Forskning och implementering av teknik och tjänster för navigering utomhus, såsom GPS, har kommit långt om man jämför med de alternativen som i dagsläget erbjuds för motparten för navigering inomhus. Användarvänliga wayfinding-lösningar för inomhusbruk är ett område som fortfarande har ett stort behov av mer forskning inriktad på rekommendationer och genomförbarhet av god praxis. Ett av våra mål under forskningsprocessen syftade till att undersöka och identifiera de mest lämpliga sätten att förmedla wayfinding-lösningar till slutanvändarna i olika situationer. För att vi skulle kunna undersöka denna uppgift använde vi oss av en benchmarking-process. Processen utfördes på ett urval av tjänster som erbjuder olika alternativ för wayfinding. Målet med denna process har varit att utreda vilka olika alternativ som finns tillgängliga i dagsläget, vad dessa tjänster erbjuder användarna i form av wayfinding stöd, och var potentiella problem kan uppstå utifrån användarens kognitiva beteende. Processen har även lyft fram områden som rör god praxis för wayfinding och de teknologiska begränsningar som tillhör valet av mobila enheter eller andra digitala plattformar. Vår forskning har visat att det finns flera olika lösningsalternativ som är tillgängliga för implementation i dagsläget. Dock har alla de alternativ som erbjuds sina egna specifika styrkor, svagheter och begränsningar kopplat till både den teknik som används, såväl som användbarheten för slutanvändarna. Det slutliga resultatet av vår forskning är en sammanställning av kvalitativa data och rekommendationer som hanterar både digitala och användar-fokuserade begränsningar som är sammanlänkade till vårt specifika fall. Det resultat som lyfts fram i vår forskning bör dock inte limiteras till endast vårt specifika fall. Istället bör det snarare ses som en referenspunkt för organisationer eller utvecklare som har ett intresse av att implementera wayfinding-lösningar, med syfte att hjälpa sina besökare för att navigera inomhus, eller för framtida forskning inom inomhusnavigering och wayfinding. / Research and implementation of use when it comes to outdoor navigation and GPS systems have come quite far compared to their indoor alternatives. Pedestrian friendly wayfinding solutions for indoor use are still lagging behind, and even more so when it comes to recommendations on implementation of best practice. One of our goals during the research process was aimed at finding the most adequate ways of conveying wayfinding solutions to end-users in different situations. In order to perform this task, we used a benchmarking process on a selection of wayfinding alternatives. The goal of this process have been focused on finding out which solutions are available at this moment, what they offer the users in terms of wayfinding support, and where issues might arise based on cognitive user theory, wayfinding best practice and technological limitations concerning mobile devices or different digital platforms. During our research we found that there are several different solutions that are available for implementation, but that they all come with their own specific strengths and limitations on both the technological side and for the end-users concerning usability. The result of our research has been a collection of qualitative data, and recommendations concerning digital and user limitations connected to our specific case. However, the result of this research should not be limited to our case alone, but rather as a reference point for organizations or developers that wish to implement indoor solutions for users, or for future research within the area of indoor navigation and wayfinding.

