Random Forest vs. SVM vs. KNN in classifying Smartphone and Smartwatch sensor data using CRISP-DM
Sadiq Jaffer Saleh, Sayed Qasim Ali, Ahmed M. Zeki · 2020 International Conference on Data Analytics for Business and Industry: Way Towards a Sustainable Economy (ICDABI) · 2020
Nowadays IoT sensors become one of the major sources of data, starting from home automation going to daily devices. Focusing on handsets that have the most significant contribution factor on data blooming and booming. The problem at hand is data mining methods comparison, for selecting the best method that serves sensor data. Methodology used was CRISP-DM. This paper found Random Forest data mining method to work best under the described circumstances.