DNN-based LTE Signal Propagation Modelling for Positioning Fingerprint DB Generation
1
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
In this paper, we propose a signal propagation modeling technique for generating a positioning fingerprint DB based on Long Term Evolution (LTE) signals. When a DB is created based on the location-based signal information collected in an urban area, gaps in the DB due to uncollected areas occur. The spatial interpolation method for filling the gaps has limitations. In addition, the existing gap filling technique through signal propagation modeling does not reflect the signal attenuation characteristics according to directions occurring in urban areas by considering only the signal attenuation characteristics according to distance. To solve this problem, this paper proposes a Deep Neural Network (DNN)-based signal propagation functionalization technique that considers distance and direction together. To verify the performance of this technique, an experiment was conducted in Seocho-gu, Seoul. Based on the acquired signals, signal propagation characteristics were modeled for each method, and Root Mean Squared Errors (RMSE) was calculated using the verification data to perform comparative analysis. As a result, it was shown that the proposed technique is improved by about 4.284 dBm compared to the existing signal propagation model. Through this, it can be confirmed that the DNN-based signal propagation model proposed in this paper is excellent in performance, and it is expected that the positioning performance will be improved based on the fingerprint DB generated through it.
Abstract
In this paper, we propose a signal propagation modeling technique for generating a positioning fingerprint DB based on Long Term Evolution (LTE) signals. When a DB is created based on the location-based signal information collected in an urban area, gaps in the DB due to uncollected areas occur. The spatial interpolation method for filling the gaps has limitations. In addition, the existing gap filling technique through signal propagation modeling does not reflect the signal attenuation characteristics according to directions occurring in urban areas by considering only the signal attenuation characteristics according to distance. To solve this problem, this paper proposes a Deep Neural Network (DNN)-based signal propagation functionalization technique that considers distance and direction together. To verify the performance of this technique, an experiment was conducted in Seocho-gu, Seoul. Based on the acquired signals, signal propagation characteristics were modeled for each method, and Root Mean Squared Errors (RMSE) was calculated using the verification data to perform comparative analysis. As a result, it was shown that the proposed technique is improved by about 4.284 dBm compared to the existing signal propagation model. Through this, it can be confirmed that the DNN-based signal propagation model proposed in this paper is excellent in performance, and it is expected that the positioning performance will be improved based on the fingerprint DB generated through it.
참고문헌 (12)
- J.B. Andersen, "Propagation measurements and models for wireless communications channels", IEEE Communications Magazine, 33(1), pp.42~49 (1995), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
- 조성윤, "LTE Signal Propagation Model-based Fingerprint DB Generation for Positioning in Emergency Rescue Situation", Journal of Positioning, Navigation, and Timing, 9(3), pp.157~167 (2020), 사단법인 항법시스템학회[DOI]
- 조성윤, "위치추정 전자지문기법을 위한 전파전달 모델 및 공간상관기법 기반의 효율적인 데이터베이스 생성", 제어.로봇.시스템학회 논문지, 20(7), pp.774~781 (2014), 제어·로봇·시스템학회[DOI]
- Cho, Y. H., "Study on the activation functions for efficient learning in DNN", IEIE, 11, pp.800~803 (2016)
- Cho, Y. S., "Feasibility analysis on LTE RSRP fingerprint DB estimation using sparse war-driving collecting data for emergency location", ISGNSS 2019proceedings, pp.51~58 (2019)
- Ismail, A. H., "WiFi RSS Fingerprint Database Construction for Moblie Robot Indoor Positioning System", 2016IEEE International Conference on Systems, Man, and Cybernetics (SMC), pp.1561~1566 (2016)
- "Adam : A Method for Stochastic Optimization" (2015)[URL]
- Kolodziej, K. W., "Local positioning systems:LBS applications and Services" (2006), Taylor &Francis Group
- Lee, J. Y., "DNN-based wireless positioning in an outdoor environment", ICASSP, pp.3799~3803 (2018)
- Guoquan Li, "Indoor Positioning Algorithm Based on the Improved RSSI Distance Model", Sensors, 18(9), pp.2820~ (2018), MDPI AG[DOI]
- F. Saez de Adana, "Propagation model based on ray tracing for the design of personal communication systems in indoor environments", IEEE Transactions on Vehicular Technology, 49(6), pp.2105~2112 (2000), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
- Quoc Duy Vo, "A Survey of Fingerprint-Based Outdoor Localization", IEEE Communications Surveys & Tutorials, 18(1), pp.491~506 (2016), Institute of Electrical and Electronics Engineers (IEEE)[DOI]