Creation of a web application that implements an algorithm for solving a symbolic regression problem based on an artificial immune system
Abstract
The initial data for the symbolic regression problem is the set of free parameters and the corresponding set of function values of these parameters. In addition, the set of all functions allowed for superposition and restrictions for them, if they are required, are specified. It is worth choosing continuously differentiable functions as functions. Each solution obtained must be evaluated. To do this, an objective function is determined, which determines the degree of approximation of the resulting solution to the expected results. Since the assessment uses given sets - points, various metrics, and errors can be used as the objective function. The superposition of the selected features is a chromosome and a potential solution and is represented as a binary tree. To estimate the survival rate of each chromosome, it is necessary to specify an objective function (survival function). It is also called a measure of affinity. One of the proposed functions has been selected. One of the operators of the artificial immune system (AIS) is selection, the process of selecting the best candidates to “receive” a new generation of chromosomes. Also, the best individuals of the old population can be included in the next population.
The crossing is carried out according to the principle of crossing over. In biology, crossing over is the process of exchanging sections of homologous chromosomes. In our case, when the chromosomes are binary trees, it is necessary to obtain an heir, i.e. a combination of these trees. Another operator is chromosome mutation. This stage is necessary to introduce diversity into the population and prevent the solution from falling into a local maximum or minimum. The entire algorithm of the immune system is given. To successfully create a web application, you need to list the technologies. The Java programming language was chosen. The choice fell on PostgreSQL as the DBMS. Spring Framework was used to create the server part, and VueJs was used for the client part. The data model and package structure are given. Testing has been carried out.
Full Text:
PDF (Russian)References
Astachova I., Ushakov S., Selemenev A., Hitskova J. The application of an artificial immune system for solving the identification problem // ITM Web of Conferences. – 2017. – Vol. 9. – Article number: 02003. https://doi.org/10.1051/itmconf/20170902003
Astachova I. F., Ushakov S. A., Shashkin A. I., Belyaeva N. V. The application of artificial immune system for parallel process of calculation and their comparison with existing methods // Journal of Physics: Conference Series. – 2019. – Vol. 1202, No. 1. – Article number: 012003. https://doi.org/10.1088/1742-6596/1202/1/012003
Astachova I. F., Makoviy K. A., Khitskova Y. V. Possibilities for predicting the state of usability web resources // Journal of Physics: Conference Series. –2021. – Vol. 1902, No. 1. – Article number: 012029. https://doi.org 10.1088/1742-6596/1742-6596/1902/1/012029
Astachova I., Kiseleva E. The application of the artificial immune system for design, development and using of the hybrid system in education. In: Sukhomlin V., Zubareva E. (eds) Modern Information Technology and IT Education. SITITO 2017. Communications in Computer and Information Science, vol. 1204. – Cham: Springer, 2017. – P. 67-75. https://doi.org/10.1007/978-3-030-78273-3_7
Dasgupta D. (Ed.). Artificial immune systems and their applications. – Springer Science & Business Media, 2012.
Dasgupta D., Yu S., Nino F. Recent advances in artificial immune systems: models and applications // Applied Soft Computing. – 2012. – Vol. 11, issue 2. – P. 1574-1587. https://doi.org/10.1016/j.asoc.2010.08.024
Hart E., Timmis J. Application Areas of AIS: The Past, The Present and The Future. In: Jacob C., Pilat M.L., Bentley P.J., Timmis J.I. (eds) Artificial Immune Systems. ICARIS 2005. Lecture Notes in Computer Science, vol. 3627. Berlin, Heidelberg: Springer, 2005. P. 483-497. https://doi.org/10.1007/11536444_37
Hart E., Timmis J. Application areas of AIS: The past, the present and the future // Applied soft computing. – 2008. – Vol. 8, issue 1. – P. 191-201. https://doi.org/10.1016/j.asoc.2006.12.004
Mamady D., Tan G., Toure M. L., Alfawaer Z. M. An Artificial Immune System Based Multi-Agent Robotic Cooperation. In: Sobh T., Elleithy K., Mahmood A., Karim M.A. (eds) Novel Algorithms and Techniques In Telecommunications, Automation and Industrial Electronics. – Dordrecht: Springer, 2008. – P. 60-67. https://doi.org/10.1007/978-1-4020-8737-0_12
Uy N. Q., Hoai N. X., O’Neill M., McKay R. I., Galván-López E. Semantically-based crossover in genetic programming: application to real-valued symbolic regression // Genetic Programming and Evolvable Machines. – 2011. – Vol. 12, No. 2. – P. 91-119. https://doi.org/10.1007/s10710-010-9121-2
Watkins A., Timmis J., Boggess L. Artificial Immune Recognition System (AIRS): An Immune-Inspired Supervised Learning Algorithm // Genetic Programming and Evolvable Machines. – 2004. – Vol. 5, No. 3. – P. 291-317. https://doi.org/10.1023/B:GENP.0000030197.83685.94
Joshi S., Borse M. Detection and Prediction of Diabetes Mellitus Using Back-Propagation Neural Network // 2016 International Conference on Micro-Electronics and Telecommunication Engineering (ICMETE). – Ghaziabad, India: IEEE Computer Society, 2016. – P. 110-113. https://doi.org/10.1109/ICMETE.2016.11
Jayashree J., Kumar S. A. Linear Discriminant Analysis Based Genetic Algorithm with Generalized Regression Neural Network – A Hybrid Expert System for Diagnosis of Diabetes // Programming and Computer Software. – 2018. – Vol. 44. – P. 417-427. https://doi.org/10.1134/S0361768818060063
Refbacks
- There are currently no refbacks.
Abava Кибербезопасность MoNeTec 2024
ISSN: 2307-8162