Indoor Path Recognition Based on Wi-Fi Fingerprints
1
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
The existing indoor localization method using Wi-Fi fingerprinting has a high collection cost and relatively low accuracy, thus requiring integrated correction of convergence with other technologies. This paper proposes a new method that significantly reduces collection costs compared to existing methods using Wi-Fi fingerprinting. Furthermore, it does not require labeling of data at collection and can estimate pedestrian travel paths even in large indoor spaces. The proposed pedestrian movement path estimation process is as follows. Data collection is accomplished by setting up a feature area near an indoor space intersection, moving through the set feature areas, and then collecting data without labels. The collected data are processed using Kernel Linear Discriminant Analysis (KLDA) and the valley point of the Euclidean distance value between two data is obtained within the feature space of the data. We build learning data by labeling data corresponding to valley points and some nearby data by feature area numbers, and labeling data between valley points and other valley points as path data between each corresponding feature area. Finally, for testing, data are collected randomly through indoor space, KLDA is applied as previous data to build test data, the K-Nearest Neighbor (K-NN) algorithm is applied, and the path of movement of test data is estimated by applying a correction algorithm to estimate only routes that can be reached from the most recently estimated location. The estimation results verified the accuracy by comparing the true paths in indoor space with those estimated by the proposed method and achieved approximately 90.8% and 81.4% accuracy in two experimental spaces, respectively.
Abstract
The existing indoor localization method using Wi-Fi fingerprinting has a high collection cost and relatively low accuracy, thus requiring integrated correction of convergence with other technologies. This paper proposes a new method that significantly reduces collection costs compared to existing methods using Wi-Fi fingerprinting. Furthermore, it does not require labeling of data at collection and can estimate pedestrian travel paths even in large indoor spaces. The proposed pedestrian movement path estimation process is as follows. Data collection is accomplished by setting up a feature area near an indoor space intersection, moving through the set feature areas, and then collecting data without labels. The collected data are processed using Kernel Linear Discriminant Analysis (KLDA) and the valley point of the Euclidean distance value between two data is obtained within the feature space of the data. We build learning data by labeling data corresponding to valley points and some nearby data by feature area numbers, and labeling data between valley points and other valley points as path data between each corresponding feature area. Finally, for testing, data are collected randomly through indoor space, KLDA is applied as previous data to build test data, the K-Nearest Neighbor (K-NN) algorithm is applied, and the path of movement of test data is estimated by applying a correction algorithm to estimate only routes that can be reached from the most recently estimated location. The estimation results verified the accuracy by comparing the true paths in indoor space with those estimated by the proposed method and achieved approximately 90.8% and 81.4% accuracy in two experimental spaces, respectively.
참고문헌 (21)
- Aarons, L., "Sparse data analysis", European journal of drug metabolism and pharmacokinetics, 18, pp.97~100 (1993)[DOI]
- Chriki, A., "SVM-based indoor localization in wireless sensor networks", 13th international wireless communications and mobile computing conference (IWCMC) (2017), IEEE
- Dabove, P., "Indoor positioning using Ultra-wide band (UWB) technologies: Positioning accuracies and sensors' performances", IEEE, 2018, 175~184
- Andreas Daffertshofer, "PCA in studying coordination and variability: a tutorial", Clinical Biomechanics, 19(4), pp.415~428 (2004), Elsevier BV[DOI]
- Rene Hansen, "Algorithmic strategies for adapting to environmental changes in 802.11 location fingerprinting", Proc. IEEE Indoor Positioning and Indoor Navigation (IPIN), pp.1~10 (2010), IEEE
- Jin, G. Y., "An indoor localization mechanism using active RFID tag", International Conference on Sensor Networks, Ubiquitous, and Trustworthy Computing (SUTC'06) (2006), IEEE
- Kaemarungsi, K., "Efficient design of indoor positioning systems based on location fingerprinting", 2005 International Conference on Wireless Networks, Communications and Mobile Computing, pp.181~186 (2005), IEEE
- Kaune, R., "Accuracy studies for TDOA and TOA localization", 2012 15th International Conference on Information Fusion, pp.408~415 (2012)
- James M. Keller, "A fuzzy K-nearest neighbor algorithm", IEEE Transactions on Systems, Man, and Cybernetics, SMC-15(4), pp.580~585 (1985), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
- Leu, J. -S., "Received signal strength fingerprint and footprint assisted indoor positioning based on ambient Wi-Fi signals", Proc. IEEE Veh. Technol. Conf. ( V TC Spring), pp.1~5 (2012)
- Chuanhua Lu, "Indoor Positioning System Based on Chest-Mounted IMU", Sensors, 19(2), pp.420~ (2019), MDPI AG[DOI]
- Mainetti, L., "A survey on indoor positioning systems", IEEE, 22nd international conference on software, telecommunications and computer networks (SoftCOM), pp.111~120 (2014)
- German Martin Mendoza-Silva, "Environment-Aware Regression for Indoor Localization Based on WiFi Fingerprinting", IEEE Sensors Journal, 22(6), pp.4978~4988 (2022), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
- Mika, S., "Fisher discriminant analysis with kernels", Neural networks for signal processing IX: Proceedings of the 1999 IEEE Signal Processing Society Workshop (Cat. No.98TH8468) (1999)
- Parlett, B. N., "The symmetric eigenvalue problem" (1998), Society for industrial and Applied Mathematics
- So, J., "An improved location estimation method for Wi-Fi fingerprint-based indoor localization", International Journal of Software Engineering, and Its Applications, 7, pp.77~86 (2013)[DOI]
- Shixiong Xia, "Indoor Fingerprint Positioning Based on Wi-Fi: An Overview", ISPRS International Journal of Geo-Information, 6(5), pp.135~ (2017), MDPI AG[DOI]
- Xu, J., "AOA Cooperative Position Localization", IEEE GLOBECOM 2008 - 2008 IEEE Global Telecommunications Conference, pp.1~5 (2008)
- Yamasaki, R., "TDOA location system for IEEE 802.11b WLAN", IEEE Wireless Communications and Networking Conference, pp.2338~2343 (2005)
- 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]
- Yuan Zhuang, "Smartphone-Based Indoor Localization with Bluetooth Low Energy Beacons", Sensors, 16(5), pp.596~ (2016), MDPI AG[DOI]