INFORMATION TECHNOLOGY OF ANALYSIS AND SYNTHESIS OF EXPLAINED MODELS OF ARTIFICIAL INTELLIGENCE BASED ON VERBAL METHODS
DOI:
https://doi.org/10.26906/SUNZ.2024.3.158Keywords:
explained models of artificial intelligence, verbal decision-making methodsAbstract
The subject matters of the article is the analysis and synthesis of explained models of artificial intelligence. The goal of the work is to develop an information technology for analyzing and synthesizing explained models of artificial intelligence based on verbal methods. The following tasks were solved in the article: analysis of mathematical formulas and methods used to explain decisions made by artificial intelligence models, analysis of methods, classes, frameworks, and functions of software libraries, as well as their use to explain decisions made by artificial intelligence models, synthesis of explained verbal models of artificial intelligence, development of a system for synthesizing explained verbal models of artificial inte lligence. The following methods are used: system analysis, verbal decision-making methods (formation of a system of concepts in a particular subject area, formation of an ordinal classification of object/process states, ordering object/process states from a particular class, determining the best state of an object/process), methods of modeling and designing information systems (use case diagrams, activity diagrams). The following results were obtained: the mathematical formulas and methods used to explain decisions made by artificial intelligence models are analyzed. An approach to the synthesis of explained verbal models of artificial intelligence is proposed. The methods, classes, frameworks, and functions of software libraries, as well as their use to explain decisions made by artificial intelligence models, are analyzed. A project of a system for synthesizing explained verb al models of artificial intelligence was developed. Conclusions: verbal analysis methods prove to be effective for synthesizing explained artificial intelligence models, which includes several stages: defining a system of concepts, creating criterion de scriptions of states, classifying them, organizing them, and selecting the best state. They emphasize the importance of using linguistic information together with numerical data for a comprehensive analysis of complex problems. By integrating elements of verbal analysis into explained artificial intelligence models, it is possible to improve user interaction, understanding, and perception of artificial intelligence systems.Downloads
References
Mishra, P. Model Explainability and Interpretability. Practical Explainable AI Using Python. Apress, Berkeley, CA. 2022. P. 1–22. DOI: https://doi.org/10.1007/978-1-4842-7158-2_1
Montesinos López, O. A., Montesinos López, A., Crossa, J. Linear Mixed Models. Multivariate Statistical Machine Learning Methods for Genomic Prediction. Springer, Cham. 2022. P. 141–170. DOI: https://doi.org/10.1007/978-3-030-89010-0_5
Starbuck, C. Linear Regression. The Fundamentals of People Analytics. Springer, Cham. 2023. P. 181–206. DOI: https://doi.org/10.1007/978-3-031-28674-2_10
Elements of Generalized Linear Mixed Models / Salinas Ruíz, J. et al. Generalized Linear Mixed Models with Applications in Agriculture and Biology. Springer, Cham. 2023. P. 1–42. DOI: https://doi.org/10.1007/978-3-031-32800-8_1
Linear Regression / James, G. et al. An Introduction to Statistical Learning. Springer Texts in Statistics. Springer, Cham. 2023. P. 69–134. DOI: https://doi.org/10.1007/978-3-031-38747-0_3
Wüthrich, M. V., Merz, M. Generalized Linear Models. Statistical Foundations of Actuarial Learning and its Applications. Springer Actuarial. Springer, Cham. 2023. P.111–205. DOI: https://doi.org/10.1007/978-3-031-12409-9_5
