Telemedicine Based on Human Activity Recognition in Elderly Healthcare

Nowadays, telemedicine can provide remote clinical services for the elderly, using smart devices like embedded sensors, via real-time communication with the healthcare provider. In particular, inertial measurement sensors such as accelerometers embedded in smartphones can provide sensory data fusion...

Full description

Saved in:
Bibliographic Details
Published inStudies in health technology and informatics Vol. 302; p. 987
Main Authors Ghouchan Nezhad Noor Nia, Raheleh, Arzehgar, Afrooz, Dehdeleh, Vajiheh, Eslami, Saeid
Format Journal Article
LanguageEnglish
Published Netherlands 18.05.2023
Subjects
Aged
Health Facilities
Human Activities
Humans
Smartphone
Telemedicine - methods
Bayesian Networks
Healthcare
Human Activity
Markov Model
Recognition
Online AccessGet more information

Cover

More Information
Summary:Nowadays, telemedicine can provide remote clinical services for the elderly, using smart devices like embedded sensors, via real-time communication with the healthcare provider. In particular, inertial measurement sensors such as accelerometers embedded in smartphones can provide sensory data fusion for human activities. Thus, the technology of Human Activity Recognition can be applied to handle such data. In recent studies, the three-dimensional axis has been used to detect human activities. Since most changes in individual activities occur in the x- and y-axis, the label of each activity is determined using a new two-dimensional Hidden Markov Mode based on these two axes. To evaluate the proposed method, we use the WISDM dataset which is based on an accelerometer. The proposed strategy is compared to General Model and User-Adaptive Model. The results indicate that the proposed model is more accurate than the others.
ISSN:1879-8365
DOI:10.3233/SHTI230323