Comparative Analysis of Selected Machine Learning Algorithms Based on Generated Smart Home Dataset

Abstract

There has being recent interest in applying machine learning techniques in smart homes for the purpose of securing the home. This paper presents the comparative study on six classification algorithms based on generated smart home datasets. These includes Logistics Regression, Support vector machine, Random forest, K-Nearest Neighbor, Decision Tree and Gaussian Naïve Bayes. Two different smart home datasets were generated and used to train and test the algorithms. The confusion matrix was used to evaluate the outputs of the classifiers. From the confusion matrix, Prediction Accuracy, Precision, Recall and F1-Score of the models were calculated. The Support Vector Machine (SVM) outperformed the other algorithms in terms of accuracy on both datasets with values of 67.89 and 88.56 respectively. The SVM and Logistics Regression also maintained the highest precision of 100.0 as compared to the other algorithms.

Citation: Musa Martha Ozohu and Oghenekaro Linda Uchenna (2021) Comparative Analysis of Selected Machine Learning Algorithms Based on Generated Smart Home Dataset, European Journal of Computer Science and Information Technology, Vol.9, No.4, pp.1-15, 2021

 

Keywords: classification algorithms, smart home, support vector machine

Article Review Status: Published

Pages: 42-53 (Download PDF)

Creative Commons Licence
This work by European American Journals is licensed under a Creative Commons Attribution-NonCommercial-NoDerivs 3.0 Unported License