An architecture of Distributed Beta Wavelet Networks for large image classification in MapReduce

MapReduce has become a dominant parallel computing paradigm for storing and processing massive data due to its excellent scalability, reliability, and elasticity. In this paper, we present a new architecture of Distributed Beta Wavelet Networks {DBWN} for large image classification in MapReduce model. First to prove the performance of wavelet networks, a parallelized learning algorithm based on the Beta Wavelet Transform is proposed. Then the proposed structure of the {DBWN} is itemized. However the new algorithm is realized in MapReduce model. Comparisons with Fast Beta Wavelet Network {FBWN} are presented and discussed. Results of comparison have shown that the {DBWN} model performs better than {FBWN} model in classification rate and in the context of training run time.