CBN-VAE: A Data Compression Model with Efficient Convolutional Structure for Wireless Sensor Networks

Abstract

Data compression is a useful method to reduce the communication energy consumption in wireless sensor networks (WSNs). Most existing neural network compression methods focus on improving the compression and reconstruction accuracy (i.e., increasing parameters and layers), ignoring the computation consumption of the network and its application ability in WSNs. In contrast, we pay attention to the computation consumption and application of neural networks, and propose an extremely simple and efficient neural network data compression model. The model combines the feature extraction advantages of Convolutional Neural Network (CNN) with the data generation ability of Variational Autoencoder (VAE) and Restricted Boltzmann Machine (RBM), we call it CBN-VAE. In particular, we propose a new efficient convolutional structure: Downsampling-Convolutional RBM (D-CRBM), and use it to replace the standard convolution to reduce parameters and computational consumption. Specifically, we use the VAE model composed of multiple D-CRBM layers to learn the hidden mathematical features of the sensing data, and use this feature to compress and reconstruct the sensing data. We test the performance of the model by using various real-world WSN datasets. Under the same network size, compared with the CNN, the parameters of CBN-VAE model are reduced by 73.88% and the floating-point operations (FLOPs) are reduced by 96.43% with negligible accuracy loss. Compared with the traditional neural networks, the proposed model is more suitable for application on nodes in WSNs. For the Intel Lab temperature data, the average Signal-to-Noise Ratio (SNR) value of the model can reach 32.51 dB, the average reconstruction error value is 0.0678 °C. The node communication energy consumption can be reduced by 95.83%. Compared with the traditional compression methods, the proposed model has better compression and reconstruction accuracy. At the same time, the experimental results show that the model has good fault detection performance and anti-noise ability. When reconstructing data, the model can effectively avoid fault and noise data.

Biosignal Compression Toolbox for Digital Biomarker Discovery

“…However, by open-sourcing the Biosignal Data Compression Toolbox, we expect to cultivate a community where researchers will test and contribute novel data compression methods on the data that we have released, further expanding the reach of the current study. Recent research in using deep convolutional autoencoders for biosignal data compression [ 35 , 36 ] has shown great promise and should be included in the Biosignal Data Compression Toolbox in future work. Future work will involve developing and testing methods for quantifying signal characteristics to determine optimal data compression pipelines for other biosignals.…”

Frequency Selective Auto-Encoder for Smart Meter Data Compression

“…Related to representative types of AE compression models [ 33 , 34 ], there are vanilla [ 35 ], sparse [ 36 ], and variational [ 37 ] AE model. The vanilla AE structure is a basic AE model, which is composed of an encoder and a decoder network as shown in Figure 1 .…”

On the Optimal Calculation of the Rice Coding Parameter

“…Several other compression methods have been proposed for resource-constrained IoT devices. Most of the proposed data compression methods in the literature for IoT applications-e.g., [26][27][28][29][30][31]-are lossy. Those works propose an estimator method that extracts enough information from a time-sequence and then encodes the minimum set of parameters to recreate, as close as possible, the original information based on the transmitted parameters of the estimator method.…”