Feature contribution to an In-depth understanding of the machine learning model interpretation

• Autorzy: Kumar Angati Kalyan , Assegie Tsehay Admassu , Salau Ayodeji Olalekan , Napa Komal Kumar , Suguna R.

Identyfikatory

DOI

10.15199/48.2024.02.29

Warianty tytułu

PL

Funkcja przyczyniająca się do dogłębnego zrozumienia interpretacji modelu uczenia maszynowego

• Języki publikacji: EN

Abstrakty

EN

A transparent and understandable machine learning model refers to a model that is accurate, effective, explainable, and interpretable to humans. An interpretable model reduces the gap between complex algorithms and human understanding, allowing users to trust and comprehend the process of the model's decision-making. To that end, Machine-learning models can provide information about the importance of each input feature in making predictions. Model interpretation helps users understand the factors that have the most significant impact on the model's decisions. This study implements feature importance-based model interpretation by employing a heart disease dataset. The simulation result demonstrates that with feature importance analysis, the decision-making process of the extra tree classification algorithm is easily explainable.

PL

Przejrzysty i zrozumiały model uczenia maszynowego odnosi się do modelu, który jest dokładny, skuteczny, zrozumiały i możliwy do interpretacji przez ludzi. Interpretowalny model zmniejsza lukę między złożonymi algorytmami a ludzkim zrozumieniem, pozwalając użytkownikom zaufać i zrozumieć proces podejmowania decyzji w modelu. W tym celu modele uczenia maszynowego mogą dostarczać informacji o znaczeniu każdej cechy wejściowej w tworzeniu prognoz. Interpretacja modelu pomaga użytkownikom zrozumieć czynniki, które mają największy wpływ na decyzje modelu. W tym badaniu zastosowano interpretację modelu opartą na ważności funkcji, wykorzystując zestaw danych dotyczących chorób serca. Wynik symulacji pokazuje, że dzięki analizie ważności cech proces decyzyjny algorytmu klasyfikacji dodatkowego drzewa jest łatwy do wyjaśnienia.

Słowa kluczowe

EN

explainable AI; model explanation; local explanation

PL

wyjaśnialna sztuczna inteligencja; wyjaśnienie modelu; wyjaśnienie lokalne

• Wydawca: Wydawnictwo SIGMA-NOT
• Czasopismo: Przegląd Elektrotechniczny
• Rocznik: 2024
• Tom: R. 100, nr 2
• Strony: 145--148
• Opis fizyczny: Bibliogr. 19 poz., rys., tab.

Twórcy

autor

Kumar Angati Kalyan

• Department of Computer Science & Engineering (Data Science), Madanapalle, Andhra Pradesh, India

autor

Assegie Tsehay Admassu

• Department of Computer Science College of Engineering and Technology, Injibara University, Injibara, Ethiopia

• https://orcid.org/0000-0003-1566-0901

autor

Salau Ayodeji Olalekan

• Department of Electrical/Electronics and Computer Engineering, Afe Babalola University, Ado-Ekiti, Nigeria

• https://orcid.org/0000-0002-6264-9783+

autor

Napa Komal Kumar

autor

Suguna R.

• Department of Computer Science and Engineering, Vel Tech Rangarajan Dr. Sagunthala R & D Institute of Science and Technology, Chennai, Tamilnadu, India

