This thesis is a part of a research project performed by two MS students Yang Yang and the author. The overall objective of the project is the design, implementation, and performance evaluation of algorithms for newborn localization and tracking in hospitals using Apple iBeacon technology. In the research project, I lead the path-loss modeling of iBeacon, design of algorithms for in-room presence detection system, and analysis of the accelerometer sensor. My partner, Yang Yang, leads the performance evaluation of the localization system using Cramer Rao Lower Bound (CRLB). This manuscript describes the project with a focus on my contributions in modeling the behavior of sensors and presence detection algorithms. Today, RFID detection is the most popular indoor detection technique. It provides high precision detection rate to distinguish the number of people in certain rooms of a building. However, special scanners and manual operations are required. This increases the cost and operation complexity. With the recent introduction of iBeacon by Apple, possibility of more efficient in-room presence detection has emerged for specific applications. An example of these applicatons is recording the number of visitors and newborns in a nursery room inside a hospital. The iBeacon uses Bluetooth Low Energy (BLE) technology for proximity broadcasting. Additionally, iBeacon carries a motion detection sensor, which can be utilized for counting the number of people and newborns entering and leaving a room. In this thesis we introduce a novel intelligent in-room presence detection system using iBeacon for the newborns in hospitals to determine the number of visitors and newborns' location in the nursery room. We first develop a software application on iPhone to receive and extract the necessary data from iBeacon for further analysis. We build the path-loss model for the iBeacon based on the received signal strength (RSS) of the iBeacon, which is used for performance evaluation using CRLB in Yang Yang's project. We also utilize the accelerometer in the smart phones to improve the performance of our detection system.

This master thesis investigates the possibility to automatically label and classify radio waves for presence detection, where the objective is to obtain information about the number of people in a room based on channel estimates. Labeling data for machine learning is time consuming and tedious process. To address this two approaches are evaluated. One was to develop a framework to generate labels with the aid of computer vision AI. The other relies on unsupervised learning classifiers complemented with heuristics to generate the labels. The investigation also studies the performance of the classifiers as a function of the TX/RX configuration, SNR, number of consecutive samples in a feature vector, bandwidth and frequency band. When someone moves in a room the propagation environment changes and induces variations in the channel estimates, compared to when the room is empty. These variations are the fundamental concept that is exploited in this thesis. Two methods are suggested to perform classification without the need of training data. The first uses random trees embeddings to construct a random forest without labels and the second using statistical bootstrapping with a random forest classifier. The labels used for annotation indicate whether were zero, one or two people in the room. The performance of binary and non-binary classification is evaluated both for the two blind detection models, as well as the performance of the unsupervised learning techniques Kmeans and self-organizing maps. For classification both supervised and unsupervised learning use random forest classifiers. Results show that random forest classifiers perform well for this kind of problem, and that random tree embeddings are able to extract relational data that could be used for automatic labeling of the data.

Cette thèse s’inscrit dans le domaine de la conception et de la réalisation de systèmes intelligents, associés à une technologie de capteurs sol. Elle vise à concevoir un outil automatisé et intelligent destiné à détecter principalement les chutes de personnes âgées en milieu hospitalier, afin de fournir une information supplémentaire au personnel soignant. Premièrement, les différentes technologies de capteurs appliquées aux revêtements de sol ont été étudiées. Parmi les technologies recensées, les capteurs piézoélectriques planaires en polymères ont été retenus pour l’élaboration du système intelligent. Ensuite, la caractérisation de la solution technique retenue a permis de définir les conditions et limites d’utilisation du capteur. Les aspects de robustesse et de durabilités ont été évalués à l’aide de méthodes développées à ces effets. Enfin, des algorithmes de détection ont été développés en vue de détecter les chutes, les pas et la présence de personnes sur des surfaces délimitées par le système. Des stratégies de classification basées sur la corrélation de Pearson, des algorithmes d’apprentissages ou des algorithmes à seuils ont été utilisés. / This thesis is part of the field of design and elaboration of smart systems combined with a flooring sensor technology. The main objective deal with the design of an automated and smart tool to detect falls of elderly people in hospitals or nursing homes, in order to provide additional information to healthcare workers. First, various sensor technologies applied to floor covering have been studied. Among the technologies identified, piezoelectric planar polymer sensors have been chosen for the development of the smart system. Then, the characterization of the validated technical solution allows to define conditions and limits of use of the sensor. The robustness and durability were evaluated using methods that were specifically developed to address these aspects. Finally, detection algorithms have been developed to detect falls, footsteps and presence of people on our sensors. Classification strategies based on Pearson’s correlation, machine learning algorithms or threshold based algorithm have been used.

