Improving Accuracy in Malware Detection for Health Sensor Data by Novel Ada Boost M1Algorithm over Convolutional Neural Networks-Long Short-Term Memory Networks

Abstract

Aim: The Aim of research is to increase the accuracy of prediction the Malware detection for Health Sensor Data using the
Convolutional Neural Networks-Long Short-Term(CNN-LSTM) in Comparison with Novel AdaBoostM1. Materials and Methods: In the Convolutional Neural Networks-Long Short-Term algorithm, the sample size is n=10, while in the Novel AdaBoostM1Algorithm, the sample size is n=10 and the g-power value of 80% and datasets are collected from various web sources with recent research findings and threshold 0.05%, confidence interval 95% mean and standard deviation. Results and Discussions: Convolutional Neural Networks-Long Short-Term algorithm provides mean accuracy of 79.6%. when compared to the Novel AdaBoostM1algorithm with a mean accuracy of 97.8%. Statistical insignificant difference was observed between Novel Novel AdaBoostM1 and Convolutional Neural Networks-Long Short-Term, p = 0.893 (p>0.05). Conclusion: Novel AdaBoostM1achieved significantly better Accuracy than CNN-LSTM Algorithm in Malware Detection for Health sensor data comparison.