Supervised machine learning algorithms to determine the location of Wi-Fi devices
DOI:
https://doi.org/10.26439/ciis2022.6074Keywords:
indoor location, machine learning, RSSI, Wi-FiAbstract
This article aims to choose the best-supervised machine learning algorithm for locating a terminal that supports Wi-Fi in a specific scenario. It uses a dataset of 2000 received signal strength indicator (RSSI) records obtained from 7 access points (AP), loaded into eight supervised machine learning algorithms. The algorithm that produces the most accurate prediction is then chosen, even when fewer APs are available. The Naive Bayes algorithm achieved the highest accuracy for the 7AP (99 % accuracy) scenario and for a smaller number of APs. The algorithms based on neural networks had the worst performance. The article proposes future research on the location of Wi-Fi devices indoors.
Downloads
References
AlQahtani, A. A. S., & Choudhury, N. (2021). Machine learning for location prediction using rssi on Wi-Fi 2.4 GHz frequency band. En 2021 IEEE 12th Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON) (pp. 0336-0342). DOI: 10.1109/IEMCON53756.2021.9623104
Bellavista-Parent, V., Torres-Sospedra, J., & Perez-Navarro, A. (2021). New trends in indoor positioning based on WiFi and machine learning: A systematic review. En 2021 International Conference on Indoor Positioning and Indoor Navigation (IPIN) (pp. 1-8). https://doi.org/10.1109/IPIN51156.2021.9662521
Cao, X., Zhuang, Y., Yang, X., Sun, X., & Wang, X. (2021). A universal Wi-Fi fingerprint localization method based on machine learning and sample differences. Satellite Navigation, 2, 27. https://doi.org/10.1186/s43020-021-00058-8
Çelik, H., & Çinar, A. (2021). An application on ensemble learning using KNIME. En 2021 International Conference on Data Analytics for Business and Industry (ICDABI) (pp. 400-403). https://doi.org/10.1109/ICDABI53623.2021.9655815
Chauhan, C., & Sehgal, S. (2018). Sentiment classification for mobile reviews using KNIME. En 2018 International Conference on Computing, Power and Communication Technologies (GUCON) (pp. 548-553). https://doi.org/10.1109/GUCON.2018.8674946
Feltrin, L. (2015). KNIME an open source solution for predictive analytics in the geosciences [Software and data sets]. IEEE Geoscience and Remote Sensing Magazine, 3(4), 28-38. https://doi.org/10.1109/MGRS.2015.2496160
George, D., & Rao, S. (2017). Enabling rural connectivity: long range Wi-Fi versus super Wi-Fi. En 2017 IEEE International Conference on Computational Intelligence and Computing Research (ICCIC) (pp. 1-4). https://doi.org/10.1109/ICCIC.2017.8524142
Insany, G. P., Ayu, M. A., & Mantoro, T. (2021). Using machine learning techniques and Wi-Fi signal strength for determining indoor user location. En 2021 IEEE 7th International Conference on Computing, Engineering and Design (ICCED). doi: 10.1109/ICCED53389.2021.9664859
Jayant G., R., Perumal, B., Narayanan, S., Thakur, P., & Bhatt, R. (2017). User localization in an indoor environment using Fuzzy Hybrid of Particle Swarm Optimization & Gravitational Search Algorithm with Neural Networks. En Proceedings of Sixth International Conference on Soft Computing for Problem Solving, Advances in Intelligent Systems and Computing (vol. 546). https://doi.org/10.1007/978-981-10-3322-3_27
KNIME. (s. f.). KNIME Open Source Story. https://www.knime.com/knime-open-source-story
KNIME. (2020, 25 de junio). Classification_and_Predictive_Modelling. https://hub.knime.com/knime/spaces/Examples/latest/04_Analytics/04_Classification_and_Predictive_Modelling
Koovimol, P., & Pattaramalai, S. (2021). Experimental machine learning for RSSI fingerprint in indoor WiFi localization. En 2021 18th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technology (ECTI-CON) (pp. 1018-1021). DOI: 10.1109/ECTI-CON51831.2021.9454865
Maaloul, K., Abdelhamid, N. M., & Lejdel, B. (2022). Machine learning based indoor localization using Wi-Fi and smartphone in a shopping malls. En B. Lejdel, E. Clementini & L. Alarabi (Eds.), Artificial Intelligence and Its Applications. AIAP 2021. Lecture Notes in Networks and Systems (vol. 413). https://doi.org/10.1007/978-3-030-96311-8_1
Muenzberg, A., Sauer, J., Hein, A., & Roesch, N. (2019). Checking the plausibility of nutrient data in food datasets using KNIME and big data. En 2019 International Conference on Wireless and Mobile Computing, Networking and Communications (WiMob). https://doi.org/10.1109/WiMOB.2019.8923233
Sabanci, K., Yigit, E., Ustun, D., Toktas, A., & Aslan, M. (2018). WiFi based indoor localization: Application and comparison of machine learning algorithms. En 2018 XXIIIrd International Seminar/Workshop on Direct and Inverse Problems of Electromagnetic and Acoustic Wave Theory (DIPED) (pp. 246-251). https://doi.org/10.1109/DIPED.2018.8543125
Singh, N., Choe, S., & Punmiya, R. (2021). Machine learning based indoor localization using Wi-Fi RSSI fingerprints: An overview. IEEE Access, 9, 127150-127174. https://doi.org/10.1109/ACCESS.2021.3111083
Tahat, A., Awwad, R., Baydoun, N., Al-Nabih, S., & Edwan, T. A. (2021). An empirical evaluation of machine learning algorithms for indoor localization using dual-band WiFi. En 2021 2nd European Symposium on Software Engineering (pp. 106-111). https://doi.org/10.1145/3501774.3501790
Universidad de California en Irvine. (2017, 4 de diciembre). Wireless Indoor Localization, by Rajen Bhatt [Dataset]. Machine Learning Repository. https://archive-beta.ics.uci.edu/ml/datasets/wireless+indoor+localization
Wadhwa, S., Rai, P., & Kaushik, R. (2019). Machine learning based indoor localization using wi-fi fingerprinting. International Journal of Recent Technology and Engineering, 8(3), 502-506. https://doi.10.35940/ijrte.A2133.098319
Xue, J., Liu, J., Sheng, M., Shi, Y., & Li, J. (2020). A WiFi fingerprint based high-adaptability indoor localization via machine learning. China Communications, 17(7), 247-259. https://doi.org/10.23919/J.CC.2020.07.018
Xun, W., Sun, L., Han, C., Lin, Z., & Guo, J. (2020). Depthwise separable convolution based passive indoor localization using CSI Fingerprint. En 2020 IEEE Wireless Communications and Networking Conference (WCNC) (pp. 1-6). https://doi.org/10.1109/WCNC45663.2020.9120638
