Bio-Inspired Hyperparameter Optimization for Convolutional Neural Networks: The Artificial Protozoa Optimizer (APO) Approach

Hyperparameter configuration remains one of the most consequential and computationally expensive challenges in the design of high-performance Convolutional Neural Networks (CNNs). This paper introduces the Artificial Protozoa Optimizer (APO), a novel bio-inspired metaheuristic algorithm that models the adaptive foraging, dormancy, and reproductive behaviors of protozoan microorganisms to efficiently navigate complex, non-convex hyperparameter search spaces. When integrated with a YOLOv8-based CNN for farmland intrusion detection, APO automated the selection of nine critical hyperparameters—including initial learning rate (lr0), momentum, weight decay, mosaic augmentation, mixup, translation, scale, shear, and horizontal flip probability—yielding transformative and consistent improvements across all performance metrics. Validated on a custom dataset of 1,850 annotated farmland images across three intrusion classes (Human, Animal, No-Intrusion), the APO-CNN system achieved an overall accuracy of 97.84%, a macro-averaged precision of 98.53%, a mean Average Precision at 50% IoU (mAP@0.5) of 98.24%, and a false positive rate of just 0.72%—representing improvements of over 11 percentage points relative to the un-optimized baseline. Benchmarked against 32 state-of-the-art optimization algorithms, APO demonstrated superior convergence behavior and solution quality. The algorithm's parsimonious two-parameter design (neighbor pairs np and maximum proportion fraction pfmax) renders it computationally efficient and practically deployable on resource-constrained IoT edge platforms. This study establishes APO as a compelling and generalizable tool for automated hyperparameter optimization in applied deep learning systems.

Artificial Protozoa Optimizer, Bio-inspired Metaheuristic, Hyperparameter Optimization, YOLOv8, Farmland Intrusion Detection

1. Abdul Rahim, S., and Manoharan, A. (2024a). An optimization-based feature selection and hybrid Spiking VGG 16 for intrusion detection in the CPS perception layer. IEEE Access, 12, 152709–152720. [Google Scholar] [Crossref]

2. Abdul Rahim, S., and Manoharan, A. (2024b). Fractional Artificial Protozoa Optimization enabled deep learning for intrusion detection and mitigation in cyber-physical systems. IEEE Access, 12, 194077–194090. [Google Scholar] [Crossref]

3. Al-Bahri, M., et al. (2024). Enhancing IoT network security through digital object architecture-based approaches. Qubahan Academic Journal, 4(1), 224–239. [Google Scholar] [Crossref]

4. Bergstra, J., and Bengio, Y. (2012). Random search for hyper-parameter optimization. Journal of Machine Learning Research, 13, 281–305. [Google Scholar] [Crossref]

5. Bochkovskiy, A., Wang, C. Y., and Liao, H. Y. M. (2020). YOLOv4: Optimal speed and accuracy of object detection. arXiv:2004.10934. [Google Scholar] [Crossref]

6. El-Ghamry, A., Darwish, A., and Hassanien, A. E. (2023). An optimized CNN-based intrusion detection system for reducing risks in smart farming. Internet of Things, 22, 100709. [Google Scholar] [Crossref]

7. Falkner, S., Klein, A., and Hutter, F. (2018). BOHB: Robust and efficient hyperparameter optimization at scale. ICML 2018. [Google Scholar] [Crossref]

8. Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep Learning. MIT Press. [Google Scholar] [Crossref]

9. Kennedy, J., and Eberhart, R. (1995). Particle swarm optimization. ICNN 1995. [Google Scholar] [Crossref]

10. LeCun, Y., Bengio, Y., and Hinton, G. (2015). Deep learning. Nature, 521(7553), 436–444. [Google Scholar] [Crossref]

11. Li, Z., et al. (2019). Hyperparameter optimization for machine learning models based on Bayesian optimization. Journal of Electronic Science and Technology, 17(1). [Google Scholar] [Crossref]

12. Mirjalili, S., et al. (2016). Multi-verse optimizer: A nature-inspired algorithm. Neural Computing and Applications, 27(2), 495–513. [Google Scholar] [Crossref]

13. Smith, L. N. (2017). Cyclical learning rates for training neural networks. WACV 2017. [Google Scholar] [Crossref]

14. Snoek, J., Larochelle, H., and Adams, R. P. (2012). Practical Bayesian optimization of machine learning algorithms. NeurIPS 2012. [Google Scholar] [Crossref]

15. Storn, R., and Price, K. (1997). Differential evolution – a simple and efficient heuristic for global optimization. Journal of Global Optimization, 11(4), 341–359. [Google Scholar] [Crossref]

16. Wang, X., Snášel, V., Mirjalili, S., Pan, J. S., Kong, L., and Shehadeh, H. A. (2024). Artificial Protozoa Optimizer (APO): A novel bio-inspired metaheuristic algorithm for engineering optimization. Knowledge-Based Systems, 295, 111737. [Google Scholar] [Crossref]

17. Zhang, H., et al. (2018). mixup: Beyond empirical risk minimization. ICLR 2018. [Google Scholar] [Crossref]