TY - GEN
T1 - COMPARATIVE ANALYSIS OF DIFFERENT MACHINE LEARNING MODELS FOR HUMAN ACTIVITY RECOGNITION
AU - Sawalha, G.
AU - Abuouelezz, W.
AU - Alhammadi, E.
AU - Alteneiji, A.
AU - Poon, K.
AU - Ali, N.
N1 - Publisher Copyright:
© 2023 Computers and Industrial Engineering. All rights reserved.
PY - 2023
Y1 - 2023
N2 - The application of Machine Learning (ML) algorithms to Human Activity Recognition (HAR) is a rapidly growing field of research with potential applications in elderly care. Recently, Deep Learning (DL) approaches have emerged as powerful alternatives, exhibiting significantly better recognition accuracy and superior performance. As a result, deep learning techniques have gained increasing attention and interest in the field of HAR, as they offer a promising way forward for advancing our understanding of human activity patterns and behaviors. This paper presents an in-depth comparative analysis of different machine learning models for the purpose of identifying the best model for an AI Elderly Activity Recognition System. Through this study, we analyze the performance of different models such as Neural Network (NN), 1D Convolutional Neural Network (1D-CNN), and Long Short-Term Memory (LSTM) network to identify activities such as walking, standing/idle positions, running, falls, Parkinson's and antalgic gait using both raw and preprocessed data.
AB - The application of Machine Learning (ML) algorithms to Human Activity Recognition (HAR) is a rapidly growing field of research with potential applications in elderly care. Recently, Deep Learning (DL) approaches have emerged as powerful alternatives, exhibiting significantly better recognition accuracy and superior performance. As a result, deep learning techniques have gained increasing attention and interest in the field of HAR, as they offer a promising way forward for advancing our understanding of human activity patterns and behaviors. This paper presents an in-depth comparative analysis of different machine learning models for the purpose of identifying the best model for an AI Elderly Activity Recognition System. Through this study, we analyze the performance of different models such as Neural Network (NN), 1D Convolutional Neural Network (1D-CNN), and Long Short-Term Memory (LSTM) network to identify activities such as walking, standing/idle positions, running, falls, Parkinson's and antalgic gait using both raw and preprocessed data.
KW - Deep Learning
KW - Elderly Healthcare
KW - Human Activity Recognition
KW - Long Short-Term Memory
KW - Neural Networks
UR - http://www.scopus.com/inward/record.url?scp=85184106629&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85184106629
T3 - Proceedings of International Conference on Computers and Industrial Engineering, CIE
SP - 580
EP - 589
BT - 50th International Conference on Computers and Industrial Engineering, CIE 2023
A2 - Dessouky, Yasser
A2 - Shamayleh, Abdulrahim
T2 - 50th International Conference on Computers and Industrial Engineering: Sustainable Digital Transformation, CIE 2023
Y2 - 30 October 2023 through 2 November 2023
ER -