Kleinbaum, D. G., Klein, M. Important Special Cases of the Logistic Model. Logistic Regression. Statistics for Biology and Health. Springer, New York, NY. 2010. P. 41–71. DOI: https://doi.org/10.1007/978-1-4419-1742-3_2
Logistic Regression / Weisburd, D. et al. Advanced Statistics in Criminology and Criminal Justice. Springer, Cham. 2022. P. 127–185. DOI: https://doi.org/10.1007/978-3-030-67738-1_4
Logistic Regression / Backhaus, K. et al. Multivariate Analysis. Springer Gabler, Wiesbaden. 2021. P. 267–354. DOI: https://doi.org/10.1007/978-3-658-32589-3_5
Grąbczewski, K. Techniques of Decision Tree Induction. Meta-Learning in Decision Tree Induction. Studies in Computational Intelligence. 2014. Vol. 498. P. 11–117. DOI: https://doi.org/10.1007/978-3-319-00960-5_2
Barros, R.C., de Carvalho, A.C.P.L.F., Freitas, A.A. Decision-Tree Induction. Automatic Design of Decision-Tree Induction Algorithms. SpringerBriefs in Computer Science. Springer, Cham. 2015. P. 7–45. DOI: https://doi.org/10.1007/978-3-319-14231-9_2
Kozak, J. Ant Colony Decision Tree Approach. Decision Tree and Ensemble Learning Based on Ant Colony Optimization. Studies in Computational Intelligence. 2019. Vol. 781. P. 45–80. DOI: https://doi.org/10.1007/978-3-319-93752-6_3
Construction of Optimal Decision Trees and Deriving Decision Rules from Them / Azad, M. et al. Decision Trees with Hypotheses. Synthesis Lectures on Intelligent Technologies. Springer, Cham. 2022. P. 41–53. DOI: https://doi.org/10.1007/978-3-031-08585-7_4
Seni, G., Elder, J. F. Importance Sampling and the Classic Ensemble Methods. Ensemble Methods in Data Mining. Synthesis 031-01899-2_4
Seni, G., Elder, J. F. Predictive Learning and Decision Trees. Ensemble Methods in Data Mining. Synthesis Lectures on Data Mining and Knowledge Discovery. Springer, Cham. 2010. P. 14–27. DOI: https://doi.org/10.1007/978-3-031-01899-2_2
Cutler, A., Cutler, D. R., Stevens, J. R. Random Forests. Zhang, C., Ma, Y. (eds) Ensemble Machine Learning. Springer, New York, NY. 2012. P. 157–175. DOI: https://doi.org/10.1007/978-1-4419-9326-7_5
Ferreira, A. J., Figueiredo, M. A. T. Boosting Algorithms: A Review of Methods, Theory, and Applications. Zhang, C., Ma, Y. (eds) Ensemble Machine Learning. Springer, New York, NY. 2012. P. 35–85. DOI: https://doi.org/10.1007/978-1-4419-9326-7_2
Štulajter, F. Random Processes and Time Series. Predictions in Time Series Using Regression Models. Springer, New York, NY. 2002. P. 51–71. DOI: https://doi.org/10.1007/978-1-4757-3629-8_2
Das, M., Ghosh, S. K. Standard Bayesian Network Models for Spatial Time Series Prediction. Enhanced Bayesian Network Models for Spatial Time Series Prediction. Studies in Computational Intelligence. 2020. Vol. 858. P. 11–22. DOI: https://doi.org/10.1007/978-3-030-27749-9_2
Estimation Under Normal Mixture Models for Financial Time Series Data /Sun, L H. Et al. Copula-Based Markov Models for Time Series. SpringerBriefs in Statistics(). Springer, Singapore. 2020. P. 55–72. DOI: https://doi.org/10.1007/978-981-15-4998-4_4
Brockwell, P. J., Davis, R. A. ARMA Models. Introduction to Time Series and Forecasting. Springer Texts in Statistics. Springer, Cham. 2016. P. 73–96. DOI: https://doi.org/10.1007/978-3-319-29854-2_3
Interval Evaluation of Stationary State Probabilities for Markov Set-Chain Models / O. Akhiiezer et al. 10th International Conference on Advanced Computer Information Technologies (ACIT). 2020. P. 82–85. DOI: https://doi.org/10.1109/ACIT49673.2020.9208932
