A Review on Explainable Artificial Intelligence Methods, Applications, and Challenges
Abstract
Explainable Artificial Intelligence (XAI) has emerged as a critical area of research and development in the field of artificial intelligence. This abstract provides an overview of XAI, covering its methods, applications, and challenges. XAI Methods: XAI methods aim to enhance the transparency and interpretability of complex machine learning models. Model-agnostic techniques like LIME and model-specific methods like SHAP have gained prominence in providing explanations for AI predictions. The field also explores interpretable deep learning architectures and approaches to make neural networks more transparent. XAI Applications: XAI finds applications across diverse domains. In healthcare, XAI assists in interpreting medical diagnoses and treatment recommendations. In finance, it aids in risk assessment and regulatory compliance. XAI is crucial in autonomous vehicles to explain decision-making processes, contributing to safety and trust. In customer service, it improves chatbot interactions by providing understandable responses. Moreover, XAI has relevance in agriculture, manufacturing, energy efficiency, education, content recommendation, and more. XAI Challenges: Despite its significance, XAI faces several challenges. Balancing model complexity with interpretability remains a fundamental trade-off. Detecting and mitigating bias in AI systems is crucial, especially in sensitive domains. Ensuring ethical considerations, data privacy, and user consent are paramount. Challenges also include providing explanations for high-stakes decisions, addressing the need for human oversight, and adapting to international and cultural norms. In conclusion, XAI plays a pivotal role in making AI systems more transparent, fair, and accountable. As it continues to evolve, it is poised to shape the future of AI by enabling users to understand and trust AI systems, fostering responsible AI development, and addressing ethical and practical challenges in various applications.
Keywords
References
W. Samek, T. Wiegand and K.-R. Müller, "Explainable Artificial Intelligence: Understanding Visualizing and Interpreting Deep Learning Models", ITU J. ICT Discov. - Spec. Issue 1 - Impact Artif. Intell. AI Commun. Netw. Serv., vol. 1, pp. 1-10, Dec. 2017.
Adadi, A., & Berrada, M. (2018). Peeking inside the black-box: A survey on explainable artificial intelligence (XAI). IEEE Access, 6, 52138–52160.
Abdul, A., Vermeulen, J., Wang, D., Lim, B. Y., & Kankanhalli, M. (2018). Trends and trajectories for explainable, accountable and intelligible systems: An HCI research agenda. Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems (CHI) (pp. 1–18).
Alam, L., & Mueller, S. (2021). Examining the effect of explanation on satisfaction and trust in AI diagnostic systems. BMC Medical Informatics and Decision Making, 21(1), 1–15.
Arrieta, A. B., Díaz-Rodríguez, N., Del Ser, J., Bennetot, A., Tabik, S., Barbado, A., García, S., Gil-López, S., Molina, D., Benjamins, R., Chatila, R., & Herrera, F. (2020). Explainable rtificial intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI. Information Fusion, 58, 82–115.
Bauer, K., Hinz, O., van der Aalst, W., & Weinhardt, C. (2021). Expl(AI)n it to me – Explainable AI and information systems research. Business & Information Systems Engineering, 63, 79–82.
Bertrand, A., Belloum, R., Eagan, J. R., & Maxwell, W. (2022). How cognitive biases affect XAI-assisted decision-making: A systematic review. Proceedings of the 2022 AAAI/ACM Conference on AI, Ethics, and Society (pp. 78–91).
Bunde, E. (2021). AI-assisted and explainable hate speech detection for social media moderators – A design science approach. Proceedings of the 2021 Annual Hawaii International Conference on System Sciences (HICSS) (pp. 1264–1274).
Chakrobartty, S., & El-Gayar, O. (2021). Explainable artificial intelligence in the medical domain: a systematic review. AMCIS 2021 Proceedings (p. 1).
Angelov, P., & Soares, E. (2020). Towards explainable deep neural networks (xDNN). Neural Networks, 130, 185–194.
Burkart, N., & Huber, M. F. (2020). A survey on the explainability of supervised machine learning. arXiv preprint arXiv:2011.07876.
Naeem Hamad, Alshammari Bandar M., Ullah Farhan Explainable artificial intelligence-based IoT device malware detection mechanism using image visualization and fine-tuned CNN-based transfer learning model Comput. Intell. Neurosci. (2022), Article 7671967
Alicioglu Gulsum, Sun Bo (2022), A survey of visual analytics for Explainable Artificial Intelligence methods Comput. Graph. 102 pp. 502-520.
Walia S., Kumar K., Agarwal S., Kim H. (2022), Using XAI for deep learning-based image manipulation detection with Shapley additive explanation Symmetry, 14 p. 1611,
Al Hammadi Ahmed Y., Yeun Chan Yeob, Damiani Ernesto, Yoo Paul D., Hu Jiankun, Yeun Hyun Ku, Yim Man-Sung (2021),Explainable artificial intelligence to evaluate industrial internal security using EEG signals in IoT framework Ad Hoc Netw., 123
Rozanec Joze M., Fortuna Blaz, Mladenic Dunja(2022), Knowledge graph-based rich and confidentiality preserving Explainable Artificial Intelligence (XAI) Inf. Fusion, 81 pp. 91-102.
W. Samek, G. Montavon, A. Vedaldi, L. K. Hansen, K. R. Muller, (2019), Explainable AI: Interpreting, Explaining and Visualizing Deep Learning (Springer Nature).
Ferreira, J. J., & Monteiro, M. S. (2020). What are people doing about XAI user experience? A survey on AI explainability research and practice. 2020 International Conference on Human-Computer Interaction (HCII) (pp. 56–73).
