W4: Real-Time Surveillance of People and Their Activities
IEEE Transactions on Pattern Analysis and Machine Intelligence
Support vector machines: hype or hallelujah?
ACM SIGKDD Explorations Newsletter - Special issue on “Scalable data mining algorithms”
Wireless Communications: Principles and Practice
Wireless Communications: Principles and Practice
Incremental Learning with Support Vector Machines
ICDM '01 Proceedings of the 2001 IEEE International Conference on Data Mining
Incremental Support Vector Machine Construction
ICDM '01 Proceedings of the 2001 IEEE International Conference on Data Mining
Vehicle classification in distributed sensor networks
Journal of Parallel and Distributed Computing
Classification of moving humans using eigen-features and support vector machines
CAIP'05 Proceedings of the 11th international conference on Computer Analysis of Images and Patterns
Mobile agent based wireless sensor network for intelligent maintenance
ICIC'05 Proceedings of the 2005 international conference on Advances in Intelligent Computing - Volume Part II
IEEE Transactions on Wireless Communications
Distributed classification of Gaussian space-time sources in wireless sensor networks
IEEE Journal on Selected Areas in Communications
Distributed multitarget classification in wireless sensor networks
IEEE Journal on Selected Areas in Communications
Incremental training of support vector machines
IEEE Transactions on Neural Networks
Hi-index | 0.00 |
Target classification, especially visual target classification, in complex situations is challenging for image recognition in wireless sensor networks (WSNs). The distributed and online learning for target classification is significant for highly-constrained WSNs. This paper presents a collaborative target classification algorithm for image recognition in WSNs, taking advantages of the collaboration for the data mining between multi-sensor nodes. The proposed algorithm consists of three steps, target detection and feature extraction are based on single-sensor node processing, whereas target classification is implemented by collaboration between multi-sensor nodes using collaborative support vector machines (SVMs). For conquering the disadvantages of inevitable missing rate and false rate in target detection, the proposed collaborative SVM adopts a robust mechanism for adaptive sample selection, which improves the incremental learning of SVM by just fusing the information from a selected set of wireless sensor nodes. Furthermore, a progressive distributed framework for collaborative SVM is also introduced for enhancing the collaboration between multi-sensor nodes. Experimental results demonstrate that the proposed collaborative target classification algorithm for image recognition can accomplish target classification quickly and accurately with little congestion, energy consumption and execution time.