Bibliografia

• [1] K.N. Kunze, A.V. Karhade, A.J. Sadauskas, J.H. Schwab, and B.R. Levine, " Development of Machine Learning Algorithms to Predict Clinically Meaningful Improvement for the Patient-Reported Health State After Total Hip Arthroplasty," The Journal of Arthroplasty, 2020. DOI: https://doi.org/10.1016/j.arth.2020.03.019.
• [2] B. Kailkhura, B. Gallagher, S. Kim, A. Hiszpanski, and T. Y. Han, “Reliable and explainable machine-learning methods for accelerated material discovery,” Computational Materials, 2019, DOI: https://doi.org/10.1038/s41524-019-0248-2.
• [3] L. a Kohoutová et al., “Toward a unified framework for interpreting machine-learning models in neuroimaging,” Nature Protocols, 2020, DOI: https://doi.org/10.1038/s41596-019- 0289-5.
• [4] T.A. Assegie, A.O. Salau, C.O. Omeje, and S.L. Braide, “Multivariate sample similarity measure for feature selection with a resemblance model,” International Journal of Electrical and Computer Engineering, vol. 13, no. 3, 2023, pp. 3359- 3366, DOI: 10.11591/ijece.v13i3.pp3359-3366
• [5] G. Stiglic, P. Kocbek, N. Fijacko, M. Zitnik, K. Verbert, and L. Cilar, “Interpretability of machine learning-based prediction models in healthcare,” Advanced Review Willey, 2020, DOI: 10.1002/widm.1379
• [6] Z. Li et al., “Extracting spatial effects from machine learning model using local interpretation method: An example of SHAP and XGBoost,” Computers, Environment and Urban Systems, 2022, DOI: https://doi.org/10.1016/j.compenvurbsys.2022.101845
• [7] A. Chatzimparmpas, R.M. Martins, L. Jusufi, and A. Kerren, “A survey of surveys on the use of visualization for interpreting machine learning models,” Information Visualization 2020, Vol. 19(3) 207–233, DOI: https://doi.dox.org/10.1177/1473871617751245.
• [8] B. Kailkhura, B. Gallagher, S. Kim, A. Hiszpanski, and T. Y. Han, “Hybrid Feature Selection Algorithm and Ensemble Stacking for Heart Disease Prediction,” International Journal of Advanced Computer Science and Applications, Vol. 14, No. 2, 2023.
• [9] J. Zacharias, M. Zahn, J. Chen, and O. Hinz, “Designing a feature selection method based on explainable artificial intelligence Electronic Markets, 2022, 32:2159–2184 DOI: https://doi.org/10.1007/s12525-022-00608-1.
• [10] Q. Qiao, A.Y. Kaltungo, and R.E. Edwards, “Developing a machine learning based building energy consumption prediction approach using limited data: Boruta feature selection and empirical mode decomposition,” Enegery Reports, 2023, DOI: https://doi.org/10.1016/j.egyr.2023.02.046.
• [11] H. Salah, and S. Srinivas, “Explainable machine learning framework for predicting long-term cardiovascular disease risk among adolescents,” Scientific Reports (2022) 12:21905, DOI: https://doi.org/10.1038/s41598-022-25933-5.
• [12] N.I. Papandrianos et al., “An Explainable Classification Method of SPECT Myocardial Perfusion Images in Nuclear Cardiology Using Deep Learning and Grad-CAM,” Applied Science, 2022, 12, 7592. DOI: https://doi.org/ 10.3390/app12157592.
• [13] B. Kailkhura, B. Gallagher, S. Kim, A. Hiszpanski, and T. Y. Han, “Explainable Information Retrieval using Deep Learning for Medical images,” Computer Science and Information Systems, 2019, DOI: https://doi.org/10.2298/CSIS201030049S.
• [14] R.K. Sheu, and M.S.l Pardesh, “A Survey on Medical Explainable AI (XAI): Recent Progress, Explainability Approach, Human Interaction and Scoring System,” Sensors 2022, 22, 8068, DOI: https://doi.org/10.3390/ s22208068.
• [15] G. Abdulsalam, S. Meshoul2, and H. Shaiba, “Explainable Heart Disease Prediction Using Ensemble-Quantum Machine Learning Approach,” Intelligent Automation & Soft Computing DOI: 10.32604/iasc.2023.032262.
• [16] P. Guleria et al., “XAI Framework for Cardiovascular Disease Prediction Using Classification Techniques,” International Journal of Advanced Computer Science and Applications, Vol. 14, No. 2, 202Electronics 2022, 11, 4086, DOI: https:// doi.org/10.3390/electronics112440863.
• [17] A. Pedro, and M. Sanchez, “Development of an Explainable Prediction Model of Heart Failure Survival by Using Ensemble Trees,” IEEE, 2020, DOI: 10.1109/BigData50022.2020.9378460.
• [18] A.O. Salau, E.D. Markus, T.A. Assegie, C.O. Omeje, and J. N. Eneh, “Influence of Class Imbalance and Resampling on Classification Accuracy of Chronic Kidney Disease Detection,” Mathematical Modelling of Engineering Problems, vol. 10, no. 1, February, 2023, pp. 48-54, DOI: https://doi.org/10.18280/mmep.100106.
• [19] T.A. Assegie, “Evaluation of Local Interpretable Model-Agnostic Explanation and Shapley Additive Explanation for Chronic Heart Disease Detection,” Proceedings of Engineering and Technology Innovation, vol. 23, 2023, pp. 48-59, DOI: https://doi.org/10.46604/peti.2023.10101.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa nr POPUL/SP/0154/2024/02 w ramach programu "Społeczna odpowiedzialność nauki II" - moduł: Popularyzacja nauki i promocja sportu (2025).