This thesis outlines a multiple-camera wireless image superresolution system which uses off-the-shelf components. The system presented demonstrates the reconstruction of a high-resolution image from multiple low-resolution images acquired from different wireless camera nodes. Each camera node participating in the system consists of a dedicated camera for image acquisition as well as a Bluetooth USB communications card for wireless transmission of data. Low-resolution images are captured at these nodes and are transmitted to the central vision server, where they are processed and registered onto a common projective plane. The registration process is arrived at through the RANdom SAmple Consensus (RANSAC) algorithm. Once the set of low-resolution images has been registered, a single high-resolution image is reconstructed. The super-resolution process used to obtain the high-resolution output is the Projection Onto Convex Sets (POCS) technique. Reconstruction results are presented. / Thesis / Master of Applied Science (MASc)

This thesis compares and evaluates the accuracy of two RSSI-based tri-lateration methods in an indoor setting, implementing either Wi-Fi andBluetooth Low Energy (BLE) while using commercially available hardware.The purpose of evaluation is part of the long-term vision of improving thesafety of workers in adverse environments such as factories, by providing awearable Indoor Positioning System where other systems like GPS are notsuitable due to signal obstruction. Within a confined space replicating in-tended real-world conditions in terms of signal attenuation and adversity,30 consecutive measurements of signal strength readings (RSSI) to threereference nodes were collected at 10 randomized sample positions, andwas repeated across 5 tests. The accuracy of trilateration was evaluatedusing an averaged Root Mean Square Error (RMSE) over the five tests. Itwas observed that RSSI using Wi-Fi achieved better accuracy of predictingthe actual position within the testing environment than signal-strength us-ing BLE, with Wi-Fi and BLE achieving an accuracy of 0.88 and 1.85 metersrespectively. However, because of the power efficiency of BLE it is a viablecandidate for a future low-cost and device-based Indoor Localization Sys-tem to potentially be used and worn by workers. The results while alignedwith similar existing literature, infer what a low-cost indoor positioningsystem might achieve. Future research with the goal of developing suchsolutions could benefit from implementing both Wi-Fi and BLE as the basisof signal strength trilateration.

Modern indoor positioning systems encounter challenges inherent to indoor environments. Signal changes can stem from various factors like object movement, signal propagation, or obstructed line of sight. This thesis explores a supervised machine learning approach that integrates Bluetooth Low Energy (BLE) and inertial sensor data to achieve consistent angle and distance estimations. The method relies on BLE angle estimations and signal strength alongside additional sensor data from an Inertial Measurement Unit (IMU). Relevant features are extracted and a supervised learning model is trained and then validated on familiar environment tests. The model is then gradually introduced to more unfamiliar test environments, and its performance is evaluated and compared accordingly. This thesis project was conducted at the u-blox office and presents a comprehensive methodology utilizing their existing hardware. Several extensive experiments were conducted, refining both data collection procedures and experimental setups. This iterative approach facilitated the improvement of the supervised learning model, resulting in a proposed model architecture based on transformers and convolutional layers. The provided methodology encompasses the entire process, from data collection to the evaluation of the proposed supervised learning model, enabling direct comparisons with existing angle estimation solutions employed at u-blox. The results of these comparisons demonstrate more accurate outcomes compared to existing solutions when validated in familiar environments. However, performance gradually declines when introduced to a new environment, encountering a wider range of signal conditions than the supervised model had trained on. Distance estimations are then compared with the path loss propagation equation, showing an overall improvement. / Moderna inomhuspositioneringssystem möter utmaningar som förekommer i inomhusmiljöer. Signalförändringar kan bero på olika faktorer som objektets rörelse, signalutbredning eller blockerad siktlinje. Denna kandidat avhandling undersöker ett övervakat maskininlärningssätt som integrerar Bluetooth Low Energy (BLE) och tröghetssensorer för att uppnå konsekventa vinkel- och avståndsberäkningar. Metoden bygger på BLE-vinkelberäkningar och signalstyrka tillsammans med ytterligare sensordata från en Inertial Measurment Unit (IMU). Relevanta funktioner extraheras och en övervakad inlärningsmodell tränas och valideras sedan på tester i bekanta miljöer. Modellen introduceras sedan gradvis till mer obekanta testmiljöer, och dess prestanda utvärderas och jämförs därefter. Detta examensarbete genomfördes på u-blox kontor och presenterar en omfattande metodik som utnyttjar deras befintliga hårdvara. Flera omfattande experiment genomfördes, vilket förfinade både datainsamlingsprocedurer och experimentuppsättningar. Detta iterativa tillvägagångssätt underlättade förbättringen av den övervakade inlärningsmodellen, vilket resulterade i en föreslagen modellarkitektur baserad på transformatorer och konvolutionella lager. Den tillhandahållna metodiken omfattar hela processen, från datainsamling till utvärdering av den föreslagna övervakade inlärningsmodellen, vilket möjliggör direkta jämförelser med befintliga vinkelberäkningslösningar som används på u-blox. Resultaten av dessa jämförelser visar mer exakta resultat jämfört med befintliga lösningar när de valideras i bekanta miljöer. Dock minskar prestandan gradvis när den introduceras till en ny miljö, där den möter ett bredare spektrum av signalförhållanden än vad inlärningsmodellen har tränats på. Avståndsberäkningar jämförs sedan med en matematisk formel, kallat path loss propagation ekvationen, som ger distans som en funktion av uppmätt signalstyrka.

