Open Access Open Access  Restricted Access Subscription or Fee Access

Unlocking the Potential: Machine Learning Driven Explainable AI Applications Across Diverse Domains

Mritunjay Kumar Ranjan, Kushal Roy, Anushka Mahind, Devashish Bhavsar, Somesh Nemade, Arif Md. Sattar

Abstract


Explainable artificial intelligence (XAI) aims to make discoveries and output generated by machine learning algorithms accessible to human users in a trustworthy and easy-to-understand manner. It describes the impact of an AI model and any potential biases, helping in characterizing models with accuracy, fairness, transparency, and outcomes in decision-making powered by AI. XAI focuses on understanding the data used to train the model, its predictions, the specific elements involved in producing those predictions, and the role of the algorithms used. There are several primary categories of approaches to explain AI systems, such as self-interpretable models and post-hoc justifications. The four pillars of explainable artificial intelligence are explicitness, meaningfulness, explanatory accuracy, and knowledge boundaries. AI has been widely used in the medical field, with applications ranging from clinical decision support to cancer localization in MRI scans to report reading and analysis in radiology and pathology. However, AI has also been applied in other areas of the medical industry, with concerns about its perceived "black box" nature, which can lower trust in its accuracy. This has led to the popularity of explainable artificial intelligence (XAI) in the healthcare industry. This study provides an introductory overview of various methods for explaining and understanding predictions generated by complex machine learning models like deep neural networks. It explores various methodologies, including LIME, anchors, Graph LIME, LRP, DTD, PDA, TCAV, XGNN, SHAP, ASV, break-down, Shapley Flow, textual explanations of visual models, causal models, integrated gradients, meaningful perturbations, and X-NeSyL.

Full Text:

PDF

References


Tantithamthavorn CK, Jiarpakdee J. Explainable AI for Software Engineering. 2021 36th IEEE/ACM International Conference on Automated Software Engineering (ASE), Melbourne, Australia. 2021; 1–2. doi: 10.1109/ASE51524.2021.9678580.

Datta G, Joshi N, Gupta K. Study of NMT: An Explainable AI based approach. 2021 5th International Conference on Information Systems and Computer Networks (ISCON), Mathura, India. 2021; 1–4. doi: 10.1109/ISCON52037.2021.9702396.

Heimerl A, Weitz K, Baur T, André E. Unraveling ML Models of Emotion With NOVA: Multi-Level Explainable AI for Non-Experts. IEEE Trans Affect Comput. 2022 Jul–Sep 1; 13(3): 1155–1167. doi: 10.1109/TAFFC.2020.3043603.

Ryu J, Park C, Park J, Cho N, Park J, Cho G. Development of Neural Network Model with Explainable AI for Measuring Uranium Enrichment. IEEE Trans Nucl Sci. 2021 Nov; 68(11): 2670–2681. doi: 10.1109/TNS.2021.3116090.

Ehsan U, Riedl MO. (2020). Human-centered explainable AI: Towards a reflective sociotechnical approach. In: Stephanidis C, Kurosu M, Degen H, Reinerman-Jones, L. (eds) HCI International 2020-Late Breaking Papers: Multimodality and Intelligence. HCII 2020. Lecture Notes in Computer Science, vol. 12424. Springer, Cham. Available at: https://doi.org/10.1007/978-3-030-60117-1_33.

Deramgozin M, Jovanovic S, Rabah H, Ramzan N. A Hybrid Explainable AI Framework Applied to Global and Local Facial Expression Recognition. 2021 IEEE International Conference on Imaging Systems and Techniques (IST), Kaohsiung, Taiwan. 2021; 1–5. doi: 10.1109/IST50367.2021.9651357.

Ng CH, Abuwala HS, Lim CH. Towards More Stable LIME For Explainable AI. 2022 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS), Penang, Malaysia. 2022; 1–4. doi: 10.1109/ISPACS57703.2022.10082810.

Chhatwal R, Gronvall P, Huber-Fliflet N, Keeling R, Zhang J, Zhao H. Explainable Text Classification in Legal Document Review A Case Study of Explainable Predictive Coding. 2018 IEEE International Conference on Big Data (Big Data), Seattle, WA, USA. 2018; 1905–1911. doi: 10.1109/BigData.2018.8622073.

Pham D, et al. A Case Study of Human-AI Interactions Using Transparent AI-Driven Autonomous Systems for Improved Human-AI Trust Factors. 2022 IEEE 3rd International Conference on Human-Machine Systems (ICHMS), Orlando, FL, USA. 2022; 1–6. doi: 10.1109/ICHMS56717.2022.9980662.

