2026-05-04T20:59:03.813Z http://ezaposleni.singidunum.ac.rs/rest/sciNaucniRezultati/oai

ezaposleni.singidunum.ac.rs/rest/sciNaucniRezultati/oai:3:11605 2025-10-02T20:27:49Z 3

Multiheaded Neural Network Optimization Handled by Modified Metaheuristic Optimizer for Increased Forecasting Performance, Chapter in LNNS Lecture Notes in Networks and Systems: ICICC 2025: Innovative Computing and Communications, Springer, volume 1439 2025 http://ezaposleni.singidunum.ac.rs/rest/sciNaucniRezultati/oai/record/3/11605 https://link.springer.com/chapter/10.1007/978-981-96-7137-3_7 M. Mihajlovic L. Jovanovic M. Antonijevic S. Andjelic T. Zivkovic M. Zivkovic N. Bacanin Cryptocurrencies, particularly Ethereum (ETH), have significantly influenced the global economy, offering numerous investment opportunities. However, their inherent market volatility presents challenges for accurate forecasting. This study investigates the application of multiheaded artificial neural networks (ANNs) for predicting ETH prices. To improve forecasting performance, this work introduces a modified metaheuristic optimization algorithm, a variant of the particle swarm optimization (PSO) algorithm. A comparative analysis is conducted using a publicly available dataset to evaluate the model’s effectiveness. The modified algorithm consistently delivers superior results, optimizing the multiheaded ANN model to achieve a mean squared error (MSE) of 0.43908. Collected outcomes indicate that the proposed model is a viable solution for real-world cryptocurrency forecasting, balancing accuracy with computational efficiency. bookPart Springer, Singapore 69 82 10.1007/978-981-96-7137-3_7 LNNS Lecture Notes in Networks and Systems: ICICC 2025: International Conference on Innovative Computing and Communications, volume 1439