The work deals with the issue of indoor positiong system in the enviroment of the Android operating system, based on the efficient standard Bluetooth Low Energy, with conjunction of bluetooth beacons. The outcome of master‘s thesis is system topology, description of its components, standards needed for his creation and finally construction of the system.

This thesis deals with creating a library for the Android OS which enables efficient wireless communication with platform Arduino. The target is to create an application for Android OS, using a created library that allows you to capture data from various sensors and control effectors. The work describes basic wireless interfaces for Android OS and Arduino platform. The main benefits and drawbacks functions are also introduced. The comparison of current consumption for modules HM-10 and DIGI S1 has been carried out as well. Possibility of data acquisition and effector controlling exercises have been tested and verified.

The indoor positioning system is a series of networking systems used to monitor/locate objects at indoor area as opposed that of GPS which does the same at outdoor. The increase in the popularity of the Internet of Things made the demand for Bluetooth Low Energy technology more and more essential due to their compatibility in the smartphones which makes it to access easier. The BLE’s reliable signal and accuracy in calculating the distance has a cutting edge on others in IPS. In this thesis, the Bluetooth Low Energy indoor positioning system was designed and implemented in the office area, and the positionofIoTdevicesweremonitored. OntheIoTdevices,thebeaconswereplaced. And thesebeaconswerecoveringtheofficearea. Thereceiver,smartphoneinourcase,recorded theReceivedSignalStrengthIndicationofthetransmittedsignalsfromthebeaconswithin the range of the signal and stored the collected data in a database. Two experiments have beenconducted. Oneisforbeaconsthatarestationaryandonethatismoving. Toevaluate these experiments, a few tests were performed to predict the position of beacons based on therecordedreceivedsignalstrength’s. Inthecaseofstationarybeacons, itoffersaccuracy range from 1 m to 5 m, and 3 m to 9.5 m in anticipating the position of each beacon in the case of moving beacon. This methodology was a mixture of fingerprinting and an algorithm of multilateration. Finally, the experiments show that the algorithm used provides the most accurate indoor position using BLE beacons that can be monitored through an Android-based application in real-time.

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.

This thesis explores the possibilities of constructing an indoor positioning system based on Bluetooth Smart technology. Two non-trainable trilateration approaches and two trainable fingerprinting were implemented and evaluated at Mobiento's offices in Stockholm, Sweden. A trilateration approach is based on finding a sought location based on known distances towards know locations, at least three locations and distances are needed. A fingerprinting approach is based on creating a radio map, which describes transmission signals within the room, towards different transmitters. A set amount of coordinates are assigned a fingerprint. These are then used as reference points for a sought location. For each major approach, trilateration and fingerprinting, a weighted approach is conducted. These approaches are evaluated in a disturbance free environment in term of accuracy, implementation and setup. In terms of accuracy, the non-weighted fingerprinting approach performs slightly better than the weighted fingerprinting approaches. Both of these are more accurate than the trilateration approaches. When it comes to implementation and setup, the trilateration algorithms impose less cost. These allow for better scalability when the indoor environment becomes larger.

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.

Denna rapport beskriver ett kandidatarbete som genomfördes i kursen TDDD96 Kandidatprojekt i programvaruutveckling år 2023. Den produkt som framställdes under projektet är en webbapplikation för felsökning av informationsskyltar via Bluetooth och arbetet genomfördes med en agil arbetsmetodik. Syftet med denna rapport är att förklara hur projektgruppen arbetade under kandidatprojektet och skapade värde för kunden, samt att belysa både tekniska lärdomar och andra erfarenheter som projektgruppen fick under arbetet. Rapporten beskriver överförbar kunskap gällande projektarbeten respektive utveckling med Bluetooth som kan vara användbar i framtida projekt. För att dokumentera erfarenheter, skapa värde för kunden och förbättra arbetsprocessen under projektet genomfördes mätningar, testning, informationssamling, prototypframställning och utvärderingsmöten i form av retrospektiv och en muddy-cards-utvärdering.  Projektgruppen har utvecklat en webbapplikation som använder sig av Web Bluetooth API för att hämta en godtyckligt stor fil givet att användaren skriver in dess sökväg i felsökningsapplikationen. För att skicka filer av godtycklig storlek delas de upp i paket som alla skickas separat. En av de främsta fördelarna med det använda API:t är att ingen nedladdning eller installation krävs men en stor nackdel är att det inte är kompatibelt med alla webbläsare. Vidare har erfarenheter såsom för- och nackdelar med mobbprogrammering, vikten av olika sprintlängder, antal scrum-möten samt uppdelning av arbete dokumenterats. Under projektet har det även visats att en systemanatomi hjälper utvecklare att dela in och se kopplingar mellan olika delar i ett system samt att kundmöten är centrala för att säkerställa att en beställd produkt är av värde för kunden.