An improved ANN-based sequential global-local approximation for small medical data analysis

Ivan Izonin; Roman Tkachenko; Roman Bliakhar; Michal Kovac; Yevgeniy Bodyanskiy; Olha Chala

doi:10.4108/eetpht.9.3320

Authors

Dr Ivan Izonin Lviv Polytechnic National University https://orcid.org/0000-0002-9761-0096
Prof. Roman Tkachenko Lviv Polytechnic National University https://orcid.org/0000-0002-9802-6799
Roman Bliakhar Lviv Polytechnic National University https://orcid.org/0000-0001-8478-5308
Prof. Michal Kovac Slovak University of Technology in Bratislava https://orcid.org/0000-0003-4526-1071
Prof. Yevgeniy Bodyanskiy Institute of Theological Studies of Our Lady of Immaculate Conception https://orcid.org/0000-0001-5418-2143
Olha Chala Kharkiv National University of Radio Electronics https://orcid.org/0000-0002-7603-1247

DOI:

https://doi.org/10.4108/eetpht.9.3320

Keywords:

small data approach, non-iterative training, global-local approximation, GRNN, machine learning, body fat prediction task

Abstract

INTRODUCTION: The task of approximation of complex nonlinear dependencies, especially in the case of short datasets, is important in various applied fields of medicine. Global approximation methods describe the generalized behavior of the model, while local methods explain the behavior of the model at specific data points. Global-local approximation combines both approaches, which makes such methods a powerful tool for processing short sets of medical data that can have both broad trends and local variations.

OBJECTIVES: This paper aims to improve the method of sequential obtaining global and local components of the response surface to increase the accuracy of prediction in the case of short sets of medical data.

METHODS: In this paper, the authors developed a new method that combined two ANNs: a non-iterative SGTM neural-like structure for obtaining the global component and GRNN as a powerful tool of local approximation in the case of short datasets.

RESULTS: The authors have improved the method of global-local approximation due to the use of a General Regression Neural Network instead of RBF ANN for obtaining the local component, which ensured an increase in the accuracy of the body fat prediction task. The authors optimized the operation of the method and investigated the efficiency of the sequential obtaining global and local components of the response surface in comparison with the efficiency using a number of existing methods.

CONCLUSION: The conducted experimental studies for solving the body fat prediction task showed the high efficiency of using the improved method in comparison with a number of existing methods, including ensemble methods.

Downloads

Download data is not yet available.

Author Biographies

Dr Ivan Izonin, Lviv Polytechnic National University

Associated Professor at the Department of Artificial Intelligence, Lviv Polytechnic National University, Lviv, Ukraine

Prof. Roman Tkachenko, Lviv Polytechnic National University

Professor at the Department of Publishing Information Technologies, Lviv Polytechnic National University, Lviv, Ukraine

Roman Bliakhar, Lviv Polytechnic National University

PhD student the the Department of Artificial Intelligence, Lviv Polytechnic National University, Lviv, Ukraine

Prof. Michal Kovac, Slovak University of Technology in Bratislava

Professor at the Faculty of Informatics and Information Technologies, Slovak University of Technology, Bratislava, Slovak Republic

Prof. Yevgeniy Bodyanskiy, Institute of Theological Studies of Our Lady of Immaculate Conception

Scientific Head, Dr. Sci., Prof.; Professor at the Deapartment, Dr. Sci., Prof. (Control Systems Research Laboratory; Department of Artificial Intelligence )

Olha Chala , Kharkiv National University of Radio Electronics

Researcher at the Control Systems Research Laboratory, Kharkiv National University of Radio Electronics, Kharkiv, Ukraine

References

Fan Z, Chiong R, Hu Z, Keivanian F, Chiong F. Body fat prediction through feature extraction based on anthropometric and laboratory measurements. Huk M, editor. PLoS ONE. 2022 Feb 22;17(2):e0263333.

Berezsky O, Zarichnyi M, Pitsun O. Development of a metric and the methods for quantitative estimation of the segmentation of biomedical images. EEJET. 2017 Dec 25;6(4 (90)):4–11. DOI: https://doi.org/10.15587/1729-4061.2017.119493

Babenko V, Panchyshyn A, Zomchak L, Nehrey M, Artym-Drohomyretska Z, Lahotskyi T. Classical Machine Learning Methods in Economics Research: Macro and Micro Level Examples. WSEAS TRANSACTIONS ON BUSINESS AND ECONOMICS. 2021 Jan 5;18:209–17. DOI: https://doi.org/10.37394/23207.2021.18.22

Babichev S, Lytvynenko V, Škvor J, Korobchynskyi M, Voronenko M. Information Technology of Gene Expression Profiles Processing for Purpose of Gene Regulatory Networks Reconstruction. In: 2018 IEEE Second International Conference on Data Stream Mining Processing (DSMP). 2018. p. 336–41. DOI: https://doi.org/10.1109/DSMP.2018.8478452

Mochurad L. Optimization of Regression Analysis by Conducting Parallel Calculations. CEUR-WS.org. 2021;2870:982–96.

