Open AccessAn Improved Fingerprint Algorithm Based on Wireless Sensor Networks
Author(s) -
Long Cheng,
Ze Liu,
Liang Feng
Publication year - 2019
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1302/2/022093
Subject(s) - non line of sight propagation , computer science , fingerprint (computing) , wireless sensor network , sample (material) , algorithm , k nearest neighbors algorithm , wireless , positioning technology , data mining , artificial intelligence , real time computing , computer network , telecommunications , chemistry , chromatography
With the wide application of positioning technology in real life, people have particularly become concerned about the improvement of the accuracy of positioning. One of the common methods to deal with such problems is wireless sensor networks (WSN). Reducing the non-line-of-sight (NLOS)error and optimizing the positioning accuracy are the main technical problem. In this paper, we propose an improved fingerprint algorithm to enhance the accuracy of positioning. The traditional k-Nearest Neighbor (KNN) algorithm has the problem of sample imbalance, which leads to the individual data directly determining the decision result. Our proposed algorithm can effectively solve the problem of sample imbalance. Simulation results and experimental results illustrate that our algorithm is superior to KNN algorithm.