Performance Comparison of Machine Learning Algorithms for Received Signal Strength-Based Indoor LOS/NLOS Classification of LTE Signals
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
An indoor navigation system that utilizes long-term evolution (LTE) signals has the benefit of no additional infrastructure installation expenses and low base station database management costs. Among the LTE signal measurements, received signal strength (RSS) is particularly appealing because it can be easily obtained with mobile devices. Propagation channel models can be used to estimate the position of mobile devices with RSS. However, conventional channel models have a shortcoming in that they do not discriminate between line-of-sight (LOS) and non-line-of-sight (NLOS) conditions of the received signal. Accordingly, a previous study has suggested separated LOS and NLOS channel models. However, a method for determining LOS and NLOS conditions was not devised. In this study, a machine learning-based LOS/NLOS classification method using RSS measurements is developed. We suggest several machine-learning features and evaluate various machinelearning algorithms. As an indoor experimental result, up to 87.5% classification accuracy was achieved with an ensemble algorithm. Furthermore, the range estimation accuracy with an average error of 13.54 m was demonstrated, which is a 25.3% improvement over the conventional channel model.
Abstract
An indoor navigation system that utilizes long-term evolution (LTE) signals has the benefit of no additional infrastructure installation expenses and low base station database management costs. Among the LTE signal measurements, received signal strength (RSS) is particularly appealing because it can be easily obtained with mobile devices. Propagation channel models can be used to estimate the position of mobile devices with RSS. However, conventional channel models have a shortcoming in that they do not discriminate between line-of-sight (LOS) and non-line-of-sight (NLOS) conditions of the received signal. Accordingly, a previous study has suggested separated LOS and NLOS channel models. However, a method for determining LOS and NLOS conditions was not devised. In this study, a machine learning-based LOS/NLOS classification method using RSS measurements is developed. We suggest several machine-learning features and evaluate various machinelearning algorithms. As an indoor experimental result, up to 87.5% classification accuracy was achieved with an ensemble algorithm. Furthermore, the range estimation accuracy with an average error of 13.54 m was demonstrated, which is a 25.3% improvement over the conventional channel model.
참고문헌 (32)
- Al-Hourani, A., "Modeling air-to-ground path loss for low altitude platforms in urban environments", 2014 IEEE GLOBECOM, pp.2898~2904 (2014)
- Angelis, G. D., "GNSS", cellular hybrid positioning system for mobile users in urban scenarios, 2012, pp.14, 313~321
- Barral, V., "NLOS classification based on RSS and ranging statistics obtained from low-cost UWB devices", Proc. EUSIPCO, pp.1~5 (2019)
- Dabove, P, "Towards high accuracy GNSS real-time positioning with smartphones", Advances in Space Research, 63, pp.94~102 (2019)[DOI]
- Dong, Y., "Real-time NLOS", LOS identification for smartphone-based indoor positioning systems using WiFi RTT and RSS, 2022, pp.22, 5199~5209
- Esrafilian, O., "Threedimensional-map-based trajectory design in UAVaided wireless localization systems", IEEE Internet of Things Journal, 8, pp.9894~9904 (2020)[DOI]
- Fan, J, "Non-line-of-sight identification based on unsupervised machine learning in ultra wideband systems", IEEE Access, 7, pp.32464~32471 (2019)[DOI]
- Fang, S. H., "An enhanced ZigBee indoor positioning system with an ensemble approach", IEEE Communications Letters, 16, pp.564~567 (2012)[DOI]
- Jayaweera, S. K, "On the capacity of multiple-antenna systems in Rician fading", IEEE Transactions on Wireless Communications, 4, pp.1102~1111 (2005)[DOI]
- Jia, M., "Ground vehicle navigation integrity monitoring for multi-constellation GNSS fused with cellular signals of opportunity", Proc. ITSC, 19-22 Sept 2021, pp.3978~3983 (2021)
- Jiang, C., "UWB NLOS", LOS classification using deep learning method, 2020, pp.24, 2226~2230
- 강태원, "LTE 신호의 CRS를 이용한 TOA 기반 거리 측정 방법", 한국항행학회논문지, 23(5), pp.437~443 (2019), 한국항행학회
- Lee, H., "Neural network-based ranging with LTE channel impulse response for localization in indoor environments", Proc. ICCAS, pp.939~944 (2020)
- 이하림, "도심 지역 LTE 측위 기반 무인항공기 안전거리 생성 알고리즘 연구 및 시각화 도구 개발", 한국항행학회논문지, 23(5), pp.408~414 (2019), 한국항행학회
- Lee, H., "Optimal parameter inflation to enhance the availability of single-frequency GBAS for intelligent air transportation", IEEE Transactions on Intelligent Transportation Systems, 23, pp.17801~17807 (2022)[DOI]
- Lee, H, "LTE RSS-based positioning method using separated LOS and NLOS channel models", Proc. 2022 IPNT Conference, pp.69~72 (2022)
- Lee, H., "Urban road safety prediction: A satellite navigation perspective", IEEE Intelligent Transportation Systems Magazine, 14, pp.94~106 (2022)[DOI]
- Lee, J., "Monitoring and mitigation of ionospheric anomalies for GNSS-based safety critical systems", IEEE Signal Processing Magazine, 34, pp.96~110 (2017)[DOI]
- Li, X, "Collaborative localization with received-signal strength in wireless sensor networks", IEEE Transactions on Vehicular Technology, 56, pp.3807~3817 (2007)[DOI]
- Marano, S., "NLOS identification and mitigation for localization based on UWB experimental data", IEEE Journal on selected areas in communications, 28, pp.1026~1035 (2010)[DOI]
- Montavon, G., "Methods for interpreting and understanding deep neural networks", Digital signal processing, 73, pp.1~15 (2018)[DOI]
- Noble, W. S, "What is a support vector machine?", Nature biotechnology, 24, pp.1565~1567 (2006)[DOI]
- Sagi, O, "Ensemble learning: A survey", Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 8, pp.e1249~ (2018)[DOI]
- Seo, J., "Availability impact on GPS aviation due to strong ionospheric scintillation", IEEE Transactions on Aerospace and Electronic Systems, 47, pp.1963~1973 (2011)[DOI]
- Shamaei, K., "Exploiting LTE signals for navigation: Theory to implementation", IEEE Transactions on Wireless Communication, 17, pp.2173~2189 (2018)[DOI]
- Tepedelenlioglu, C., "The Ricean K factor: estimation and performance analysis", IEEE Transactions on Wireless Communications, 2, pp.799~810 (2003)[DOI]
- Uradzinski, M., "Advanced indoor positioning using zigbee wireless technology", Wireless Personal Communications, 97, pp.6509~6518 (2017)[DOI]
- Williams, C. K, "Gaussian processes for machine learning" (2006), MIT press
- Xiao, C., "Statistical simulation models for Rayleigh and Rician fading", Proc. IEEE ICC '03, pp.3524~3529 (2003)
- Xiao, Z., "Non-line-of-sight identification and mitigation using received signal strength", IEEE Transactions on Wireless Communications, 14, pp.1689~1702 (2014)[DOI]
- Yang, C, "WiFi-based indoor positioning", IEEE Communications Magazine, 53, pp.150~157 (2015)[DOI]
- Zheng, Y. R, "Simulation models with correct statistical properties for Rayleigh fading channels", IEEE Transactions on communications, 51, pp.920~928 (2003)[DOI]