Context: Indoor positioning systems have become more widespread over the past decade, mainly due to devices such as Bluetooth Low Energy beacons which are low at cost and work effectively. The context of this thesis is to localize and help people navigate to the office equipment, meeting rooms, etc., in an office environment using machine learning algorithms. This can help the employees to work more effectively and conveniently saving time. Objective: To perform a literature review of various machine learning models in indoor positioning that are suitable for an office environment. Also, to experiment with those selected models and compare the results based on their performance. Android smartphone and BLE beacons have been used to collect RSSI values along with their respective location coordinates for the dataset. Besides, the accuracy of positioning is determined by using state-of-the-art machine learning algorithms to train the dataset. Using performance metrics such as Euclidean distance error, CDF curve of Euclidean distance error, RMSE and MAE to compare results and select the best model for this research. Methods: A Fingerprinting method for indoor positioning is studied and applied for the collection of the RSSI values and (x, y) location coordinates from the fixed beacons. A literature review is performed on various machine learning models appropriate for indoor positioning. The chosen models were experimented and compared based on their performances using performance metrics such as CDF curve, MAE, RSME and Euclidean distance error. Results: The literature study shows that Long Short Term Memory and Multi-layer perceptron, Gradient boosting, XG boosting and Ada boosting is suitable for models for indoor positioning. The experimentation and comparison of these models show that the overall performance of Long short-term memory network was better than multiplayer Perceptron, Gradient boosting, XG boosting and Adaboosting. Conclusions: After analysing the acquired results and taking into account the real-world scenarios to which this thesis is intended, it can be stated that the LSTM network provides the most accurate location estimation using beacons. This system can be monitored in real-time for maintenance and personnel tracking in an office environment.

Personal telehealth plays a crucial role in addressing global challenges of aging population and rising cost for health care. Tiny and wirelessly connected medical sensors, for example embedded in clothes or on the body, will be an integrated part of lifestyle, and will allow hospitals to remotely diagnose patients in their home.  In this thesis, a wireless bio-sensing with smart phone based monitoring system is proposed to provide a home based telehealth care for continuous monitoring. The system consists of two main parts: a wireless sensor and a health application on the smart phone. This thesis is to design the first part of the system - a wireless temperature and electrocardiography (ECG) sensor. The sensor integrates ECG front-end analog block, a micro-controller and a Bluetooth low energy (BLE) connectivity IC on a single board. To achieve the miniaturization of the sensor and users’ comfort in mind, the sensor is designed as a miniaturized hybrid system utilizing flexible batteries and printed electrodes. This can efficiently detect ECG signals and transfer them to a smart phone through BLE link.

It is very common in everyday life for people to use data generated by sensors like accelerometers and gyroscopes, whether they are on the mobile phone, smartwatch or other smart devices, for analysis of their movement or tracking their habits. This study is focused on boxing, and proposes a test where the generated data are put through machine learning algorithms in order to output information on the type of punch thrown by the user. Furthermore, the possibility of implementing ML on Android is examined. This thesis was performed by conducting a literature study, and an experimental study. For the literature study, researches similar to this were examined to gather information and insight on what the most common practices are, regarding the setup of the device used to collect the data, both in terms of sensor placement on the body and sensor setup like the optimal data output rates. The experimental part was conducted using custom hardware implementing an accelerometer and a gyroscope in which the wearer of this device would proceed to throw 6 types of punches (jab, cross, left & right uppercut, and left & right hook) to generate the data to be analyzed. It was technically possible to use Android for ML, but it was the least optimum way to execute the algorithms, so a PC was used instead. After putting the data through multiple ML algorithms, the results show that with our current hardware set up it was not possible for the ML algorithms to adequately classify the type of punches with mediocre accuracy scores ranging from 37.37% - 59.16% depending on the algorithm.

Den här uppsatsen beskriver processen av att skapa en plattformsoberoende mobilapplikation för att koppla upp mobila enheter mot trådlösa sensorer med hjälp av Bluetooth Low Energy, samla in data från uppkopplade sensorer och ladda upp den insamlade datan till en molnlagringstjänst. Allt eftersom konsumenter och forskare använder fler sensorer och andra Bluetooth-enheter, [1] ökar behovet av simplare och standardiserade lösningar för att arbeta med dessa. En litteraturstudie har genomförts där information om närliggande forskning insamlats och viktig information om de nödvändiga mjukvarukomponenter som krävs har utvärderats. I kombination med litteraturstudien har en IT-artefakt utvecklats i form av en mobilapplikation som har testats utefter insamlade krav för att säkerställa applikationens funktionalitet. Syftet med det här arbetet är att tydliggöra och konkretisera en mjukvaruutvecklingsprocess som kan användas för att skapa en mobilapplikation av det här slaget, samt vilka potentiella svårigheter som finns i dagsläget med att utforma den här typen av applikationer. Resultaten visar att en del tillverkare inte följer standarden för Bluetooth-kommunikation, detta gör det svårt att skriva generaliserade metoder för att hämta data från sensorer av alla typer och från samtliga tillverkare. / This thesis describes the process of creating a platform-independent mobile application for connecting mobile devices to wireless sensors using Bluetooth Low Energy, collecting data from connected sensors and uploading the collected data to a cloud storage service. As consumers and researchers use more sensors and other Bluetooth-devices, [1] one could argue that there is a need for simpler and standardised solutions to working with these. A literature study has been conducted where information on related research has been collected and important information about the necessary software components has been evaluated. In combination with the literature study, an IT artefact has been developed in the form of a mobile application that has been tested according to collected requirements to ensure the application's functionality. The purpose of this work is to contribute with a clear scientific process over what is required to create a mobile application of this kind and what potential difficulties exist in present-day design of this type of applications. The results show that some manufacturers may not be following the standards for Bluetooth data communication, thus making it hard to write generalized methods for retrieving data from sensors of any type or manufacturer.

