Unlabeled Wi-Fi RSSI Indoor Positioning by Using IMU
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Wi-Fi Received Signal Strength Indicator (RSSI) is considered one of the most important sensor data types for indoor localization. However, collecting a RSSI fingerprint, which consists of pairs of a RSSI measurement set and a corresponding location, is costly and time-consuming. In this paper, we propose a Wi-Fi RSSI learning technique without true location data to overcome the limitations of static database construction. Instead of the true reference positions, inertial measurement unit (IMU) data are used to generate pseudo locations, which enable a trainer to move during data collection. This improves the efficiency of data collection dramatically. From an experiment it is seen that the proposed algorithm successfully learns the unsupervised Wi-Fi RSSI positioning model, resulting in 2 m accuracy when the cumulative distribution function (CDF) is 0.8.
Abstract
Wi-Fi Received Signal Strength Indicator (RSSI) is considered one of the most important sensor data types for indoor localization. However, collecting a RSSI fingerprint, which consists of pairs of a RSSI measurement set and a corresponding location, is costly and time-consuming. In this paper, we propose a Wi-Fi RSSI learning technique without true location data to overcome the limitations of static database construction. Instead of the true reference positions, inertial measurement unit (IMU) data are used to generate pseudo locations, which enable a trainer to move during data collection. This improves the efficiency of data collection dramatically. From an experiment it is seen that the proposed algorithm successfully learns the unsupervised Wi-Fi RSSI positioning model, resulting in 2 m accuracy when the cumulative distribution function (CDF) is 0.8.
참고문헌 (18)
- Abbas, M., "WiDeep: WiFi-based accurate and robust indoor localization system using deep learning", IEEE International Conference on Pervasive Computing and Communications, pp.1~10 (2019)
- Peter Brida, "Algorithm for Dynamic Fingerprinting Radio Map Creation Using IMU Measurements", Sensors, 21(7), pp.2283~ (2021), MDPI AG[DOI]
- Changhao Chen, "IONet: Learning to Cure the Curse of Drift in Inertial Odometry", Proceedings of the AAAI Conference on Artificial Intelligence, 32(1) (2018), Association for the Advancement of Artificial Intelligence (AAAI)[DOI]
- Chen, G., "Measurement-based RSS-multipath neural network indoor positioning technique", IEEE Canadian Conference on Electrical and Computer Engineering (CCECE), pp.1~7 (2014)
- Chong, D., "Indoor location algorithm research based on neural network", International Conference on Signal Processing (ICSP), pp.1499~1502 (2014)
- Xiaoqian Du, "CRCLoc: A Crowdsourcing-Based Radio Map Construction Method for WiFi Fingerprinting Localization", IEEE Internet of Things Journal, 9(14), pp.12364~12377 (2022), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
- Herath, S., "RoNIN: Robust Neural Inertial Navigation in the Wild: Benchmark, Evaluations, and New Methods", IEEE International Conference on Robotics and Automation (ICRA), pp.3146~3152 (2020)
- Baoqi Huang, "An Online Radio Map Update Scheme for WiFi Fingerprint-Based Localization", IEEE Internet of Things Journal, 6(4), pp.6909~6918 (2019), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
- Jedari, E., "Wi-Fi based indoor location positioning employing random forest classifier", International Conference on Indoor Positioning and Indoor Navigation (IPIN), pp.1~5 (2015)
- Minkyu Lee, "Voronoi Tessellation Based Interpolation Method for Wi-Fi Radio Map Construction", IEEE Communications Letters, 16(3), pp.404~407 (2012), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
- 임재욱, "TOA Based Indoor Positioning Algorithm in NLOS Environments", Journal of Positioning, Navigation, and Timing, 10(2), pp.121~130 (2021), 사단법인 항법시스템학회[DOI]
- Liu, J., "AutLoc: Deep Autoencoder for Indoor Localization with RSS Fingerprinting", International Conference on Wireless Communications and Signal Processing (WCSP), pp.1~6 (2018)
- 오종택, "WiFi 핑거프린트 위치추정 방식에서 W-KNN의 가중치에 관한 연구", 한국인터넷방송통신학회 논문지, 17(6), pp.105~111 (2017), 한국인터넷방송통신학회[DOI]
- J. H. Seong, "Selective Unsupervised Learning-Based Wi-Fi Fingerprint System Using Autoencoder and GAN", IEEE Internet of Things Journal, 7(3), pp.1898~1909 (2020), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
- 타이광퉁, "반지도식 자기조직화지도를 이용한 wifi fingerprint 보정 방법", 한국통신학회논문지, 42(2), pp.536~544 (2017), 한국통신학회[DOI]
- 유재현, "준 지도식 GAN을 이용한 와이파이 전자지문 기반 실내 위치 인식", 제어.로봇.시스템학회 논문지, 26(12), pp.1116~1121 (2020), 제어·로봇·시스템학회[DOI]
- 유재현, "A Study of Multi-Target Localization Based on Deep Neural Network for Wi-Fi Indoor Positioning", Journal of Positioning, Navigation, and Timing, 10(1), pp.49~54 (2021), 사단법인 항법시스템학회[DOI]
- Han Zou, "Adversarial Learning-Enabled Automatic WiFi Indoor Radio Map Construction and Adaptation With Mobile Robot", IEEE Internet of Things Journal, 7(8), pp.6946~6954 (2020), Institute of Electrical and Electronics Engineers (IEEE)[DOI]