Collaborative Target Classification for Image Recognition in Wireless Sensor Networks
ADMA '07 Proceedings of the 3rd international conference on Advanced Data Mining and Applications
A survey on wireless sensor networks deployment
WSEAS TRANSACTIONS on COMMUNICATIONS
Challenges for wireless sensor networks deployment
DIWEB'08 Proceedings of the 8th WSEAS international conference on Distance learning and web engineering
Equal-Gain Combination for adaptive distributed classification in Wireless Sensor Networks
International Journal of Ad Hoc and Ubiquitous Computing
EUC'07 Proceedings of the 2007 international conference on Embedded and ubiquitous computing
On the design of soft-decision fusion rule for coding approach in wireless sensor networks
WASA'06 Proceedings of the First international conference on Wireless Algorithms, Systems, and Applications
Performance analysis of different types of sensor networks for cognitive radios
Journal of Electrical and Computer Engineering
Hi-index | 0.01 |
In this paper, we consider the distributed classification problem in wireless sensor networks. Local decisions made by local sensors, possibly in the presence of faults, are transmitted to a fusion center through fading channels. Classification performance could be degraded due to the errors caused by both sensor faults and fading channels. Integrating channel decoding into the distributed fault-tolerant classification fusion algorithm, we obtain a new fusion rule that combines both soft-decision decoding and local decision rules without introducing any redundancy. The soft decoding scheme is utilized to combat channel fading, while the distributed classification fusion structure using error correcting codes provides good sensor fault-tolerance capability. Asymptotic performance of the proposed approach is also investigated. Performance evaluation of the proposed approach with both sensor faults and fading channel impairments is carried out. These results show that the proposed approach outperforms the system employing the MAP fusion rule designed without regard to sensor faults and the multiclass equal gain combining fusion rule