Target Tracking and Classification from Labeled and Unlabeled Data in Wireless Sensor Networks
Tracking the locations and identities of moving targets in the surveillance area of wireless sensor networks is studied. In order to not rely on high-cost sensors that have been used in previous researches, we propose the integrated localization and classification based on semi-supervised learning,...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2014-12-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | http://www.mdpi.com/1424-8220/14/12/23871 |
| _version_ | 1817991888611835904 |
|---|---|
| author | Jaehyun Yoo Hyoun Jin Kim |
| author_facet | Jaehyun Yoo Hyoun Jin Kim |
| author_sort | Jaehyun Yoo |
| collection | DOAJ |
| description | Tracking the locations and identities of moving targets in the surveillance area of wireless sensor networks is studied. In order to not rely on high-cost sensors that have been used in previous researches, we propose the integrated localization and classification based on semi-supervised learning, which uses both labeled and unlabeled data obtained from low-cost distributed sensor network. In our setting, labeled data are obtained by seismic and PIR sensors that contain information about the types of the targets. Unlabeled data are generated from the RF signal strength by applying Gaussian process, which represents the probability of predicted target locations. Finally, by using classified unlabeled data produced by semi-supervised learning, identities and locations of multiple targets are estimated. In addition, we consider a case when the labeled data are absent, which can happen due to fault or lack of the deployed sensor nodes and communication failure. We overcome this situation by defining artificial labeled data utilizing characteristics of support vector machine, which provides information on the importance of each training data point. Experimental results demonstrate the accuracy of the proposed tracking algorithm and its robustness to the absence of the labeled data thanks to the artificial labeled data. |
| first_indexed | 2024-04-14T01:19:19Z |
| format | Article |
| id | doaj.art-f719ce75c8ed4553966acc8b670d8910 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-14T01:19:19Z |
| publishDate | 2014-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-f719ce75c8ed4553966acc8b670d89102022-12-22T02:20:43ZengMDPI AGSensors1424-82202014-12-011412238712388410.3390/s141223871s141223871Target Tracking and Classification from Labeled and Unlabeled Data in Wireless Sensor NetworksJaehyun Yoo0Hyoun Jin Kim1Department of Mechanical and Aerospace Engineering, Seoul National University, 599 Gwanangno, Gwanak-gu, Seoul KS013, KoreaDepartment of Mechanical and Aerospace Engineering, Seoul National University, 599 Gwanangno, Gwanak-gu, Seoul KS013, KoreaTracking the locations and identities of moving targets in the surveillance area of wireless sensor networks is studied. In order to not rely on high-cost sensors that have been used in previous researches, we propose the integrated localization and classification based on semi-supervised learning, which uses both labeled and unlabeled data obtained from low-cost distributed sensor network. In our setting, labeled data are obtained by seismic and PIR sensors that contain information about the types of the targets. Unlabeled data are generated from the RF signal strength by applying Gaussian process, which represents the probability of predicted target locations. Finally, by using classified unlabeled data produced by semi-supervised learning, identities and locations of multiple targets are estimated. In addition, we consider a case when the labeled data are absent, which can happen due to fault or lack of the deployed sensor nodes and communication failure. We overcome this situation by defining artificial labeled data utilizing characteristics of support vector machine, which provides information on the importance of each training data point. Experimental results demonstrate the accuracy of the proposed tracking algorithm and its robustness to the absence of the labeled data thanks to the artificial labeled data.http://www.mdpi.com/1424-8220/14/12/23871low-cost sensor networkmulti-target trackingsemi-supervised learningGaussian process |
| spellingShingle | Jaehyun Yoo Hyoun Jin Kim Target Tracking and Classification from Labeled and Unlabeled Data in Wireless Sensor Networks Sensors low-cost sensor network multi-target tracking semi-supervised learning Gaussian process |
| title | Target Tracking and Classification from Labeled and Unlabeled Data in Wireless Sensor Networks |
| title_full | Target Tracking and Classification from Labeled and Unlabeled Data in Wireless Sensor Networks |
| title_fullStr | Target Tracking and Classification from Labeled and Unlabeled Data in Wireless Sensor Networks |
| title_full_unstemmed | Target Tracking and Classification from Labeled and Unlabeled Data in Wireless Sensor Networks |
| title_short | Target Tracking and Classification from Labeled and Unlabeled Data in Wireless Sensor Networks |
| title_sort | target tracking and classification from labeled and unlabeled data in wireless sensor networks |
| topic | low-cost sensor network multi-target tracking semi-supervised learning Gaussian process |
| url | http://www.mdpi.com/1424-8220/14/12/23871 |
| work_keys_str_mv | AT jaehyunyoo targettrackingandclassificationfromlabeledandunlabeleddatainwirelesssensornetworks AT hyounjinkim targettrackingandclassificationfromlabeledandunlabeleddatainwirelesssensornetworks |