La localisation des personnes et des objets à l’intérieur des bâtiments basée sur les réseaux WLAN connaît un intérêt croissant depuis quelques années ; ce système peut être un parfait complément pour fournir des informations de localisation statique ou dynamique dans des environnements où les techniques de positionnement telles que GPS ne sont pas efficaces. Le manuscrit de thèse propose une nouvelle approche pour définir un système WLAN de positionnement indoor (WLAN-IPS) comme un problème d'optimisation combinatoire afin de garantir à la fois une qualité de communication et une minimisation de l'erreur de positionnement via le réseau. Cette approche est caractérisée par plusieurs questions difficiles que nous abordons en trois étapes.Dans un premier temps, nous avons conçu un réseau WLAN-IPS et mis en œuvre une plateforme de test. Nous avons examiné la performance du système sous diverses contraintes expérimentales et nous nous sommes penchés sur l'analyse des relations entre l'erreur de positionnement et les facteurs environnementaux externes. Ces relations ont permis de proposer des indicateurs pour évaluer l'erreur de positionnement. Ensuite nous avons proposé un modèle physique qui définit tous les paramètres majeurs rencontrés en WLAN-IPS à partir de la littérature. L'objectif initial des infrastructures WLAN étant de fournir un accès radio de qualité au réseau, nous avons introduit un objectif supplémentaire qui est de minimiser l'erreur de localisation dans le contexte IPS. Deux indicateurs principaux ont été définis afin d'évaluer la qualité de service (QoS) et l'erreur de localisation pour LBS (Location-Based Services). Enfin après avoir défini la formulation mathématique du problème d'optimisation et les indicateurs clés de performance, nous avons proposé un algorithme mono-objectif et un algorithme multicritère basés sur Tabu Search et Variable Neighborhood Search pour fournir des bonnes solutions en temps raisonnable. Les simulations montrent que ces deux algorithmes sont très efficaces pour le problème d'optimisation que nous avons posé. / Indoor Positioning Systems (IPS) using the existing WLAN have won growing interest in the last years, it can be a perfect supplement to provide location information of users in indoor environments where other positioning techniques such as GPS, are not much effective. The thesis manuscript proposes a new approach to define a WLAN-based indoor positioning system (WLAN-IPS) as a combinatorial optimization problem to guarantee the requested communication quality while optimizing the positioning error. This approach is characterised by several difficult issues we tackled in three steps.At first, we designed a WLAN-IPS and implemented it as a test framework. Using this framework, we looked at the system performance under various experimental constraints. Through these experiments, we went as far as possible in analysing the relationships between the positioning error and the external environmental factors. These relationships were considered as evaluation indicators of the positioning error. Secondly, we proposed a model that defines all major parameters met in the WLAN-IPS from the literature. As the original purpose of the WLAN infrastructures is to provide radio communication access, we introduced an additional purpose which is to minimize the location error within IPS context. Two main indicators were defined in order to evaluate the network Quality of Service (QoS) and the positioning error for Location-Based Service (LBS). Thirdly, after defining the mathematical formulation of the optimisation problem and the key performance indicators, we proposed a mono-objective algorithm and a multi-objective algorithm which are based on Tabu Search metaheuristic to provide good solutions within a reasonable amount of time. The simulations demonstrate that these two algorithms are highly efficient for the indoor positioning optimization problem.

By scanning the area for Bluetooth-signals, users can find and subscribe to Bluetooth-advertisements and thus estimate its current position. The position is used to identify what actions could be executed in the premises. This report explains the underlying technology and proposes a system architecture for a Android application that together with user authentication, WebSockets and API's could control doors, ventilation, lighting and other indoor devices wirelessly. This project was carried out in collaboration with ÅF Technology AB, Embedded Systems, where the goal was to conduct a pre-study and propose how to add contextual awareness to mobile devices, implement and evaluate a working system. / Genom att läsa av området på Bluetooth-signaler kan användare hitta och prenumerera på Bluetooth-annonseringar och därmed skatta sin position. Positionen används för att identifiera vilka handlingar som trådlöst kan uträttas i lokalen. Denna rapport förklarar bakomliggande teknik och föreslår systemarkitektur för en Android applikation som tillsammans med Autentisering, WebSockets och tillhörande API kan styra närliggande elektriska enheter, så som ventilation, dörrar och kaffemaskiner. Detta projekt utfördes tillsammans med ÅF Technology AB, Embedded Systems där målet är att genomföra en förstudie där möjliga teknologier, arkitektur, API:er samt hårdvara utvärderas som ligger till grund för implementering och utvärdering av ett fungerande system.

In dieser Arbeit wird der Einsatz von Leckwellenleiter (engl. Leaky Coaxial Cable, LCX) zur funkgestützten Indoor-Positionierung in Fahrgastzellen untersucht. Mit Hilfe eines erstellten Vorgehensmodells werden zwei unterschiedliche LCX-Prototypen speziell für den Ortungseinsatz entwickelt. Hierbei wird die elektromagnetische Feldberechnung verwendet, um sowohl Leckwellenleiterstrukturen als auch deren Einsatz in einer Fahrgastzelle zu bewerten. Nach Fertigung beider Leckwellenleiter erfolgt eine messtechnische Validierung in einer vordefinierten Fahrgastzellenumgebung. Der Einsatz dieser Prototypen zur Indoor-Positionierung wird sowohl in Modell- als auch in realen Fahrzeugumgebungen, wie der AutoTram Extra Grand des Fraunhofer IVI, durchgeführt. Eine statistische Betrachtung von Messergebnissen sowie die Vorstellung eines zonenselektiven Positionierungsansatzes schließen diese Arbeit.

