input mechanism and its strengths. Predicting user interruptibility can be performed at a reasonable rate, still considering personal variance of each individual
Mobiililaitteita käytetään suurenevissa määrin henkilökohtaisen terveyden, mielentilan ja fyysisten aktiviteettien seuraamiseen. Modernien laitteiden suorituskykykapasiteetti sallii myös tämänkaltaisen seurannan automatisoinnin. Tämä diplomityö hahmottaa suunnittelun, toteutuksen ja arvioinnin kahden kuukauden mittaisen käyttöönoton avulla järjestelmälle, jonka tarkoitus on auttaa yksittäisiä käyttäjiä ja tutkijoita keräämään tämänkaltaista seuraamistietoa. Työssä esitetyn järjestelmän nimi on LifeTracker. LifeTracker on kaksitasoinen järjestelmä, joka sisältää Android applikaation, jota käytetään tiedon keräämiseen henkilökohtaiseen ja tutkimuskäyttöön, ja Webkäyttöliittymän, jota käytetään tutkimusten parametrien määrittelemiseen. Applikaation fokus on uudenlaisessa syöttömekanismissa seurantatiedolle, joka käyttää ponnahdusikkunoita reaktiivisena syöttömekanismina, jotka esitetään käyttäjille sopivina aikoina. Työ selittää järjestelmän suunnittelun yksityiskohtaisesti käyttötapausten, vaatimusmäärittelyn ja käyttöliittymämallien avulla, ja toteutuksen sekä Web-käyttöliittymälle ja Android applikaatiolle. Android applikaatio arvioidaan käytettävyyden ja tiedonkeruun tehokkuuden suhteen käyttäen käyttäjähaastatteluja ja SUS-menetelmää. Suoritamme myös kvantitatiivisen analyysin koneoppimismalleista, joita käytetään käyttäjän keskeyttämisen ennakoimiseen. Käyttöönoton tulokset kertovat, että käyttäjät joilla on aikaisempaa kokemusta elämänhallintasovellusten kanssa ymmärtävät uudenlaisen syöttömekanismin edut ja vahvuudet. Käyttäjän keskeyttäminen voidaan myös ennakoida riittävällä tarkkuudella, ottaen huomioon muutokset yksittäisten käyttäjien välillä

Patients with lower limbs problems are an increasing population in the US and many of them require surgery and its subsequent post-op Physical Therapy (PT). For all these patients, tracking their progress and evolution towards full recovery is very important. To assess the patients and track their progress, patients are usually required to perform very specific tests administered by a physical therapist. These tests either require very expensive equipment or rather require the subjective experience of the physical therapist who administer them. One of these tests is the Functional Gait Assessment (FGA) test, perhaps the most widely adopted one for gait assessment. This thesis presents a system for Clinical Gait Assessment using exclusively the sensors embedded in today’s smartphones. The system processes the raw sensor data to perform the FGA test and calculate additional metrics, capable of identifying problems in the human gait. The system is therefore objective, as it is based on measurements; cheap, as it only requires a smartphone; mobile, as it can be used pretty much anywhere; and self-care, as it does not need the presence of a physical therapist. The system was designed and tested on the Android OS with the phone attached to the back of the user using a belt or elastic band. It includes a new step detection algorithm with a mean absolute error of ±1 and algorithms to detect the deviation from a straight path with an accuracy of 90%, 80%, 35%, and 30% for each of the required deviation levels of the FGA test. Additionally, the system includes autocorrelation and DTW metrics, which provide additional information to detect different impediments of the user gait.

Electrical and Computer Engineering
M.S.E.E.
The Smartphone-based Compression-Induced System (SCIS) is developed to obtain the mechanical properties of a tumor. Using a SCIS smartphone app, we obtain tactile images, and we developed data security methodology in this thesis. The first version of the system (SCIS V1) is developed using the symmetric key encryption, which protects all medical data from hackers. AES (Advanced Encryption Standard) encryption method is used to protect the data during the transmission. Encrypted data by AES is securely stored in the cloud server and used for processing in the local server. This security system uses Xcode and Python to encrypt and decrypt data. Even if the encrypted data is hacked, contents will be unreadable. In order to increase some of the scrutiny features of SCIS, we developed a new version. The second version (SCIS V2) includes the AES data encryption, the user authentication control, security key exchange system, and communication security. User authentication control part is the first step in preventing the accidental data leakage. Combining symmetric key encryption and asymmetric security key exchange is very effective to prevent attacks because the data and keys are encrypted before transmission. The data transmission protocol used in this system is also a secure protocol, which includes Secure Sockets Layer/Transport Layer Security (SSL/TLS). This protocol is the asymmetric encryption transmission protocol, which is used to transport encrypted data and encrypted keys in SCIS V2 systems. The Compression-Induced System Data Security is fully implemented in SCIS V2.
Temple University--Theses

Abstract. Smart phones together with plethora of different sensors create a massive data collection system. This system can be also used for storing, analyzing, and broadcasting data. Data can be anything that can be metered or derived, from chemical compounds to traffic congestion to advertisement data to users’ activity or health statistics. Using the sensors already present in smartphones together with Bluetooth capable controller chips to add more sophisticated sensors, user creates an easily extendable monitoring system that does not require an internet connection. After embedded initialization programming, configuring and managing these chips can be done with a smartphone using Bluetooth communication stack. This study presents an Android-library for managing BLE peripherals and an app to collecting and store the recorded data. Bluetooth devices are scanned and connected through Bluetooth Low Energy interface and data is stored to persistent Room database.Tiivistelmä. Älypuhelimet yhdessä lukuisten eri antureiden kanssa luovat massiivisen järjestelmän tietojen keräämiseksi, tallentamiseksi, lähettämiseksi ja analysoimiseksi. Nämä tiedot voivat olla mitä tahansa kemiallisista yhdisteistä liikenteen ruuhkautumiseen ja mainosdatan esittämisestä käyttäjän aktiivisuuteen ja terveystilastoihin. Käyttämällä älypuhelimen valmiiksi olemassa olevia sensoreita ja yhdistelemällä niitä Bluetooth -ominaisuudella varustettuun ohjaussiruun kehittyneempien sensorien kanssa, käyttäjä saa luotua helposti laajennettavan monitorointi verkoston, joka ei vaadi internet yhteyttä. Käyttöönotettaessa tarvitun sulautetun ohjelmakoodin jälkeen, sensorilaitteita voi ohjata älypuhelimella, käyttäen Bluetooth radiota. Tässä tutkimuksessa esitellään Android-kirjasto BLE sensorien hallintaan, yhdistettynä tietojen keräämiseksi ja tallentamiseksi rakennettuun appiin. Bluetooth-laitteet skannataan ja liitetään Bluetooth Low Energy -rajapinnan kautta ja näistä luettu data tallennetaan paikalliseen Room-tietokantaan.