Stupnytskyi M, Zhukov V, Gorbach T, Biletskii O, Kutucu H. Analysis of the Early Posttraumatic Period Pathophysiology in Case of the Severe Combined Thoracic Trauma Using Multivariate Logistic Regression. CEUR-WS.org. 2019;2488:330–9.

Geche F, Mitsa O, Mulesa O, Horvat P. Synthesis of a Two Cascade Neural Network for Time Series Forecasting. In: 2022 IEEE 3rd International Conference on System Analysis & Intelligent Computing (SAIC) [Internet]. Kyiv, Ukraine: IEEE; 2022 [cited 2023 Feb 13]. p. 1–5. Available from: https://ieeexplore.ieee.org/document/9922991/ DOI: https://doi.org/10.1109/SAIC57818.2022.9922991

Grzymała-Busse JW, Rza̧sa W. Local and Global Approximations for Incomplete Data. In: Peters JF, Skowron A, editors. Transactions on Rough Sets VIII [Internet]. Berlin, Heidelberg: Springer Berlin Heidelberg; 2008 [cited 2023 May 6]. p. 21–34. (Lecture Notes in Computer Science; vol. 5084). Available from: http://link.springer.com/10.1007/978-3-540-85064-9_2 DOI: https://doi.org/10.1007/978-3-540-85064-9_2

Bisikalo O, Kharchenko V, Kovtun V, Krak I, Pavlov S. Parameterization of the Stochastic Model for Evaluating Variable Small Data in the Shannon Entropy Basis. Entropy. 2023 Jan 17;25(2):184. DOI: https://doi.org/10.3390/e25020184

Krak I, Barmak O, Manziuk E. Using visual analytics to develop human and machine‐centric models: A review of approaches and proposed information technology. Computational Intelligence. 2020 Feb 18;coin.12289. DOI: https://doi.org/10.1111/coin.12289

Salazar A, Vergara L, Safont G. Generative Adversarial Networks and Markov Random Fields for oversampling very small training sets. Expert Systems with Applications. 2021 Jan 1;163:113819. DOI: https://doi.org/10.1016/j.eswa.2020.113819

Costa L da F. A Global Approach to Local Approximations [Internet]. 2023 [cited 2023 May 6]. Available from: https://hal.science/hal-03944359

Haftka RT. Combining global and local approximations. AIAA Journal. 1991 Sep;29(9):1523–5. DOI: https://doi.org/10.2514/3.10768

Bartels S. Combination of Global and Local Approximation Schemes for Harmonic Maps into Spheres. Journal of Computational Mathematics. 2009;27(2–3):170–83.

Van Der Smagt P, Groen F. Approximation with neural networks: between local and global approximation. In: Proceedings of ICNN 95 - International Conference on Neural Networks ICNN-95 [Internet]. Perth, WA, Australia: IEEE; 1995 [cited 2023 May 6]. p. 1060–4 vol.2. Available from: http://ieeexplore.ieee.org/document/487568/ DOI: https://doi.org/10.1109/ICNN.1995.487568

Wedge D, Ingram D, Mclean D, Mingham C, Bandar Z. On Global–Local Artificial Neural Networks for Function Approximation. IEEE Trans Neural Netw. 2006 Jul;17(4):942–52. DOI: https://doi.org/10.1109/TNN.2006.875972

Tkachenko R, Doroshenko A, Izonin I, Tsymbal Y, Havrysh B. Imbalance Data Classification via Neural-Like Structures of Geometric Transformations Model: Local and Global Approaches. In: Hu Z, Petoukhov S, Dychka I, He M, editors. Advances in Computer Science for Engineering and Education [Internet]. Cham: Springer International Publishing; 2019 [cited 2023 May 1]. p. 112–22. (Advances in Intelligent Systems and Computing; vol. 754). Available from: http://link.springer.com/10.1007/978-3-319-91008-6_12 DOI: https://doi.org/10.1007/978-3-319-91008-6_12

Herrera LJ, Pomares H, Rojas I, Guillén A, Rubio G, Urquiza J. Global and local modelling in RBF networks. Neurocomputing. 2011 Sep;74(16):2594–602. DOI: https://doi.org/10.1016/j.neucom.2011.03.027

Medykovskvi M, Pavliuk O, Sydorenko R. Use of Machine Learning Technologys for the Electric Consumption Forecast. In: 2018 IEEE 13th International Scientific and Technical Conference on Computer Sciences and Information Technologies (CSIT). 2018. p. 432–5. DOI: https://doi.org/10.1109/STC-CSIT.2018.8526617