Indoor Positioning System (IPS) are becoming more common in many areas such as retail, warehouses, smart facilities, and manufacturing.In recent years, Bluetooth Low Energy (BLE)-based IPS has become increasingly popular due to its low cost and low energy consumption. One of the more recent updates, Bluetooth 5.1, provides the ability to compute the location using Angle of Arrival (AoA) or Angle of Departure (AoD). These new features have allowed for better positioning accuracies, where AoA-based positioning has shown sub-meter accuracy. An application area for BLE-based IPS is retail stores where the technology can benefit both the store and its customers. This thesis investigates how to populate a database to be used with an IPS in a real-life store. The assumption is that customers will have BLE equipped devices and run an application that will send the properly formatted BLE advertisements, such that an BLE IPS can locate the user in the store. Additionally, we assume that the application can use the device's e-compass or other means to determine in which direction the user's device is oriented. Based on the position and orientation of the user, the software is assumed to access a database to know what item(s) are near the customer. However, the question remains of how did this data get into the database? This degree project explores this in detail and assesses the amount of time and effort needed to populate this database and the amount of time and effort needed to keep this database up to date. This project followed an iterative Design Science Research (DSR) methodology where the artifact is the database. A relational database was used as they are widely used and joins can easily be performed and it is easy to modify existing tables. The application was developed in Spring Boot and React. Amazon Web Services (AWS) was used to host and provide the necessary services for the database and application. The result showed that the estimated time needed to populate the database in a supermarket with a sales area of 5300 m2, 36623 products, and 220 containers is 106.64 hours and 107.13 hours in the worst case assuming a walking speed of 1.4 m s-1. Updating a product would take 10.34 s and 10.37 s if the time it takes for a staff member to walk to the place where the product is located is excluded. / Inomhuspositioneringssystem (IPS) har blivit allt vanligare inom många områden. De senaste åren har Bluetooth Low Energy (BLE)-baserad inomhuspositionering blivit mer populärt på grund av egenskaper som låg kostnad och låg energikonsumption. En av de senaste versionerna; Bluetooth 5.1 kan beräkna positionen med hjälp av ankomstvinkeln (eng. Angle of Arrival (AoA)) och utgångsvinkeln (eng. Angle of Departure (AoD)). Angle of Arrival (AoA)-baserad positionering kan uppnå en noggrannhet under 1 m. Ett Bluetooth Low Energy (BLE)-baserat IPS kan tillämpas i butiker där det kan gynna både butikens medarbetare och dess kunder. Detta examensarbete kommer att undersöka hur en databas som ska användas med ett IPS i en butik kan populeras. Antagandet i detta projekt är att kunderna kommer ha BLE utrustade enheter som kör ett program som tillåter att användaren kan lokalisera sig i butiken. Dessutom antar vi att applikationen kan använda enhetens e-kompass eller annan hårdvara för att kunna avgöra i vilken riktning användarens enhet är orienterad. Baserat på användarens position och riktning, antas det att mjukvaran kan komma åt databasen och veta vilka produkter som ligger i närheten av kunden. Dock kvarstår frågan: Hur sparades denna data i databasen? Det här examensarbetet kommer alltså att undersöka hur en databas i en butik kan vara uppbyggd om vi utgår från antagandet att BLE är tillämpat i butiken. Vi kommer även bedöma hur mycket tid som krävs för att populera en databas och hålla denna databas uppdaterad. Ett iterativ arbetsätt tillämpades i examensarbetet. I projektet användes en relationsdatabas eftersom det är enkelt att utföra join-operationer och uppdatera tabbeller i databasen. Applikationen som skapades tillhandahåller funktioner för att spara, uppdatera, radera och söka produkter i databasen. Frontend var kodad i React och backend var kodad i Spring Boot. Amazon Web Services (AWS) molntjänser och deras verktyg användes för att köra applikationen och databasen. Resultatet visade att populera en databas med produkter i en mataffär med en säljyta på 5300 m2, 36623 produkter, och 220 behållare (hyllor, kylskåp, etc.) tog 106.64 timmar i bästa fall och 107.13 timmar i värsta fall om vi antar en gångfart i 1.4 m s-1.