Approved for public release, distribution is unlimited / Modern technology is making virtual environments a part of daily life. However, some constraints about the usage of virtual environments, such as the need for high performance and well-configured computers, prevent users from accessing virtual environments in some places other than special computer rooms. Mobile devices may be used to solve this limitation in a virtual environment. The remote-control approach to access virtual worlds on the Internet or on a corporate network is a new concept that opens new doors to users. First step of this approach is already in use, such as games implemented for mobile devices using the screen of a mobile device as display, and has given satisfying results for some users. This research will take the user, who not only wants to be mobile but also does not want to sacrifice high resolution textures and complex models, closer to his/her goal. Mobile devices provide mobility to the user, but sacrifice not only the reality of the virtual environments but also screen size, which is very important for visibility of complex virtual environments. The hybrid approach with wireless internet connection by using mobile devices as remote control gives the user the advantages of mobility over desktop PCs. On the other hand, the realism provided by high-quality PCs on the server side exceeds the capabilities of mobile devices. / Lieutenant Junior Grade, Turkish Navy

La maturité de la télématique et des technologies de l’information et la communication (TIC), ainsi que l’avènement du big data dans le transport ont conduit à des développements foisonnants dans le domaine des systèmes de transports intelligents (ITS), aussi bien sur le plan des technologies de recueil que du traitement innovant de l’information. Il est désormais possible de connaître les conditions de circulation et les états de trafic sur la plupart des sections d’un réseau routier sans avoir recours à des infrastructures intrusives de collecte de données, de transmettre l’information résultante via des réseaux sans fil et de traiter rapidement toutes ces données multi-sources disponibles. La constitution de grandes bases de données a naturellement fait évoluer la pratique de gestion du trafic et plus particulièrement les méthodes de prévision. Ces méthodes ont connu un renouveau en s’inspirant des travaux produits en apprentissage statistique. Néanmoins, la façon d’appréhender le problème de la prévision est restée à une échelle locale. Pour chaque section de route, un modèle de prévision est adapté et optimisé. Notre travail de thèse présente un cadre de prévision du trafic routier qui aborde la question à l’échelle du réseau. L’étude menée au sein de ces travaux de thèse vise à exposer et évaluer cette nouvelle approche, dite globale, au regard d’approches usuelles, puis à analyser sa sensibilité vis-à-vis de divers facteurs. Après un positionnement par rapport à l’état de l’art en théorie du trafic, le cadre prédictif fondé sur des méthodes de prévision multi-variées par apprentissage est détaillé. Une version multidimensionnelle des k plus proches voisins, modèle parcimonieux et simple, est évaluée sur divers cas d’études. L’originalité réside dans l’exploitation de données issues de méthodes innovantes de collecte (e.g. Bluetooth, véhicules traceurs, véhicules connectés). Par la suite, les performances de l’approche initiale sont comparées à d’autres méthodes d’apprentissage. Un effort particulier est porté sur l’adaptation de méthodes à noyaux au cadre prédictif global. Les performances obtenues laissent entrevoir une typologie des méthodes en fonction des caractéristiques spatiotemporelles du réseau. Afin d’améliorer les performances en prévision et de réduire les temps de calcul, une méthode d’identification et de sélection des sections critiques du réseau est proposée. Les résultats prouvent qu’un sous-ensemble restreint de sections est en effet suffisant pour garantir des performances satisfaisantes en généralisation. Enfin, la résilience du cadre prédictif est évaluée au regard des événements non récurrents affectant le fonctionnement nominal du réseau, comme des incidents ou des conditions météorologiques dégradées. Les résultats soulignent l’impact de ces conditions non récurrentes sur la prévision temps-réel de la dynamique court-terme d’un réseau et permettent de dresser une feuille de route pour l’élaboration d’un cadre prédictif résilient et opérationnel. Cette nouvelle vision de la prévision s’inscrit dans les perspectives actuelles en termes d’applications sur les modules embarqués et les objectifs des gestionnaires d’infrastructures. / The maturity of information and communication technologies and the advent of Big Data have led to substantial developments in intelligent transportation systems (ITS) : from data collection to innovative processing solutions. Knowledge of current traffic states is available over most of the network range without the use of intrusive infrastructure-side collection devices, instead relying on wireless transmission of multi-source data. The increasing use of huge databases had a strong influence on traffic management, including forecasting methods. These approaches followed the recent trend towards innovative works on statistical learning. However, the prediction problem remains mainly focused on the local scale. The prediction for each road link relies on a dedicated, optimized and adapted prediction model. Our work introduces a traffic-forecasting framework able to tackle network scale problems. The study conducted in this thesis aims to present and evaluate this new “global” approach, in comparison to most-used existing works, and then to analyze its sensitivity to several factors. The traffic-forecasting framework, based on multi-variate learning methods, is detailed after a review of the literature on traffic flow theory. A multi-dimensional version of the k nearest-neighbors, a simple and sparse model, is evaluated through several use cases. The originality of the work stands on the processing approach, applied to data collected through new measurement process (e.g. Bluetooth, floating car data, connected vehicles). Then, the performance of our primary approach is compared to other learning-based methods. We propose an adaptation of kernel-based methods for the global prediction framework. The obtained results show that global approaches perform as well as usual approaches. The spatial and temporal specificities of the methods are highlighted according to the prediction accuracy. To improve the forecasting accuracy and reduce the computation time, we propose an identification and selection method targeting critical links. The results demonstrate that the use of a restricted subset of links is sufficient to ensure acceptable performances during validation tests. Finally, the prediction framework resilience is evaluated with respect to non-recurrent events as incidents or adverse weather conditions affecting the nominal network operations. The results highlight the impact of these non-recurrent conditions on real-time forecasting of short-term network dynamics. This enables the design of a further operational and resilient prediction framework. This perspective of forecasting matches the current applications relying on embedded systems and addressing the traffic network supervisor’s expectations.

