SVM+KF Target Tracking Strategy Using the Signal Strength in Wireless Sensor Networks
Target Tracking (TT) (DBSCNA: density-based spatial clustering of application with noise; DPF: distributed particle filter; ELM: extreme learning machine; EKF: extended Kalman filter (KF); GRNN: generalized regression neural network; KF: Kalman filter; LBE: learning-by-example; MLE: maximum likeliho...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-07-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/20/14/3832 |
id |
doaj-daaa79c8bec54b80a71ff46c634f9bf3 |
---|---|
record_format |
Article |
spelling |
doaj-daaa79c8bec54b80a71ff46c634f9bf32020-11-25T02:37:45ZengMDPI AGSensors1424-82202020-07-01203832383210.3390/s20143832SVM+KF Target Tracking Strategy Using the Signal Strength in Wireless Sensor NetworksXing Wang0Xuejun Liu1Ziran Wang2Ruichao Li3Yiguang Wu4Key Laboratory of Virtual Geographic Environment (Nanjing Normal University), Ministry of Education,Nanjing 210023, ChinaKey Laboratory of Virtual Geographic Environment (Nanjing Normal University), Ministry of Education,Nanjing 210023, ChinaKey Laboratory of Virtual Geographic Environment (Nanjing Normal University), Ministry of Education,Nanjing 210023, ChinaKey Laboratory of Virtual Geographic Environment (Nanjing Normal University), Ministry of Education,Nanjing 210023, ChinaKey Laboratory of Virtual Geographic Environment (Nanjing Normal University), Ministry of Education,Nanjing 210023, ChinaTarget Tracking (TT) (DBSCNA: density-based spatial clustering of application with noise; DPF: distributed particle filter; ELM: extreme learning machine; EKF: extended Kalman filter (KF); GRNN: generalized regression neural network; KF: Kalman filter; LBE: learning-by-example; MLE: maximum likelihood estimator; NN: neural network; PF: particle filter; RSSI: received signal strength indication; RR: ridge regression; RMSE: root-mean-square-error; SVM: support vector machine; TT: target tracking; UKF: unscented KF; WSNs: wireless sensor networks) is a fundamental application of wireless sensor networks. TT based on received signal strength indication (RSSI) is by far the cheapest and simplest approach, but suffers from a low stability and precision owing to multiple paths, occlusions, and decalibration effects. To address this problem, we propose an innovative TT algorithm, known as the SVM+KF method, which combines the support vector machine (SVM) and an improved Kalman filter (KF). We first use the SVM to obtain an initial estimate of the target’s position based on the RSSI. This enhances the ability of our algorithm to process nonlinear data. We then apply an improved KF to modify this estimated position. Our improved KF adds the threshold value of the innovation update in the traditional KF. This value changes dynamically according to the target speed and network parameters to ensure the stability of the results. Simulations and real experiments in different scenarios demonstrate that our algorithm provides a superior tracking accuracy and stability compared to similar algorithms.https://www.mdpi.com/1424-8220/20/14/3832wireless sensor networktarget trackingsupport vector machineKalman filtering |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Xing Wang Xuejun Liu Ziran Wang Ruichao Li Yiguang Wu |
spellingShingle |
Xing Wang Xuejun Liu Ziran Wang Ruichao Li Yiguang Wu SVM+KF Target Tracking Strategy Using the Signal Strength in Wireless Sensor Networks Sensors wireless sensor network target tracking support vector machine Kalman filtering |
author_facet |
Xing Wang Xuejun Liu Ziran Wang Ruichao Li Yiguang Wu |
author_sort |
Xing Wang |
title |
SVM+KF Target Tracking Strategy Using the Signal Strength in Wireless Sensor Networks |
title_short |
SVM+KF Target Tracking Strategy Using the Signal Strength in Wireless Sensor Networks |
title_full |
SVM+KF Target Tracking Strategy Using the Signal Strength in Wireless Sensor Networks |
title_fullStr |
SVM+KF Target Tracking Strategy Using the Signal Strength in Wireless Sensor Networks |
title_full_unstemmed |
SVM+KF Target Tracking Strategy Using the Signal Strength in Wireless Sensor Networks |
title_sort |
svm+kf target tracking strategy using the signal strength in wireless sensor networks |
publisher |
MDPI AG |
series |
Sensors |
issn |
1424-8220 |
publishDate |
2020-07-01 |
description |
Target Tracking (TT) (DBSCNA: density-based spatial clustering of application with noise; DPF: distributed particle filter; ELM: extreme learning machine; EKF: extended Kalman filter (KF); GRNN: generalized regression neural network; KF: Kalman filter; LBE: learning-by-example; MLE: maximum likelihood estimator; NN: neural network; PF: particle filter; RSSI: received signal strength indication; RR: ridge regression; RMSE: root-mean-square-error; SVM: support vector machine; TT: target tracking; UKF: unscented KF; WSNs: wireless sensor networks) is a fundamental application of wireless sensor networks. TT based on received signal strength indication (RSSI) is by far the cheapest and simplest approach, but suffers from a low stability and precision owing to multiple paths, occlusions, and decalibration effects. To address this problem, we propose an innovative TT algorithm, known as the SVM+KF method, which combines the support vector machine (SVM) and an improved Kalman filter (KF). We first use the SVM to obtain an initial estimate of the target’s position based on the RSSI. This enhances the ability of our algorithm to process nonlinear data. We then apply an improved KF to modify this estimated position. Our improved KF adds the threshold value of the innovation update in the traditional KF. This value changes dynamically according to the target speed and network parameters to ensure the stability of the results. Simulations and real experiments in different scenarios demonstrate that our algorithm provides a superior tracking accuracy and stability compared to similar algorithms. |
topic |
wireless sensor network target tracking support vector machine Kalman filtering |
url |
https://www.mdpi.com/1424-8220/20/14/3832 |
work_keys_str_mv |
AT xingwang svmkftargettrackingstrategyusingthesignalstrengthinwirelesssensornetworks AT xuejunliu svmkftargettrackingstrategyusingthesignalstrengthinwirelesssensornetworks AT ziranwang svmkftargettrackingstrategyusingthesignalstrengthinwirelesssensornetworks AT ruichaoli svmkftargettrackingstrategyusingthesignalstrengthinwirelesssensornetworks AT yiguangwu svmkftargettrackingstrategyusingthesignalstrengthinwirelesssensornetworks |
_version_ |
1724793540992565248 |