The purpose of this thesis is to investigate how the LoRa modulation configuration affects precision and accuracy when using LoRa for indoor positioning in non-line-of-sight conditions. The aim is to research if an optimum combination of spreading factor, bandwidth, and code rate factor can be found to result in the best possible positioning accuracy and precision, under certain predefined conditions. An experiment was conducted, where quantitative data was collected from an experimental setup. The experiment consisted of two testbeds which also included an analysis between them. Two kinds of test units were used in the experiment. The LoRa 868 MHz transmitter, which represented the unknown position, and the receivers that were used to estimate the position of the transmitter. The experiment gathered the RSSI values between the transmitter and receivers at different configurations and locations. The data collected from the experiment were analyzed using mathematical theory to answer the research question. The most accurate and precise value for each individual transmission parameter was established in the first testbed and used as the base data rates in the second testbed, to evaluate the best performing parameters simultaneously. The mean accuracy in testbed 1 varied from 180 cm to 388 cm, and the mean precision ranged between 0.432 dBm to 1.298 dBm. The mean accuracy in testbed 2 varied from 341 cm to 455 cm, and the mean precision ranged between 0.275 dBm to 1.495 dBm.  The experimental results indicate no connections between the data rate and precision. No correlation is found between the accuracy and the data rate. The standard deviation and absolute error fluctuate independently of the data rate and the transmitter position. In regard to the given results, the authors conclude that no linear relationship is found between the LoRa modulation configuration and the precision and accuracy of a position, in the selected environment. The experimental results show that LoRa could be used for indoor positioning applications where a rough estimation of a position is adequate since the mean accuracy is quite low for almost all tested modulation configurations. There could be applications where other factors, such as the energy consumption or communication range, are of more importance than accuracy. For those applications, LoRa could still be an adequate choice of technology.

The work done in this report as requested by H&D Wireless is performed by using an already developed real time positioning system called Griffin Enterprise Positioning Service and integratingit with ultrasound sensors for presence detection in order to enable assets to park in a visualized environment being actualized by tagging the asset with radio technology hardware. The testing environment was deployed with radio technology hardware equipped for transmitting and receiving radio signals for position estimation of tagged objects where hardware tags emits radio signals being received by sensing radio technology chips called sensepoints which also serves as communication links for further data processing.The thesis focus is on evaluating how different radio technologies combined with different positioning techniques perform in terms of accuracy and precision in positioning tests to assess eachones positioning performance characteristic and the technologies upsides and downsides.This was firstly evaluated by comparing three different technology positioning techniques based on one for Bluetooth Low Energy and two using Ultra Wideband technology being subject to generic tests including a static, dynamic and a walking positioning test for each technology.These initial tests were utilized as a foreground to evaluate which of the two positioning techniques based on Ultra Wideband technology that would compete in the parking tests alongside Bluetooth Low Energy that would serve as the primary objective to accomplish in the thesis.A final implication on parking tags between the two technologies is that Bluetooth Low Energy had to be implemented with higher requirement restrictions for parking due to insufficient relative accuracy and precision in parking positioning which also limited its ability to be parked in alternative manners explored but with power efficiency as a highly valuable aspect for consideration of this technology. Parking tag using Ultra Wideband technology proved highly successful as it saw large distance margins to be allowed parking in all test cases as well as exhibiting sufficient positioning performance to be considered for alternative parking methods without risk of exposure for failed attempts of parking. / Arbetet utfört i denna rapport på order av H&D Wireless utfördes genom att använda en redan utvecklat realtids positionerings tjänst vid namn Griffin Enterprise Positioning Service och integreradetta system med ultraljudssensorer för närvaro upptäckning för att på så sätt göra det möjligt för tillgångar att parkera i en visualiserad miljö möliggjord av att märkta tillgångar, också kallade taggar, med radioteknologisk hårdvara. Test miljön var utformad med radioteknologisk hårdvara föratt kunna sända och ta emot radio signaler för positionerings estimering av märkta objekt där dessa taggar utsänder radio signaler som upptas av kännande radioteknologiska chip som kallas för sensepoints vilka också tjänar som kommunikationslänkar för vidarearbetning av data.Uppsatsen fokuserar på att utvärder hur radioteknologierna Bluetooth Low Energy och Ultra Wideband tillsammans med