Optimizing Edge Computing for Activity Recognition: A Bidirectional LSTM Approach on the PAMAP2 Dataset
Received: 30 August 2024 | Revised: 25 September 2024 | Accepted: 4 October 2024 | Online: 21 October 2024
Corresponding author: Amar Y. Jaffar
Abstract
This study investigates the application of a Bidirectional Long Short-Term Memory (BiLSTM) model for Human Activity Recognition (HAR) using the PAMAP2 dataset. The aim was to enhance the accuracy and efficiency of recognizing daily activities captured by wearable sensors. The proposed BiLSTM-based model achieved outstanding performance, with 98.75% training accuracy and 99.27% validation accuracy. It also demonstrated high precision, recall, and F1 scores (all 0.99). Comparative analysis with state-of-the-art models, including Deep-HAR and CNN-BiLSTM-BiGRU, revealed that the proposed BiLSTM model surpassed their performance. These results highlight the potential of the proposed approach for real-time HAR applications in edge computing, particularly where accurate and efficient activity recognition is crucial.
Keywords:
human activity recognition, bidirectional long short-term memory, PAMAP2 dataset, deep learning, edge computing, wearable sensorsDownloads
References
J. Wang, Y. Chen, S. Hao, X. Peng, and L. Hu, "Deep learning for sensor-based activity recognition: A survey," Pattern Recognition Letters, vol. 119, pp. 3–11, Mar. 2019.
H. Ullah and A. Munir, "Human Action Representation Learning Using an Attention-Driven Residual 3DCNN Network," Algorithms, vol. 16, no. 8, Aug. 2023, Art. no. 369.
S. Yao, S. Hu, Y. Zhao, A. Zhang, and T. Abdelzaher, "DeepSense: A Unified Deep Learning Framework for Time-Series Mobile Sensing Data Processing," in Proceedings of the 26th International Conference on World Wide Web, Perth, Australia, Apr. 2017, pp. 351–360.
K. Warunsin, K. Promjiraprawat, and O. Chitsobhuk, "Human Activity Recognition Using Long Short-Term Memory Network." ICIC International, 2023.
N. Hassan, A. S. M. Miah, and J. Shin, "A Deep Bidirectional LSTM Model Enhanced by Transfer-Learning-Based Feature Extraction for Dynamic Human Activity Recognition," Applied Sciences, vol. 14, no. 2, Jan. 2024, Art. no. 603.
Y. Li and L. Wang, "Human Activity Recognition Based on Residual Network and BiLSTM," Sensors, vol. 22, no. 2, Jan. 2022, Art. no. 635.
S. Jameer and H. Syed, "Deep SE-BiLSTM with IFPOA Fine-Tuning for Human Activity Recognition Using Mobile and Wearable Sensors," Sensors, vol. 23, no. 9, Apr. 2023, Art. no. 4319.
M. Alanazi, R. S. Aldahr, and M. Ilyas, "Human Activity Recognition through Smartphone Inertial Sensors with ML Approach," Engineering, Technology & Applied Science Research, vol. 14, no. 1, pp. 12780–12787, Feb. 2024.
A. Reiss and D. Stricker, "Creating and benchmarking a new dataset for physical activity monitoring," in Proceedings of the 5th International Conference on PErvasive Technologies Related to Assistive Environments, Heraklion, Greece, Jun. 2012, pp. 1–8.
D. Anguita, A. Ghio, L. Oneto, X. Parra Perez, and J. L. Reyes Ortiz, "A public domain dataset for human activity recognition using smartphones," presented at the Proceedings of the 21th International European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, 2013, pp. 437–442.
J. Wang, Q. Long, PiRahc, K. Liu, and Y. Xie, "Human Action Recognition on Cellphone Using Compositional Bidir-LSTM-CNN Networks," presented at the 2019 International Conference on Computer, Network, Communication and Information Systems (CNCI 2019), May 2019, pp. 687–692.
K. Xia, J. Huang, and H. Wang, "LSTM-CNN Architecture for Human Activity Recognition," IEEE Access, vol. 8, pp. 56855–56866, 2020.
T. H. Tan, C. J. Huang, M. Gochoo, and Y. F. Chen, "Activity Recognition Based on FR-CNN and Attention-Based LSTM Network," in 2021 30th Wireless and Optical Communications Conference (WOCC), Taipei, Taiwan, Oct. 2021, pp. 146–149.