Parkinson’s disease (PD) is a second most common neurological disorder that affects up to 10 million people worldwide. However, in spite of this vast number of patients, there is still no universal and applicable for everyone type of treatment. The current way of PD handling is followed by semiannual clinical visits with observations on the place and the corresponding medication prescription. However, the problem is that PD has an evolving nature and its symptoms may vary several times per day. Thus, the current way of observation does not provide a full picture of the disease and makes the personal treatment plan customization impossible. This study aims at the development of a new way of patient observation via mobile devices that can increase the patients’ medication adherence. The outcome of the study is the mobile application that leverages smartphone’s inbuilt sensors in order to keep track of subject’s state of health during the day. In order to encourage patients to regularly follow health sampling, the application uses gamification approach: the sampling sessions are implemented as a short-term accelerometer-based game that asks patients to play it several times per day. Along with it, with the use of smartphones notifications, the application reminds patients to take medications on time and record the timestamps to the application medication journal. The designed application will be used as a tool for continuous observation on the PD patients. The combination of datasets collected with the application can be used in the future studies in order to estimate the correlation between the medication effect and the severity of PD during the day.

Objectives: Dental Monitoring® (“DM,” Dental Monitoring, Paris, France), is a cloud-based software that allows orthodontists to track patients’ treatment remotely. The purpose of this study was to investigate the accuracy of the software in making linear measurements. Methods: Patients took intraoral photographs using the DM application, immediately followed by impressions for plaster models. Intercanine and intermolar width and arch depth measurements were made by DM and compared to measurements made on the plaster models. Data was analyzed using two one-sided t-tests for equivalence with equivalence bounds of +/-0.5mm. Significance level was set at 0.05. Results: Thirty sets of measurements were compared. The intercanine and intermolar measurement differences were on average 0.17mm and -0.02mm, respectively, and were deemed equivalent. The arch depth measurements had an average difference of -0.54mm and were deemed not equivalent. Conclusion: The monitoring software seems to provide an accurate assessment of linear tooth movements.

Thesis (MEng)--Stellenbosch University, 2015.
ENGLISH ABSTRACT: Road accidents are a growing concern for governments and is rising to become one of the leading causes of death in developing countries. Aggressive driving is one of the major causes of road accidents, and it is therefore important to investigate ways to improve people's driving habits. The ubiquitous presence of smartphones provides a new platform on which to implement sensor networks in vehicles, and therefore this thesis focuses on the use of smartphones to monitor a person's driving behaviour. The framework for a smartphone-based system that can detect and classify various driving manoeuvres is researched. As a proof of concept, a system is developed that specifically detects lateral driving manoeuvres and that classifies them as aggressive or not, using a supervised learning classification algorithm. Existing solutions found in research literature are investigated and presented. The best existing solution, a dynamic time warping classification approach, is also implemented and tested. We use an aggressive driving model that is based on the angle of a turn, the lateral force exerted on the vehicle and its speed through the turn. The tests and results of the implemented manoeuvre detection and classifcation algorithms are presented, and thoroughly discussed. The performance of each classifer is tested using the same data set, and a quantitative comparison are made between them. Ultimately, a lateral driving manoeuvre detection and recognition system was successfully developed, and its potential to be implemented on a smartphone was substantiated. The suitability of supervised learning classi ers for classifying aggressive driving, in comparison to dynamic time warping classifcation, was successfully demonstrated and used to validate our aggressive driving model. Conceivably, this work can be employed in the future to develop an holistic smartphone-based driver behaviour monitoring system, which can be easily deployed on a large scale to help make the public drive better. This would make our roads safer, reducing the occurrence of road accidents and fatalities.
AFRIKAANSE OPSOMMING: Padongelukkige is 'n groeiende bekommernis vir regerings en is een van die hoof oorsake van sterftes in ontwikkelende lande. Aggressiewe bestuur is een van die grootste oorsake van padongelukke, en dit is dus belangrik om ondersoek in te stel oor hoe mense se bestuurgewoontes verbeter kan word. Die alomteenwoordigheid van slimfone bied 'n nuwe platform waarop sensor netwerke geïmplementeer kan word in voertuie. Daarom fokus hierdie tesis op die gebruik van slimfone om 'n persoon se bestuurgedrag te moniteer. Die raamwerk vir 'n slimfoon-gebaseerde stelsel wat verskeie bestuurbewegings kan opspoor en klassifiseer is nagevors. As 'n bewys van die konsep, is 'n stelsel ontwikkel wat spesifiek laterale bestuurbewegings opspoor en dan klassifiseer of dit aggressief is of nie, met behulp van 'n klassifikasie algoritme wat onder toesig geleer is. Bestaande oplossings gevind in navorsingsliteratuur word ondersoek en aangebied. Die beste bestaande oplossing, 'n dinamiese tyd buiging klassifikasie benadering, word ook geïmplementeer en getoets. Ons gebruik 'n aggressiewe bestuurmodel wat gebaseer is op die hoek van 'n draai, die laterale krag wat uitgeofen is op die voertuig en sy spoed deur die draai. Die toetse en die resultate van die geïmplementeer beweging opsporing en klassifisering algoritmes word aangebied, en deeglik bespreek. Die prestasie van elke klassifiseerder is getoets met behulp van dieselfde stel data, en 'n kwantitatiewe vergelyking is tussen beide gemaak. Oplaas is 'n laterale bestuurbeweging bemerking en herkenning stelsel suksesvol ontwikkel en sy potensiaal om geïmplementeer te word op 'n slimfoon is gestaaf. Die geskiktheid van die onder-toesig-geleerde klassifiseerders vir die klassifikasie van aggressiewe bestuur, in vergelyking met dinamiese tyd buiging klassifikasie, was suksesvol gedemonstreer en gebruik om ons aggressiewe bestuurmodel te bewys. Hierdie werk kan in die toekoms gebruik word in 'n holistiese slimfoon-gebaseerde bestuurdergedrag monitering stelsel, wat maklik op groot skaal ontplooi kan word om te help verseker dat die publiek beter bestuur. Dit sal ons paaie veiliger maak, en die voorkoms van padongelukke en sterftes verminder.

