Optimizing network lifetime: ERBS-REE for resilient object detection and tracking in resource-constrained WSN environments

In resource-constrained wireless sensor network (WSN) environment object detection and tracking have many challenges such as low network lifetime, throughput, and efficiency. This study proposed a novel method called the Ensemble Random Bayes Support Vector-based Random Electric Eel (ERBS-REE) algorithm to enhance object detection. This work aims to enhance the efficiency of object tracking by employing techniques namely Support Vector Machine, Random Forest, and Naïve Bayes through ensemble voting. SVM is utilized to detect objects, Random Forest is employed to manage noisy data and Naïve Bayes through ensemble voting is implemented for classification of objects. The Electric Eel Optimizer is employed with a random update strategy to enhance the performance of the ERBS-REE method. The evaluation metrics such as throughput, average detection rate, energy consumption, network lifetime, and end-to-end delay are utilized to validate the performance of the method. The ERBS-REE method is compared with existing methods and the experimental results illustrate the performance of the ERBS-REE method in object detection and tracking. As a result, the ERBS-REE method efficiently detects moving objects within WSN while maintaining low energy consumption. Also, the ERBS-REE method is appropriate for applications such as environmental monitoring, and industrial automation and operates in challenging environments where human presence is limited.