Compare of Machine Learning and Deep Learning Approaches for Human Activity Recognition

• Published in: 2022 30th International Conference on Electrical Engineering (ICEE) pp. 592 - 596
• Main Authors: Moradi, Babak, Aghapour, Mohammad, Shirbandi, Afshin
• Format: Conference Proceeding
• Language: English
• Published: IEEE 17.05.2022
• Subjects: Activity recognition; Bi-Directional LSTM; Bidirectional control; CNN; CNN-LSTM; Electrical engineering; Human activity recognition; Human computer interaction; Logistic Regression; LSTM; Machine learning algorithms; Support vector machines; SVM with RBF kernel; Training
• DOI: 10.1109/ICEE55646.2022.9827335

Human-centered computing is an emerging research field that aims to understand human behavior and integrate users and their social context with computer systems. This research aimed to find the best algorithm for human activity recognition. We used Logistic Regression, SVM with RBF kernel; CNN, LSTM, Bi-Directional LSTM, and CNNLSTM algorithms for analyzing the data. The data analysis measured and compared the accuracy and training time. The most accuracy belonged to the CNN-LSTM and Bi-Directional LSTM, and the least training time belonged to the SVM with RBF kernel