Attention dilated deep learning network-based distributed data mining with energy efficient Heuristic-aided routing model in WSN

Wireless Sensor Networks (WSNs) are comprised of autonomous nodes, where the physical devices and other equipment are embedded for monitoring the environment. Yet, it consumes larger energy consumption while it fails to provide the optimal routing path. The data aggregation in WSN is accomplished by several classification approaches, but the delay and utilization of the resource are high. So, it is necessary to solve the challenges by implementing the developed model for the energy efficient routing in WSN. A distributed data mining scheme is developed based on a deep learning approach to provide greater energy efficiency and optimal load balancing in WSN. The distributed data mining is performed to distribute the appropriate data to the sensor nodes. This data distribution highly reduces the overhead at the fusion center. The data are categorized via Fused Deep Structural Network (FDSNet), where the Attention-based Dilated Deep Temporal Context Networks (DTCN) are fused with a Deep Shallow Network. The necessary data are distributed to the sensor nodes. The optimal routing is carried out based on optimal path selection using Stability Bound-based Energy Valley Optimizer (SBEVO). The optimal routing is done via the multi-objective functions such as “energy consumption, PDR, delay, and shortest path”. The energy-efficient data transmission is accomplished with the help of developed distributed data mining with a routing scheme. The developed energy-efficient optimal routing in WSN is compared to conventional routing approaches with several performance metrics to show energy efficiency. While comparing with existing methods, the developed model attains the value of 0.95% with regards of accuracy, precision, and F1-score. These findings of the developed model show accurate performance with an efficient routing mechanism in WSN.