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

Abstract

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.

Distributed energy‐efficient data reduction approach based on prediction and compression to reduce data transmission in IoT networks

“…Several data reduction algorithms based on clustering techniques have been proposed in the past few years 25–33 . The PFF strategy is used in the sensor and aggregator devices 25 .…”

“…Then, using independent component analysis on cluster head IoT devices, an algorithm is developed to gather the data. The data gathering phase is carried out on clusters with higher data correlation 31 . Previous study 33 suggests an integrated divide and conquer with improved K‐means strategy for data gathering with power saving in WSNs.…”

“…Several data reduction algorithms based on clustering techniques have been proposed in the past few years. [25][26][27][28][29][30][31][32][33] The PFF strategy is used in the sensor and aggregator devices. 25 The Jaccard similarity is used by researchers in the sensor node to lower the redundancy of data, and set similarity in the aggregator node to minimize duplicated sets of data.…”

“…The data gathering phase is carried out on clusters with higher data correlation. 31 Previous study 33 suggests an integrated divide and conquer with improved K-means strategy for data gathering with power saving in WSNs. It gathers the data at two different levels: node and cluster head.…”

Novel Approaches to Identify Clusters Using Independent Components Analysis with Application

“…Shahina and Kumar [17] proposed a clustering approach based on similarity, which grouped the sensor node with similar data as a cluster for combining data. After that, an algorithm is proposed which combines the data making use of ICA, which is applied on cluster head sensor nodes.…”