No description available.

Indiana University-Purdue University Indianapolis (IUPUI) / In today’s world, the applications of Unmanned Aerial Vehicle (UAV) systems are leaping by extending their scope from military applications on to commercial and medical sectors as well. Owing to this commercialization, the need to append external hardware with UAV systems becomes inevitable. This external hardware could aid in enabling wireless data transfer between the UAV system and remote Wireless Sensor Networks (WSN) using low powered architecture like Thread, BLE (Bluetooth Low Energy). The data is being transmitted from the flight controller to the ground control station using a MAVlink (Micro Air Vehicle Link) protocol. But this radio transmission method is not secure, which may lead to data leakage problems. The ideal aim of this research is to address the issues of integrating different hardware with the flight controller of the UAV system using a light-weight protocol called UAVCAN (Unmanned Aerial Vehicle Controller Area Network). This would result in reduced wiring and would harness the problem of integrating multiple systems to UAV. At the same time, data security is addressed by deploying an encryption chip into the UAV system to encrypt the data transfer using ECC (Elliptic curve cryptography) and transmitting it to cloud platforms instead of radio transmission.

No description available.

With the increasing use of electronic devices, the need for affordable wireless services specifically context-aware services, in a so-called Personal Area Network (PAN) is becoming an area with significant potential. Service discovery is a basic function. Even though a number of service discovery protocols have been implemented, a specific protocol for a PAN environment may need to be developed, as the characteristics of a PANs differ from other networking environments. Thus, the specific requirements for service discovery from a PAN perspective were studied. Methods for service discovery will be described that take into account both local and remote services. These methods will then be evaluated in a SIP telephony infrastructure to decide where a call should be delivered. The location of a person is done by using the implemented service discovery. / Med en ökad användning av elektroniska enheter blir behovet av trådlösa tjänster, speciellt context-medvetna tjänster i så kallade Personal Area Network (PAN), ett område med betydlig potential. Service Discovery är en grundläggande funktion. Även om flera service discovery protocols har implementerats finns det behov av ett specifikt protokoll för PAN-miljöer då egenskaperna hos ett PAN skiljer sig från andra nätverksmiljöer. Således studerades de specifika krav för service discovery från ett PAN perspektiv. Metoder för service discovery kommer att ta med i beräkningen båda lokala och avlägna tjänster. Dessa metoder utvärderas i en SIP telephony infrastructure för att avgöra var en påringning ska levereras. Lokalisering av en användare sker genom det implementerade service discovery-protokollet.

This thesis discusses the design considerations for a machine conditioning sensor utilizing Bluetooth low energy (BLE).

This thesis aims at evaluating a proposed interferometry Angle of Arrival method for Bluetooth Low Energy and investigating the feasibility of using it together with current technology in a keyless entry access control solution. The current technology is an evaluation kit from Texas Instrument that is used together with various types of antennae arranged in arrays. An in-depth look at it revealed that it does not implement the proposed Angle of Arrival method for Bluetooth Low Energy but the deviations are minor. Results obtained from tests with delay lines show enough accuracy for a keyless entry access control solution. However, none of the tested antenna types do. The work concludes that current technology cannot be used as a keyless entry access control solution due to strong antenna dependencies. Future work is thus proposed to be done on antenna development. / Detta arbete syftar till att utvärdera en förslagen interferometri Angle of Arrival-metod för Bluetooth Low Energy samt undersöka möjligheten att använda den tillsammans med nuvarande tekniken i nyckellös åtkomstkontroll. Den nuvarande tekniken är ett utvärderingspaket från Texas Instrument som används tillsammans med olika typer av antenner. En utförlig undersökning av tekniken avslöjade att den inte implementerar den föreslagna Angle of Arrival-metod för Bluetooth Low Energy men avvikelserna är minimala. Resultat som erhållits från tester med fördröjningslinjer visar tillräckligt noggrannhet för nyckellös åtkomstkontroll. Men ingen av de testade antenntyperna gör det. Arbetet drar slutsatsen att den nuvarande tekniken inte kan användas som nyckellös åtkomstkontroll på grund av starka antennberoende. Framtida arbete föreslås således att fokusera på antennutveckling.