FleiB, J., Bäck, E., & Thalmann, S. (2020). Explainability and the intention to use AI-based conversational agents. An empirical investigation for the case of recruiting. CEUR Workshop Proceedings (CEUR-WS.Org) (vol 2796, pp. 1–5).
Förster, M., Klier, M., Kluge, K., & Sigler, I. (2020a). Evaluating explainable artificial intelligence – what users really appreciate. Proceedings of the 2020 European Conference on Information Systems (ECIS). A Virtual AIS Conference.
Ganeshkumar, M., Ravi, V., Sowmya, V., Gopalakrishnan, E. A., & Soman, K. P. (2021). Explainable deep learning-based approach for multilabel classification of electrocardiogram. IEEE Transactions on Engineering Management, 1–13.
Gerlings, J., Shollo, A., & Constantiou, I. (2021). Reviewing the need for explainable artificial intelligence (XAI). Proceedings of the 54th Hawaii International Conference on System Sciences (HICSS) (pp. 1284–1293).
Ha, T., Sah, Y. J., Park, Y., & Lee, S. (2022). Examining the effects of power status of an explainable artificial intelligence system on users’ perceptions. Behaviour & Information Technology, 41(5), 946–958.
Fellous, J. M., Sapiro, G., Rossi, A., Mayberg, H., & Ferrante, M. (2020). Explainable artificial intelligence for neuroscience: Behavioral neurostimulation. Frontiers in Neuroscience, 13, 1346.
Gilpin, L. H., Bau, D., Yuan, B. Z., Bajwa, A., Specter, M., & Kagal, L. (2018). Explaining explanations: An overview of interpretability of machine learning. In 2018 IEEE 5th International Conference on data science and advanced analytics (DSAA). IEEE (pp. 80–89).
Exarchos K.P., et al. Review of artificial intelligence techniques in chronic obstructive lung disease IEEE J. Biomed. Health Inform. 26 (5) (2022), pp. 2331-2338.
Mohammadi E., Alizadeh M., Asgarimoghaddam M., Wang X., Simões M.G.
A review on application of artificial intelligence techniques in microgrids IEEE J. Emerg. Sel. Top. Ind. Electron. 3 (4) (2022), pp. 878-890.
Mukhamediev R.I., Popova Y., Kuchin Y., Zaitseva E., Kalimoldayev A., Symagulov A., Levashenko V., Abdoldina F., Gopejenko V., Yakunin K., et al. Review of artificial intelligence and machine learning technologies: Classification, restrictions, opportunities and challenges Mathematics, 10 (2022), p. 2552.
Wei K., Chen B., Zhang J., Fan S., Wu K., Liu G., Chen D.Explainable deep learning study for leaf disease classification Agronomy, 12 (2022), p. 1035.
Naeem Hamad, Alshammari Bandar M., Ullah Farhan Explainable artificial intelligence-based IoT device malware detection mechanism using image visualization and fine-tuned CNN-based transfer learning model Comput. Intell. Neurosci. (2022), Article 7671967.
Langer Markus, Oster Daniel, Speith Timo, Hermanns Holger, Kästner Lena, Schmidt Eva, Sesing Andreas, Baum Kevin What do we want from Explainable Artificial Intelligence (XAI)? – A stakeholder perspective on XAI and a conceptual model guiding interdisciplinary XAI research Artificial Intelligence, 296 (2021).
Minh D., Wang H.X., Li Y.F., et al. Explainable artificial intelligence: a comprehensive review Artif. Intell. Rev., 55 (2022), pp. 3503-3568.
Walia S., Kumar K., Agarwal S., Kim H. Using XAI for deep learning-based image manipulation detection with Shapley additive explanation Symmetry, 14 (2022), p. 1611.
Yang C.C. Explainable artificial intelligence for predictive modeling in healthcare J. Healthc. Inform. Res., 6 (2022), pp. 228-239.
Obayya M., Nemri N., Nour M.K., Al Duhayyim M., Mohsen H., Rizwanullah M., Sarwar Zamani A., Motwakel A. Explainable artificial intelligence enabled TeleOphthalmology for diabetic retinopathy grading and classification Appl. Sci., 12 (2022), p. 8749.
Anand Atul, Kadian Tushar, Shetty Manu Kumar, Gupta Anubha Explainable AI decision model for ECG data of cardiac disorders Biomed. Signal Process. Control, 75 (2022).
Mehta H., Passi K. Social media hate speech detection using explainable artificial intelligence (XAI) Algorithms, 15 (2022), p. 291.
Deshpande Nilkanth Mukund, et al. Explainable artificial intelligence–a new step towards the trust in medical diagnosis with AI frameworks: A review Comput. Model. Eng. Sci., 133 (2022).
Speith Timo A review of taxonomies of explainable artificial intelligence (XAI) methods 2022 ACM Conference on Fairness, Accountability, and Transparency (2022).
Pradhan Romila, et al. Explainable AI: Foundations, applications, opportunities for data management research 2022 IEEE 38th International Conference on Data Engineering, ICDE, IEEE (2022).
Islam M.R., Ahmed M.U., Barua S., Begum S. A systematic review of explainable artificial intelligence in terms of different application domains and tasks Appl. Sci., 12 (2022), p. 1353.
Zhang Y., Weng Y., Lund J. Applications of explainable artificial intelligence in diagnosis and surgery Diagnostics, 12 (2022), p. 237.
Vale, D.; El-Sharif, A.; Ali, M. Explainable artificial intelligence (XAI) post-hoc explainability methods: Risks and limitations in non-discrimination law. AI Ethics 2022, 2, 815–826.
Refbacks
- There are currently no refbacks.
Indonesian Journal of Electrical Engineering and Informatics (IJEEI)
ISSN 2089-3272
This work is licensed under a Creative Commons Attribution 4.0 International License.