Raj D, et al. Anchored Speech Recognition with Neural Transducers. ICASSP 2023–2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Rhodes Island, Greece. 2023; 1–5. doi: 10.1109/ICASSP49357.2023.10096944.

Lili L, et al. AI-Based Behavioral Competency Assessment Tool to Enhance Navigational Safety. 2021 International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME), Mauritius, Mauritius. 2021; 1–6. doi: 10.1109/ICECCME52200.2021.9590891.

Guidotti R, Monreale A, Giannotti F, Pedreschi D, Ruggieri S, Turini F. Factual and Counterfactual Explanations for Black Box Decision Making. IEEE Intell Syst. 2019 Nov–Dec 1; 34(6): 14–23. doi: 10.1109/MIS.2019.2957223.

Patel S, Lohakare M, Prajapati S, Singh S, Patel N. DiaRet: A Browser-Based Application for the Grading of Diabetic Retinopathy with Integrated Gradients. 2021 IEEE International Conference on Robotics, Automation and Artificial Intelligence (RAAI), Hong Kong. 2021; 19–23. doi: 10.1109/RAAI52226.2021.9507938.

Kuang W, Li X, Zhao X, Liu S. Unified Fast Partitioning Algorithm for Intra and Inter Predictions in Versatile Video Coding. 2022 Picture Coding Symposium (PCS), San Jose, CA, USA. 2022; 271–275. doi: 10.1109/PCS56426.2022.10018085.

Karpagam GR, Varma A, SM, SSV. Understanding, Visualizing and Explaining XAI Through Case Studies. 2022 8th International Conference on Advanced Computing and Communication Systems (ICACCS), Coimbatore, India. 2022; 647–654. doi: 10.119/ICACCS54159.2022.9785199.

Ma J, Liu L. Sea-battlefield situation assessment based on a new method combining dynamic Bayesian network with pattern matching. Proceedings of 2014 IEEE Chinese Guidance, Navigation and Control Conference, Yantai, China. 2014; 1764–1769. doi: 10.1109/CGNCC.2014.7007450.

Valdés JJ, Tchagang AB. Deterministic Numeric Simulation and Surrogate Models with White and Black Machine Learning Methods: A Case Study on Inverse Mappings. 2020 IEEE Symposium Series on Computational Intelligence (SSCI), Canberra, ACT, Australia. 2020; 2495–2503. doi: 10.1109/SSCI47803.2020.9308352.

Jayasundara S, Indika A, Herath D. Interpretable Student Performance Prediction Using Explainable Boosting Machine for Multi-Class Classification. 2022 2nd International Conference on Advanced Research in Computing (ICARC), Belihuloya, Sri Lanka. 2022; 391–396. doi: 10.1109/ICARC54489.2022.9753867.

Gillani IS, Shahzad M, Mobin A, Munawar MR, Awan MU, Asif M. Explainable AI in Drug Sensitivity Prediction on Cancer Cell Lines. 2022 International Conference on Emerging Trends in Smart Technologies (ICETST), Karachi, Pakistan. 2022; 1–5. doi: 10.1109/ICETST55735.2022.9922931.

Li H, Popa A, Thibault C, Trentini M, Seto M. A software framework for multi-agent control of multiple autonomous underwater vehicles for underwater mine counter-measures. 2010 International Conference on Autonomous and Intelligent Systems, AIS 2010, Povoa de Varzim, Portugal. 2010; 1–6. doi: 10.1109/AIS.2010.5547032.

Tayal P, Rastogi N, Ahuja TK, Tyagi S, Joshi K, Mohialden YM. Impact of AI on the Banking Industry 4.0. 2022 7th International Conference on Computing, Communication and Security (ICCCS), Seoul, Republic of Korea. 2022; 1–4. doi: 10.1109/ICCCS55188.2022.10079399.

Urakami M, Wakabayashi N, Watanabe T. A Study on Location Information Screening Method for Ship Application Using AIS Recorded Data. 2018 International Conference on Broadband Communications for Next Generation Networks and Multimedia Applications (CoBCom), Graz, Austria. 2018; 1–6. doi: 10.1109/COBCOM.2018.8443969.

Aditi A, Dubey A, Mathur A, Garg P. Credit Card Fraud Detection Using Advanced Machine Learning Techniques. 2022 5th International Conference on Computational Intelligence and Communication Technologies (CCICT), Sonepat, India. 2022; 56–60. doi: 10.1109/CCiCT56684.2022.00022.




DOI: https://doi.org/10.37628/ijosct.v9i1.948

Refbacks

  • There are currently no refbacks.