Explainable AI (XAI) for Decision Transparency in Automated Industrial Operations

  • Authors

    • Dr. Matteo Rossi Professor, Sapienza University of Rome, Italy. Author
    • Dr. Giulia Romano Associate Professor University of Milan, Italy. Author

    DOI:

    https://doi.org/10.67228/3142788X/IJMLPA-2019PII1C8R

    Published 08-05-2019

  • Explainable AI (XAI), Decision Transparency, Industrial Automation, Trustworthy AI, Human-In-The-Loop, Predictive Maintenance, Interpretable Machine Learning, Operational Safety, AI Governance, Smart Manufacturing

    Issue

    Vol. 2 No. 2 (2019)

    Section

    Articles

    How to Cite

    [1]
    M. Rossi and G. Romano, “Explainable AI (XAI) for Decision Transparency in Automated Industrial Operations”, IJMLPA, vol. 2, no. 2, pp. 01–10, Aug. 2019, doi: 10.67228/3142788X/IJMLPA-2019PII1C8R.

  • Abstract

    As industrial operations grow increasingly reliant on artificial intelligence (AI) for automation and optimization, the need for transparency in AI-driven decision-making becomes critical. Traditional black-box models often lack interpretability, creating trust issues, safety concerns, and regulatory challenges. Explainable AI (XAI) seeks to address these concerns by providing human-understandable justifications for AI decisions. This paper explores the role of XAI in enhancing decision transparency within automated industrial environments. We present an overview of XAI techniques, evaluate their applicability in various industrial scenarios such as predictive maintenance, quality control, and autonomous process management, and discuss how explainability impacts stakeholder trust, compliance, and operational safety. We also propose a framework for integrating XAI into industrial AI systems, emphasizing real-time interpretability and human-in-the-loop design. The findings underscore that explainable AI not only enhances transparency but also drives responsible and sustainable adoption of AI in industry.

  • References

    [1] Doshi-Velez, F., & Kim, B. (2017). Towards A Rigorous Science of Interpretable Machine Learning. arXiv preprint arXiv:1702.08608.

    [2] Lundberg, S. M., & Lee, S.-I. (2017). A Unified Approach to Interpreting Model Predictions. In Advances in Neural Information Processing Systems (pp. 4765–4774).

    [3] Ribeiro, M. T., Singh, S., & Guestrin, C. (2016). "Why Should I Trust You?": Explaining the Predictions of Any Classifier. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 1135–1144).

    [4] Selvaraju, R. R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., & Batra, D. (2017). Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization. In Proceedings of the IEEE International Conference on Computer Vision (pp. 618–626).

    [5] Samek, W., Montavon, G., Vedaldi, A., Hansen, L. K., & Müller, K.-R. (Eds.). (2019). Explainable AI: Interpreting, Explaining and Visualizing Deep Learning. Springer.

    [6] Ribeiro, M. T., Singh, S., & Guestrin, C. (2018). Anchors: High-Precision Model-Agnostic Explanations. In AAAI Conference on Artificial Intelligence.

    [7] Adadi, A., & Berrada, M. (2018). Peeking Inside the Black-Box: A Survey on Explainable Artificial Intelligence (XAI). IEEE Access, 6, 52138–52160.

    [8] Gunning, D. (2017). Explainable Artificial Intelligence (XAI). Defense Advanced Research Projects Agency (DARPA).

    [9] Caruana, R., Lou, Y., Gehrke, J., Koch, P., Sturm, M., & Elhadad, N. (2015). Intelligible Models for Healthcare: Predicting Pneumonia Risk and Hospital 30-day Readmission. In Proceedings of the 21st ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 1721–1730).

    [10] Holzinger, A., Biemann, C., Pattichis, C. S., & Kell, D. B. (2017). What Do We Need to Build Explainable AI Systems for the Medical Domain? arXiv preprint arXiv:1712.09923.

  • Downloads