Advertisement
Published in:
15-01-2018
Real time localization algorithm based on local linear embedding optimization in sensor networks
Published in: Cluster Computing | Special Issue 2/2019
Log inActivate our intelligent search to find suitable subject content or patents.
Select sections of text to find matching patents with Artificial Intelligence. powered by
Select sections of text to find additional relevant content using AI-assisted search. powered by
Abstract
The paper first analyzes the ranging principle and factors affecting localization error and proposes the least-squares support vector regression location algorithm based on Gaussian filter RSSI (LSSVR-GF-RSSI) for low accuracy of localization based on RSSI ranging in order to reduce the influence of ranging error based on Received Signal Strength Index (RSSI) on node localization and solve problem of localization with big error based on RSSI ranging. LSSVR-GF-RSSI first filters out RSSI value with large deviation with Gaussian function, that is, to select more accurate RSSI value, and then transforms into distance via these values, which will be served as the input of LSSVR model, and in the end, estimates the location of unknown nodes. The simulation results show that LSSVR-GF-RSSI proposed effectively reduces the error of localization of mean square without increasing additional operation time compared to that of LSSVR-RSSI.