förbestämda positionerings tekniker presterar i termer av noggranhet och precision i positionerings tester för att kunna bedöma varderas positionerings karakteristiska prestanda och teknologiernas fördelar och nackdelar. Detta påbörjades genom att utvärdera tre olika teknologiska positioneringstekniker baserade på en med Bluetooth Low Energy och två med Ultra Wideband teknologi som utsattes av generiska tester,som inkluderar ett statisk, dynamiskt och gående positionerings test genomfört för vardera teknologi. Dessa initiala tester användes som grund för att utvärdera vilka två av positionerings teknikerna baserade på Ultra Wideband teknologi som skulle utgöra kandidat i parkerings testerna vid sidan om Bluetooth Low Energy vilket var det primära målet att genomföra i uppsatsen.En följd av att parkera taggar mellan de två teknologierna var att Bluetooth Low Energy krävde högre restriktioner vid implementering för parkering eftersom den uppvisade relativ otillräcklig noggranhet och precision i dess parkerings positionering vilket också begränsade dess förmåga att kunna parkera med alternativ parkings metoder förslagna i rapporten medan dess låga effektförbrukning som en fördelaktig aspekt vid övervägande av tekniken. Att parkera en tagg med Ultra Wideband teknologi demonstrerade framgångsrika resultat då den såg stora avståndsmarginaler för att tillåtas parkera i alla testfall såväl som uppvisande av tillräcklig hög positionerings prestanda för att kunna övervägas med alternativa parkerings metoder utan risk för misslyckade försök till att bli parkerad.

Under de senaste åren har intresset för att positionera objekt inomhus ökat tack vare den tilltagande trenden kring Internet of Things (IOT). I den tekniska världen återfinns ett flertal begrepp för inomhuspositionering, däribland Real Time Locating System (RTLS). RTLS främsta egenskap är att identifiera och lokalisera objekt inomhus, kvalitetssäkra processer, informationsutbyte mellan aktörer, alarmera om objekt rör sig utanför vissa gränser. Gemensamt är att det ska effektivisera processer i flödet. En verkstadsindustri, som Scania CV AB, karaktäriseras av maskiner, rörelse, buller, personal och material. Materialet som återfinns på Scania kan påverka RTLSteknologin. Det finns idag inte en dominerande teknik för inomhuspositionering därav att det har genererat i flertalet tekniker däribland UWB, RFID, IR, BLE, Wi-Fi. Rapportens frågeställningar är vilka utvärderingskriterier som styr valet av RTLSsystem och vilka av de här kriterierna är mer kritiska än andra? samt vilka tekniker kan användas i en verkstadsindustrin idag? För att besvara rapportens frågeställningar har ett kvalitativt förhållningssätt använts. Rapporten har använt fallstudie för att kunna svara på studiens frågeställningar. En kvalitativ ansats har använts med intervjuer och observationer som genomförande på produktionsenheterna. Tidigare forskning har legat till grund för utformningen av utvärderingskriterierna. Utvärderingskriterierna har i rapportens analysdel vägts in mot teknikens förutsättningar, omgivningens preferenser och mot det specifika behovet. Slutsatsen är att behovet och omgivningen är de två viktigaste elementen att beakta vid ett beslutsfattande av RTLS-system. I ett beslutsfattande är vissa kriterier mer kritiska än andra. Då behovet styr valet av teknik blir således samtliga tekniker användbara i en verkstadsindustri. Det finns dock ingen teknik som passar samtliga behov varför det således blir viktigt att välja en leverantör med bred produktportfölj som har möjlighet att erbjuda hybrider. / During the recent years the interest of positioning has increased due to the growing trend of Internet of Things (IoT). In the technical world there are several concepts for indoor positioning, among them Real Time Locating System (RTLS). RTLS main feature is to identify and locate objects indoors, to insure the quality of processes, to exchange information between stakeholder and to alert if items move beyond certain limits. Common is that it will streamline working processes. A engineering industry, such as Scania CV AB, is characterized by objects such as machines, motions, noise, personnel and materials. These objects found in Scania may affect the RTLS technology. There is currently no dominant indoor positioning technology on the market, thus there are many different technologies including UWB, RFID, IR, BLE and Wi-Fi. The problem definition of the thesis is therefore “What evaluation criteria are affecting the decision-making process when choosing RTLS and what criteria is more critical than the other?” and “Which technologies can be used in a engineering industry today?” To answer these problem definitions a qualitative research has been issued structured by a case study. Interviews and observations has been carried out as methods at the production units. The evaluation criteria are based on previous research. The criteria have been weighed against the technical conditions, the preferences of the environment and the specific use case. The conclusion is that the use case and the environment are the two most important elements to consider when deciding on a RTLS technology. In decision-making some criteria are more critical than others. As use case directs what technology should be used, all technologies are considered to be useful in a engineering industry. However there is no technology that fits all applications, thus it is important to choose a vendor that has a comprehensive product portfolio and one that enables hybrid solutions.

