CNN-based Adaptive K for Improving Positioning Accuracy in W-kNN-based LTE Fingerprint Positioning
0
조회
0
다운로드
2
인용
0
참고문헌
키워드
초록
In order to provide a location-based services regardless of indoor or outdoor space, it is important to provide position information of the terminal regardless of location. Among the wireless/mobile communication resources used for this purpose, Long Term Evolution (LTE) signal is a representative infrastructure that can overcome spatial limitations, but the positioning method based on the location of the base station has a disadvantage in that the accuracy is low. Therefore, a fingerprinting technique, which is a pattern recognition technology, has been widely used. The simplest yet widely applied algorithm among Fingerprint positioning technologies is k-Nearest Neighbors (kNN). However, in the kNN algorithm, it is difficult to find the optimal K value with the lowest positioning error for each location to be estimated, so it is generally fixed to an appropriate K value and used. Since the optimal K value cannot be applied to each estimated location, therefore, there is a problem in that the accuracy of the overall estimated location information is lowered. Considering this problem, this paper proposes a technique for adaptively varying the K value by using a Convolutional Neural Network (CNN) model among Artificial Neural Network (ANN) techniques. First, by using the signal information of the measured values obtained in the service area, an image is created according to the Physical Cell Identity (PCI) and Band combination, and an answer label for supervised learning is created. Then, the structure of the CNN is modeled to classify K values through the image information of the measurements. The performance of the proposed technique is verified based on actual data measured in the testbed. As a result, it can be seen that the proposed technique improves the positioning performance compared to using a fixed K value.
Abstract
In order to provide a location-based services regardless of indoor or outdoor space, it is important to provide position information of the terminal regardless of location. Among the wireless/mobile communication resources used for this purpose, Long Term Evolution (LTE) signal is a representative infrastructure that can overcome spatial limitations, but the positioning method based on the location of the base station has a disadvantage in that the accuracy is low. Therefore, a fingerprinting technique, which is a pattern recognition technology, has been widely used. The simplest yet widely applied algorithm among Fingerprint positioning technologies is k-Nearest Neighbors (kNN). However, in the kNN algorithm, it is difficult to find the optimal K value with the lowest positioning error for each location to be estimated, so it is generally fixed to an appropriate K value and used. Since the optimal K value cannot be applied to each estimated location, therefore, there is a problem in that the accuracy of the overall estimated location information is lowered. Considering this problem, this paper proposes a technique for adaptively varying the K value by using a Convolutional Neural Network (CNN) model among Artificial Neural Network (ANN) techniques. First, by using the signal information of the measured values obtained in the service area, an image is created according to the Physical Cell Identity (PCI) and Band combination, and an answer label for supervised learning is created. Then, the structure of the CNN is modeled to classify K values through the image information of the measurements. The performance of the proposed technique is verified based on actual data measured in the testbed. As a result, it can be seen that the proposed technique improves the positioning performance compared to using a fixed K value.
참고문헌 (20)
- Amirisoori, S., "WI-FI Based Indoor Positioning Using Fingerprinting Methods (KNN Algorithm) in Real Environment", International Journal of Future Generation Communication and Networking, 10, pp.23~36 (2017)[DOI]
- Cheng, R. S., "Seamless guidance system combining GPS, BLE beacon, and NFC technologies", Hindawi Publishing Corporation Mobile Information Systems, 1~12 (2016)
- Cho, Y. S., "Feasibility analysis on LTE RSRP fingerprint DB estimation using sparse war-driving collecting data for emergency location", ISGNSS 2019 in conjunction with IPNT Conference proceedings, pp.51~58 (2019)
- Ge, X, "Optimization WIFI indoor positioning KNN algorithm location-based fingerprint", 2016 7th IEEE International Conference on Software Engineering and Service Science (ICSESS), pp.135~137 (2016)
- Huang, H., "Location based services: ongoing evolution and research agenda", Journal of Location Based Services, 12, pp.63~93 (2018)[DOI]
- Ismail, A. H., "WiFi RSS Fingerprint Database Construction for Mobile Robot Indoor Positioning System", 2016 IEEE International Conference on Systems, Man, and Cybernetics (SMC), pp.1561~1566 (2016)
- Adam: A Method for Stochastic Optimization, "Kingma, D. P.", ICLR, 1~15 (2015)
- Kolodziej, K. W., "Local positioning systems: LBS applications and Services" (2006), Taylor & Francis Group
- Li, B., "Method for yielding a database of location fingerprints in WLAN", IEE Proceedings - Communications, 152, pp.580~586 (2005)[DOI]
- Li, H., "Location Privacy Protection Scheme for LBS in IoT", Wireless Communications and Mobile Computing, 2021, pp.9948543~ (2021)
- Lin, T. -N., "A group-discrimination-based access point selection for wlan fingerprint ing localization", IEEE Transactions on Vehicular Technology, 63, pp.3967~3976 (2014)[DOI]
- Liu, Y., "Location, Localization, and Localizability", Journal of computer science and technology, 25, pp.274~297 (2010)[DOI]
- Njima, W., "Deep CNN for Indoor Localization in IoT-Sensor Systems", Sensors, 19, pp.3127~ (2019)[DOI]
- 오종택, "Adaptive K-nearest neighbour algorithm for WiFi fingerprint positioning", ICT Express, 4(2), pp.91~94 (2018), 한국통신학회
- Pecoraro, G., "CSI-based fingerprinting for indoor localization using LTE Signals", Eurasip Journal on Advances in Signal Processing, 2018, pp.274~297 (2018)
- Rose, N. D. R., "3D Trilateration Localization using RSSI in Indoor Environment", International Journal of Advanced Computer Science and Applications, 11, pp.385~391 (2020)[DOI]
- Sinha, R. S., "Comparison of CNN Applications for RSSI-Based Fingerprint Indoor Localization", Electronics, 8, pp.989~ (2019)[DOI]
- Subedi, S., "A Survey of Smartphone-Based Indoor Positioning System Using RF-Based Wireless Technologies", Sensors, 20, pp.7230~ (2020)[DOI]
- Vo, Q. D., "A survey of fingerprint-based outdoor localization", IEEE Communications Surveys & Tutorials, 18, pp.491~506 (2016)[DOI]
- Xia, S., "Indoor Fingerprint Positioning Based on Wi-Fi: An Overview", ISPRS International Journal of Geo-Information, 6, pp.135~ (2017)[DOI]