MACHINE LEARNING FOR AUTOMATIC CONTROL ELECTRICAL EQUIPMENT IN THE SMART HOME MODEL
Abstract
Machine Learning (Machine Learning) has been an interesting research topic and brings many important values in science and applications. This is a field of research that many scientists around the world participate in. The study “Smart Home Automation Using Machine Learning Algorithms” by John Jaihar group and members published in 2020 is one of the very new publications in the field of machine learning application for the problem of controlling electrical equipment in the smart home model. Another study can be mentioned published in 2019 by Sakshi Pandey on IoT Based Home Automation and Analysis Using Machine Learning (IoT Based Home Automation and Analysis Using Machine Learning) based on data collection. through the user’s system operation, applying algorithms to predict and give recommendations or warnings to the user. This study of the authors deals with the problem of controlling home appliances based on machine learning analyzing user habits and behaviors. Information related to the event that the user issues a command to control an electrical appliance in the home is recorded including the execution time of the command, the status of the device... and then used to train the models. Machine learning helps to perform classification, determine the command to be issued at the same time based on the trained model according to the user’s habits. The experimental results in the study have the best case accuracy with the K nearest neighbor model, decision tree, and random forest at 94 %, 95 %, and 95 % respectively.
References
Neeti Kumari, Vijay Khare, Home Automation using Speaker Identification. International Journal of Electronics, Electrical and Computational System, IJEECS, ISSN 2348-117X, 2017, Volume 6, Issue 5, May 2017.
Pandey, Sakshi and Jaiswal, Shanu and Yadav, Nitin and Sonawane, Jayashree, IoT Based Home Automation and Analysis Using Machine Learning, March 15, 2019. Available at SSRN: https://ssrn.com/abstract=3353476 or http://dx.doi.org/10.2139/ssrn.3353476 .
Xiao Guo, Zhenjiang Shen, Yajing Zhang and Teng Wu, Review on the Application of Artificial Intelligence in Smart Homes. Smart Cities 2019, 2, pp. 402 – 420; doi:10.3390/smartcities2030025.
László Kozma, k Nearest Neighbors algorithm (kNN), 2008, Helsinki University of Technology, http://www.lkozma.net/knn2.pdf.
Rukshan Manorathna, Random forests An ensemble of decision trees, 2021.
Vipin Kumar, Classification: Basic concepts, decision trees, and model evaluation, 2004, https://www-users.cse.umn.edu/~kumar001/dmbook/ch4.pdf.