Academic Journal
Temporal Convolutional Recurrent Neural Network for Elderly Activity Recognition
| العنوان: | Temporal Convolutional Recurrent Neural Network for Elderly Activity Recognition |
|---|---|
| المؤلفون: | Ng Jia Hui, Pang Ying Han, Sarmela Raja Sekaran, Ooi Shih Yin, Lillian Yee Kiaw Wang |
| المصدر: | Journal of Engineering Technology and Applied Physics, Vol 6, Iss 2, Pp 84-91 (2024) |
| بيانات النشر: | MMU Press, 2024. |
| سنة النشر: | 2024 |
| المجموعة: | LCC:Mechanics of engineering. Applied mechanics LCC:Technology |
| مصطلحات موضوعية: | elderly activity recognition, multi-stream, recurrent neural network, deep learning, temporal convolutional, Mechanics of engineering. Applied mechanics, TA349-359, Technology |
| الوصف: | Research on smartphone-based human activity recognition (HAR) is prevalent in the field of healthcare, especially for elderly activity monitoring. Researchers usually propose to use of accelerometers, gyroscopes or magnetometers that are equipped in smartphones as an individual sensing modality for human activity recognition. However, any of these alone is limited in capturing comprehensive movement information for accurate human activity analysis. Thus, we propose a smartphone-based HAR approach by leveraging the inertial signals captured by these three sensors to classify human activities. These heterogeneous sensors deliver information on various aspects of nature, motion and orientation, offering a richer set of features for more accurate representations of the activities. Hence, a deep learning approach that amalgamates long short-term memory (LSTM) in temporal convolutional network (TCN) is proposed. We use independent temporal convolutional networks, coined as temporal convolutional streams, to independently analyse the temporal data of each sensing modality. We name this architecture multi-stream TC-LSTM. The performance of multi-stream TC-LSTM is assessed on the self-collected elderly activity database. Empirical results exhibit that multi-stream TC-LSTM outperforms the existing machine learning and deep learning models, with an F1 score of 98.3 %. |
| نوع الوثيقة: | article |
| وصف الملف: | electronic resource |
| اللغة: | English |
| تدمد: | 2682-8383 |
| Relation: | https://journals.mmupress.com/index.php/jetap/article/view/1077/642; https://doaj.org/toc/2682-8383 |
| DOI: | 10.33093/jetap.2024.6.2.12 |
| URL الوصول: | https://doaj.org/article/8843bb65ebbb484494dc748987d5dda6 |
| رقم الانضمام: | edsdoj.8843bb65ebbb484494dc748987d5dda6 |
| قاعدة البيانات: | Directory of Open Access Journals |
| تدمد: | 26828383 |
|---|---|
| DOI: | 10.33093/jetap.2024.6.2.12 |