Dense Neural Networks and Local Interpretable Model-agnostic Explanations Hybrid Model for Enhanced Interpretability
Abstract
Some results that Artificial Intelligence models obtain are unclear to the users while some target audiences may not understand others. This paper propounds a system that fuses a dense neural network with Local Interpretable Model-agnostic Explanations (LIME) to evaluate the results attained on the Adult Census Income set. The model fits and predicts with reasonable success the income based on features such as Socioeconomic indications of work class and nationality. Similarly, features such as capital gain and marital status which can be allied to higher income are also clearly revealed. The main advantage of the hybrid approach is that it cannot only guarantee the high accuracy of predictions, but also the results obtained can be easily explained, so it is useful in fields that require clear interpretation, such as finance and social sciences. The explanation given by the LIME algorithm makes it possible to understand why a particular choice has been made and what features are significant for it. The Hybrid model achieved an accuracy of 87%, a Receiver Operating Characteristic (ROC) score of 91%, and a Precision-Recall of 76% confidence level in clarifying and accurately predicting an individual’s income, which it predicted to be less than or equal to $50[K] with the LIME explaining how each of the features of the dataset influenced and determine the decision of the hybrid model.
Keywords
ExplanationArtificial IntelligenceLocal InterpretableModel-agnosticincome.
References
Singh, P., Kumar, M., & Singh, V. (2024). Improving object recognition in crime scenes via local interpretable model-agnostic explanations (LIME). IEEE Access, 9, 122345– https://doi.org/10.1109/ACCESS.2024. Akkas, S., & Azad, A. (2024). GNNShap: Scalable and accurate GNN explanation using Shapley values. arXiv Preprint, arXiv:2401.04829. https://arxiv.org/abs/2401.04829 Nguyen, M. T., Ngo, Q. T., Tran, M. S., & Pham, V. H. (2024, October). Bi-gradient verification for Grad-CAM towards accurate visual explanations. In Proceedings of the IEEE International Conference on Image Processing (ICIP), Singapore. Zhang, Y., Chen, E., & Wang, J. (2021). Explainable AI: Advances and challenges. IEEE Transactions on Neural Networks and Learning Systems, 32(8), 3560–3573. https://doi.org/10.1109/TNNLS.2020. Adadi, A., & Berrada, M. (2022). Peeking inside the black-box: A survey on explainable artificial intelligence (XAI). IEEE Access, 6, 52138–52160. https://doi.org/10.1109/ACCESS.2022. Salih, A. M., Raisi-Estabragh, Z., Galazzo, I. B., Radeva, P., Petersen, S. E., Menegaz, G., & Lekadir, K. (2024). A perspective on explainable artificial intelligence methods: SHAP and LIME. Computational Intelligence, 40(4), 2831–2847. https://doi.org/10.1111/coin. Barredo Arrieta, A., Díaz-Rodríguez, N., Del Ser, J., Bennetot, A., Tabik, S., Barbado, A., ... & Herrera, F. (2024). Explainable artificial intelligence (XAI): Concepts, taxonomies, opportunities, and challenges. Computational Intelligence, 40(4), 2831–2847. https://doi.org/10.1111/coin. Vilone, G., & Longo, L. (2020). Explainable artificial intelligence: A systematic review. arXiv Preprint, arXiv:2006.00093. https://arxiv.org/abs/2006.00093 Poeta, E., Ciravegna, G., Pastor, E., Cerquitelli, T., & Baralis, E. (2023). Concept-based explainable artificial intelligence: A survey. arXiv Preprint, arXiv:2312.12936. https://arxiv.org/abs/2312.12936 Mondal, M. R. H., Bharati, S., & Podder, P. (2023). A review on explainable artificial intelligence for healthcare: Why, how, and when? arXiv Preprint, arXiv:2302.00031. https://arxiv.org/abs/2302.00031 Islam, M. R., Ahmed, M. U., Barua, S., & Begum, S. (2022). A systematic review of explainable artificial intelligence in terms of different application domains and tasks. Applied Sciences, 12(3), 1353. https://doi.org/10.3390/app12031353 Vo, D. M., Nguyen, D. T., Hoang, N.-D., Nguyen, Q. V. H., & Phung, D. (2021). Explainable artificial intelligence: A comprehensive review. Artificial Intelligence Review, 55, 3503– https://doi.org/10.1007/s10462-021-10055-7 Rengifo-Moreno, P., Miller, T., Bian, J., Chen, J. H., Liu, X., He, Z., Payrovnaziri, S. N., & Chen, Z. (2020). Explainable artificial intelligence models using real-world electronic health record data: A systematic scoping review. Journal of the American Medical Informatics Association, 27(7), 1173–1185. https://doi.org/10.1093/jamia/ocaa086 Yao, H., Atakishiyev, S., Salameh, M., & Goebel, R. (2021). Explainable artificial intelligence for autonomous driving: A comprehensive overview and field guide for future research directions. arXiv preprint arXiv:2112.11561. https://arxiv.org/abs/2112.11561 Tong, S., & Li, S. (2024). Explainable artificial intelligence for urban planning: Challenges, solutions, and future trends from a new perspective. International Journal of Advanced Computer Science and Applications, 15(7). https://doi.org/10.14569/IJACSA.2024.0150701 Akman, A., Sun, Q., & Schuller, B. W. (2024). Explainable artificial intelligence for