Subbotin S. Radial-Basis Function Neural Network Synthesis on the Basis of Decision Tree. Opt Mem Neural Networks. 2020 Jan 1;29(1):7–18. DOI: https://doi.org/10.3103/S1060992X20010051

Chumachenko D, Chumachenko T, Meniailov I, Pyrohov P, Kuzin I, Rodyna R. On-Line Data Processing, Simulation and Forecasting of the Coronavirus Disease (COVID-19) Propagation in Ukraine Based on Machine Learning Approach. In: Data Stream Mining & Processing [Internet]. Springer, Cham; 2020 [cited 2021 Mar 25]. p. 372–82. Available from: https://link.springer.com/chapter/10.1007/978-3-030-61656-4_25 DOI: https://doi.org/10.1007/978-3-030-61656-4_25

Tkachenko R. An Integral Software Solution of the SGTM Neural-Like Structures Implementation for Solving Different Data Mining Tasks. In: Babichev S, Lytvynenko V, editors. Lecture Notes in Computational Intelligence and Decision Making. Cham: Springer International Publishing; 2022. p. 696–713. (Lecture Notes on Data Engineering and Communications Technologies). DOI: https://doi.org/10.1007/978-3-030-82014-5_48

Kotsovsky V, Batyuk A, Yurchenko M. New Approaches in the Learning of Complex-Valued Neural Networks. In: 2020 IEEE Third International Conference on Data Stream Mining Processing (DSMP). 2020. p. 50–4. DOI: https://doi.org/10.1109/DSMP47368.2020.9204332

Teslyuk V, Kazarian A, Kryvinska N, Tsmots I. Optimal Artificial Neural Network Type Selection Method for Usage in Smart House Systems. Sensors. 2021 Jan;21(1):47. DOI: https://doi.org/10.3390/s21010047

Izonin I, Kryvinska N, Vitynskyi P, Tkachenko R, Zub K. GRNN Approach Towards Missing Data Recovery Between IoT Systems. In: Barolli L, Nishino H, Miwa H, editors. Advances in Intelligent Networking and Collaborative Systems. Cham: Springer International Publishing; 2020. p. 445–53. (Advances in Intelligent Systems and Computing). DOI: https://doi.org/10.1007/978-3-030-29035-1_43

Tolstyak Y, Havryliuk M. An Assessment of the Transplant’s Survival Level for Recipients after Kidney Transplantations using Cox Proportional-Hazards Model. CEUR-WS.org. 2022;3302:260–5.

Tolstyak Y, Chopyak V, Havryliuk M. An investigation of the primary immunosuppressive therapy’s influence on kidney transplant survival at one month after transplantation. Transplant Immunology. 2023 Jun;78:101832. DOI: https://doi.org/10.1016/j.trim.2023.101832

Roger Johnson. Body fat dataset [Internet]. StatLib. [cited 2023 May 6]. Available from: http://lib.stat.cmu.edu/datasets/bodyfat

Body fat prediction through feature extraction based on anthropometric and laboratory measurements. PLOS ONE. 2022 Feb 22;17(2):e0263333. DOI: https://doi.org/10.1371/journal.pone.0263333

Di Caprio D, Ebrahimnejad A, Alrezaamiri H, Santos-Arteaga FJ. A novel ant colony algorithm for solving shortest path problems with fuzzy arc weights. Alexandria Engineering Journal. 2022 May;61(5):3403–15. DOI: https://doi.org/10.1016/j.aej.2021.08.058

Sumalatha M, Parthiban L. Augmentation of Predictive Competence of Non-Small Cell Lung Cancer Datasets through Feature Pre-Processing Techniques. EAI Endorsed Trans Perv Health Tech. 2022 Nov 2;8(5):e1. DOI: https://doi.org/10.4108/eetpht.v8i5.3169

Oleksiv I, Mirzoieva D. Impact of Remittances on the Exchange Rate and Consumption: Evidence from Ukraine. Eastern European Economics. 2022 Sep 3;60(5):418–32. DOI: https://doi.org/10.1080/00128775.2022.2093751

Oleksiv I, Kharchuk V, Shulyar R, Dluhopolskyi O. Quality of Student Support at IT Educational Programmes: Case of Lviv Polytechnic National University. In: 2021 11th International Conference on Advanced Computer Information Technologies (ACIT) [Internet]. Deggendorf, Germany: IEEE; 2021 [cited 2023 Jun 3]. p. 270–5. Available from: https://ieeexplore.ieee.org/document/9548648/ DOI: https://doi.org/10.1109/ACIT52158.2021.9548648