There is a sharp increase in the number of old people living alone throughout the world. More often than not, such people require continuous and immediate care and attention in their everyday lives, hence the need for round the clock monitoring, albeit in a respectful, dignified and non-intrusive way. For example, continuous care is required when they become frail and less active, and immediate attention is required when they fall or remain in the same position for a long time. To this extent, various monitoring technologies have been developed, yet there are major improvements still to be realised. Current technologies include indoor positioning systems (IPSs) and health monitoring systems. The former relies on defined configurations of various sensors to capture a person's position within a given space in real-time. The functionality of the sensors varies depending on receiving appropriate data using WiFi, radio frequency identification (RFIO), ultrawide band (UWB), dead reckoning (OR), infrared indoor (IR), Bluetooth (BLE), acoustic signal, visible light detection, and sound signal monitoring. The systems use various algorithms to capture proximity, location detection, time of arrival, time difference of arrival angle, and received signal strength data. Health monitoring technologies capture important health data using accelerometers and gyroscope sensors. In some studies, audio fingerprinting has been used to detect indoor environment sound variation and have largely been based on recognising TV sound and songs. This has been achieved using various staging methods, including pre-processing, framing, windowing, time/frequency domain feature extraction, and post-processing. Time/frequency domain feature extraction tools used include Fourier Transforms (FTs}, Modified Discrete Cosine Transform (MDCT}, Principal Component Analysis (PCA), Mel-Frequency Cepstrum Coefficients (MFCCs), Constant Q Transform (CQT}, Local Energy centroid (LEC), and Wavelet transform. Artificial intelligence (Al) and probabilistic algorithms have also been used in IPSs to classify and predict different activities, with interesting applications in healthcare monitoring. Several tools have been applied in IPSs and audio fingerprinting. They include Radial Basis Kernel (RBF), Support Vector Machine (SVM), Decision Trees (DTs), Hidden Markov Models (HMMs), Na'ive Bayes (NB), Gaussian Mixture Modelling (GMM), Clustering algorithms, Artificial Neural Networks (ANNs), and Deep Learning (DL). Despite all these attempts, there is still a major gap for a completely non-intrusive system capable of monitoring what an elderly person living alone is doing, where and for how long, and providing a quick traffic-like risk score prompting, therefore immediate action or otherwise. In this thesis, a cost-effective and completely non-intrusive indoor positioning and activity-monitoring system for elderly people living alone has been developed, tested and validated in a typical residential living space. The proposed system works based on five phases: (1)Set-up phase that defines the typical activities of daily living (TADLs). (2)Configuration phase that optimises the implementation of the required sensors in exemplar flat No.1. (3)Learning phase whereby sounds and position data of the TADLs are collected and stored in a fingerprint reference data set. (4)Listening phase whereby real-time data is collected and compared against the reference data set to provide information as to what a person is doing, when, and for how long. (5)Alert phase whereby a health frailty score varying between O unwell to 10 healthy is generated in real-time. Two typical but different residential flats (referred to here are Flats No.1 and 2) are used in the study. The system is implemented in the bathroom, living room, and bedroom of flat No.1, which includes various floor types (carpet, tiles, laminate) to distinguish between various sounds generated upon walking on such floors. The data captured during the Learning Phase yields the reference data set and includes position and sound fingerprints. The latter is generated from tests of recording a specific TADL, thus providing time and frequency-based extracted features, frequency peak magnitude (FPM), Zero Crossing Rate (ZCR), and Root Mean Square Error (RMSE). The former is generated from distance measurement. The sampling rate of the recorded sound is 44.1kHz. Fast Fourier Transform (FFT) is applied on 0.1 seconds intervals of the recorded sound with minimisation of the spectral leakage using the Hamming window. The frequency peaks are detected from the spectrogram matrices to get the most appropriate FPM between the reference and sample data. The position detection of the monitored person is based on the distance between that captured from the learning and listening phases of the system in real-time. A typical furnished one-bedroom flat (flat No.2) is used to validate the system. The topologies and floorings of flats No.1 and No.2 are different. The validation is applied based on "happy" and "unusual" but typical behaviours. Happy ones include typical TADLs of a healthy elderly person living alone with a risk metric higher than 8. Unusual one's mimic acute or chronic activities (or lack thereof), for example, falling and remaining on the floor, or staying in bed for long periods, i.e., scenarios when an elderly person may be in a compromised situation which is detected by a sudden drop of the risk metric (lower than 4) in real-time. Machine learning classification algorithms are used to identify the location, activity, and time interval in real-time, with a promising early performance of 94% in detecting the right activity and the right room at the right time.

