Boosting Signal Strength Using Machine Learning In Wireless Sensors Under Disaster Situations

Abstract The modern era has been witnessing of exemplary evolution of technology in terms of Wireless Sensor Network (WSN). Numerous applications have added its potential and credibility both. In this study application of WSN has been targeted in Disastrous situation and that too in one particular area as Under water. Objective of this study is to achieve the target of best communication , reducing communication network overhead, to extend network lifetime, and even shortest smart routing path , if possible. A new scheme is in process of development and it will be evaluated using various key quality-of-service (QoS) parameters including energy consumption, network lifetime, throughput, packet delivery ratio (PDR), end-to-end delay, and packet loss rate (PLR). In order to achieve the target , Machine learning has been added to make the approach more robust and ready to use. Model preparation has been done using various techniques. In this work Train-test split model has been used for model preparation using Machine learning along with Dataset graphs