Received Signal Strength Fingerprinting-Based Indoor Location Estimation Employing Machine Learning
The fingerprinting technique is a popular approach to reveal location of persons, instruments or devices in an indoor environment. Typically based on signal strength measurement, a power level map is created first in the learning phase to align with measured values in the inference. Second, the loca...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-07-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/13/4605 |
| _version_ | 1797527873876131840 |
|---|---|
| author | Ladislav Polak Stanislav Rozum Martin Slanina Tomas Bravenec Tomas Fryza Aggelos Pikrakis |
| author_facet | Ladislav Polak Stanislav Rozum Martin Slanina Tomas Bravenec Tomas Fryza Aggelos Pikrakis |
| author_sort | Ladislav Polak |
| collection | DOAJ |
| description | The fingerprinting technique is a popular approach to reveal location of persons, instruments or devices in an indoor environment. Typically based on signal strength measurement, a power level map is created first in the learning phase to align with measured values in the inference. Second, the location is determined by taking the point for which the recorded received power level is closest to the power level actually measured. The biggest limit of this technique is the reliability of power measurements, which may lack accuracy in many wireless systems. To this end, this work extends the power level measurement by using multiple anchors and multiple radio channels and, consequently, considers different approaches to aligning the actual measurements with the recorded values. The dataset is available online. This article focuses on the very popular radio technology Bluetooth Low Energy to explore the possible improvement of the system accuracy through different machine learning approaches. It shows how the accuracy–complexity trade-off influences the possible candidate algorithms on an example of three-channel Bluetooth received signal strength based fingerprinting in a one dimensional environment with four static anchors and in a two dimensional environment with the same set of anchors. We provide a literature survey to identify the machine learning algorithms applied in the literature to show that the studies available can not be compared directly. Then, we implement and analyze the performance of four most popular supervised learning techniques, namely <i>k</i> Nearest Neighbors, Support Vector Machines, Random Forest, and Artificial Neural Network. In our scenario, the most promising machine learning technique being the Random Forest with classification accuracy over 99%. |
| first_indexed | 2024-03-10T09:50:01Z |
| format | Article |
| id | doaj.art-931b26ed16d348779bdac9b059621d74 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T09:50:01Z |
| publishDate | 2021-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-931b26ed16d348779bdac9b059621d742023-11-22T02:51:58ZengMDPI AGSensors1424-82202021-07-012113460510.3390/s21134605Received Signal Strength Fingerprinting-Based Indoor Location Estimation Employing Machine LearningLadislav Polak0Stanislav Rozum1Martin Slanina2Tomas Bravenec3Tomas Fryza4Aggelos Pikrakis5Department of Radio Electronics, Faculty of Electrical Engineering and Communication, Brno University of Technology, Technicka 3082/12, 616 00 Brno, Czech RepublicDepartment of Radio Electronics, Faculty of Electrical Engineering and Communication, Brno University of Technology, Technicka 3082/12, 616 00 Brno, Czech RepublicDepartment of Radio Electronics, Faculty of Electrical Engineering and Communication, Brno University of Technology, Technicka 3082/12, 616 00 Brno, Czech RepublicDepartment of Radio Electronics, Faculty of Electrical Engineering and Communication, Brno University of Technology, Technicka 3082/12, 616 00 Brno, Czech RepublicDepartment of Radio Electronics, Faculty of Electrical Engineering and Communication, Brno University of Technology, Technicka 3082/12, 616 00 Brno, Czech RepublicDepartment of Informatics, University of Piraeus, 185 34 Pireas, GreeceThe fingerprinting technique is a popular approach to reveal location of persons, instruments or devices in an indoor environment. Typically based on signal strength measurement, a power level map is created first in the learning phase to align with measured values in the inference. Second, the location is determined by taking the point for which the recorded received power level is closest to the power level actually measured. The biggest limit of this technique is the reliability of power measurements, which may lack accuracy in many wireless systems. To this end, this work extends the power level measurement by using multiple anchors and multiple radio channels and, consequently, considers different approaches to aligning the actual measurements with the recorded values. The dataset is available online. This article focuses on the very popular radio technology Bluetooth Low Energy to explore the possible improvement of the system accuracy through different machine learning approaches. It shows how the accuracy–complexity trade-off influences the possible candidate algorithms on an example of three-channel Bluetooth received signal strength based fingerprinting in a one dimensional environment with four static anchors and in a two dimensional environment with the same set of anchors. We provide a literature survey to identify the machine learning algorithms applied in the literature to show that the studies available can not be compared directly. Then, we implement and analyze the performance of four most popular supervised learning techniques, namely <i>k</i> Nearest Neighbors, Support Vector Machines, Random Forest, and Artificial Neural Network. In our scenario, the most promising machine learning technique being the Random Forest with classification accuracy over 99%.https://www.mdpi.com/1424-8220/21/13/4605Bluetoothfingerprintingindoor navigationmachine learning |
| spellingShingle | Ladislav Polak Stanislav Rozum Martin Slanina Tomas Bravenec Tomas Fryza Aggelos Pikrakis Received Signal Strength Fingerprinting-Based Indoor Location Estimation Employing Machine Learning Sensors Bluetooth fingerprinting indoor navigation machine learning |
| title | Received Signal Strength Fingerprinting-Based Indoor Location Estimation Employing Machine Learning |
| title_full | Received Signal Strength Fingerprinting-Based Indoor Location Estimation Employing Machine Learning |
| title_fullStr | Received Signal Strength Fingerprinting-Based Indoor Location Estimation Employing Machine Learning |
| title_full_unstemmed | Received Signal Strength Fingerprinting-Based Indoor Location Estimation Employing Machine Learning |
| title_short | Received Signal Strength Fingerprinting-Based Indoor Location Estimation Employing Machine Learning |
| title_sort | received signal strength fingerprinting based indoor location estimation employing machine learning |
| topic | Bluetooth fingerprinting indoor navigation machine learning |
| url | https://www.mdpi.com/1424-8220/21/13/4605 |
| work_keys_str_mv | AT ladislavpolak receivedsignalstrengthfingerprintingbasedindoorlocationestimationemployingmachinelearning AT stanislavrozum receivedsignalstrengthfingerprintingbasedindoorlocationestimationemployingmachinelearning AT martinslanina receivedsignalstrengthfingerprintingbasedindoorlocationestimationemployingmachinelearning AT tomasbravenec receivedsignalstrengthfingerprintingbasedindoorlocationestimationemployingmachinelearning AT tomasfryza receivedsignalstrengthfingerprintingbasedindoorlocationestimationemployingmachinelearning AT aggelospikrakis receivedsignalstrengthfingerprintingbasedindoorlocationestimationemployingmachinelearning |