Abstract
Particle Swarm Optimization (PSO) has demonstrated remarkable convergence capabilities in various optimization problems. It is increasingly employed in conjunction with gradient-based methods to enhance the learning process of deep neural networks. However, PSO suffers from a significant drawback, namely the propensity to become trapped in local minima, particularly in challenging multi-modal problems. To address this issue, this study introduces a novel Hybrid Particle Swarm Optimization and Genetic Algorithm with a Self-Adaptation mechanism. Self-adaptation mechanism enables the hybrid algorithm to dynamically adjust its behavior according to the current state of the global best solution search. Initial simulations conducted in this research validate the effectiveness of the proposed approach.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Albeahdili, H.M., Han, T., Islam, N.E.: Hybrid algorithm for the optimization of training convolutional neural network. Int. J. Adv. Comput. Sci. Appl. 1(6), 79–85 (2015)
Bilski, J., Kowalczyk, B., Kisiel-Dorohinicki, M., Siwocha, A., Żurada, J.M.: Towards a very fast feedforward multilayer neural networks training algorithm. J. Artif. Intell. Soft Comput. Res. 12(3), 181–195 (2022). https://doi.org/10.2478/jaiscr-2022-0012
Bilski, J., Smola̧g, J., Kowalczyk, B., Grzanek, K., Izonin, I.: Fast computational approach to the Levenberg-Marquardt algorithm for training feedforward neural networks. J. Artif. Intell. Soft Comput. Res. 13(2), 45–61 (2023). https://doi.org/10.2478/jaiscr-2023-0006
Bottou, L.: Stochastic gradient descent tricks. In: Montavon, G., Orr, G.B., Müller, K.-R. (eds.) Neural Networks: Tricks of the Trade. LNCS, vol. 7700, pp. 421–436. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-35289-8_25
Cpałka, K., Rutkowski, L.: Evolutionary learning of flexible neuro-fuzzy systems. In: Proceedings of the 2008 IEEE International Conference on Fuzzy Systems (IEEE World Congress on Computational Intelligence, WCCI 2008), Hong Kong June 1–6, CD, pp. 969–975 (2008)
Dawar, D., Ludwig, S.A.: Effect of strategy adaptation on differential evolution in presence and absence of parameter adaptation: an investigation. J. Artif. Intell. Soft Comput. Res. 8(3), 211–235 (2018)
Dziwiński, P., Avedyan, E.D.: A new method of the intelligent modeling of the nonlinear dynamic objects with fuzzy detection of the operating points. In: Rutkowski, L., Korytkowski, M., Scherer, R., Tadeusiewicz, R., Zadeh, L.A., Zurada, J.M. (eds.) ICAISC 2016. LNCS (LNAI), vol. 9693, pp. 293–305. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-39384-1_25
Dziwiński, P., Bartczuk, Ł, Tingwen, H.: A method for non-linear modelling based on the capabilities of PSO and GA algorithms. In: Rutkowski, L., Korytkowski, M., Scherer, R., Tadeusiewicz, R., Zadeh, L.A., Zurada, J.M. (eds.) ICAISC 2017. LNCS (LNAI), vol. 10246, pp. 221–232. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-59060-8_21
Dziwiński, P., Bartczuk, Ł, Goetzen, P.: A new hybrid particle swarm optimization and evolutionary algorithm. In: Rutkowski, L., Scherer, R., Korytkowski, M., Pedrycz, W., Tadeusiewicz, R., Zurada, J.M. (eds.) ICAISC 2019. LNCS (LNAI), vol. 11508, pp. 432–444. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-20912-4_40
Dziwiński, P., Bartczuk, Ł: A new hybrid particle swarm optimization and genetic algorithm method controlled by fuzzy logic. IEEE Trans. Fuzzy Syst. 28(6), 1140–1154 (2019)
Dziwiński, P., Bartczuk, Ł, Przybyszewski, K.: A population based algorithm and fuzzy decision trees for nonlinear modeling. In: Rutkowski, L., Scherer, R., Korytkowski, M., Pedrycz, W., Tadeusiewicz, R., Zurada, J.M. (eds.) ICAISC 2018. LNCS (LNAI), vol. 10842, pp. 516–531. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-91262-2_46
Dziwiński, P., PrzybyŁ, A., Trippner, P., Paszkowski, J., Hayashi, Y.: Hardware implementation of a Takagi-Sugeno neuro-fuzzy system optimized by a population algorithm. J. Artif. Intell. Soft Comput. Res. 11(3), 243–266 (2021)
Eberhart, R., Kennedy, J.: A new optimizer using particle swarm theory. In: MHS1995. Proceedings of the Sixth International Symposium on Micro Machine and Human Science 1995, pp. 39–43 (1995)