Qu’il s’agisse de suivre des patients à domicile, ou de prévenir l’isolement ou la vulnérabilité de personnes âgées, les systèmes de suivi et d'assistance électroniques qui émergent offrent des opportunités sans précédents. L’enjeu est considérable, et on assiste à un développement technologique important qui permet désormais aux particuliers ou aux établissements hospitaliers ou médico-sociaux d’assurer le diagnostic, la prévention, le contrôle, voire le traitement de patients à distance (mesures de paramètres physiologiques, administration de médicaments, détection de chutes, etc.). Ce suivi à distance est en particulier devenu possible et performant avec l’avènement des objets connectés. On peut ainsi envisager d’exploiter un réseau de capteurs embarqué sur un patient pour mesurer à distance et en temps réel la température, le rythme cardiaque ou la tension artérielle d’un patient. Les données sont transmises (et/ou stockées) au praticien pour réaliser le diagnostic et définir les traitements. Pour autant la conception optimale (choix des technologies de transmission, de stockage, etc.) ainsi que la problématique de la gestion d’énergie constituent des verrous à leur adoption. Le travail proposé dans cette thèse consiste donc à développer un outil d’aide à la conception de réseaux de capteurs médicaux communicants embarqués sur la personne. Il s’agit en particulier de fournir une information sur la faisabilité au plus tôt dans le cycle de conception, et garantir l’obtention d’un circuit « correcte par construction ». L’accent est porté sur la maîtrise (voire la réduction) de la consommation d’énergie Dans ce sens, une simulation fiable et précise permet de contrôler, dès le début du flot de conception, la consommation en énergie du réseau. Elle assure par la suite une meilleure gestion de l’énergie disponible et éventuellement une autonomie plus importante. L’outil, centré sur l’optimisation de la consommation d’énergie, est implémenté dans un environnement Matlab. Basé sur une modélisation de la consommation en énergie d’un nœud de capteur, il se veut générique aussi bien que précis. Il assure une implémentation simple de nouveaux composants à partir de fiches techniques. Ces composants sont construits sous la forme de blocs réutilisables permettant ainsi à l’utilisateur de créer sa propre librairie. En plus de l’estimation de la consommation, cet outil met en œuvre des algorithmes d’optimisation pour guider l’utilisateur vers une conception qui respecte les contraintes énergétiques et médicales de l’application (choix de composants, choix de source d’énergie, configuration du réseau, etc.). Une application est proposée d’abord au niveau d’un nœud de capteur de température corporelle communiquant par Bluetooth Low Energy. Ce même nœud est ensuite placé au sein d’un réseau de capteurs pour la surveillance de cinq paramètres physiologiques différents. Une validation expérimentale des résultats de simulation est également réalisée. / Whether it is to monitor patients at home, or to prevent the isolation and vulnerability of the elderly, the emerging electronic monitoring and assistance systems offer new opportunities. The technological development we have witnessed allows individuals, hospitals, or medical aid organizations to provide the diagnosis, prevention, control or even treatment of patients outside of conventional clinical settings (measurements of physiological parameters, drug administration, fall detection, etc.).Recent developments in connected objects made efficient remote patient monitoring possible. In other words, we are able to use a network of wearable or implantable sensors to remotely obtain real time measurements of a patient’s vital signs (temperature, heart rate, blood pressure, etc.). Data is transmitted (and / or stored) to medical