Hou Menhai1

1 Peoples' Friendship University of Russia (Moscow, Russia)

1 houmenhai@gmail.com

The article presents the research project GANet, which focuses on the optimization of neural network architectures for diabetes prediction using genetic algorithms. The main goal of the project is to develop and analyze the effectiveness of a genetic algorithm that would facilitate the automation and optimization of the design of neural network architectures for binary classification tasks. A distinctive feature of GANet is an innovative mutation strategy that allows neurons to mutate within sub-networks with varying numbers of layers and neurons, thereby contributing to the evolution of more complex and efficient structures. Experiments were conducted on a publicly available diabetes dataset, and the results demonstrate a significant improvement in the accuracy of diabetes prediction. The study confirms the effectiveness of using genetic algorithms for optimizing neural network architectures and opens new prospects for future research in this field.

Hou Menhai Optimization of neural network architecture using genetic algorithms: a case study in diabetes prediction. Neurocomputers. 2024. V. 26. № 4. Р. 35-44. DOI: https://doi.org/10.18127/j19998554-202404-04 (In Russian)

1. Metaxiotis K., Psarras J. The contribution of neural networks and genetic algorithms to business decision support. Academic myth or practical solution? Management Decision. 2004. V. 42. № 2. P. 229–242. DOI 10.1108/00251740410518534.
2. Al‐tabtabai H., Alex A.P. Using genetic algorithms to solve optimization problems in construction. Engineering, Construction and Architectural Management. 1999. V. 6. № 2. P. 121–132. DOI 10.1108/eb021105.
3. Petukhov N.I., Tsaregorodtsev D.V., Kulikov R.S., Malyshev A.P. Application of genetic algorithm for determining the locations of reference points of local navigation system and minimizing their number. Radiotekhnika. 2021. V. 85. № 9. P. 27−40. DOI 10.18127/ j00338486-202109-03 (In Russian)
4. Yao X. Evolutionary Artificial Neural Networks. International Journal of Neural Systems. 1993. V. 4. № 3. P. 203–222. DOI 10.1142/ s0129065793000171.
5. Mishra D.B., Bilgaiyan S., Mishra R., Acharya A.A., Mishra S. A Review of Random Test Case Generation using Genetic Algorithm. Indian Journal of Science and Technology. 2017. V. 10. № 30. P. 1–7. DOI 10.17485/ijst/2017/v10i30/107654.
6. Chen Z., Zhan Z., Shi W., Chen W., Zhang J. When Neural Network Computation Meets Evolutionary Computation: A Survey. Advances in Neural Networks. 2016. V. 9719. P 603–612. DOI 10.1007/978-3-319-40663-3_69.
7. Shi J., Habib M., Yan H. A Review Paper on Different Application of Genetic Algorithm for Mobile Ad-hoc Network (MANET). International Journal of Online and Biomedical Engineering. 2020. V. 16. № 5. P. 119–139. DOI 10.3991/ijoe.v16i05.13325.
8. Hosny O.A., Elbarkouky M.M.G. Elhakeem A. Construction Claims Prediction and Decision Awareness Framework using Artificial Neural Networks and Backward Optimization. Journal of Construction Engineering and Project Management. 2015. V. 5. № 1. P. 11–19. DOI 10.6106/JCEPM.2015.5.1.011.
9. Lin C.D., Anderson-Cook C.M., Hamada M.S., Moore L.M., Sitter R.R. Using Genetic Algorithms to Design Experiments: A Review. Quality and Reliability Engineering International. 2015. V. 31. № 2. P. 155–167. DOI 10.1002/qre.1591.
10. Sharma J., Singhal R.S. Genetic Algorithm and Hybrid Genetic Algorithm for Space Allocation Problems – A Review. International Journal of Computer Applications. 2014. V. 95. № 4. P. 33–37. DOI 10.5120/16585-6283.
11. Karakatič S., Podgorelec V. A survey of genetic algorithms for solving multi depot vehicle routing problem. Applied Soft Computing. 2015. V. 27. P. 519–532. DOI 10.1016/j.asoc.2014.11.005.
12. Petke J., Haraldsson S.O., Harman M., Langdon W.B., White D.R., Woodward J.R. Genetic Improvement of Software: A Comprehensive Survey. IEEE Transactions on Evolutionary Computation. 2018. V. 22. № 3. P. 415–432. DOI 10.1109/TEVC.2017.2693219.
13. Paola J.D., Schowengerdt R.A. A review and analysis of backpropagation neural networks for classification of remotely-sensed multi-spectral imagery. International Journal of Remote Sensing. 1995. V. 16. № 16. P. 3033–3058. DOI 10.1080/01431169508954607.