Non-intrusive robust human activity recognition for diverse age groups
—Many elderly prefer to live independently at their own homes. However, how to use modern technologies to ensure their safety presents vast challenges and opportunities. Being able to non-intrusively sense the activities performed by the elderly definitely has great advantages in various circumstanc...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | text |
| Language: | English |
| Published: |
Institutional Knowledge at Singapore Management University
2015
|
| Subjects: | |
| Online Access: | https://ink.library.smu.edu.sg/sis_research/5491 https://ink.library.smu.edu.sg/context/sis_research/article/6494/viewcontent/IAT2015.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Singapore Management University |
| Language: | English |
| Summary: | —Many elderly prefer to live independently at their own homes. However, how to use modern technologies to ensure their safety presents vast challenges and opportunities. Being able to non-intrusively sense the activities performed by the elderly definitely has great advantages in various circumstances. Non-intrusive activity recognition can be performed using the embedded sensors in modern smartphones. However, not many activity recognition models are robust enough that allow the subjects to carry the smartphones in different pockets with unrestricted orientations and varying deviations. Moreover, to the best of our knowledge, no existing literature studied the difference between the youth and the elderly groups in terms of human activity recognition using smartphones. In this paper, we present our approach to perform robust activity recognition using only the accelerometer readings collected from the smartphone. First, we tested our model on two published data sets and found its performance is encouraging when compared against other models. Furthermore, we applied our model on two newly collected data sets: one consists of only young subjects (mean age = 22.5) and the other consists of only elderly subjects (mean age = 70.5). The experimental results show convincing prediction accuracy for both within and across diverse age groups. This paper fills the blank of elderly activity recognition using smartphones and shows promising results, which will serve as the groundwork of our future extensions to the current model. |
|---|