Wireless communication equipment is widely available and the number of transmitters and receivers keeps increasing. In addition to communications, wireless nodes can be used for sensing. This project is focuses on human presence detection in indoor environments using measurements such as CSI that can be extracted from radio receivers and labeled using a camera and AI computer vision techniques (YoLo framework). Our goal is to understand if a room is empty or has one or two people by utilizing machine learning algorithms. We have selected SVM (Support Vector Machines) and CNN (Convolutional Neural Networks). These methods will be evaluated in different scenarios such as different locations, bandwidths of 20, 40 and 120MHz, carrier frequencies of 2.4 and 5 GHz, high/low SNR values as well as different antenna configurations (MIMO, SIMO, SISO). Both methods perform very well for classification and specifically in case of CNN it performs better in low SNR compared to SVM. We found that some of the measurements seemed to be outliers and the clustering algorithm DBScan was used in order to identify them. Last but not least, we explore whether the radio can complement computer vision in presence detection since radio waves may propagate through walls and opaque obstacles. / Trådlös kommunikationsutrustning är allmänt tillgänglig och antalet sändare och mottagare fortsätter att öka. Förutom kommunikation kan trådlösa noder användas för avkänning. Detta projekt fokuserar på mänsklig närvarodetektering i inomhusmiljöer med hjälp av mätningar som CSI som kan extraheras från radiomottagare och märkas med hjälp av en kamera och AI datorseende tekniker (YoLo-ramverket). Vårt mål är att förstå om ett rum är tomt eller har en eller två personer genom att använda maskininlärningsalgoritmer. Vi har valt SVM och CNN. Dessa metoder kommer att utvärderas i olika scenarier såsom olika platser, bandbredder på 20, 40 och 120MHz, bärvågsfrekvenser på 2,4 och 5 GHz, höga/låga SNR-värden samt olika antennkonfigurationer (MIMO, SIMO, SISO). Båda metoderna fungerar mycket bra för klassificering och specifikt i fall av CNN presterar den bättre i låg SNR jämfört med SVM. Vi fann att några av mätningarna verkade vara extremvärden och klustringsalgoritmen DBScan användes för att identifiera dem. Sist men inte minst undersöker vi om radion kan komplettera datorseende vid närvarodetektering eftersom radiovågor kan fortplanta sig genom väggar och ogenomskinliga hinder.

