2026-05-13T16:14:50.294Z http://ezaposleni.singidunum.ac.rs/rest/sciNaucniRezultati/oai

ezaposleni.singidunum.ac.rs/rest/sciNaucniRezultati/oai:1:9402 2024-12-03T20:10:47Z 1

Evolving Deep Neural Network Architectures by Sine Cosine Algorithm for Healthcare 4.0 2023 http://ezaposleni.singidunum.ac.rs/rest/sciNaucniRezultati/oai/record/1/9402 https://ieeexplore.ieee.org/abstract/document/10263180 S. Golubovic L. Jovanovic B. Radomirovic A. Njegus M. Zivkovic N. Bacanin Prevention, early diagnostics, and timely treatment have become essential in improving patient outcomes. Healthcare 4.0 makes use of emerging technologies to improve Healthcare. This work explores the potential of deep neural networks (DNN) applied to presented challenges. As early diagnostics and timely appropriate treatment DNNs are tasked with drawing conclusions from provided data and detecting outcomes. Challenges of tuning and training can be addressed with the use of metaheuristic algorithms. Therefore this work proposes and implements an improved variation of the original sine cosine algorithm (SCA) called the iteration varying SCA (IVSCA) that further improves on the admirable performance of the original. The introduced approach has been tested on three real-world medical datasets including two datasets covering heart disease and one concerning the liver and compared to several contemporary metaheuristics. The results indicate that the introduced approach has great potential when applied in healthcare, outperforming competing algorithms. conferenceObject 1 6 10.1109/InC457730.2023.10263180 2023 IEEE International Conference on Contemporary Computing and Communications (InC4), Bangalore, India