Comparison between both Methods of Explanations: LIME and SHAP
Keywords:
Deep Learning, Explainable AI, More Coming Soon...Synopsis
This is a Chapter in:
Book:
Intelligent and Sustainable Solutions
Print ISBN 978-1-6692-0012-3
Online ISBN 978-1-6692-0011-6
Series:
Chronicle of Computing
Chapter Abstract:
Structural engineers can greatly benefit from understanding the reasons behind the behavior of machine learning algorithms in several key areas, such as feature engineering, model selection, confidence in predictions, taking action based on those predictions, and the development of more user-friendly interfaces. As a result, interpretability has become a central issue in deep learning, and research into interpretable models has gained significant attention from both industry and academia. Due to their transparency, these models are often preferred because they can achieve similar accuracy to non-interpretable models in certain applications. When interpretability is crucial, they may still be chosen even if their accuracy is slightly lower. However, limiting machine learning to models that are interpretable can often be a significant drawback. In this paper, we present a case study focused on predicting crack types using model-agnostic methods to explain deep learning predictions. These methods provide considerable flexibility in model selection, explanations, and representations by treating deep learning models as black-box functions.
About this Paper
Cite this paper as:
Lahna T., Kamsu-Foguem B.(2025). Comparison between both Methods of Explanations: LIME and SHAP. In: Tiako P.F. (ed) Intelligent and Sustainable Solutions. Chronicle of Computing. OkIP. CAIF25#11. https://doi.org/10.55432/978-1-6692-0011-6_8
Presented at:
The 2025 OkIP International Conference on Artificial Intelligence Frontiers (CAIF) in Oklahoma City, Oklahoma, USA, and Online, on April 2, 2025
Contact:
Tarik Lahna
lahnatk@ucla.edu
References
Attaccalite, L., Di Mascio, P., Loprencipe, G., & Pandolfi, C. (2012). Risk Assessment Around Airport. Procedia - Social and Behavioral Sciences, 53, 851–860.
Baltaci, N., İpek, Ö., & Akbulut Yıldız, G. (2015). The Relationship between Air Transport and Economic Growth in Turkey: Cross-Regional Panel Data Analysis Approach. 7, 89–100.
Bellini, V., Cascella, M., Cutugno, F., Russo, M., Lanza, R., Compagnone, C., & Bignami, E. G. (2022). Understanding basic principles of Artificial Intelligence: a practical guide for intensivists. Acta Bio-Medica : Atenei Parmensis, 93(5), e2022297.
E. Brynjolfsson and A.N. McAfee. (2017). What’s driving the Machine Learning explosion? Harvard Business Review, 18.
Fábio Celestino Pereira and Carlos Eduardo Pereira. Embedded image processing systems for automatic recognition of cracks using uavs. IFAC-PapersOnLine, 48(10):16–21, 2015.
Kuipers, B., Feigenbaum, E. A., Hart, P. E., & Nilsson, N. J. (2017). Shakey: From Conception to History. AI Magazine, 38(1), 88–103.
LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521(7553), 436–444.
Moor, J. (2006). The Dartmouth College Artificial Intelligence Conference: The Next Fifty Years. AI Magazine, 27(4), 87.
Peneda, M. J. A., Reis, V. D., & Macário, M. do R. M. R. (2011). Critical Factors for Development of Airport Cities. Transportation Research Record, 2214(1), 1–9.
Tarik Lahna, Bernard Kamsu-Foguem, Henry Fonbeyin Abanda,Maintenance in airport infrastructure: A bibliometric analysis and future research directions, Journal of Building Engineering, Volume 76, 2023, 106876
Lundberg, S. M., & Lee, S. I. (2017). A unified approach to interpreting model predictions. Advances in Neural Information Processing Systems, 30.
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.
Zhang, X., Ming, X., Liu, Z., Yin, D., Chen, Z., & Chang, Y. (2019). A reference framework and overall planning of industrial artificial intelligence (I-AI) for new application scenarios. The International Journal of Advanced Manufacturing Technology, 101(9), 2367–2389.
Zhuang, Y., Wu, F., Chen, C., & Pan, Y. (2017). Challenges and opportunities: from big data to knowledge in AI 2.0. Frontiers of Information Technology & Electronic Engineering, 18, 3–14.
