• R. Logambigai
• S. Suba
• A. Kannan

Wireless Sensor Networks (WSNs), are essential for real - world application areas. The WSN sensor nodes have a finite amount of battery life. The life expectancy of the detector nodes is increased by making efficient use of battery capacity. The majority of the energy has been used in the transmission of a substantial volume of data that the sensor nodes have gleaned. One efficient way to decrease communication energy consumption in WSNs is data compression. Compaction Model using Denoising Autoencoder (CM-DAE), an innovative model to compress data and lower communication energy consumption, has been proposed in this work using cluster-based WSN. In the proposed work, data pruning is done by cluster member nodes using a deep-learning approach. For the purpose of transmitting sensed information to the base station, the cluster head nodes compress the data using neural networks. Using data from real sensors, the proposed model is examined and analyzed with the frameworks. The experimental results demonstrate that the suggested model outperforms other existing schemes in terms of energy savings, lifetime of the network, and ratio of delivered packets.

Multilayer Feedforward, Compaction Model, Wireless Sensor Networks (WSN), Information Gathering.

" An Efficient Data Compression Model for Wireless Sensor Networks Using Deep Learning Technique", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.10, Issue 6, page no.18-24, June-2023, Available :http://www.jetir.org/papers/JETIRFZ06004.pdf

" An Efficient Data Compression Model for Wireless Sensor Networks Using Deep Learning Technique", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.10, Issue 6, page no. pp18-24, June-2023, Available at : http://www.jetir.org/papers/JETIRFZ06004.pdf