Abstract
Efficiently classifying sheep breeds through image analysis is pivotal in modern animal husbandry, influencing critical management and breeding decisions. This study delves into automating this process by harnessing Convolutional Neural Networks (CNNs), with a particular focus on optimizing key hyperparameters—the learning rate and dropout rate—essential for refining model performance. Manual hyperparameter tuning is often time-consuming and demands expertise. To overcome this challenge, we introduce an innovative approach that utilises the Bat algorithm, a bio-inspired optimization technique. This algorithm mimics bat echolocation behaviors, skillfully navigating the complex hyperparameter search space to determine optimal values. By dynamically adjusting CNN hyperparameters, our research aims to boost classification accuracy while simplifying the tuning process. Empirical results highlight significant gains in classification accuracy and emphasizes the Bat algorithm's efficacy. The optimized CNN model, empowered by fine-tuned hyperparameters, demonstrates superior performance, promising practical applicability in real-world sheep breed classification scenarios. This study meticulously adjusts pulse rate and loudness, revealing an optimal combination of [0.001, 0.24404868], which substantially improves model performance. The findings emphasize the Bat algorithm's role in streamlining hyperparameter tuning and its potential impact on automated sheep breed classification.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Data availability
The dataset used in this article is available online and the link is provided in the reference [17].
References
Jwade SA, Guzzomi A, Mian A. On farm automatic sheep breed classification using deep learning. Comput Electron Agric. 2019;167: 105055.
Ghosh P, Mustafi S, Mukherjee K, Dan S, Roy K, Mandal SN, Banik S. Image-based identification of animal breeds using deep learning. In: Deep learning for unmanned systems. Cham: Springer; 2021. p. 415–45.
Yang Li, Shami A. On hyperparameter optimization of machine learning algorithms: theory and practice. Neurocomputing. 2020;415:295–316.
Vrbančič G, Fister I Jr, Podgorelec V. Parameter setting for deep neural networks using swarm intelligence on phishing websites classification. Int J Artif Intell Tools. 2019;28(06):1960008.
Podgorelec V, Pečnik Š, Vrbančič G. Classification of similar sports images using convolutional neural network with hyper-parameter optimization. Appl Sci. 2020;10(23):8494.
Ottoni ALC, Souza AM, Novo MS. Automated hyperparameter tuning for crack image classification with deep learning. Soft Comput. 2023;27(23):18383–402.
İnik Ö. CNN hyper-parameter optimization for environmental sound classification. Appl Acoust. 2023;202: 109168.
Lee W-Y, Park S-M, Sim K-B. Optimal hyperparameter tuning of convolutional neural networks based on the parameter-setting-free harmony search algorithm. Optik. 2018;172:359–67.
Wu J, Chen X-Y, Zhang H, Xiong L-D, Lei H, Deng S-H. Hyperparameter optimization for machine learning models based on Bayesian optimization. J Electron Sci Technol. 2019;17(1):26–40.
Rajalaxmi RR, Sruthi K, Santhoshkumar S. Bat Algorithm with CNN Parameter Tuning for Lung Nodule False Positive Reduction. In: International Conference on Computational Intelligence in Data Science. Cham: Springer; 2020. p. 131–142
Mezzah S, Tari A. Practical hyperparameters tuning of convolutional neural networks for EEG emotional features classification. Intell Syst Appl. 2023;18: 200212.
Lu J, Tan L, Jiang H. Review on convolutional neural network (CNN) applied to plant leaf disease classification. Agriculture. 2021;11(8):707.
Feurer M, Hutter F. Hyperparameter optimization. In: Automated machine learning: methods, systems, challenges. Cham: Springer; 2019. p. 3–33.
Bischl B, Binder M, Lang M, Pielok T, Richter J, Coors S, Thomas J, et al. Hyperparameter optimization: Foundations, algorithms, best practices, and open challenges. Wiley Interdiscip Rev Data Min Knowl Discov. 2023;13(2): e1484.
Ravikiran HK, Mohana HS, Jayanth J, Prapulla Kumar MS, Deepak HA. "Hybrid Codebook Optimization Technique for Vector Quantization to Preserve the Quality of the Decompressed Image." In 2023 IEEE 4th Annual Flagship India Council International Subsections Conference (INDISCON). IEEE; 2023. p. 1–7.
Gajic L, Cvetnic D, Zivkovic M, Bezdan T, Bacanin N, Milosevic S. Multi-layer perceptron training using hybridized bat algorithm. In: Computational Vision and Bio-Inspired Computing: ICCVBIC 2020. Singapore: Springer Singapore; 2021. p. 689–705
Siyamek AY. Sheep Breeds Dataset, Kaggle. 2023. Available at: https://www.kaggle.com/datasets/alaayusufsiyamek/sheep-breeds-dataset.
Zmudzinski L. Deep learning guinea pig image classification using Nvidia DIGITS and GoogLeNet. In: CS&P. 2018.
Acknowledgements
We gratefully appreciate the management and employees of NCE- H and GSSSIETW for their prompt assistance in completing the task.
Author information
Authors and Affiliations
Contributions
The authors of this work have attributed the following roles: JJ and HKR were responsible for visualisation and conceptualization, respectively. JJ and HKR contributed to the methodology, while JJ & KB provided the resources. MSS and KB were responsible for the original draught of the writing, while JJ and HKR contributed to the review and editing process. The final version of the manuscript was endorsed by all authors subsequent to their thorough review.
Corresponding author
Ethics declarations
Conflict of Interest
The authors do not possess any conflicting interests to disclose.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
This article is part of the topical collection “Advances in Computational Approaches for Artificial Intelligence, Image Processing, IoT and Cloud Applications” guest edited by Bhanu Prakash K N and M. Shivakumar.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Ravikiran, H.K., Jayanth, J., Sathisha, M.S. et al. Optimizing Sheep Breed Classification with Bat Algorithm-Tuned CNN Hyperparameters. SN COMPUT. SCI. 5, 219 (2024). https://doi.org/10.1007/s42979-023-02544-z
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s42979-023-02544-z