Comme les gens vieillissent, ils sont souvent confrontés à un certain degré de diminution des capacités cognitives ou de la force physique. Isolement de la vie sociale, mauvaise qualité de la vie, et risque accru de blessures en sont les principales conséquences. Ambient Assisted Living (AAL) est une vision de la façon dont les gens vivent leur vie dans leur propre maison, à mesure qu'ils vieillissent : handicaps ou limitations sont compensées par la technologie, là où le personnel de prestation de soins est rare ou des proches ne sont pas en mesure d'aider. Les personnes concernées sont assistés par la technologie. Le terme "ambiante" en AAL exprime, ce que cette technologie doit être, au- delà de l’assistance. Elle doit être intégrée dans l’environnement de manière à ce qu'elle ne soit pas reconnue en tant que tel. L'interaction avec les résidents doit être intuitive et naturelle. L'équipement technique doit être discret ct bien intégré. Les domaines d'application ciblés dans cette thèse sont le suivi de l’activité et la recherche de profils d'activités dans des appartements ou des petites maisons. L'acquisition d’informations concernant l’activité des résidents est vitale pour le succès de toute la technologie d’assistance. Dans de nombreux domaines de la vie quotidienne, ceci est déjà de la routine. L’état de l’art en matière de technologie de détection comprend des caméras, des barrières lumineuses, des capteurs RFID, la radiolocalisation de signal en utilisant des transpondeurs et des planchers sensibles à la pression. En raison de leurs principes de fonctionnement, ils ont malheureusement un impact important sur les environnements domestiques et de vie. Par conséquent, cette thèse est consacrée à la recherche de technologies d’acquisition d’informations de l’activité non-intrusive ayant un impact minimal sur la vie quotidienne. Deux technologies de base, la détection de présence passive sans dispositif et le suivi de charges de manière non-intrusive, sont prises en compte dans cette thèse. / As people grow older, they are often faced with some degree of decreasing cognitive abilities or physical strength. Isolation from social life, poor quality of life, and increased risk or injuries are the consequence. Ambient Assisted Living (AAL) is a vision for the way people live their life in their own home, as they grow older: disabilities or limitations are compensated for by technology, where care-giving personnel is scarce or relatives are unable to help. Affected people are assisted by technology. The term "Ambient" in AAL expresses, what this technology needs to be, beyond assistive. It needs to integrate into the living environment in such a way that it is not recognized as such any more. Interaction with residents needs to be intuitive and natural. Technical equipment should be unobtrusive and well integrated. The areas of application targeted in this thesis are activity monitoring and activity pattern discovery in apartments or small houses. The acquisition of information regarding the residents' activity is vital for the success of any assistive technology. In many areas of daily life, this is routine already. State-of-the-art sensing technology includes cameras, light barriers, RFID sensors, radio signal localization using transponders, and pressure sensitive Floors. Due to their operating principles, they have a big impact on home and living environments. Therefore, this thesis is dedicated to research for non-intrusive activity information acquisition technology, that has minimal impact on daily life. Two base technologies are taken into account in this thesis.

The aim of the thesis is to design a system based on wirelessly comunicating devices that will be able to record an information about persons presesce in certain area. Aquired data will served for evaluation of the area lighting system efficiency. Partial goals related to this work are: to analyze electricity consumption mesaurement methods, to analyze presence and movement detection methods, to analzye wireless communication methods, to desin system's HW and SW including realization, to put system into a real operation and finally, to evaluate measured data.

New technology in radar opens up new possibilities for cheap and easily integrated human body presence detection. In this work, we aim to make a proof of concept that replaces the "dead man’s grip" on an electric surfboard with a more convenient wireless system based on micro radars. To answer the research questions identified, an artifact was created. To guide the research process and ensure that rigorous methods are used for constructing and evaluating the artifact, this thesis employs the research paradigm Design Science Research. The result was that the radar signal is completely degraded without a radome when the radar is wet. With a radome, the signal strength is a third wet compared to dry. Therefore, a radome is required to protect the radar and its function from the elements. The need for blockage detection was also defined. Observing how the direct leakage signal deviates from its normal state can determine whether the sensor is being blocked. Several algorithms were developed and tuned to prove the concept. Coverage and detection speed was tested and optimized. Overall, the potential of micro radars to replace a dead man’s grip on a surfboard is very promising. / Ny radarteknik öppnar nya möjligheter för billig och lättintegrerad upptäckt av människokroppens närvaro. I det här arbetet vill vi göra ett konceptbevis som ersätter "dödmansgreppet" på en elektrisk surfbräda med ett bekvämare trådlöst system baserat på mikroradar. För att besvara de identifierade forskningsfrågorna skapades en artefakt. För att vägleda forskningsprocessen och se till att rigorösa metoder används för att konstruera och utvärdera artefakten används forskningsparadigmet Design Science Research i denna avhandling.  Resultatet var att radarsignalen försämras fullständigt utan radom när radarn är våt. Med en radome är signalstyrkan en tredjedel våt jämfört med torr. Därför krävs en radome för att skydda radarn och dess funktion från väder och vind. Behovet av blockaddetektering definierades också. Genom att observera hur den direkta läckagesignalen avviker från sitt normala tillstånd kan man avgöra om sensorn är blockerad. Flera algoritmer utvecklades och justerades för att bevisa konceptet. Täckning och detektionshastighet testades och optimerades. På det hela taget ser mikroradarns potential att ersätta dödmansgrepp på en surfbräda mycket lovande ut.