personnel who are able to perform diagnosis and define treatments accordingly. An optimal design (transmission protocols, data storage, etc.) and energy management are the bottlenecks involved in the implementation of such systems. This work proposes to develop a tool to help in the design of medical sensor networks. It aims to provide information regarding feasibility during the early stages of the design thus ensuring that a "well-constructed" circuit is obtained. The emphasis is on the control (or even reduction) of energy consumption. In this regard, an efficient energy consumption simulation at the beginning of the design flow would enable the user to decide on system parameters. This will ensure an optimal management of the available energy and eventually a longer network lifetime. The proposed tool is centered on the optimization of the energy consumption using Matlab environment. It is built over a model of the energy consumption of wireless sensor nodes. It is intended to be generic and accurate. In fact, it enables fast creation of new component description based on the datasheets. These components are reusable thus producing a growing database. In addition to energy consumption estimation, the tool uses optimization routines to guide the user through an energy aware design (picking energy sources, components, network configuration, etc.) that complies with medical requirements. An application to a single Bluetooth Low Energy body temperature sensor is first proposed. The same sensor is then included in a physiological sensor network. A physical implementation is used in order to compare the results obtained through simulation with practical measurements.

An energy-aware on-demand Bluetooth scatternet formation and routing protocol taking into account network architecture and traffic pattern is proposed. The scatternet formation protocol is able to cope with multiple sources initiating traffic simultaneously as well as prolong network lifetime. A modified Inquiry scheme using extended ID packet is introduced for fast device discovery and power efficient propagation of route request messages with low delay. A mechanism employing POLL packets in Page processes is proposed to transfer scatternet formation and route reply information without extra overhead. In addition, the energy aware forwarding nodes selection scheme is based on local information and results in more uniform network resource utilization and improved network lifetime. Simulation results show that this protocol can provide scatternet formation with reasonable delay and with good load balance which results in prolonged network lifetime for Bluetooth-based wireless sensor networks. In this research, a metric-based scatternet formation algorithm for the Bluetooth-based sensor motes is presented. It optimizes the Bluetooth network formation from the hop distance and link quality perspectives. In addition, a smart repair mechanism is proposed to deal with link/node failure and recover the network connectivity promptly with low overhead. The experiments with the Intel Mote platform demonstrate the effectiveness of the optimizations. This research also investigates the scalability of ad hoc routing protocols in very large-scale wireless ad hoc networks. A comprehensive simulation study is conducted of the performance of an on-demand routing protocol on a very large-scale, with as many as 50,000 nodes in the network. The scalability analysis is addressed based on various network sizes, node density, traffic load, and mobility. The reasons for packet loss are analyzed and categorized at each network layer. Based on the observations, we observe the effect of the parameter selection and try to exhaust the scalability boundary of the on-demand routing protocol for wireless ad hoc networks.