Billions of people on earth lack a home address. In this paper we are investigating an approach to solve this using an address system where addresses consists of a GPS location and a description of how you find your way to the house when you are within close distance to the GPS location. The aim of the paper is to measure if said description has higher quality when it’s given using speech-based or regular text entry. Our findings indicate that speech based text input gives 1.7 times more information in about 5.5 times less time. From a usability standpoint there was no indicated difference, but as the experiments were carried out during perfect conditions it is concluded that speech-based text entry would likely present more of a challenge for the users. When and if speech recognition is more widely adopted into systems for everyday use, speech-based text entry will be a good asset for increasing the amount of information collected from users in navigational contexts.
Det uppskattas att över en miljard människor lever utan en adress. Den här studien siktar till att förbättra en applösning som använder genererade adresser bestående av GPS-koordinater och en tillhörande beskrivning. Beskrivningen är menad att vägleda användaren när hon befinner sig i närområdet för att komplettera GPS-punktens eventuella osäkerhet. Syftet är att undersöka om en sådan beskrivning är av bättre kvalitet om den skapas med röstigenkänning än med vanlig text-input. Resultaten visar att röstbaserad input ger 1.7 gånger mer information än om användarna får skriva direkt i sin mobiltelefon och spenderar i snitt 5.5 gånger mindre tid med uppgiften. Användarnas utvärdering indikerar ingen skillnad i användarvänlighet, men eftersom experimenten utförts under perfekta förhållanden slås det fast att röstbaserad input förmodligen skulle innebära mer av en utmaning för användare. När och om röstigenkänning blir en mer integrerad del i vardagstekniken skulle röstbaserad text-input vara ett användbart medel att öka mängden information man får ut av användarnas egna beskrivningar.

Many students struggle when learning how to program. Research shows that lab sessions where students collaboratively solve assignments can improve the novices' learning outcome. Using algorithm visualization to make abstract concepts behind computer programs more visible and to help students explore dynamic algorithmic behaviour have also proven to be a valueable learning aid when students can interact with and influence the visualization. However, many programming courses consist of frontal lectures which do not allow students to actively interact and engage with an algorithm or its visualization. A teacher can not easily utilize the advantages of collaborative programming and visualization engagement in a lecture with the tools available. mJeliot bridges this gap and enables teachers to engage students by providing the means to solve small programming assignments during a lecture and to interact and collaborate in the classroom by utilizing the students' smartphones. Students can solve and share the solution to an assignment and can present it to the class by controlling the resulting visualization.

Context: Sensor base data is being used for many purposes in designing various memory aid systems for cognitive impaired people. Different memory aids or reminder systems are based on various technologies such as NFC, accelerometer, GPS and gyroscope. Smart phones are equipped with such sensors and can be used for assistance of persons. In this study we use smart phone sensors in order to design a context aware reminder system to assist cognitive impaired people. Objectives: Different reminder systems, needs for such systems, technologies and models used to build a reminder system are identified in this research work. Ultimate goal of the study is to assist cognitive people in their daily life activities, using available embedded technologies of smart phones. Following objectives were set to achieve the goal of the thesis work: • What are reminder systems and why do we need such systems? • What are the different kinds of technologies reported in literature for reminder systems? • What are the issues encountered by cognitive impaired/elderly people while performing their daily life activities? • How to design and implement context aware reminder system using Smartphone embedded sensors? Methods: Mix method approach is used to carry out this study. Literature review is conducted based on the notion of systematic review. Data is collected through survey and interviews, conducted in south Sweden municipality, to analyze and indentify daily life issues and problems of cognitive people. Experiments are performed in real environment to test and verify our application. We evaluate the performance of activity recognition algorithm, implemented in the application, using Weka. Results: Various reminder systems, their needs and underlined technologies are identified and reported. Activities of daily living and issues addressed by these reminder systems are also identified. Survey and interviews help us to identify issues and problems faced by cognitive impaired/elderly while performing their daily life activities. For example, we find out that cognitive people not only forget their daily life activities but also during performing these activities. Conclusions: Many proposed models in literature are related to each other and use similar sensor based data from various technologies. Based on literature review, survey and interviews we have concluded that context based reminder system is essential for cognitive disabled people. It leads us to design a context based reminder system for android based smart phones. The preliminary tests help us to verify our model but there is absolute need for further empirical verification and validation.

Bisphenol A (BPA), an emerging environmental contaminant and endocrine disrupting compound, has been observed globally in surface water and waste leachates at concentrations that are hazardous to aquatic life and potentially to humans. Limitations in field monitoring on account of the extensive laboratory infrastructure required for standard BPA detection warrants investigation into portable or handheld sensing platforms. In this work, we evaluated a standalone smartphone-based fluorescence sensing method for identifying BPA from water samples. Toward this goal, we demonstrated the novel application of 8-hydroxypyrene-1,3,6-trisulfonic acid (HPTS) as a fluorescent probe with suitable specificity to BPA compared to functionally and structurally similar hormone and endocrine disrupting compounds. Using this method, bisphenol A was quantifiable through both standard fluorescence spectroscopy and smartphone detection, with an empirical binding constant of K-SV = 2040 M-1 and a direct, unfiltered detection limit of 4.4 mu M from unprocessed samples, suitable for waste leachate and industrial samples. Implementation of further digital image processing and smartphone spectroscopy methods may help to lower this detection limit, bearing promise for future direct detection of bisphenol A from wastewater leachate and environmental samples via smartphones.

Diagnostic biosensors are on the rise in the global market due to the increasing prevalence of diseases. Specifically, the point-of-care segment has made great strides due to the improvement of biosensors' user-friendliness, simplicity, and clinical capabilities in the comfort of one's home. Although there are conventional diagnostic techniques, they are mutually time-consuming, costly, and labor-intensive. Not to mention, they are primarily dependent on bench-top or large immovable equipment. The widespread availability of smartphones has potentiated optical biosensors towards delivery of rapid and point-of-care diagnostic biosensors. Due to the affordability and user-friendliness of smartphones, smartphone-based biosensors may become ubiquitously available. Additionally, microfluidic platforms possess small footprints and portability towards development of true point-of-care and real-time diagnostic biosensors. In this dissertation, development of multiple diagnostic biosensors on microfluidic platforms is discussed. Diagnostic biosensors equipped with a smartphone-based optical detection show great promise of bringing clinical and bench-top laboratory capabilities for the convenience of the user, with reduced time, costs, and labor requirements. The widespread availability of point-of-care and real-time diagnostic biosensors may show promise in securing global health.

