Computational Design and Temporal Signal Analysis for Wearable Smart Textiles: AI-Driven Sensor Layout Optimization and Deep Learning-Based Anomaly Detection

Zixi Liu

doi:10.54254/2755-2721/2025.MH24964

Abstract

Smart wearable fabrics are breaking through the technical bottlenecks of traditional health monitoring. The key lies in solving the adaptation problem between sensor layout and dynamic perception. By targeting pain points such as signal distortion and high false detection rate existing in current schemes, this study builds a new framework driven by the dual engines of “algorithm design + deep learning”. Through a hybrid optimization model integrating genetic algorithm and reinforcement learning, the global search for optimal solutions for multi-objective parameters (constraint coverage, signal redundancy, and wearing comfort) was realized for the first time, and the best sensor array layout scheme was found. At the end of data processing, the bidirectional long short-term memory (Bi-LSTM) network based on the attention mechanism can accurately capture abnormal fluctuations in time series data, complete diagnostic decisions within 120 milliseconds, and the detection accuracy rate reaches 95.4%, showing stronger anti-environmental interference capability compared to traditional methods. These breakthroughs pave the way for the practical application of smart clothing, especially in scenarios with strict real-time requirements such as sports rehabilitation and elderly monitoring, where the application potential is obvious. Further research will focus on integrating model lightweighting and autonomous power supply to further improve the energy efficiency ratio and wearable adaptability of the system.

Keywords: Smart Textiles , Wearable Sensing , Sensor Layout Optimization , Deep Learning , Bi-LSTM

Article Information

Received: 2 July 2025

Published: 11 July 2025

DOI: https://doi.org/10.54254/2755-2721/2025.MH24964

Article Type: Research Article

Cite this article

Liu,Z. (2025). Computational Design and Temporal Signal Analysis for Wearable Smart Textiles: AI-Driven Sensor Layout Optimization and Deep Learning-Based Anomaly Detection. Applied and Computational Engineering,156,8-13.

Data availability

The datasets used and/or analyzed during the current study will be available from the authors upon reasonable request.

Disclaimer/Publisher's Note

The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of EWA Publishing and/or the editor(s). EWA Publishing and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content.

About this Volume

Volume Title: ACE Vol.156

Part of Series: Applied and Computational Engineering

ISSN: 2755-2721 (Print) / 2755-273X (Online)

Copyright & License

[1]Li, Y., & Wang, L. (2022). Human activity recognition based on residual network and BiLSTM. Sensors, 22(3), 635.MDPI

[2]Nafea, O., Abdul, W., & Muhammad, G. (2021). Sensor-based human activity recognition with spatio-temporal deep learning. Sensors, 21(6), 2141.MDPI

[3]Mekruksavanich, S., & Jitpattanakul, A. (2021). Biometric user identification based on human activity recognition using wearable sensors: An experiment using deep learning models. Electronics, 10(3), 308.MDPI

[4]Gao, W., Zhang, L., Teng, Q., He, J., & Wu, H. (2021). DanHAR: Dual attention network for multimodal human activity recognition using wearable sensors. Applied Soft Computing, 111, 107728.MDPI

[5]Qiu, S., Zhao, H., Jiang, N., Wang, Z., Liu, L., An, Y., ... & Fortino, G. (2022). Multi-sensor information fusion based on machine learning for real applications in human activity recognition: State-of-the-art and research challenges. Information Fusion, 80, 241–265.MDPI

[6]Tang, Y., Zhang, L., Min, F., & He, J. (2022). Multi-scale deep feature learning for human activity recognition using wearable sensors. IEEE Transactions on Industrial Electronics, 70(3), 2106–2116.MDPI

[7]Khan, I. U., Afzal, S., & Lee, J. W. (2022). Human activity recognition via hybrid deep learning based model. Sensors, 22(1), 323.MDPI

[8]Cheng, X., Zhang, L., Tang, Y., Liu, Y., Wu, H., & He, J. (2022). Real-time human activity recognition using conditionally parametrized convolutions on mobile and wearable devices. IEEE Sensors Journal, 22(6), 5889–5901.MDPI

[9]Coelho, Y. L., dos Santos, F. D. A. S., Frizera-Neto, A., & Bastos-Filho, T. F. (2021). A lightweight framework for human activity recognition on wearable devices. IEEE Sensors Journal, 21(20), 24471–24481.MDPI

[10]Han, C., Zhang, L., Tang, Y., Huang, W., Min, F., & He, J. (2022). Human activity recognition using wearable sensors by heterogeneous convolutional neural networks. Expert Systems with Applications, 198, 116764.MDPI

[11]Dirgová Luptáková, I., Kubovčík, M., & Pospíchal, J. (2022). Wearable sensor-based human activity recognition with transformer model. Sensors, 22(5), 1911.MDPI+1MDPI+1

[12]Dua, N., Singh, S. N., & Semwal, V. B. (2022). Multi-input CNN-GRU based human activity recognition using wearable sensors. Computing, 104(6), 1461–1478.MDPI

[13]Jain, R., Semwal, V. B., & Kaushik, P. (2022). Deep ensemble learning approach for lower extremity activities recognition using wearable sensors. Expert Systems, 39(3), e12743.MDPI