Activity recognition of stroke-affected people using wearable sensor
Stroke is one of the leading causes of long-term disability worldwide, placing huge burdens on individuals and society. Further, automatic human activity recognition is a challenging task that is vital to the future of healthcare and physical therapy. Using a baseline long short-term memory recurren...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Electronics and Telecommunications Research Institute (ETRI)
2023-12-01
|
| Series: | ETRI Journal |
| Subjects: | |
| Online Access: | https://doi.org/10.4218/etrij.2022-0242 |
| _version_ | 1797266520538087424 |
|---|---|
| author | Anusha David Rajavel Ramadoss Amutha Ramachandran Shoba Sivapatham |
| author_facet | Anusha David Rajavel Ramadoss Amutha Ramachandran Shoba Sivapatham |
| author_sort | Anusha David |
| collection | DOAJ |
| description | Stroke is one of the leading causes of long-term disability worldwide, placing huge burdens on individuals and society. Further, automatic human activity recognition is a challenging task that is vital to the future of healthcare and physical therapy. Using a baseline long short-term memory recurrent neural network, this study provides a novel dataset of stretching, upward stretching, flinging motions, hand-to-mouth movements, swiping gestures, and pouring motions for improved model training and testing of stroke-affected patients. A MATLAB application is used to output textual and audible prediction results. A wearable sensor with a triaxial accelerometer is used to collect preprocessed real-time data. The model is trained with features extracted from the actual patient to recognize new actions, and the recognition accuracy provided by multiple datasets is compared based on the same baseline model. When training and testing using the new dataset, the baseline model shows recognition accuracy that is 11% higher than the Activity Daily Living dataset, 22% higher than the Activity Recognition Single Chest- Mounted Accelerometer dataset, and 10% higher than another real-world dataset.
|
| first_indexed | 2024-04-25T01:02:00Z |
| format | Article |
| id | doaj.art-c6c8180ab3184c189e0b87ae187dc90c |
| institution | Directory Open Access Journal |
| issn | 1225-6463 |
| language | English |
| last_indexed | 2024-04-25T01:02:00Z |
| publishDate | 2023-12-01 |
| publisher | Electronics and Telecommunications Research Institute (ETRI) |
| record_format | Article |
| series | ETRI Journal |
| spelling | doaj.art-c6c8180ab3184c189e0b87ae187dc90c2024-03-11T02:32:28ZengElectronics and Telecommunications Research Institute (ETRI)ETRI Journal1225-64632023-12-014561079108910.4218/etrij.2022-0242Activity recognition of stroke-affected people using wearable sensorAnusha DavidRajavel RamadossAmutha RamachandranShoba SivapathamStroke is one of the leading causes of long-term disability worldwide, placing huge burdens on individuals and society. Further, automatic human activity recognition is a challenging task that is vital to the future of healthcare and physical therapy. Using a baseline long short-term memory recurrent neural network, this study provides a novel dataset of stretching, upward stretching, flinging motions, hand-to-mouth movements, swiping gestures, and pouring motions for improved model training and testing of stroke-affected patients. A MATLAB application is used to output textual and audible prediction results. A wearable sensor with a triaxial accelerometer is used to collect preprocessed real-time data. The model is trained with features extracted from the actual patient to recognize new actions, and the recognition accuracy provided by multiple datasets is compared based on the same baseline model. When training and testing using the new dataset, the baseline model shows recognition accuracy that is 11% higher than the Activity Daily Living dataset, 22% higher than the Activity Recognition Single Chest- Mounted Accelerometer dataset, and 10% higher than another real-world dataset. https://doi.org/10.4218/etrij.2022-0242accelerometerhuman activitylstmrecognitionstrokeswearable sensor |
| spellingShingle | Anusha David Rajavel Ramadoss Amutha Ramachandran Shoba Sivapatham Activity recognition of stroke-affected people using wearable sensor ETRI Journal accelerometer human activity lstm recognition strokes wearable sensor |
| title | Activity recognition of stroke-affected people using wearable sensor |
| title_full | Activity recognition of stroke-affected people using wearable sensor |
| title_fullStr | Activity recognition of stroke-affected people using wearable sensor |
| title_full_unstemmed | Activity recognition of stroke-affected people using wearable sensor |
| title_short | Activity recognition of stroke-affected people using wearable sensor |
| title_sort | activity recognition of stroke affected people using wearable sensor |
| topic | accelerometer human activity lstm recognition strokes wearable sensor |
| url | https://doi.org/10.4218/etrij.2022-0242 |
| work_keys_str_mv | AT anushadavid activityrecognitionofstrokeaffectedpeopleusingwearablesensor AT rajavelramadoss activityrecognitionofstrokeaffectedpeopleusingwearablesensor AT amutharamachandran activityrecognitionofstrokeaffectedpeopleusingwearablesensor AT shobasivapatham activityrecognitionofstrokeaffectedpeopleusingwearablesensor |