Available ear and hearing health care services are not sufficient to meet the burden of disabling hearing loss, particularly within developing countries such as South Africa. Attempts to meet the needs of underserved populations may require a move towards community-based primary care along with the integration of recent mHealth approaches whereby primary health care personnel facilitate ear and hearing health care. The objective of this study was to determine the clinical utility of a community-based program for identification of hearing loss, using smartphone hearing screening (hearScreenTM) operated by community health care workers (CHWs), in a developing South African community and to survey experiences of the CHWs. An exploratory, descriptive cross-sectional research design was used. The study comprised two phases. During phase one, 24 CHWs were trained to conduct hearing screening in the underserved community of Mamelodi using automated test protocols (sweep performed at 1, 2 and 4kHz bilaterally at an intensity of 25dB HL for children and 35dB HL for adults), employed by the hearScreenTM mHealth solution operating on low cost Android phones using calibrated headphones (Sennheiser HD202 II). A total of 820 community members were screened for hearing loss over a 12-week period. The results were analyzed in terms of referral rates of the hearing screening program, compliance of test environment noise during screening, and time proficiency of the screenings. During phase 2, CHWs completed a questionnaire regarding their perceptions and experiences of the hearing screening program. Data analysis was conducted on 108 children (2-15 years) and 598 adults (16-85 years) screened. Referral rates for children and adults were 12% and 6.5% respectively. Noise levels only had a significant effect on referral results at low intensities of 25dB HL at 1KHz (p<0.05). Age effects were significant for adult referral rates (p<0.05) demonstrating a significantly lower referral rate in younger (below 45 years) as opposed to older (45 years and above) adults (4.3% compared to 13.2%). Majority of CHWs responded positively regarding their involvement and experiences using the hearScreenTM tool in terms of usability, need for services, value to community members and time efficiency. Results of this study indicated that community-based hearing screening programs can be successfully integrated into underserved contexts by CHWs using an mHealth solution. The hearScreenTM smartphone application offers benefits such as automated test protocols and interpretation, integrated noise monitoring, data capturing and data sharing. Appointment of a program coordinator, as well as the integration of informational counseling and minor software changes were recommended towards an effective and sustainable program.
Dissertation (MCommPath)--University of Pretoria, 2015.
Speech-Language Pathology and Audiology
MCommPath
Unrestricted

This thesis project has been performed at (and for) a company named Strödata. The purpose of the project has been to perform a risk analysis on Strödata’s web based business system, and specifically analyze how access to the business system through smartphones would affect the risks posed to the system. This has been done to help decide if smartphone access should be enabled. An implementation of a web application which is suited for use on a smartphone has also been developed, as a proof-of-concept, to grant access to a limited part of the business system. The method used to perform the risk analysis has been CORAS, as presented by Braber et al in [1]. CORAS is a risk analysis method designed with IT-systems specifically in mind. The method is divided into seven steps. The new web application is an ASP.NET MVC3 site that uses JavaScript, jQuery and Ajax-JSON. The risk analysis showed, among other things, that the benefits of enabling smartphone access to the business system are larger than the risks it introduces. Smartphone access also opens up many new possibilities to implement interesting new features or improve old ones. The risk analysis also showed that there are risks to the system that need to be dealt with. For these, risks treatments were identified to lessen their probabilities and/or their consequences should they occur. Some treatments were completely successful in eliminating the risks they treat, others were not. However, the treatments that were not completely successful did reduce the risks far enough that perhaps they should be re-evaluated as un-/acceptable. The conclusions that can be drawn from this thesis project are that although enabling smartphone access to the business system introduces new risks to the system, the access also reduces certain risks. How costly the new risks are and how much the access reduces risks varies from company to company and from system to system. For Strödata, the reduction to certain risks was large enough to outweigh the new risks that would be introduced. Regarding the possibility to implement smartphone access to the business system, it is possible using more modern technologies, methods and frameworks; such as those mentioned above.

The research presented in this thesis investigates a smartphone-based framework for universal remote control. Taking the toy remote control car as a case study, Universal Controller (UniC) framework is developed, implemented, and tested. UniC uses an Android phone as the main controller, Arduino hardware as an adapter to interface with the control target, and Bluetooth as the wireless communication. It is shown the feasibility and advantages of smartphone-based controller in comparison to the traditional remote control approach.

Thesis: M.C.P., Massachusetts Institute of Technology, Department of Urban Studies and Planning, 2016.
This electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections.
Cataloged from student-submitted PDF version of thesis.
Includes bibliographical references (pages 117-119).
Recently, the rapid development of smartphone technologies has brought new opportunities for the citizen travel survey. Based on a survey performed using a smartphone app, Moves, in Beijing, China, this thesis discusses the survey design and implementation process as well as the mobility analysis methods. The survey was launched in January 2016. This thesis is based on data from 258 subjects. The air quality is monitored through several objective measures. However, citizens' subjective feelings have rarely been investigated. This thesis develops the Perceived Air Quality (PAQ) measure that captures the sensory reactions to air pollution. The PAQ data are collected through questionnaires, which are part of the travel survey. A strong correlation is found between daily average PAQ and AQI, indicating that the PAQ could become a meaningful indicator for air quality. However, the strong correlation only exists in the aggregated level. Finally, the thesis evaluates the association between travel behavior and air quality. Travel behavior is measured by number of trips, number of non-motorized trips, percentage of non-motorized trips, total distance traveled and total travel time. The air quality is measured by AQI and PAQ. The Random Effect regression models show that the association between travel behavior and air quality is pretty weak. It indicates that currently not many Beijing residents are taking air quality as a crucial factor when making travel decisions.
by Zelin Li.
M.C.P.