Esmin, A.A.A., Lambert-Torres, G., Alvarenga, G.B.: Hybrid evolutionary algorithm based on PSO and GA mutation. In: 2006 Sixth International Conference on Hybrid Intelligent Systems (HIS2006), p. 57. IEEE (2006)
Esmin, A.A., Matwin, S.: HPSOM: a hybrid particle swarm optimization algorithm with genetic mutation. Int. J. Innov. Comput. Inf. Control 9(5), 1919–1934 (2013)
Fang, N., Zhou, J., Zhang, R., Liu, Y., Zhang, Y.: A hybrid of real coded genetic algorithm and artificial fish swarm algorithm for short-term optimal hydrothermal scheduling. Int. J. Electr. Power Energy Syst. 62, 617–629 (2014)
Gabryel, M., Lada, D., Filutowicz, Z., Patora-Wysocka, Z., Kisiel-Dorohinicki, M., Yi Chen, G.: Detecting anomalies in advertising web traffic with the use of the variational autoencoder. J. Artif. Intell. Soft Comput. Res. 12(4), 255–266 (2022)
Gabryel, M., Scherer, M.M., Sułkowski, Ł., Damaševičius, R.: Decision making support system for managing advertisers by ad fraud detection. J. Artif. Intell. Soft Comput. Res. 11, 331–339 (2021)
Gabryel, M., Kocić, M.: Application of a neural network to generate the hash code for a device fingerprint. In: Rutkowski, L., Scherer, R., Korytkowski, M., Pedrycz, W., Tadeusiewicz, R., Zurada, J.M. (eds.) ICAISC 2021. LNCS (LNAI), vol. 12855, pp. 456–463. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-87897-9_40
Kan, X., et al.: A novel PSO-based optimized lightweight convolution neural network for movements recognizing from multichannel surface electromyogram. Complexity 2020, 1–15 (2020)
Łapa, K., Cpałka, K., Przybył, A.: Genetic programming algorithm for designing of control systems. Inf. Technol. Control 47(5), 668–683 (2018)
Liang, J.J., Qin, A.K., Suganthan, P.N., Baskar, S.: Comprehensive learning particle swarm optimizer for global optimization of multimodal functions. IEEE Trans. Evol. Comput. 10(3), 281–295 (2006)
Łapa, K., Cpałka, K., Kisiel-Dorohinicki, M., Paszkowski, J., Dȩbski, M., Le, V.-H.: Multi-population-based algorithm with an exchange of training plans based on population evaluation. J. Artif. Intell. Soft Comput. Res. 12(4), 239–253 (2022). https://doi.org/10.2478/jaiscr-2022-0016
Mizera, M., Nowotarski, P., Byrski, A., Kisiel-Dorohinicki, M.: Fine tuning of agent-based evolutionary computing. J. Artif. Intell. Soft Comput. Res. 9(2), 81–97 (2019)
Nickabadi, A., Ebadzadeh, M.M., Safabakhsh, R.: A novel particle swarm optimization algorithm with adaptive inertia weight. Appl. Soft Comput. 11(4), 3658–3670 (2011)
Phong, N.H., Santos, A., Ribeiro, B.: PSO-Convolutional neural networks with heterogeneous learning rate. IEEE Access 10 89970–89988 (2022)
Rutkowski, T., Romanowski, J., Woldan, P., Staszewski, P., Nielek, R., Rutkowski, L.: A content-based recommendation system using neuro-fuzzy approach. FUZZ-IEEE 2018, 1–8 (2018)
Shi, Y., Eberhart, R.: A modified particle swarm optimizer. In: 1998 IEEE International Conference on Evolutionary Computation Proceedings. IEEE World Congress on Computational Intelligence (Cat. No. 98TH8360), pp. 69–73. IEEE (1998)
Trelea, I.C.: The particle swarm optimization algorithm: convergence analysis and parameter selection. Inf. Process. Lett. 85(6), 317–325 (2003)
Wang, L., Yang, B., Orchard, J.: Particle swarm optimization using dynamic tournament topology. Appl. Soft Comput. 48, 584–596 (2016)
Wei, Y., et al.: Vehicle emission computation through microscopic traffic simulation calibrated using genetic algorithm. J. Artif. Intell. Soft Comput. Res. 9(1), 67–80 (2019)
Zhang, Z.: Improved Adam optimizer for deep neural networks. In: 2018 IEEE/ACM 26th International Symposium on Quality of Service (IWQoS). IEEE (2018)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Dziwiński, P., Bartczuk, Ł. (2023). A New Hybrid Particle Swarm Optimization and Evolutionary Algorithm with Self-Adaptation Mechanism. In: Rutkowski, L., Scherer, R., Korytkowski, M., Pedrycz, W., Tadeusiewicz, R., Zurada, J.M. (eds) Artificial Intelligence and Soft Computing. ICAISC 2023. Lecture Notes in Computer Science(), vol 14125. Springer, Cham. https://doi.org/10.1007/978-3-031-42505-9_31
Download citation
DOI: https://doi.org/10.1007/978-3-031-42505-9_31
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-42504-2
Online ISBN: 978-3-031-42505-9
eBook Packages: Computer ScienceComputer Science (R0)