Performance analysis of the decision review system in cricket using CNN in comparison with SVM algorithm

This study aims to assess and compare the accuracy and efficiency of Conventional Neural Networks (CNN) and Support Vector Machine (SVM) algorithms within the Decision Review System (DRS) used in cricket, focusing on enhancing umpire decision-making and evaluating this machine learning tools’ effectiveness in the sport. Using a dataset of 3,400 analyses and assessing video quality for prediction, each model was tested with a sample size of 10, selected through ClinCalc for statistical relevance. Results show that SVM achieved a superior accuracy rate of 99%, significantly outperforming CNN, which had an accuracy of 97.4%, with the difference confirmed as statistically significant (p