Grâce à l’émergence dans la vie quotidienne des appareils de plus en plus populaires que sont les smartphones et les tablettes, la tâche de postionner l'utilisateur par le biais de son téléphone est une problématique fortement étudiée dans les domaines non seulement de la recherche mais également des communautés industrielles. Parmi ces technologies, les approches GPS sont devenues une norme et ont beaucoup de succès pour une localisation en environnement extérieur. Par contre, le Wi-Fi, les capteurs inertiels et le Bluetooth sont plutôt préférés pour les tâches de positionnement dans un environnement intérieur.Pour ce qui concerne le positionnement des smartphones, les approches basées sur les « empreintes digitales » (fingerprint) Wi-Fi sont bien établies. D'une manière générale, ces approches tentent d'apprendre la fonction de correspondance (cartographie) des caractéristiques du signal Wi-Fi par rapport à la position de l’appareil dans le monde réel. Elles nécessitent généralement une grande quantité de données pour obtenir une bonne cartographie. Lorsque ces données d'entraînement disponibles sont limitées, l'approche basée sur les empreintes digitales montre alors des taux d’erreurs élevés et devient moins stable. Dans nos travaux, nous explorons d’autres approches, différentes, pour faire face à cette problématique du manque de données d'entraînement. Toutes ces méthodes sont testées sur un ensemble de données public qui est utilisé lors d’une compétition internationale à la Conférence IPIN 2016.En plus du système de positionnement basé sur la technologie Wi-Fi, les capteurs inertiels du smartphone sont également utiles pour la tâche de suivi. Les trois types de capteurs, qui sont les accéléromètres, le gyroscope et la boussole magnétique, peuvent être utilisés pour suivre l'étape et la direction de l'utilisateur (méthode SHS). Le nombre d'étapes et la distance de déplacement de l'utilisateur sont calculés en utilisant les données de l'accéléromètre. La position de l'utilisateur est calculée par trois types de données avec trois méthodes comprenant la matrice de rotation, le filtre complémentaire et le filtre de Madgwick. Il est raisonnable de combiner les sorties SHS avec les sorties de Wi-Fi, car les deux technologies sont présentes dans les smartphones et se complètent. Deux approches combinées sont testées. La première approche consiste à utiliser directement les sorties Wi-Fi comme points de pivot pour la fixation de la partie de suivi SHS. Dans la deuxième approche, nous comptons sur le signal Wi-Fi pour construire un modèle d'observation, qui est ensuite intégré à l'étape d'approximation du filtre à particules. Ces combinaisons montrent une amélioration significative par rapport au suivi SHS ou au suivi Wi-Fi uniquement.Dans un contexte multiutilisateur, la technologie Bluetooth du smartphone pourrait fournir une distance approximative entre les utilisateurs. La distance relative est calculée à partir du processus de numérisation du périphérique Bluetooth. Elle est ensuite utilisée pour améliorer la sortie des modèles de positionnement Wi-Fi. Nous étudions deux méthodes. La première vise à créer une fonction d'erreur qui permet de modéliser le bruit dans la sortie Wi-Fi et la distance approximative produite par le Bluetooth pour chaque intervalle de temps spécifié. La seconde méthode considère par contre cette relation temporelle et la contrainte de mouvement lorsque l'utilisateur se déplace. Le modèle d'observation du filtre à particules est une combinaison entre les données Wi-Fi et les données Bluetooth. Les deux approches sont testées en fonction de données réelles, qui incluent jusqu'à quatre utilisateurs différents qui se déplacent dans un bureau. Alors que la première approche n'est applicable que dans certains scénarios spécifiques, la deuxième approche montre une amélioration significative par rapport aux résultats de position basés uniquement sur le modèle d'empreintes digitales Wi-Fi
With the popularity of smartphones and tablets in daily life, the task of finding user’s position through their phone gains much attention from both the research and industry communities. Technologies integrated in smartphones such as GPS, Wi-Fi, Bluetooth and camera are all capable for building a positioning system. Among those technologies, GPS has approaches have become a standard and achieved much success for the outdoor environment. Meanwhile, Wi-Fi, inertial sensors and Bluetooth are more preferred for positioning task in indoor environment.For smartphone positioning, Wi-Fi fingerprinting based approaches are well established within the field. Generally speaking, the approaches attempt to learn the mapping function from Wi-Fi signal characteristics to the real world position. They usually require a good amount of data for finding a good mapping. When the available training data is limited, the fingerprinting-based approach has high errors and becomes less stable. In our works, we want to explore different approaches of Wi-Fi fingerprinting methods for dealing with a lacking in training data. Based on the performance of the individual approaches, several ensemble strategies are proposed to improve the overall positioning performance. All the proposed methods are tested against a published dataset, which is used as the competition data of the IPIN 2016 Conference with offsite track (track 3).Besides the positioning system based on Wi-Fi technology, the smartphone’s inertial sensors are also useful for the tracking task. The three types of sensors, which are accelerate, gyroscope and magnetic, can be employed to create a Step-And-Heading (SHS) system. Several methods are tested in our approaches. The number of steps and user’s moving distance are calculated from the accelerometer data. The user’s heading is calculated from the three types of data with three methods, including rotation matrix, Complimentary Filter and Madgwick Filter. It is reasonable to combine SHS outputs with the outputs from Wi-Fi due to both technologies are present in the smartphone. Two combination approaches are tested. The first approach is to use directly the Wi-Fi outputs as pivot points for fixing the SHS tracking part. In the second approach, we rely on the Wi-Fi signal to build an observation model, which is then integrated into the particle filter approximation step. The combining paths have a significant improvement from the SHS tracking only and the Wi-Fi only. Although, SHS tracking with Wi-Fi fingerprinting improvement achieves promising results, it has a number of limitations such as requiring additional sensors calibration efforts and restriction on smartphone handling positions.In the context of multiple users, Bluetooth technology on the smartphone could provide the approximated distance between users. The relative distance is calculated from the Bluetooth inquiry process. It is then used to improve the output from Wi-Fi positioning models. We study two different combination methods. The first method aims to build an error function which is possible to model the noise in the Wi-Fi output and Bluetooth approximated distance for each specific time interval. It ignores the temporal relationship between successive Wi-Fi outputs. Position adjustments are then computed by minimizing the error function. The second method considers the temporal relationship and the movement constraint when the user moves around the area. The tracking step are carried out by using particle filter. The observation model of the particle filter are a combination between the Wi-Fi data and Bluetooth data. Both approaches are tested against real data, which include up to four different users moving in an office environment. While the first approach is only applicable in some specific scenarios, the second approach has a significant improvement from the position output based on Wi-Fi fingerprinting model only

