A novel hybrid model for bluetooth low energy-based indoor localization using machine learning in the internet of things

Yıl 2024, Cilt: 30 Sayı: 1, 36 - 43, 29.02.2024

Yasin Görmez Halil Arslan Yunus Emre Işık Sercan Tomaç

Öz

Indoor localization involves pinpointing the location of an object in an interior space and has several applications, including navigation, asset tracking, and shift management. However, this technology has not yet been perfected, and many methods, such as triangulation, Kalman filters, and machine learning models have been proposed to address indoor localization problems. Unfortunately, these methods still have a large degree of error that makes them ill-suited for difficult cases in real-time. In this study, we propose a hybrid model for Bluetooth low energy-based indoor localization. In this model, the triangulation method is combined with several machine learning methods (naïve Bayes, k-nearest neighbor, logistic regression, support vector machines, and artificial neural networks) that are optimized and tested in three different environments. In the experiment, the proposed model performed similarly to the solo triangulation model in easy and medium cases; however, the proposed model obtained a much smaller degree of error for hard cases than either solo triangulation or machine learning models alone.

Anahtar Kelimeler

Internet of Things, Indoor localization, Bluetooth low energy, Machine learning, Triangulation

Nesnelerin internetinde iç mekân lokalizasyonu için makine öğrenimini kullanan bluetooth düşük enerji tabanlı özgün hibrit model

Öz

İç mekân konumlandırma, bir nesnenin iç mekândaki konumunun tam olarak belirlenmesi olarak tanımlanabilir ve navigasyon, varlık takibi ve vardiya yönetimi olmak üzere bir çok uygulama alanı bulunmaktadır. İç mekân konumlandırma problemlerini çözmek için üçgenleme, Kalman filtreleri ve makine öğrenmesi modelleri gibi birçok yöntem önerilmiştir ancak hala istenilen başarı oranları elde edilememiştir. Bu yöntemler deney ortamlarında başarılı sonuçlar elde etse de, gerçek zamanlı durumlarda hata oranları çok fazla olabilmektedir. Bu çalışmada, Bluetooth düşük enerji tabanlı iç mekân konumlandırma için hibrit bir model önerilmiştir. Bu modelde, üçgenleme yöntemini, üç farklı ortamda optimize edilmiş ve test edilmiş birkaç makine öğrenmesi yöntemiyle (Naive Bayes, k-en yakın komşu, lojistik regresyon, destek vektör makineleri ve yapay sinir ağları) birleştiren hibrit bir yaklaşım kullanılmıştır. Çalışmada önerilen model, kolay ve orta durumlarda üçgenleme modeline benzer şekilde performans göstermiş; ancak önerilen model, zor durumlar için üçgenleme veya tek başına makine öğrenimi modellerinden çok daha küçük bir hata oranı elde etmiştir.

Anahtar Kelimeler

Nesnelerin interneti, İç mekân konumlandırma, Buluetooth düşük enerji, Makine öğrenmesi, Üçgenleme

