EXPLAINABLE AI (XAI): ENHANCING TRANSPARENCY AND TRUST IN AI SYSTEMS

Authors

  • Ali A Professor, Department of Computer Science & Engineering, Acropolis Institute of Technology & Research, Indore (M.P.)
  • Jain R

Keywords:

Explainable Artificial Intelligence (XAI), Trust, Transparency, SHAP (SHapley Additive exPlanations), Healthcare Diagnostics

Abstract

Explainable Artificial Intelligence (XAI) has emerged as a critical field addressing transparency and trust issues inherent in AI systems. This paper presents a comprehensive review of XAI methodologies, with a focus on their applications and the trade-offs between model accuracy and interpretability. A simulated case study in healthcare diagnostics demonstrates the practical utility of XAI techniques like SHAP (SHapley Additive exPlanations). The analysis highlights the importance of features such as tumor size and texture in predicting malignancy, providing insights into the model’s decision-making process. The paper concludes with a discussion of future directions in XAI, emphasizing the need for standardized evaluation metrics and hybrid models that balance transparency and performance.

References

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

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

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

Lundberg, S. M., & Lee, S.-I. (2017). A Unified Approach to Interpreting Model Predictions. Advances in Neural Information Processing Systems, 30, 4765-4774.

Caruana, R., et al. (2015). Intelligible Models for Healthcare: Predicting Pneumonia Risk and Hospital 30-Day Readmission. Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 1721-1730.

Downloads

Published

2022-04-01

How to Cite

Ali, A., & Jain, R. (2022). EXPLAINABLE AI (XAI): ENHANCING TRANSPARENCY AND TRUST IN AI SYSTEMS . COMPUSOFT: An International Journal of Advanced Computer Technology, 11, 3991–3994. Retrieved from https://ijact.in/index.php/j/article/view/624

Issue

Vol. 11 (2022): Jan-Dec

Section

Review Article

License

Copyright (c) 2022 COMPUSOFT: An International Journal of Advanced Computer Technology

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

©2023. COMPUSOFT: AN INTERNATIONAL OF ADVANCED COMPUTER TECHNOLOGY by COMPUSOFT PUBLICATION is licensed under a Creative Commons Attribution 4.0 International License. Based on a work at COMPUSOFT: AN INTERNATIONAL OF ADVANCED COMPUTER TECHNOLOGY. Permissions beyond the scope of this license may be available at Creative Commons Attribution 4.0 International Public License.