[ES] Una de las áreas de investigación que está recibiendo más atención recientemente es la de vehículos autónomos. Los investigadores están en este momento centrados en el tercer de los cinco niveles de autonomía, los cuales son: asistencia en la conducción, automatización parcial, automatización condicional, alta automatización y automatización completa. A pesar de los rápidos progresos que están habiendo en este campo, la adopción de estas soluciones llevará tiempo no sólo debido a cuestiones legales, sino también por el hecho de que los avances tecnológicos se enfrentan a un lento respaldo por parte de los fabricantes. Además, la baja tasa de renovación de vehículos de carretera, dificulta el despliegue de tecnologías innovadoras, como es el caso de la red vehicular. Ocho años después de la introducción de la norma 802.11p para la comunicación vehicular del Instituto de Ingenieros Eléctricos y Electrónicos (IIEE), los vehículos que se usan a diario todavía carecen de la capacidad de comunicarse entre sí. Este hecho impide el uso de las muchas aplicaciones de seguridad del Sistema de Inteligencia de Transporte (SIT) que aprovecha la red vehicular para el intercambio de datos. La forma obvia de manejar este problema es poner las tecnologías disponibles a la disposición de los usuarios comunes para desarrollar soluciones que se puedan implementar fácilmente y, además, económicas. Por esta razón, trasladamos nuestra atención a los dispositivos inteligentes, especialmente a los teléfonos inteligentes, los cuales han recorrido un largo camino desde la primera introducción de teléfonos móviles a finales del siglo XX. Hoy en día casi todos llevan uno en su bolsillo a donde sea que vayan, permitiéndoles no sólo hacer llamadas, sino también medir y controlar diferentes parámetros con la ayuda de los muchos sensores integrados que están disponibles para estos dispositivos compactos pero potentes. Nuestro objetivo es estudiar los efectos de la integración de los teléfonos inteligentes a la red vehicular para desarrollar aplicaciones de seguridad del SIT. La elección de los teléfonos inteligentes aquí no solo está justificada por su amplia disponibilidad y uso, sino también porque están evolucionando hacia terminales de alto rendimiento con microprocesadores de múltiples núcleos cargados dotados de un grupo suficientemente diverso de sensores. En esta tesis proponemos tres diferentes aplicaciones de seguridad SIT para teléfonos inteligentes, diseñados para aprovechar el entorno de red vehicular: una aplicación de generación de advertencia llamada Messiah que alerta a los conductores de la presencia de vehículos de emergencia en las cercanías; una aplicación de Advertencia de Colisión Frontal (ACF) que advierte a los conductores si no se mantiene la distancia de seguridad mínima entre el vehículo que va delante y el que lo sigue; y, por último, una aplicación que tiene como objetivo ayudar a los conductores con asistencia visual durante el adelantamiento, llamada EYES. Todas estas aplicaciones han sido desarrolladas para la plataforma Android, y dependen de la transmisión de datos entre vehículos. Dado que los vehículos que utilizamos día a día no admiten la posibilidad de comunicarse entre sí, también diseñamos GRCBox, que es una unidad integrada de bajo coste que permite la comunicación del Vehículo a Todo (V2X). A partir de nuestro estudio de aplicaciones para dispositivos móviles diseñados para redes vehiculares, descubrimos que el uso de teléfonos inteligentes proporciona una nueva dirección para la investigación relacionada con SIT y redes vehiculares al permitir la adopción rápida de las soluciones existentes, donde los usuarios pueden descargar y usar las aplicaciones con sólo un clic a un botón. Al mismo tiempo, la portabilidad y compacidad de los dispositivos los hace limitados en términos de velocidad, potencia de procesamiento y precisi
[CAT] Una de les àrees d'investigació que està rebent més atenció recentment és la de vehicles autònoms. Els investigadores estan en este moment centrats en el tercer dels cinc nivells d'autonomia, els quals són: assistència en la conducció, automatització parcial, automatització condicional, alta automatització i automatització completa. Malgrat els ràpids progressos que s'estan donant en este camp, l'adopció d'estes solucions portarà temps no sols degut a qüestions legals, sinó també pel fet que els avanços tecnològics s'enfronten a un lent recolzament per part dels fabricants. A més a més, la baixa taxa de renovació de vehicles de carretera, dificulta el desplegament de tecnologies innovadores com és el cas de la xarxa vehicular. Huit anys després de la introducció de la norma 802.11p per a la comunicació vehicular de l'Institut d'Enginyers Elèctrics i Electrònics (IEEE), els vehicles que s'utilitzen a diari encara manquen de la capacitat de comunicar-se entre sí. Este fet impedeix l'ús de les moltes aplicacions de seguretat del Sistema d'Intel·ligència de Transport (SIT) que aprofita la xarxa vehicular per a l'intercanvi de dades. La forma òbvia de tractar aquest problema és posar les tecnologies disponibles a la disposició dels usuaris comuns per a desenvolupar solucions que es puguen implementar fàcilment, còmodes d'adoptar i, a més a més, econòmiques. Per aquesta raó, traslladem la nostra atenció als dispositius intel·ligents, especialment als telèfons intel·ligents, els quals han recorregut un llarg camí des de la primera introducció de telèfons mòbils a finals del segle XX. Hui en dia quasi tots porten un en la butxaca on siga que vagen, permetent-los no sols fer cridades, sinó també mesurar i controlar diferents paràmetres amb l'ajuda dels molts sensors integrats que estan disponibles per a estos dispositius compactes però potents. El nostre objectiu és estudiar els efectes de la integració dels telèfons intel·ligents a la xarxa vehicular per a desenvolupar aplicacions de seguretat del SIT. L'elecció dels telèfons intel·ligents ací no està sols justificada per la seua àmplia disponibilitat i ús, sinó també perquè estan evolucionant cap a terminals d'alt rendiment amb microprocessadors de múltiples nuclis dotats amb un grup suficientment divers de sensors. En esta tesi proposem tres diferents aplicacions de seguretat SIT per a telèfons intel·ligents, dissenyats per a aprofitar l'entorn de xarxa vehicular: una aplicació de generació d'advertència anomenada Messiah que alerta els conductors de la presència de vehicles d'emergència en les proximitats; una aplicació Advertència de Col·lisió Frontal (ACF) que adverteix els conductors si no mantenen la distància de seguretat mínima entre el vehicle que va davant i el que el segueix; i, per últim, una aplicació que té com objectiu ajudar els conductors amb assistència visual durant l'avançament, anomenat EYES. Totes aquestes aplicacions han sigut desenvolupades per a la plataforma Android, i depenen de la transmissió de dades entre vehicles. Donat que els vehicles que utilitzem a diari no admeten la possibilitat de comunicar-se entre sí, també dissenyem GRCBox, que és una unitat integrada de baix cost que permet la comunicació de Vechicle a Tot (V2X). A partir del nostre estudi d'aplicacions per a dispositius mòbils dissenyats per a xarxes vehiculars, descobrim que l'ús de telèfons intel·ligents proporciona una nova direcció per a la investigació relacionada amb SIT i xarxes vehiculars al permetre l'adopció ràpida de les solucions existents, on els usuaris poden descarregar i utilitzar les aplicacions amb un sol clic a un botó. Però al mateix temps, la portabilitat i la compacitat dels dispositius els fa limitats en termes de velocitat, potència de processament i precisió del sensor integrat, cosa que afecta al rendiment de les aplicacions.
[EN] One of the research areas that is receiving a lot of attention recently is autonomous vehicles. Researchers are currently focused on the third level of autonomy out of the five levels, which are: drive assistance, partial automation, conditional automation, high automation, and full automation. Even though rapid progress is being made in this field, the adoption of these solutions will take time not only due to legal issues, but also due to the fact that technological improvements face slow endorsement by manufacturers. Also, the slow renewal rate of vehicles on road hinders the deployment of novel technologies, as is the case of Vehicular Networks (VNs). Eight years after the introduction of the IEEE 802.11p standard for vehicular communication, vehicles used on a daily basis still lack the capability of communicating with one other. This fact impedes the use of the many ITS safety applications that take advantage of VNs for data exchange. The obvious way to handle this problem is to use the available technologies at the disposal of common users to develop solutions that are easily deployable, effortless to adopt, and moreover, cost effective. For this reason we shift our attention to smart devices, specially smartphones, which have come a long way since the first introduction of mobile phones in the late 20th century. Nowadays, nearly everyone carries one in their pocket anywhere they go, allowing them to not only make calls, but also to measure and monitor different parameters with the help of the many on-board sensors that are available to these compact yet powerful devices. Our objective is to study the effects of integrating smartphones to vehicular networks, to develop ITS safety applications. The choice of smartphones here is not only justified by their wide availability and use, but also because they are evolving towards high performance terminals with multi-core microprocessors packed with a sufficiently diverse group of sensors. In this thesis we propose three different ITS safety applications for smartphones, designed to take advantage of the vehicular network environment: a warning generation application called Messiah that alerts drivers of the presence of emergency vehicles in close proximity; a FCW application which warns drivers if a minimum safe distance is not maintained between the vehicle ahead and the one following it; and lastly an application that aims to aid drivers with visual assistance while overtaking, named EYES. All these applications have been developed for the Android platform, and are dependent on the data transmission among vehicles. Since vehicles we use on a day to day basis still do not accommodate the possibility to communicate with one another, we also designed the GRCBox, which is a low cost on-board unit that supports V2X communication. From our study of applications for mobile devices designed for VNs, we found that the use of smartphones provides a new direction to research related to ITS and VNs by allowing a quick adoption of the existing solutions, where users are able to download and use applications just by one click of a button. But at the same time, the portability and compactness of the devices makes them limited in terms of speed, processing power, and accuracy of the on-board sensor, thus affecting the performance of the applications. In our case, the simpler Messiah application performed very well, while the EYES application that is dependent on GPS data, and the FCW application which required heavy processing and use of the camera due to its dependence on plate recognition, were affected by the hardware limitations of the smartphones.
Patra, S. (2019). Development and evaluation of smartphone-based ITS applications for vehicular networks [Tesis doctoral no publicada]. Universitat Politècnica de València. https://doi.org/10.4995/Thesis/10251/124058
TESIS

