Self-Adaptive Gathering for Energy-Efficient Data Stream in Heterogeneous Wireless Sensor Networks Based on Deep Learning

Abstract

Big data streams are available across the growing heterogeneous wireless sensor networks, with characteristics of vast volume and dynamic transmission. Energy efficiency improvement in big data stream gathering is becoming a challenge. In this article, a self-adaptive gathering algorithm for multisource heterogeneous big data streams with sliding windows is proposed, which can improve the energy efficiency for data stream processing due to adaptively adjusting the window size based on the difference of data probability distribution between adjacent windows. In order to save the spatial correlation of a heterogeneous data stream, the Gaussian Bernoulli Matrix Variable Restricted Boltzmann Machine (GBMVRBM) is proposed to deal with the multi-source data separately, and then a joint layer is used to fuse the data features of different modalities. The probability distribution of sliding window data is obtained by the energy function of the GBMVRBM, and the Hoeffding boundary is adopted to ensure that the probability distribution variation between the windows can be detected in time. The algorithm is tested on the Clemson University Audio Visual Experiments database, and it can be concluded that the algorithm proposed in this article can not only detect the data change in time, but also expand the window size to process the data efficiently.