An Elitism Strategy Based Genetic Algorithm for Streaming Pattern Discovery in Wireless Sensor Networks

This letter presents a pattern discovery algorithm for multi-streams mining in wireless sensor networks. The algorithm adapts operators of Genetic Algorithm with Elitism Strategy into the iteration in tracking weights. We describe the algorithm, give the explanation of correctness, and evaluate its performance using simulation. We conclude that the proposed algorithm can reduce the reconstruction error, and decrease the number of hidden variables so it is more suitable for wireless sensor networks than the existing distributed algorithms.