medical applications: A review. arXiv preprint arXiv:2412.01829. https://arxiv.org/abs/2412.01829 Singh, P., Gohel, P., & Mohanty, M. (2021). Explainable AI: Current status and future directions. arXiv preprint arXiv:2107.07045. https://arxiv.org/abs/2107.07045 Ghafoor, S. K., Islam, S. R., Eberle, W., & Ahmed, M. (2021). Explainable artificial intelligence approaches: A survey. arXiv preprint arXiv:2101.09429. https://arxiv.org/abs/2101.09429 Förster, M., Klier, M., Sigler, I., Brasse, J., & Broder, H. R. (2023). Explainable artificial intelligence in information systems: A review of the status quo and future research directions. Electronic Markets, 33(1), 26. https://doi.org/10.1007/s12525-022-00550-7 Wood, J., AlShami, A., Mersha, M., Lam, K., & Kalita, J. (2024). Explainable artificial intelligence: A survey of needs, techniques, applications, and future direction. arXiv preprint arXiv:2409.00265. https://arxiv.org/abs/2409.00265 Tsagkaris, K. K., Chatzis, K. K., Plataniotis, K. N., Rodis, N., & Papadopoulos, N. (2023). Multimodal explainable artificial intelligence: A comprehensive review of methodological advances and future research directions. arXiv preprint arXiv:2306.05731. https://arxiv.org/abs/2306.05731 Liu, S., Datta, A., Gomes, C., & Natraj, L. (2023). A survey of explainable AI and proposal for a discipline of explanation engineering. arXiv preprint arXiv:2306.01750. https://arxiv.org/abs/2306.01750 Narayanan, P. J., & Gupta, A. (2024). A survey on concept-based approaches for model improvement. arXiv preprint arXiv:2403.14566. https://arxiv.org/abs/2403.14566 Shaalan, K., Basiouni, A., & Abdelqader, K. (2024). Unlocking the future: Systematic review of the progress and challenges in explainable artificial intelligence (XAI). SSRN Electronic Journal. https://doi.org/10.2139/ssrn.1234567 Kumar, S., Gupta, S., Shah, V., Sundararajan, P., & Raj, A. (2022). XAI in financial systems: Opportunities and challenges. AI and Society, 38(3), 1257–1274. https://doi.org/10.1007/s00146-022-01395-4 Patel, N., Sharma, S., Chauhan, D., Kaur, H., & Verma, R. (2023). Human-centric XAI: Designing for comprehensibility. ACM Transactions on Interactive Intelligent Systems, 12(4), Article 1–24. https://doi.org/10.1145/3579946 Gupta, A., Rani, P., Bansal, N., Sharma, R., & Singh, M. (2022). Exploring explainable artificial intelligence in education. Computers & Education, 183, 104523. https://doi.org/10.1016/j.compedu.2022.104523 Martinez, P., Perez, R., Castro, L., Fernandez, D., & Rodriguez, J. (2023). Legal applications of explainable artificial intelligence. AI & Law, 30, 45–72. https://doi.org/10.1007/s10506-023-09322-0 Wang, M., Zhao, L., Chen, Q., Zhang, Y., & Li, H. (2023). Multimodal explainable artificial intelligence: A comprehensive review. Journal of Artificial Intelligence Research, 78, 523–567. Sinha, S., Desai, P., Sharma, R., Singh, A., & Reddy, V. (2023). Explainable AI for cybersecurity: Techniques, challenges, and opportunities. Computers & Security, 131, https://doi.org/10.1016/j.cose.2023.102567 Patel, L., Brown, G., Miller, D., Jones, M., & Cooper, E. (2023). Cultural perspectives on explainable AI. AI and Ethics, 2(2), 87–101. https://doi.org/10.1007/s43681-023-00234- 7 Islam, Z., Khan, B., Ali, N., Rahman, M., & Ahmed, F. (2023). Lightweight explainable AI models for IoT applications. IEEE Internet of Things Journal, 10(1), 873–885. https://doi.org/10.1109/JIOT.2022.3209876 Clarke, A., Patel, S., Walker, D., Meyer, T., & Thomson, J. (2024). Standardizing XAI evaluation: Towards interoperable explainability metrics. Journal of Artificial Intelligence Research, 81, 123–152. https://doi.org/10.1613/jair.1.14123 Wei, Z., Wang, Y., Wang, Y., & Mei, Q. (2020). Densely connected deep neural network considering connectivity of pixels for automatic crack detection. arXiv preprint arXiv:2006.00093. https://arxiv.org/abs/2006.00093 Aggarwal, C. C. (2023). Neural networks and deep learning: A textbook. Springer. https://doi.org/10.1007/978-3-031-40847-8 Anwar, M. S., Usama, M., & Imran, M. (2023). Deep learning: Systematic review, models, challenges, and research directions. Neural Computin
More Articles from INTERNATIONAL JOURNAL OF COMPUTER SCIENCE AND MATHEMATICAL THEORY
A Flexible Edge Search Algorithm for Graceful Tree Labeling
Author: Michael Arnold and Fabio Vitor
Advances in Algorithmic Contract Scoring for Pre-Negotiation Yield Optimization and Risk Retention
Author: Ngozi Samuel Uzougbo, Michael Ominyi, Cyril Chimelie Anichukwueze, Blessing, Chika Jones
DevTest flow: Designing a Scalable Continuous Testing Pipeline for High-Velocity Software Delivery
Author: Lawal Ahmed Oladimeji, Achori Busayo, Akeju BusayoZainab, Saka Samson, Damilare, Mbah Demian Chidi, Runsewe Similoluwa Mayowa, Oladiti Luqman, Abiodun
Assessing Blackboard LMS Implementation, Adoption Barriers and Digital Transformation in Tertiary Institutions in Kogi State, Nigeria
Author: Okolo Clement, Eluemuno
Intelligent Cybercrime Prediction and Control Model Using Hybrid Machine Learning Algorithms for Ddos and Phishing Attack Mitigation
Author: Chukumeka Gift Iroanwusi, Davies Isobo Nelson