Environmental factors can have a significant impact on an individual's health and well-being, and a primary characteristic of environments is air quality. Air sensing equipment is available to the public, but it is often expensive,stationary, or unusable for persons without technical expertise. The goal of this project is to develop an inexpensive and portable sensor module for public use. The system is capable of measuring temperature in Celsius and Fahrenheit, heat index, relative humidity, and carbon dioxide concentration. The sensor module, referred to as the "sniffer," consists of a printed circuit board that interconnects a carbon dioxide sensor, a temperature/humidity sensor, an Arduino microcontroller, and a Bluetooth module. The sniffer is small enough to be worn as a pendant or a belt attachment, and it is rugged enough to consistently collect and transmit data to a user's smartphone throughout their workday. The accompanying smartphone app uses Bluetooth and GPS hardware to collect data and affix samples with a time stamp and GPS coordinates. The accumulated sensor data is saved to a file on the user's phone, which is then examined on a standard computer.

Falls are one of the greatest problems facing ageing and older persons. Due to age-related changes and frailty, individuals may unintentionally lose balance or stability while performing activities of daily living, even without any external cause. Exercise programs focusing on muscle strengthening and balance retraining can be effective as part of a fall prevention approach in both community and residential aged care settings. This thesis is focused on the adaptation of effective fall prevention exercises/programs into a smartphone. The smartphone must guide the older persons throughout the exercises as well as advice about the desired frequency/duration of exercises and, when possible, evaluate the movement being performed (i.e. by using e.g. the accelerometer and gyroscope). So that older persons can make the exercises safely and easily on their own, as well as receive feedback about their movements' performance.

Falls are one of the greatest problems facing ageing and older persons. Due to age-related changes and frailty, individuals may unintentionally lose balance or stability while performing activities of daily living, even without any external cause. Exercise programs focusing on muscle strengthening and balance retraining can be effective as part of a fall prevention approach in both community and residential aged care settings. This thesis is focused on the adaptation of effective fall prevention exercises/programs into a smartphone. The smartphone must guide the older persons throughout the exercises as well as advice about the desired frequency/duration of exercises and, when possible, evaluate the movement being performed (i.e. by using e.g. the accelerometer and gyroscope). So that older persons can make the exercises safely and easily on their own, as well as receive feedback about their movements' performance.

碩士
國立高雄應用科技大學
電機工程系博碩士班
103
Recently, the aging problem of population becomes serious in Taiwan. The burden of caregivers is increasing. One of the major health risks among elderly people is the sudden fall without noticing. By the way, most of the elderly people has a variety of chronic diseases and the process of their taking medicine could be improperly. In this thesis, we present a smartphone based residential healthcare gateway in order to reach the remote health care for the elderly, such as fall detection and taking medicine problem, and reduce the burden of caregiver. We use an Android based smart phone as the gateway platform. We build an elderly healthcare application witch fulfills the home health care functions. A wearable sensor device for monitoring the activities of elderly people is also proposed. The gateway can send an alert to the remote server, when the accident of fall happens with help of the sensor device. With collected the information of the elderly daily life, we can achieve the purpose of remote health care and reducing the burden of caregivers. The future work includes reducing the false alarming by using multiple fall-detecting mechanisms, and combining different type of monitoring methods in this remote care system.

碩士
國立臺灣大學
工程科學及海洋工程學研究所
100
The Smartphone Based Shopping Assistant System (SBSAS) is an application platform, which delivers several ancillary real time services that can be used in warehouse-styled retail store (e.g., Costco). The application platform comprises Item Positioning System (IPS) and Item Information System (IIS). IPS assists in finding specific item in different stocks. IIS assists customers in producing or making records as shopping list, and provides personalized coupon, in order to make customers find convenience, delight and economization in shopping. A Store powered by the system is possible to increase sales performance and smooth the stream of customers; In addition, manufacturers and stores are allowed to cooperatively trade data with customers in purpose of market analyzing and producing personalized services for different customers. There are three main functions in this system. First, customers can obtain detailed item information by selecting target item in customized item list; also add items toward shopping list. Second, customers are allowed to download two kinds of coupon, the Daily Promotion and the innovative “Hotwheel Promotion”. The Daily Promotion is a personalized coupon recommended by the system, and Hotwheel Promotion provides off-line game-liked access to obtain the coupon, which is combined with indoor positioning techniques. Third, customers are allowed to operate positioning and navigating functions in order to search target items in reality. After recognizing and decoding the QR-Code tags in environment to locate customers’ own position, one can obtain the optimized navigating routes by observing map, or operate SF (Stock Fluoroscope), which is a unique augmented reality system aiding customers to see the actual position of target item in screen through the camera lens. We concentrate on describing the designs and tests of SF, which is the core technology of this thesis.

碩士
明新科技大學
電機工程研究所
101
The advent of aging society, the elderly care and safety issues cannot be ignored. According to the Bureau of Health Promotion, Department of Health, R.O.C.(Taiwan) information, In addition to traffic accidents, Falling is the main reason of accident casualties for the elderly. When elderly falls, no one beside instant help often caused more serious injuries. Smart phones with built-in sensors, GPS and Internet access, are suitable detecting tools for the elderly. In this research, we proposed an APP on smart phones to monitor the elder’s motion. If falling occurs, the notification will send to emergency unit. At the same time, falling location will be recorded in system and will be pointed out to alarm someone who entered the area what is called fall risk area (FRA). Experimental results show that, after automatic learning with LBS (Location Based Service) information, the accuracy of this system is higher than LBS-less.

