Classification of CommSense data using learning algorithms

Abstract

In our previous work we have shown the design of a Communication based Sensing (CommSense) system. The current work presents analysis of the data captured by a CommSense system. Analysis is performed using Support Vector Machines (SVM) and a Multi-layer Perceptron (MLP) which are commonly used supervised learning algorithms. The predicted results are presented in the form of a confusion matrix and an analysis is presented showing the percentage of error in prediction.