A Machine Learning-based Secured and Energy-efficient Data Transmission in Mobile Ad-Hoc Networks (MANET)

Mobile hoc networks (MANET) are wireless networks of mobile devices that set up Data Transmission (DT) links independently without a fixed framework. Because topology changes constantly, MANET lines are often interrupted and out of balance. So, making sure that DT works well and reliably while also making good use of network resources is a problematic issue that MANET needs to solve. The suggested solution is to create a DT method to deal with these issues. This method aims to improve DT by sending data as quickly as possible while using as little time. As learning examples, the suggested method uses a range of mobile gadgets. Support Vector Machine (SVM) classes are trained to be weak groups. Supervised SVM can sort the surrounding nodes into groups with better link quality and lower energy use. The results of weak learners are combined to create a robust classifier, which guarantees that the data transfer works well. An experimental test checks the amount of power used, the packet transfer rate, the time it takes, and the output. The number of mobile nodes and data packages will be changed during the analysis.