Prediction of Packet Delivery Ratio Using Lasso Regression in Comparison with Linear Regression Algorithm for Multi Input Multi Output Network

Abstract

The aim of the study is to predict the accurate Packet Delivery Ratio (PDR) using the dataset provided with the help of the machine learning technique Novel Linear and compared with Lasso regression algorithms. Sklearn machine learning library in python is used to perform Regression with help of 10000 PDR values generated using python in which about 1 - 50 SNR (Signal to Noise Ratio) and its corresponding Packet Delivery Ratio (PDR) are obtained. Sample sizes of the two groups are 10 each. Novel lasso regression is considered as Group 2 with 10 samples and Linear regression is considered as Group 1 with 10 samples and these samples were calculated using g power with a pretest power of 80 and a 0.05 alpha value (Error rate). PDR of lasso regression is 96.56 % and PDR of Linear regression is 95.48 % for corresponding SNR is 4 db. The independent sample T-test was examined and found to have a significance level of P less than 0.05. Prediction of PDR for Novel Lasso Regression algorithm is significantly better than the Linear regression algorithm.