DEEP LEARNING FOR RECOGNIZING DAILY HUMAN ACTIVITIES USING SMART HOME SENSORS
Issued Date
2023-12-01
Resource Type
ISSN
1881803X
Scopus ID
2-s2.0-85179062488
Journal Title
ICIC Express Letters
Volume
17
Issue
12
Start Page
1375
End Page
1383
Rights Holder(s)
SCOPUS
Bibliographic Citation
ICIC Express Letters Vol.17 No.12 (2023) , 1375-1383
Suggested Citation
Mekruksavanich S., Jantawong P., Surinta O., Hnoohom N., Jitpattanakul A. DEEP LEARNING FOR RECOGNIZING DAILY HUMAN ACTIVITIES USING SMART HOME SENSORS. ICIC Express Letters Vol.17 No.12 (2023) , 1375-1383. 1383. doi:10.24507/icicel.17.12.1375 Retrieved from: https://repository.li.mahidol.ac.th/handle/20.500.14594/91502
Title
DEEP LEARNING FOR RECOGNIZING DAILY HUMAN ACTIVITIES USING SMART HOME SENSORS
Other Contributor(s)
Abstract
One of the vital purposes of health-related studies is to enhance people’s living conditions and well-being. Solutions for smart homes could offer occupants preventive care based on the identification of regular activities. Recent advancements and developments in sensor technology have raised the demand for intelligent household products and services. The rising volume of data necessitates the development of the deep learning domain for the automated identification of human motions. Moreover, networks with long short-term memory have been used to represent spatio-temporal sequences recorded by smart home sensors. This study proposed ResNeXt-based models that learn to identify human behaviors in smart homes to increase detection capability. Experiment findings generated on a publicly available benchmark dataset known as CASAS data demonstrate that ResNeXt-based techniques surpass conventional DL approaches, achieving improved outcomes compared to the existing research. ResNeXt outperformed the benchmark approach by an average of 84.81%, 93.57%, and 90.38% for the CASAS Cairo, CASAS Milan, and CASAS Kyoto3 datasets, respectively.