DEDF: lightweight WSN distance estimation using RSSI data distribution-based fingerprinting

• Published in: Neural computing & applications Vol. 27; no. 6; pp. 1567 - 1575
• Main Authors: Luo, Qinghua, Yan, Xiaozhen, Li, Junbao, Peng, Yu, Tang, Yumei, Wang, Jiaqi, Wang, Dan
• Format: Journal Article
• Language: English
• Published: London Springer London 01.08.2016
• Subjects: Artificial Intelligence; Computational Biology/Bioinformatics; Computational Science and Engineering; Computer Science; Data Mining and Knowledge Discovery; Image Processing and Computer Vision; Original Article; Probability and Statistics in Computer Science; Wireless sensor network; Distance estimation; Fingerprinting; Distribution
• ISSN: 0941-0643; 1433-3058
• DOI: 10.1007/s00521-015-1956-2

When estimating the distance for wireless sensor networks (WSNs), we always suppose that a fixed curve model exists between the received signal strength indicator (RSSI) and communication distance. But there exist some negative factors in practice, which makes this assumption to contradict with the situation in real communication environment. It results in large distance estimation error with low efficiency. Thus, a lightweight WSN communication distance estimation method is presented, which is called distance estimation using distribution-based fingerprinting. First, we considered the uncertainty in RSSI values, and got the fingerprinting relationship in terms of RSSI data distribution, which is gained through a statistical calculation. Then, a data matching algorithm is implemented to estimate the communication distance. Finally, RSSI values in different conditions are utilized to validate this method. Experimental results demonstrated that the new method can obtain better results with high efficiency than other related methods, and can be applied in WSN localization system.