@article{article_1637721, title={Fish Species Classification with Deep Learning and Bayesian Optimization: Effectiveness and Comparative Results}, journal={International Journal of Pure and Applied Sciences}, volume={11}, pages={92–107}, year={2025}, DOI={10.29132/ijpas.1637721}, author={Aydilek, Hüseyin and Erten, Mustafa Yasin}, keywords={Derin öğrenme, Balık türü sınıflandırma, MobilNetV2, VGG19, DenseNet121, Bayes optimizasyonu.}, abstract={This study examines the effectiveness of deep learning-based models in the classification and monitoring of fish species. A dataset obtained from the Kaggle platform, containing 31 different fish species, was used to train MobileNetV2, DenseNet121, and VGG19 models. Bayesian optimization was applied to enhance model performance and determine the optimal hyperparameters. The results indicate that models trained with Bayesian optimization achieved significantly higher accuracy compared to those trained with randomly assigned hyperparameters. Additionally, the ensemble learning approach, which combined the outputs of individual models, yielded the best classification performance. This study demonstrates that deep learning techniques serve as a crucial tool for marine ecosystem conservation and sustainable fisheries practices.}, number={1}, publisher={Munzur Üniversitesi}