Similarity-based clustering and data aggregation with independent component analysis in wireless sensor networks

Wireless sensor networks are consisted of group of sensor nodes, which are scattered in inaccessible areas with limited resources. Data aggregation and clustering methods minimize sensor network's energy usage by reducing the quantity of data transmission. Machine learning techniques like reinforcement learning, neural networks, and swarm intelligence significantly cut down the transmission of data and make use of network's distributive features. Quantity of aggregated data can be reduced if the measured data are similar. Based on this concept, a similarity based clustering method is proposed in which sensor node with similar data are grouped as a cluster for data aggregation. Then an algorithm is proposed that aggregates the data using independent component analysis which is performed on cluster head sensor nodes. Data aggregation process is executed on clusters which are having higher data similarity. Implementation shows that proposed method is performing better in terms of computational overhead, aggregation ratio, and energy consumption.