EDC-ER: An Efficient Data Compression Method for Energy Reduction in WBANs

Abstract

The Wireless Body Area Networks (WBANs) are a set of sensors on the human body that are designed in very small sizes. Sensors are faced with the exchange of a huge amount of data in real time and usually have measurement errors in different environmental conditions. They sometimes record repetitive, unimportant, and defective data which causes them to run out of energy consumption. One of the most effective methods to save the energy of sensors is the use of data compression. The compression methods in the WBANs have four issues: 1-incompatibility with the datasets obtained from biosensors, 2- lack of accuracy in prediction methods, 3- unsuitable for repetitive data environments, and 4- high energy consumption. To solve these problems, a new method called Efficient Data Compression for Energy Reduction (EDC-ER) is presented. EDC-ER method uses Recurrent Neural Network (RNN) and Run Length Encoding (RLE) which involves four key steps: 1- create and fit the Long Short-Term Memory (LSTM) network to adapt it to the dataset, 2- prediction using LSTM to achieve high accuracy, 3- calculate the error to reduce data volume, and 4- compress by RLE to reduce data volume more and save energy. First, the dataset of biosensors is divided into train and test. Prediction occurs by LSTM at the sensor level, and then the error of predicted data from the original data is coded by the RLE lossless algorithm. The presented method has a very good performance in energy consumption, data volume reduction by removing unimportant and repetitive data in the exchange of information between sensors and sink, high accuracy in data prediction, and achieving a high compression rate due to low error. The EDC-ER method is implemented on the dataset received from body sensors including blood pressure systolic, blood pressure diastolic, heart rate, respiration, and SPO2. In the last step, the differences between predictions and original signals are coded by four famous lossless algorithms: RLE, Huffman, Lempel Ziv Welch (LZW), and Arithmetic. Three measurements of Compression Ratio (CR), Energy Remaining (ER), and Root Mean Square Error (RMSE) after data compression have been measured. Our results compared with state-of-art lossless coding methods. Results show the EDC-ER method with RNN and RLE has the highest energy saving on average of 98% by maintaining the appropriate compression ratio.

Keywords

• Wireless body area network
• energy conservation
• data compression
• LSTM
• RLE