Advancing AI-Powered Wearables - A Novel Approach for Real-Time Health Monitoring
DOI:
https://doi.org/10.32628/CSEIT2390383Keywords:
AI-powered wearables, health monitoring, ECG analysis, LSTM, Transformer models, federated learning, real-time inference, multimodal sensor dataAbstract
With a focus on heart rate and ECG signal analysis, this study investigates the function of wearable technology driven by artificial intelligence in real-time health monitoring. It investigates how well Transformer models and Long Short-Term Memory (LSTM) networks can increase prediction accuracy. This study offers a comparative analysis of these models using publicly accessible datasets and clearly defined evaluation metrics. Additionally, the study evaluates their performance using F1-score, recall, accuracy, and precision. The study also discusses clinical applicability and model interpretability. However, it's important to note that the study is limited by the scope and quality of the publicly available datasets. To improve wearable healthcare solutions, future research will concentrate on integrating multimodal sensor data, developing federated learning techniques for safe AI implementation, and improving real-time inference on edge AI platforms.
References
- Pantelopoulos, A., & Nikolaou, N. (2022). Advances in wearable sensor-based health monitoring. IEEE Transactions on Biomedical Engineering. https://doi.org/10.1109/TBME.2022.3145678
- Vaswani, A., et al. (2017). Attention is all you need. Advances in Neural Information Processing Systems (NeurIPS), 30. arXiv:1706.03762. https://arxiv.org/abs/1706.03762
- McMahan, B., et al. (2017). Communication-efficient federated learning. Advances in Neural Information Processing Systems (NeurIPS), 30. arXiv:1710.06963. https://arxiv.org/abs/1710.06963
- Goldberger, A. L., et al. (2000). PhysioNet: Components of a complex physiologic signals archive. Circulation, 101(21), e215-e220. https://doi.org/10.1161/01.CIR.101.23.e215
- Dataset: Goldberger, A. L., et al. (2000). MIT-BIH Arrhythmia Database. PhysioNet. https://doi.org/10.13026/C2F305
- Yildirim, O., et al. (2018). ECG classification using deep learning models. Biomedical Signal Processing and Control, 43, 152-162. https://doi.org/10.1016/j.bspc.2018.03.005
- Kingma, D. P., & Ba, J. (2014). Adam: A method for stochastic optimization. arXiv preprint, arXiv:1412.6980. https://arxiv.org/abs/1412.6980
- Ioffe, S., & Szegedy, C. (2015). Batch normalization: Accelerating deep network training. International Conference on Machine Learning (ICML), 448-456.
- Han, D., et al. (2021). Real-time edge AI for wearable healthcare applications. IEEE Transactions on Mobile Computing, 22(1), 256-270. https://doi.org/10.1109/TMC.2021.3055648
- Privacy-Preserving Federated Learning in Healthcare - A Secure AI Framework. (2024). International Journal of Scientific Research in Computer Science, Engineering and Information Technology, 10(3), 703-707. https://doi.org/10.32628/CSEIT2410347
- Abadi, M., et al. (2016). TensorFlow: A system for large-scale machine learning. USENIX Symposium on Operating Systems Design and Implementation (OSDI), 265-283.
- Schroff, F., et al. (2015). FaceNet: A unified embedding for face recognition and clustering. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 815-823.
- Esteva, A., et al. (2017). Dermatologist-level classification of skin cancer with deep neural networks. Nature, 542(7639), 115-118.
- Deng, J., et al. (2009). ImageNet: A large-scale hierarchical image database. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 248-255.
- Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9(8), 1735-1780. https://doi.org/10.1162/neco.1997.9.8.1735
- Sankar, T. B., Kumar, S. A., & Tarun, G. B. S.. (2018). A Sustainable and Automated Irrigation and Field Monitoring System Using IoT. International Journal of Technical Innovation in Modern Engineering & Science, 4(12), 268–274. Retrieved from https://www.ijtimes.com/index.php/ijtimes/article/view/186, DOI: 10.5281/zenodo.14948446
Downloads
Published
Issue
Section
License
Copyright (c) IJSRCSEIT
This work is licensed under a Creative Commons Attribution 4.0 International License.