Rapporten handlar om icke följsamhet i samband med medicinering och de stora problem som medföljer om en patient inte följer sin medicinska rådgivning. Icke följsamhet är ett stort problem i dag, både för samhället och individen. För samhället är det mycket kostsamt att hantera alla felmedicineringar och för individen kan det handla om liv eller död. Syftet med detta arbetet är att utveckla en IT-artefakt med ändamålet att förbättra följsamheten för patienter som dagligen tar medicin. Detta med hjälp av en mobilapplikation som använder Bluetooth för positionering av medicinen. IT-artefakten ska fungerar som ett stöd och hjälpmedel genom att underlätta för en patient i samband med medicinering. Denna forskning använder sig av Design Science Research Methodology (DSRM). Medverkande företag i detta arbete har varit konsultföretaget Knowit Luleå. Arbetet resulterade i en IT-artefakt, samt sex stycken designprinciper, samtliga utifrån problemet icke följsamhet i syfte att bidra till förbättrad följsamhet. / The thesis deals with non-adherence in connection with medication and the major problems that arise if a patient does not follow the medical advice. Non-adherence is a major problem today, both for society and for the individual. For society is is very costly to handle all medication errors and for the individual it can be about life or death. The purpose of this thesis is to develop an IT artifact with the purpose of improving adherence for patients taking medication daily. This is done by using a mobile application that uses Bluetooth for positioning the medicine. The artifact will serve as a support and aid by facilitating a patient that is taking medication. This research uses Design Science Research Methodology (DSRM). Contributing company in this work have been Knowit Luleå. The work resulted in an IT artifact, as well as six design principles, all based on the problem of non-adherence in order to contribute to improved adherence.

Ce travail de thèse consiste en une étude théorique et expérimentale d'un système detransmission à application universelle. Un système de capteurs ou multi-capteurs sans filsdédié à des différentes applications ayant comme point commun, une basse amplitude. Ils'inspire donc des plates forme des réseaux sans fils existant dans le monde technologique.Nous présentons dans ce mémoire les différentes raisons qui expliquent l'intérêt majeursuscité par un tel système, nous aborderons plus profondément une des applications dusystème, à savoir le domaine neurophysiologique. A partir des choix d'architecture et dessimulations expérimentales correspondantes nous relayons étape par étape les différentesphases qui nous ont mené à réaliser les prototypes en tenant en compte les résultats desuns et des autres, pour finir ensuite par une étude comparative des différents prototypesréalisés et des perspectives envisagées. / This thesis work is a theoretical and experimental study of a universal applicationtransmission system. A wireless sensor or multi-sensor system dedicated to different low-magnitudeapplications. It is inspired from wireless networks platforms of the moderntechnological world.In this dissertation, the different reasons for the interest aroused by such a system, arepresented, we will more deeply study one of the applications of this system, namely theneurophysiological area. From the choice of the architecture and corresponding experimentalsimulations we will explain, step by step, the different phases which led us to realize theprototypes taking into account the results of each phase, then finally a comparative studyof different prototypes realized and the prospects envisaged.

The advance on areas to the technology has proportionate new forms to create and to store given. Daily, the organizations accumulate given on diverse processes, e many of these, they are worked the field in the format of spread sheets, questionnaires and other ways of survey, restricted the simple notes. With the sprouting of computational devices with reduced dimensions, known as PDA (Personal digital assistants) or Pocket PC, associates to a new paradigm, mobility. The work to follow, it will go to show to the possibility of use of mobile computational systems in the simplification of collection processes and data processing the field, detailing three systems in distinct areas, that they use technology GPS (Global Position System) with connection without wire Bluetooth making possible the geoprocessing of the databases. The areas chosen in question and its respective systems had been the precision farming, Urban Registry and the farm management. / O avanço das áreas ligadas à tecnologia tem proporcionado novas formas de criar e armazenar dados. Diariamente, as organizações acumulam dados sobre diversos processos, e muitos destes são trabalhados a campo no formato de planilhas, questionários e outros meios de levantamento, restritos a simples apontamentos. Com o surgimento de dispositivos computacionais com dimensões reduzidas, conhecidos como PDA (Personal digital assistants) ou Pocket PC, associados a um novo paradigma, a mobilidade, o trabalho a seguir irá mostrar a possibilidade de utilização de sistemas computacionais móveis na simplificação de processos de coleta e processamento de dados a campo, detalhando três sistemas em áreas distintas, que utilizam tecnologia GPS com conexão sem fio Bluetooth, que possibilita o geoprocessamento das bases de dados. As áreas escolhidas em questão e seus respectivos sistemas foram a agricultura de precisão, cadastro urbano e a gestão rural.