碩士
龍華科技大學
電機工程系碩士班
107
Nowadays, the society is developing rapidly. Under the enormous pressure of busy life, people pay more and more attention to the quality of life. The demand for lighting is no longer just a simple life, but it can satisfy the user's spiritual needs, and it is convenient to control and needs to reduce energy consumption to achieve energy saving effect. Therefore, this paper provides a smart phone-based LED control system that controls the color of the lighting with a smart phone. It can control the lighting device to meet different life situations according to the user's preference, and provide users with a comfortable lighting environment, not only at any time. Control the color of the lighting anywhere, and also provide energy-saving features. This system uses Bluno as the main core of lighting control, combined with clock module and light intensity sensor, and then controls the lighting device through smart phone. This system uses Bluno as the main core of lighting control, combined with clock module and light intensity sensor, and then controls the lighting device through smart phone. This system provides three functions: manual control, time control and automatic. control, Manual control is to manually control red, green and blue light by smart phone, and provide different illumination colors through different combinations of three lights; time control allows users to set time for the lighting device to automatically turn off; The automatic control can sense the sunlight illumination. If the preset value is exceeded, the light will be turned off automatically to achieve the energy saving effect. These three functions can be selected according to the needs of the user.

碩士
淡江大學
資訊工程學系碩士在職專班
102
Augmented Reality development was extended from virtual reality technology. Although it already developed for almost 20 years, but these years the trend of Smartphone is getting more and more popular make Argument Reality technology is from indoor application to outdoor application. Nowadays most of Smartphones built variant sensor and position search component inside helps Argument Reality technology to become a real moveable technology. And because of Smartphones built-in a lot of sensors and electronic components so it replace a lot of traditional electric devices , one of the devices is navigator. Nowadays some companies developed Apps on Smartphone for navigation but most of them illustrate the path indication by maps and simulation images but paint picture is hard to indicate very clearly, complicated roadways especially. So this theme research apply GPS system of Smartphone to get the vehicle position and integrate Google Maps API sources to build maps and routing planning function. After the routing planning is generated system will compute the distance by Great-circle distance theory and azimuth then utilize the result with perspective projection theory to draw direction indicator on the screen. In order to increase the reaction time and overcome the difference Of GPS system apply Orientation Sensor to assist with it and let the navigation indicator can be switch immediately. Finally Smartphone camera capture the real time scene in front of vehicle and Augmented Reality technology combine the indicator on it. Comparing traditional navigation system and Augmented Reality navigation system the new system let user easier and more intuitional in indicate driver follow the indication of planning routing.

碩士
國立雲林科技大學
電子工程系
105
Global Positioning System (GPS) has been developed for many years and is widely used in various fields. It provides users with instant access to location information via smart devices. But GPS in the indoor environment is vulnerable to the shadow of complex buildings and multi-path effects, resulting in loss of GPS positioning function. Most people live in the indoor environment for more than 80% of the time, so the demand for indoor positioning system, has become an important issue. In this thesis, Visible Light Communication (VLC) technology combined with ARM Microcontrollers and Smartphone devices is integrated to serve as lighting, com-munication and positioning. To make the positioning system easy to be implemented in the Smartphone, the Audio Jack port is used to connect smartphone with VLC receiver. We use the Received Signal Strength Indicator (RSSI) to determine the distance be-tween the reference point and the target point in the indoor environment. And the loca-tion of the target point is estimated by the trilateral measurement and location method of the intelligent mobile phone, and finally the indoor positioning result is presented in the intelligent mobile phone. We use time division multiplexing (TDM) technology in the VLC system for timing management, to avoid interference from adjacent lights. Finally, the indoor location measurement results in the prototype positioning system show the maximum position error of 3cm and the average position error of 1.86cm. It can be concluded that the VLC-based Smartphone indoor positioning system can accurately estimate the location of the user in the indoor environment by using the Smartphone.

碩士
國立臺灣師範大學
資訊工程學系
101
Stolen vehicle detection has become an important task for police officers in many countries. In order to make investigating and seizing the stolen vehicles more convenient and efficient, we propose a smartphone-based automatic stolen vehicle detection system based on image processing and computer vision technologies, combining with license plate recognition (LPR) and fault-tolerant retrieval techniques. The proposed system will improve efficiency of investigation and reduce the burden of human operation. 　　In this study, we utilize the smartphone equipped with Android operating system instead of personal digital assistant (PDA) because the smartphones are more and more popular and powerful. We just scan and capture images of the static vehicles on the roadside by using cell phone camera instead of manually inputting the license numbers one by one. Next, the captured images are sending to the server via wireless network, and then the license plate numbers can be obtained based on the LPR procedure. After finishing this procedure, the system will use the fault-tolerant retrieval technique based on Markov edit distance to retrieve the license numbers of stolen vehicles in database even though the LPR result are imperfect. Finally, the server will send the stolen vehicle information to the smartphone for user confirmation. If the matching is correct, the user can press “Confirm” button to send the image, license number, time, location and Google Map to the police center. 　　The proposed system is developed based on Model-View-Controller (MVC) design pattern. It will make system more efficiency and better performance. In addition, people can download the APP to help the police with stolen vehicle detection.

碩士
國立成功大學
資訊工程學系碩博士班
101
Physical inactivity is a global public health problem, and it causes the intermediate risk factors of overweight and obesity, where they represent a strong risk factor for developing these chronic diseases, such as diabetes and cardiovascular diseases. We propose a two-layered classification approach to effectively recognize the physical activities while the smartphone is placed at any four common positions on the body. Then we implement a Life Record app on smartphone that automatically classifies physical activities and records them as the personal life logs. For assisting users in comprehending their daily activities, the system also provides the visualization interface that shows the brief descriptions of their life logs. We test the classification model with the real dataset that was collected from nine participants for their daily life. The results show our model achieves high performance with more than 92% overall accuracy in the recognition of four physical activity types. In addition, based on participants’ experience that they used Life Record app within two weeks, we found the participants could effectively trace their daily activities and expressed a high intention to use the app even after the end of the study. We demonstrate that the system possesses less limitation to monitor daily activities that the users are not restricted to carry their smartphones in specific positions. Another major benefit of our system is to provide a complete overview of personal activities, which enhances the self-awareness of physical activity in our daily life through an intuitive visualization interface. Furthermore, analysis of life logs can also be applied in specific services or recommendation applications in the future.