Lightweight detection and classification for wireless sensor networks in realistic environments

Lin Gu, Dong Jia, Pascal Vicaire, Ting Yan, Liqian Luo, Ajay Tirumala, Qing Cao, Tian He, John A. Stankovic, Tarek Abdelzaher, Bruce H. Krogh

Research output: Chapter in Book/Report/Conference proceedingConference contribution

181 Scopus citations

Abstract

A wide variety of sensors have been incorporated into a spectrum of wireless sensor network (WSN) platforms, providing flexible sensing capability over a large number of low-power and inexpensive nodes. Traditional signal processing algorithms, however, often prove too complex for energy-and-cost-effective WSN nodes. This study explores how to design efficient sensing and classification algorithms that achieve reliable sensing performance on energy-andcost- effective hardware without special powerful nodes in a continuously changing physical environment. We present the detection and classification system in a cutting-edge surveillance sensor network, which classifies vehicles, persons, and persons carrying ferrous objects, and tracks these targets with a maximum error in velocity of 15%. Considering the demanding requirements and strict resource constraints, we design a hierarchical classification architecture that naturally distributes sensing and computation tasks at different levels of the system. Such a distribution allows multiple sensors to collaborate on a sensor node, and the detection and classification results to be continuously refined at different levels of the WSN. This design enables reliable detection and classification without involving high-complexity computation, reduces network traffic, and emphasizes resilience and adaptation to the realistic environment. We evaluate the system with performance data collected from outdoor experiments and field assessments. Based on the experience acquired and lessons learned when developing this system, we abstract common issues and introduce several guidelines which can direct future development of detection and classification solutions based on WSNs. Categories and Subject Descriptors C.2.1 [Computer-Communication Networks]: Network Architecture and Design; C.3 [Computer System Organization]: Special Purpose And Application-Based Systems-Real-Time and embedded systems; C.4 [Performance of Systems]: Design Studies General Terms Design, Experimentation, Measurement, Performance.

Original languageEnglish (US)
Title of host publicationSenSys 2005 - Proceedings of the 3rd International Conference on Embedded Networked Sensor Systems
PublisherAssociation for Computing Machinery
Pages205-217
Number of pages13
ISBN (Print)159593054X, 9781595930545
DOIs
StatePublished - Jan 1 2005
Event3rd ACM International Conference on Embedded Networked Sensor Systems, SenSys 2005 - San Diego, CA, United States
Duration: Nov 2 2005Nov 4 2005

Publication series

NameSenSys 2005 - Proceedings of the 3rd International Conference on Embedded Networked Sensor Systems

Other

Other3rd ACM International Conference on Embedded Networked Sensor Systems, SenSys 2005
CountryUnited States
CitySan Diego, CA
Period11/2/0511/4/05

Keywords

  • Classification
  • Vigilnet
  • Wireless sensor networks

Fingerprint Dive into the research topics of 'Lightweight detection and classification for wireless sensor networks in realistic environments'. Together they form a unique fingerprint.

  • Cite this

    Gu, L., Jia, D., Vicaire, P., Yan, T., Luo, L., Tirumala, A., Cao, Q., He, T., Stankovic, J. A., Abdelzaher, T., & Krogh, B. H. (2005). Lightweight detection and classification for wireless sensor networks in realistic environments. In SenSys 2005 - Proceedings of the 3rd International Conference on Embedded Networked Sensor Systems (pp. 205-217). (SenSys 2005 - Proceedings of the 3rd International Conference on Embedded Networked Sensor Systems). Association for Computing Machinery. https://doi.org/10.1145/1098918.1098941