Petrov, S. Latent Variable Grammars for Natural Language Parsing. Coarse-to-Fine Natural Language Processing. Theory and Applications of Natural Language Processing. Springer, Berlin, Heidelberg. 2011. P. 7–46. DOI: https://doi.org/10.1007/978-3-642-22743-1_2
Goyal, P., Pandey, S., Jain, K. Introduction to Natural Language Processing and Deep Learning. Deep Learning for Natural Language Processing. Apress, Berkeley, CA. 2018. P. 1–74. DOI: https://doi.org/10.1007/978-1-4842-3685-7_1
Kulkarni, A., Shivananda, A. Advanced Natural Language Processing. Natural Language Processing Recipes. Apress, Berkeley, CA. 2019. P. 97–128. DOI: https://doi.org/10.1007/978-1-4842-4267-4_4
Harris, I. G., Harris, C. B. Generation of Verification Artifacts from Natural Language Descriptions. Soeken, M., Drechsler, R. (eds) Natural Language Processing for Electronic Design Automation. Springer, Cham. 2020. P. 37–70. DOI: https://doi.org/10.1007/978-3-030-52273-5_3
Catta, D., Moot, R., Retoré, C. Dialogical Argumentation and Textual Entailment. Loukanova, R. (eds) Natural Language https://doi.org/10.1007/978-3-030-63787-3_7
Rodrigues, M., Teixeira, A. Extracting Relevant Information Using a Given Semantic. Advanced Applications of Natural Language Processing for Performing Information Extraction. SpringerBriefs in Electrical and Computer Engineering(). Springer, Cham. 2015. P. 37–50. DOI: https://doi.org/10.1007/978-3-319-15563-0_4
Гринченко, М., Роговий, М. Модель ідентифікації задач спринту проєкту на основі їх опису. Сучасний стан наукових досліджень та технологій в промисловості, 2023. 4(26), Р. 33–44. https://doi.org/10.30837/ITSSI.2023.26.033
Gianfagna, L., Di Cecco, A. Explainable AI: Needs, Opportunities, and Challenges. Explainable AI with Python. Springer, Cham. 2021. P. 27–46. DOI: https://doi.org/10.1007/978-3-030-68640-6_2
Mishra, P. Explainability for Ensemble Supervised Models. Explainable AI Recipes. Apress, Berkeley, CA. 2023. P. 119–206. DOI: https://doi.org/10.1007/978-1-4842-9029-3_4
Handling Missing Values in Local Post-hoc Explainability / Cinquini, M. et al. Longo, L. (eds) Explainable Artificial Intelligence. xAI 2023. Communications in Computer and Information Science. 2023. Vol. 1902. P. 256–278. DOI: https://doi.org/10.1007/978-3-031-44067-0_14
Explainable AI Methods - A Brief Overview / Holzinger, A. et al. Holzinger, A., Goebel, R., Fong, R., Moon, T., Müller, KR., Samek, W. (eds) xxAI - Beyond Explainable AI. xxAI 2020. Lecture Notes in Computer Science(). 2022. Vol. 13200. P. 13–38. DOI: https://doi.org/10.1007/978-3-031-04083-2_2
Kamath, U., Liu, J. Post-Hoc Interpretability and Explanations. Explainable Artificial Intelligence: An Introduction to Interpretable Machine Learning. Springer, Cham. 2021. P. 167–216. DOI: https://doi.org/10.1007/978-3-030-83356-5_5
Kumar, D., Mehta, M. A. An Overview of Explainable AI Methods, Forms and Frameworks. Mehta, M., Palade , V., Chatterjee, I. (eds) Explainable AI: Foundations, Methodologies and Applications. Intelligent Systems Reference Library. 2023. Vol. 232. 2023. P. 43–59. DOI: https://doi.org/10.1007/978-3-031-12807-3_3
Vuppalapati, C. ML Models: Food Security and Climate Change. Artificial Intelligence and Heuristics for Enhanced Food https://doi.org/10.1007/978-3-031-08743-1_6
Sonar Signal Prediction Using Explainable AI for IoT Environment / Yadav, T. et al. Bansal, H.O., Ajmera, P.K., Joshi, S., Bansal, R.C., Shekhar, C. (eds) Next Generation Systems and Networks. BITS-EEE-CON 2022. Lecture Notes in Networks and Systems. 2023. Vol. 641. P. 209–222. DOI: https://doi.org/10.1007/978-981-99-0483-9_19
