AI-Based Predictive Maintenance in Edge IoT Devices: A Proactive Approach to Latency Reduction
DOI:
https://doi.org/10.63282/3050-9246.IJETCSIT-V3I1P107Keywords:
Explainable AI (XAI), Transparency, Artificial Intelligence, Predictive Maintenance, Edge computingAbstract
Integrating Artificial Intelligence (AI) into healthcare management has numerous benefits, especially in the diagnosis, treatment, and management of patients. Still, deploying the latest complex and frequently barely interpretable AI models, especially in key decision-making tasks, has spurred several urgent issues concerning trust, interpretability, and ethical use of AI. Explainable AI (XAI) has been developed to meet these challenges by making the AI model's decisions explainable to both the clinician and the patient. This paper seeks to discuss the work of XAI as a tool for improving the reliability of purposes and moral standards of medical AI systems. It elaborates on methods like model-agnostic explanations, attention-based methods, saliency maps, and inherently explainable models to classify their suitability in radiology, oncology, and clinical decision support systems. Additionally, the paper discusses the ethical and legal reasons for implementing the XAI, including GDPR and patient consent. In this paper, based on the literature review and case studies, explainability enhances user trust, aids in model reviewing, and enables bias detection in the algorithms. In conclusion, applying XAI in clinical practice benefits healthcare AI and patients and emphasizes responsible AI that respects people’s values and preferences
Downloads
References
[1] Zhu, T., Ran, Y., Zhou, X., & Wen, Y. (2019). A survey of predictive maintenance: Systems, purposes, and approaches. arXiv preprint arXiv:1912.07383.
[2] Liu, Y., Yu, W., Dillon, T., Rahayu, W., & Li, M. (2021). Empowering IoT predictive maintenance solutions with AI: A distributed system for manufacturing plant-wide monitoring. IEEE Transactions on Industrial Informatics, 18(2), 1345-1354.
[3] Lee, D., & Yoon, S. N. (2021). Application of artificial intelligence-based technologies in the healthcare industry: Opportunities and challenges. International journal of environmental research and public health, 18(1), 271.
[4] Compare, M., Baraldi, P., & Zio, E. (2019). Challenges to IoT-enabled predictive maintenance for industry 4.0. IEEE Internet of Things Journal, 7(5), 4585-4597.
[5] Ayvaz, S., & Alpay, K. (2021). Predictive maintenance system for production lines in manufacturing: A machine learning approach using IoT data in real-time. Expert Systems with Applications, 173, 114598.
[6] Chen, B., Wan, J., Celesti, A., Li, D., Abbas, H., & Zhang, Q. (2018). Edge computing in IoT-based manufacturing. IEEE Communications Magazine, 56(9), 103-109.
[7] Hassan, N., Gillani, S., Ahmed, E., Yaqoob, I., & Imran, M. (2018). The role of edge computing in the Internet of Things. IEEE Communications Magazine, 56(11), 110-115.
[8] Pan, J., & McElhannon, J. (2017). Future edge cloud and edge computing for Internet of Things applications. IEEE Internet of Things Journal, 5(1), 439-449.
[9] Zhang, K., Leng, S., He, Y., Maharjan, S., & Zhang, Y. (2018). Mobile edge computing and networking for green and low-latency Internet of Things. IEEE Communications Magazine, 56(5), 39-45.
[10] Raptis, T. P., Passarella, A., & Conti, M. (2018, May). Maximizing industrial IoT network lifetime under latency constraints through edge data distribution. In 2018 IEEE Industrial Cyber-Physical Systems (ICPS) (pp. 708-713). IEEE.
[11] Sharanya, S., Venkataraman, R., & Murali, G. (2022). Edge AI: from the perspective of predictive maintenance. In Applied Edge AI (pp. 171-192). Auerbach Publications.
[12] Tieng, H., Yang, H. C., & Li, Y. Y. (2021). Data acquisition and preprocessing. Industry 4.1: Intelligent Manufacturing with Zero Defects, 25-68.
[13] Hashemian, H. M. (2010). State-of-the-art predictive maintenance techniques. IEEE Transactions on Instrumentation and Measurement, 60(1), 226-236.
[14] Li, E., Zeng, L., Zhou, Z., & Chen, X. (2019). Edge AI: On-demand accelerating deep neural network inference via edge computing. IEEE transactions on wireless communications, 19(1), 447-457.
[15] Bohr, A., & Memarzadeh, K. (2020). The rise of artificial intelligence in healthcare applications. In Artificial Intelligence in Healthcare (pp. 25-60). Academic Press.
[16] Munir, A., Blasch, E., Kwon, J., Kong, J., & Aved, A. (2021). Artificial intelligence and data fusion at the edge. IEEE Aerospace and Electronic Systems Magazine, 36(7), 62-78.
[17] Belli, F., Hollmann, A., & Wong, W. E. (2010, June). Towards scalable robustness testing. In 2010 Fourth International Conference on Secure Software Integration and Reliability Improvement (pp. 208-216). IEEE.
[18] Nentwich, C., & Reinhart, G. (2021). Towards data acquisition for predictive maintenance of industrial robots. Procedia CIRP, 104, 62-67.
[19] Adler, R. M., & Cottman, B. H. (1989, January). A development framework for distributed artificial intelligence. In Proceedings The Fifth Conference on Artificial Intelligence Applications (pp. 115-116). IEEE Computer Society.
[20] Guo, M., Li, L., & Guan, Q. (2019). Energy-efficient and delay-guaranteed workload allocation in IoT-edge-cloud computing systems. IEEE Access, 7, 78685-78697.