F. Hernandez, L. F. Suarez, J. Villamizar, and M. Altuve, "Human Activity Recognition on Smartphones Using a Bidirectional LSTM Network," in 2019 XXII Symposium on Image, Signal Processing and Artificial Vision (STSIVA), Bucaramanga, Colombia, Apr. 2019, pp. 1–5.
D. Yilmaz and İ. E. Büyüktahtakın, "Learning Optimal Solutions via an LSTM-Optimization Framework," Operations Research Forum, vol. 4, no. 2, Jun. 2023, Art. no. 48.
V. Aswal, V. Sreeram, A. Kuchik, S. Ahuja, and H. Patel, "Real-Time Human Activity Generation using Bidirectional Long Short Term Memory Networks," in 2020 4th International Conference on Intelligent Computing and Control Systems (ICICCS), Madurai, India, May 2020, pp. 775–780.
G. Mohmed, D. A. Adama, and A. Lotfi, "Fuzzy Feature Representation with Bidirectional Long Short-Term Memory for Human Activity Modelling and Recognition," in Advances in Computational Intelligence Systems, Portsmouth, UK, 2020, pp. 15–26.
V. B. Semwal, A. Gupta, and P. Lalwani, "An optimized hybrid deep learning model using ensemble learning approach for human walking activities recognition," The Journal of Supercomputing, vol. 77, no. 11, pp. 12256–12279, Nov. 2021.
P. Gong, C. Wang, and L. Zhang, "MMPoint-GNN: Graph Neural Network with Dynamic Edges for Human Activity Recognition through a Millimeter-Wave Radar," in 2021 International Joint Conference on Neural Networks (IJCNN), Shenzhen, China, Jul. 2021, pp. 1–7.
L. Alawneh, B. Mohsen, M. Al-Zinati, A. Shatnawi, and M. Al-Ayyoub, "A Comparison of Unidirectional and Bidirectional LSTM Networks for Human Activity Recognition," in 2020 IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops), Austin, TX, USA, Mar. 2020, pp. 1–6.
"Workout Action Recognition in Video Streams Using an Attention Driven Residual DC-GRU Network," Computers, Materials and Continua, vol. 79, no. 2, pp. 3067–3087, May 2024.
M. Alanazi, R. S. Aldahr, and M. Ilyas, "Human Activity Recognition through Smartphone Inertial Sensors with ML Approach," Engineering, Technology & Applied Science Research, vol. 14, no. 1, pp. 12780–12787, Feb. 2024.
A. Dey, S. Biswas, and L. Abualigah, "Efficient Violence Recognition in Video Streams using ResDLCNN-GRU Attention Network," ECTI Transactions on Computer and Information Technology (ECTI-CIT), vol. 18, no. 3, pp. 329–341, Jul. 2024.
A. Tehrani, M. Yadollahzadeh-Tabari, A. Zehtab-Salmasi, and R. Enayatifar, "Wearable Sensor-Based Human Activity Recognition System Employing Bi-LSTM Algorithm," The Computer Journal, vol. 67, no. 3, pp. 961–975, Apr. 2024.
G. Bhola and D. K. Vishwakarma, "A review of vision-based indoor HAR: state-of-the-art, challenges, and future prospects," Multimedia Tools and Applications, vol. 83, no. 1, pp. 1965–2005, Jan. 2024.
S. Mekruksavanich and A. Jitpattanakul, "Deep Convolutional Neural Network with RNNs for Complex Activity Recognition Using Wrist-Worn Wearable Sensor Data," Electronics, vol. 10, no. 14, Jul. 2021, Art. no. 1685.
S. Gupta, "Deep learning based human activity recognition (HAR) using wearable sensor data," International Journal of Information Management Data Insights, vol. 1, no. 2, Nov. 2021, Art. no. 100046.
Downloads
How to Cite
License
Copyright (c) 2024 Anupama Bollampally, J. Kavitha, P. Sumanya, P. Rajesh, Amar Y. Jaffar, Wesam N. Eid, Hussain M. Albarakati, Fahd M. Aldosari, Ayman A. Alharbi
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain the copyright and grant the journal the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) after its publication in ETASR with an acknowledgement of its initial publication in this journal.
