Binary Information Press
Wireless Sensor Networks (WSNs) usually have limited energy and transmission capacity, which can't match the transmission of a large number of data collected by sensor nodes. So, it is necessary to perform in-network data compression in the WSN. This paper proposes an algorithm of data compression based on multiple Principal Component Analysis (multiple-PCA), iteratively using PCA method in multiple layers. Theoretically and experimentally, the proposed algorithm can efficiently remove the spatial-temporal correlation between the raw sensor measurements and also that between the Principal Components (PCs) of the neighboring cluster-heads and efficiently improve the data compression ratio under the premise of ensuring the data reconstruction accuracy, thus better reduce the energy consumption of sensor nodes.