Aiming at the severe energy and computing resource constraints of Wireless Sensor Network (WSN), based on rough set theory and ART2 network, a distributed data mining model for WSN is proposed. This model poses a three-layer MLP for data aggregation in the clustered sensor network. And the input layer neuron and the first layer neuron are located in every cluster member, while the second layer neuron and the output layer neuron are located in every cluster head. The features of the training samples were extracted to build up the decision table; the rough set theory was applied to reduce the decision table. Finally, the reduced decision attributes were used to construct ART2 neural network classification data. Constructed data mining algorithm can be integrated in each sensor network node. Simulation results prove data dimension is reduced and data redundancy is eliminated after the raw-data is processed by data mining algorithm, and the communication traffic is decreased and the life of WSN is extended.
[1]
Ian F. Akyildiz,et al.
Wireless sensor networks
,
2007
.
[2]
Davide Brunelli,et al.
Wireless Sensor Networks
,
2012,
Lecture Notes in Computer Science.
[3]
Cheng Wu,et al.
Reduction method based on a new fuzzy rough set in fuzzy information system and its applications to scheduling problems
,
2006,
Comput. Math. Appl..
[4]
Sun Youxian.
Node Association Rule Mining in Wireless Sensor Networks
,
2007
.
[5]
Andrzej Skowron,et al.
Rough sets and Boolean reasoning
,
2007,
Inf. Sci..
[6]
Eiichiro Tazaki,et al.
Rough neural classifier system
,
2002,
IEEE International Conference on Systems, Man and Cybernetics.
[7]
Zhang Jian-ming,et al.
Survey on data aggregation techniques in wireless sensor networks
,
2006
.