Les systèmes de localisations existants présentent des insuffisances au niveau desapplications en environnement indoor. Ces insuffisances se traduisent soit par la non-disponibilité des signaux (le GPS) dans ce type d’environnement, soit par leur manque de précision quand ils sont prévus à cet effet. Ces limites ont motivé la recherche de nouvelles techniques. Les transmissions Ultra-Large Bande (ULB) de par leur singularité en matière de précision et de faible puissance d’émission, s’avèrent être la meilleure réponse à la problématique ci-dessus. Nous avons donc choisi cette technique pour mettre au point un procédé de localisation endogène permettant d’assurer, avec précision, la continuité des services de localisation dans les environnements indoor. Ce procédé s’appuie sur la localisation en trois dimensions (3-D). Il utilise la technique temporelle de différenciation du temps d’arrivée (TDOA). Cette technique permet de mieux tirer profit de la bonne résolution temporelle de l’ULB et de pallier au problème de synchronisation entre l’émetteur et le récepteur. Deux techniques de transmission ULB ont été étudiées : la technique d’accès multiples par séquence directe (DS-CDMA) et la technique d’accès multiples par sauts temporels (TH-CDMA). Une autre étape importante de notre étude a été de développer un algorithme non-itératif de localisation en 3-D pour réduire le temps de calcul. En effet, l’utilisation d’un algorithme non-itératif permet d’optimiser les performances du système en termes de temps de calcul voire de coûts de consommation énergétique. Après l’étude théorique des différents blocs du système, le système a été tout d’abord simulé dans le canal Gaussien (AWGN) et les canaux IEEE.802.15.4a indoor. Il a été ensuite testé dans différents environnements réels de types laboratoires. Les résultats obtenus démontrent que l’utilisation des techniques de transmission basées sur la technologie radio impulsionnelle ULB permet d’obtenir un système de localisation en 3-D avec une précision centimétrique pour les applications indoor. / Existing positioning systems have deficiencies in applications indoor environment. These deficiencies result is the non-availability of signals (GPS) in this type of environment, either by their lack of precision when they are provided for this purpose. These limitations have led to research for novel techniques. Ultra-Wide Band (UWB) transmission techniques due to their uniqueness in terms of fine resolution and low power emission, prove to be the best answer to this problem. So we choose this technique to develop a process to ensure self location, with accuracy, continuity of location services in indoor environments. This method is based on the location in three dimensions (3-D). It uses the Time Difference Of Arrival (TDOA) technique. This technique allows to better take advantage of the high time resolution of the ULB and overcome the problem of synchronization between the transmitter and the receiver. Two UWB transmission techniques were studied: the Direct Sequence multiple access technique (DS-CDMA) and Time Hopping (TH-CDMA) multiple access technique. Another important step in our study was to develop a non-iterative positioning algorithm in 3-D to reduce the computation time. Indeed, using a non-iterative algorithm optimizes system performance in terms of computing time or cost of energy consumption. After the theoretical study of the system, the proposed positioning system was firstly simulated in Additive White Gaussian Noise (AWGN) channel and indoor IEEE.802.15.4a channels. It was then tested in various real environments types laboratories. The results obtained show that using UWB impulse radio technology transmission techniques allows to achieve a high accuracy 3-D location system in order of centimeter for applications in indoor environments.