Brad, S., Ștetco, E. An Interactive Artificial Intelligence System for Inventive Problem-Solving. Nowak, R., Chrząszcz, J., Brad, S. (eds) Systematic Innovation Partnerships with Artificial Intelligence and Information Technology. TFC 2022. IFIP Advances in Information and Communication Technology. 2022. Vol. 655. P. 165–177. DOI: https://doi.org/10.1007/978-3-031-17288-5_15
Yan, W. Q. Convolutional Neural Networks and Recurrent Neural Networks. Computational Methods for Deep Learning. Texts in Computer Science. Springer, Singapore. 2023. P. 69–124. DOI: https://doi.org/10.1007/978-981-99-4823-9_3
Paaß, G., Giesselbach, S. Foundation Models for Text Generation. Foundation Models for Natural Language Processing. Artificial Intelligence: Foundations, Theory, and Algorithms. Springer, Cham. 2023. P. 227–311. DOI: https://doi.org/10.1007/978-3-031-23190-2_6
Vuppalapati, C. The Role of the Government and the AI Readiness. Machine Learning and Artificial Intelligence for Agricultural Economics. International Series in Operations Research & Management Science. 2021. Vol. 314. P. 479–548. DOI: https://doi.org/10.1007/978-3-030-77485-1_7
Ye, A., Wang, Z. Data Preparation and Engineering. Modern Deep Learning for Tabular Data. Apress, Berkeley, CA. 2023. P. 95–179. DOI: https://doi.org/10.1007/978-1-4842-8692-0_2
Фастовський Е. Г, Єльчанінов Д. Б. Інформаційна технологія аналізу та синтезу поясненних моделей штучного інтелекту. Теоретичні та практичні дослідження молодих вчених [Електронний ресурс] : зб. тез доп. 17-ї Міжнар. наук.-практ. конф. магістрантів та аспірантів, 28-30 листопада 2023 р. C. 85. URL: https://repository.kpi.kharkov.ua/handle/KhPI-Press/71485
Conversational AI: What Is It, How Does It Work, and Why Does It Matter?. URL: https://www.247.ai/insights/conversationalai-what-it-and-how-does-it-work (дата звернення: 29.02.2024)
Moshkovich H, Mechitov A, Olson D. Verbal Decision Analysis. Multiple Criteria Decision Analysis: State of the Art Surveys. International Series in Operations Research & Management Science. 2005. Vol. 78. P. 609–633. DOI: https://doi.org/10.1007/0-387-23081-5_15
Butow P, Hoque E. Using artificial intelligence to analyse and teach communication in healthcare. The Breast. 2020. Vol. 50; P. 49–55. DOI: https://doi.org/10.1016/j.breast.2020.01.008
Фастовський Е. Г. Синтез поясненних вербальних моделей штучного інтелекту. Інформаційні технології: теорія і практика. I (VII) міжнародна науково-практична конференція здобувачів вищої освіти і молодих учених "Інформаційні технології: теорія і практика". Тези доповідей (Дніпро 20 – 22 березня 2024). 2024. С. 225–227, URL: https://ir.nmu.org.ua/handle/123456789/166564
AKM Bahalul Haque, A. K. M. Najmul Islam, Patrick Mikalef. Explainable Artificial Intelligence (XAI) from a user Change. 2023. Vol. 186, Part A. Article 122120. DOI: https://doi.org/10.1016/j.techfore.2022.122120
How to explain AI systems to end users: a systematic literature review and research agenda / Laato S. et al. Internet Research. 2022. Vol. 32, No 7. P. 1–31.
Aly A., Tapus A. A model for synthesizing a combined verbal and nonverbal behavior based on personality traits in humanrobot interaction. 8th ACM/IEEE International Conference on Human-Robot Interaction (HRI). 2013. P. 325–332. DOI: https://doi.org/10.1109/HRI.2013.6483606
A Protocol for the Diagnosis of Autism Spectrum Disorder Structured in Machine Learning and Verbal Decision Analysis / Evandro Andrade et al. Computational and Mathematical Methods in Medicine. 2021. Vol. 2021. Article ID 1628959. DOI: https://doi.org/10.1155/2021/1628959
Фастовський Е. Г. Проєкт системи синтезу поясненних вербальних моделей штучного інтелекту. 28-й Міжнародний молодіжний форум "Радіоелектроніка та молодь у ХХІ столітті". Зб. матеріалів форуму (Харків 16 – 18 квітня 2024). 2024. Т. 6. С. 74–76. DOI: https://doi.org/10.30837/IYF.IIS.2024.074
