Abstract
Data compression is very important in wireless sensor networks (WSNs) with the limited energy of sensor nodes. Data communication results in energy consumption most of the time; the lifetime of sensor nodes is usually prolonged by reducing data transmission and reception. In this paper, we propose a new Stacked RBM Auto-Encoder (Stacked RBM-AE) model to compress sensing data, which is composed of a encode layer and a decode layer. In the encode layer, the sensing data is compressed; and in the decode layer, the sensing data is reconstructed. The encode layer and the decode layer are composed of four standard Restricted Boltzmann Machines (RBMs). We also provide an energy optimization method that can further reduce the energy consumption of the model storage and calculation by pruning the parameters of the model. We test the performance of the model by using the environment data collected by Intel Lab. When the compression ratio of the model is 10, the average Percentage RMS Difference value is 10.04%, and the average temperature reconstruction error value is 0.2815 °C. The node communication energy consumption in WSNs can be reduced by 90%. Compared with the traditional method, the proposed model has better compression efficiency and reconstruction accuracy under the same compression ratio. Our experiment results show that the new neural network model can not only apply to data compression for WSNs, but also have high compression efficiency and good transfer learning ability.
Highlights
Research has found sensor networks suitable to collect environment information, such as temperature, light and humidity in harder-to-reach areas
We developed a hybrid model named Stacked Restricted Boltzmann Machines (RBMs)-AE that combines four standard RBMs with the feature of auto-encoder to compress and reconstruct the sensing data
We proposed a new method of data compression, which has better reconstruction accuracy than the traditional algorithm under the same compression ratio
Summary
Research has found sensor networks suitable to collect environment information, such as temperature, light and humidity in harder-to-reach areas. Unmanned vehicles need GPS and accelerometer to locate themselves, and to get information regarding their environments using a camera and lidar [2]. By fusing these multi-modal sensor data, they can predict the moving trajectory of nearby objects. The increase in WSNs applications and sensor nodes have led to an explosion in the amount of sensing data. If the sensing data collected by WSNs are directly sent to a gateway, it will consume a lot of power and increase the probability of transmission errors. These factors have motivated efficient technologies to reduce energy consumption and extend the lifetime of WSNs
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