Kaynakça

• [1] Calderoni L, Ferrara M, Franco A, Maio D. “Indoor localization in a hospital environment using Random Forest classifiers”. Expert Systems with Application, 42(1), 125-134, 2015.
• [2] Álvarez-Díaz N, Caballero-Gil P. “Decision support system based on indoor location for personnel management”. Remote Sensors, 13(2), 248-257, 2021.
• [3] Beaconstac. “10 Airports Using Beacons to Take Passenger Experience to the Next Level”. https://blog.beaconstac.com/2016/03/10-airports-using-beacons-to-take-passenger-experience-to-the-next-level (2023).
• [4] Jianyong Z, Haiyong L, C. Zili, Zhaohui L. “RSSI based bluetooth low energy indoor positioning”. International Conference on Indoor Positioning and Indoor Navigation, Buson, Korea, 27-30 October 2014.
• [5] Mussina A, Aubakirov S. “RSSI based bluetooth low energy indoor positioning”. IEEE 12th International Conference on Application of Information and Communication Technologies (AICT), Almaty, Kazkhstan, 17-19 October 2018.
• [6] Yoon PK, Zihajehzadeh S, Kang BS, Park EJ. “Adaptive Kalman filter for indoor localization using Bluetooth Low Energy and inertial measurement unit”. 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Milan, Italy, 25-29 August 2015.
• [7] Xu B, Zhu X, Zhu H. “An efficient indoor localization method based on the long short-term memory recurrent neuron network”. IEEE Access, 7(1), 123912-123921, 2019.
• [8] Dinh TMT, Duong NS, Sandrasegaran K. “Smartphone-based indoor positioning using BLE iBeacon and reliable lightweight fingerprint MAP”. IEEE Sensors Journal, 20(17), 10283-10294, 2020.
• [9] Iqbal Z, Luo D, Henry P, Kazemifar S, Rozario T, Yan Y, Westover K, Lu W, Nguyen D, Long T, Wang J, Choy H, Jiang S. “Accurate real time localization tracking in a clinical environment using bluetooth low energy and deep learning”. Plos One, 13(10), 205392-205393, 2018.
• [10] Giuliano R, Cardarilli GC, Ceserani C, Di Nunzio L, Fallucchi F, Fazzolari R, Mazzenga F, Re M, Vizzarri A. “Indoor localization system based on bluetooth low energy for museum applications”. Electronics, 9(6), 1055-1056, 2020.
• [11] Peng Y, Fan W, Dong X, Zhang X. “An iterative weighted KNN (IW-KNN) based indoor localization method in bluetooth low energy (BLE) environment”. International IEEE Conferences on Ubiquitous Intelligence Computing, Advanced and Trusted Computing, Scalable Computing and Communications, Cloud and Big Data Computing, Internet of People, and Smart World Congress, Toulouse, France, 18-21 July 2016.
• [12] Terán M, Aranda J, Carrillo H, Mendez D, Parra C. “IoT-Based system for indoor location using bluetooth low energy”. IEEE Colombian Conference on Communications and Computing (COLCOM), Cartagena, Colombia, 16-18 August 2017.
• [13] Baronti P, Barsocchi P, Chessa S, Mavilia F, Palumbo F. “Indoor bluetooth low energy dataset for localization, tracking, occupancy, and social interaction”. Sensors, 18(12), 4462-4464, 2018.
• [14] Sadowski S, Spachos P. “RSSI-Based indoor localization with the internet of things”. IEEE Access, 6(1), 30149-30161, 2018.
• [15] Hou X, Arslan T. “Monte Carlo localization algorithm for indoor positioning using Bluetooth low energy devices”. International Conference on Localization and GNSS, Nottingham, United Kingdom, 27-29 July 2017.
• [16] Röbesaat J, Zhang P, Abdelaal M, Theel O. “An improved BLE indoor localization with kalman-based fusion: an experimental study”. Sensors, 17(5), 951-977, 2017.
• [17] Mackey A, Spachos P. “Performance evaluation of beacons for indoor localization in smart buildings”. IEEE Global Conference on Signal and Information Processing, Montreal, Canada, 14-16 November 2017.
• [18] Ji M, Kim J, Jeon J, Cho Y. “Analysis of positioning accuracy corresponding to the number of BLE beacons in indoor positioning system”. 17th International Conference on Advanced Communication Technology, PyeongChang, South Korea, 1-3 July 2015.
• [19] Qureshi UM, Umair Z, Duan Y, Hancke GP. “Analysis of Bluetooth Low Energy (BLE) based indoor localization system with multiple transmission power levels”. IEEE 27th International Symposium on Industrial Electronics, Cairns, Australia,13-15 June 2018.
• [20] Kayış O, Çakmak Y, Utku S. “Indoor navigation system with using mobile devices”. Pamukkale University Journal of Engineering Sciences, 24(2), 238-245, 2018.
• [21] Hou X, Arslan T, Juri A, Wang F. “Indoor localization for bluetooth low energy devices using weighted off-set triangulation algorithm”. Proceedings of the 29th International Technical Meeting of the Satellite Division of The Institute of Navigation, Portland, USA, 12-16 September 2016.
• [22] Yu X, Wang H, Wu J. “A method of fingerprint indoor localization based on received signal strength difference by using compressive sensing”. EURASIP Journal on Wireless Communications and Networking, 2020(1), 1-13, 2020.
• [23] Peterson LE. “K-nearest Neighbor”. http://www.scholarpedia.org/article/K-nearest_neighbor (21.02.2009).
• [24] Murphy KP. “Naive Bayes Classifiers”. University of British Columbia, Vancouver , Canada, 18, 2006.
• [25] Amazon Web Services. “Lojistik Regresyon Nedir?-Lojistik Regresyon Modeline Ayrıntılı Bakış-AWS”. https://aws.amazon.com/tr/what-is/logistic-regression (24.02.2023).
• [26] Wright RE. “Logistic regression”. American Psychological Association, 10(2), 217-244, 1995.
• [27] Jain AK, Mao J, Mohiuddin KM. “Artificial neural networks: a tutorial”. Computer, 29(3), 31-44, 1996.
• [28] Noble WS. “What is a support vector machine?”. Nature Biotechnology, 24(12), 1565-1567, 2006.
• [29] Mesut A, Öztürk E. “A method to improve full-text search performance of MongoDB”. Pamukkale University Journal of Engineering Sciences, 28(5), 720-729, 2022.
• [30] This reference is hidden Yasin G, Halil A, Ömer Faruk K. “Efficient and Scalable Broker Design for the Internet of Things Environments”. 28th Signal Processing and Communications Applications Conference (SIU), Gaziantep, Turkey, 05-07 October 2020.
• [31] Gwon Y, Jain R, Kawahara T. “Robust indoor location estimation of stationary and mobile users”. IEEE INFOCOM, Hong Kong, China, 07-11 March 2004.
• [32] scikit-learn: machine learning in Python. “Scikit-Learn 0.23.2 Documentation”. https://scikit-learn.org/stable/ (20.10.2020).
• [33] Wikipedia. “Precision and Recall”. https://en.wikipedia.org/w/index.php?title=Precision_and_recall&oldid=1122267443 (24.02.2023).