Paper ID: 7562

A Coal Mine Underground Localization Algorithm Based on the Feature Vector

Guo Yinjing, Song Xianqi, Yang Lei& Lv Wenhong

Shandong University of Science and Technology, No. 579, Qianwan'gang Road, Qingdao Economic & Technical Development Zone, Qingdao City, Shandong Province, 266510, PRC




To enhance the position estimation accuracy of an underground localization system in a coal mine roadway, an algorithm based on the feature vector of received signals is presented in this paper. The algorithm includes three steps: the construction process of the feature vector database and distance database, the vector matching process and the localization process. When a signal vector is received, it only needs to calculate the distance from the received vector to the center vector of each subset, and then compare it with the data in the distance database. After multiple filtering and comparing the source of the strongest signal, the coordinates closest to the received vector can be found. Finally, compared with KNN and WKNN algorithm, the experiment shows that the maximum error of this algorithm is 4 meters, the average error is 1.62 meters. In addition, within 1 meter of localization error, the X-axis localization accuracy is 98%, and the Y-axis localization accuracy is 86%. What is more, the algorithm takes much less time than the first two algorithms. so the algorithm can meet the requirements of coal mine safety system and underground   personnel localization system.

Keywords: underground localization algorithm; RSSI; feature vector; database construction; FVMA.


Taniura, Y. & Oguchi, K., Indoor Location Recognition Method Using RSSI Values wn System with Small Wireless Nodes, Telecommunications and Signal Processing (TSP). Ieee Communications Letters, 40, pp. 52-55, 2017.

Weixing, X. & Weining, Q., Improved Wi-Fi RSSI Measurement for Indoor Localization, Ieee Sensors Journal, 17(7), pp. 2224-2230, 2017.

Simon, Y. & Marzieh, D., Wireless RSSI Fingerprinting Localization, Signal Processing, 131, pp. 235-244, 2017.

Jin, L. & Yinjing, G., Design of Underground Wireless Positioning System Based on Fingerprint Algorithm, QingDao:Shandong University of Science and Technology, pp.47-45, 2013.

Shengyi, J., Pang Guansong,Wu Meiling.An Improved K-Nearest-Neighbor Algorithm for Text Categorization, Expert Systems with Applications, 29(1), pp. 1503-1509, 2012.

Shaowu, M., Huanguo, Z. & Chongchao, H., Application of Improved K Shortest Path Algorithm in Communication Network, Journal of Wuhan University (Science Edition), 5(6), pp. 534-538, 2013.

Lakmali, B.D.S. & Dias, D., Database Correlation for GSM Location in Outdoor & Indoor Environments, International Conference on Information and Automation for Sustainability, pp. 42-47,2008.

Chunyan, L. & Wangjian., Constrained KNN Indoor Positioning Model Based on Set Clustering Fingerprint Database [J], Journal of Wuhan University Information Science Edition, 39(11), pp:1287-1292, Nov.2014.

Kong, C., Chunlei, S. & Jiabin, C., Positioning Fingerprint Indoor Positioning Algorithm Based on Improved WKNN [J]. Navigation Positioning and Timing, 3(4), pp:58-64, July.2016.

Lu, Y., The Design of Underground Personnel Positioning System Based on Improved Weighted Centroid Algorithm, China Mining Magazine. 26(2), pp. 169-173, 2017.

Yazhou, Z. & WuFei, Wifi Indoor Location Baesd on K-means, Proceedings of 2016 International Conference On Audio, Language and Image Processing (ICALIP), pp.663-667,2017.

Abdullah, O. & Abdel-Qader, I., K-Means-Jensen-Shannon Divergence for a WLAN Indoor Positioning System, 7th IEEE Annual Ubiquitous Computing, Electronics and Mobile Communication Conference (IEEE UEMCON),Presented at IEEE COMMUNICATION LETTERS, 2016.

Zhou, F. & Lin, K., RSSI Indoor Localization Through A Bayesian StrategyAdvanced Information Technology, Electronic and Automation Control Conference (IAEAC), pp.1975-1979, 2017 IEEE 2nd.

Cheng, Z, & Jiazheng, Y., Bluetooth Indoor Positioning Based on RSSI and Kalman Filter, WIRELESS PERSONAL COMMUNICATIONS, 96(3), pp. 4115-4130, OCT. 2017.

ISSN: 2338-5502