Classification of Microorganism Using Convolutional Neural Network and H2O AutoML
DOI:
https://doi.org/10.52846/stccj.2024.4.1.60Keywords:
CNN, AutoML, microorganism, transfer learningAbstract
The study advances microorganism image classification through a hybrid approach that integrates a Convolutional Neural Network (CNN), modified from the VGG19 architecture, with an ensemble model powered by H2O AutoML. Employing data augmentation and feature extraction, the approach enhances performance on a dataset encapsulating a broad spectrum of microorganism classes. The CNN model shows significant accuracy enhancements in complex bacteria classes, as depicted by the confusion matrix. Concurrently, the AutoML ensemble delivers comparable accuracy, notably in some classes where CNNs struggles. This research highlights the complementary strengths of deep learning and AutoML, demonstrating their impact in achieving high-precision microorganism recognition. Such advancements promise to significantly benefit bioinformatics and diagnostic applications, addressing the complexity of multi-class image classification tasks. The results indicate a successful combination of CNN and AutoML methodologies, setting a benchmark in automated microorganism classification, and also showcase the unique contributions and nuances of each method.
References
Wahid, M., Ahmed, T., & Habib, M. A., “Classification of Microscopic Images of Bacteria Using Deep Convolutional Neural Network,” 2018, pp. 217-220.
Sohail, A., Nawaz, N., Shah, A., Rasheed, S., Ilyas, S., & Ehsan, M. K., “A Systematic Literature Review on Machine Learning and Deep Learning Methods for Semantic Segmentation,” IEEE Access, 2022, pp. 1.
Nurtanio, I., Bustamin, A., Yohannes, C., & Handoyo, A., “Multi Classification of Bacterial Microscopic Images Using Inception V3,” ILKOM Jurnal Ilmiah, 2022, vol. 14, pp. 80-90.
García, R., Rodríguez, S., Martínez, B., Hernández-Gracidas, C., & Torres, R., “Deep Learning Architectures for Fast Identification of Bacterial Strains in Resource-Constrained Devices,” Aplicaciones Científicas y Tecnológicas de las Ciencias Computacionales, 2021.
Konopka, A., Struniawski, K., Kozera, R., Trzcinski, P., Sas -Paszt, L., Lisek, A., Górnik, K., Derkowska, E., Gluszek, S., Sumorok, B., & Fra̧ C, M., “Classification of Soil Bacteria Based on Machine Learning and Image Processing,” 2022, Computational Science – ICCS 2022, pp. 263-277.
Kruk, M., Kozera, R., Osowski, S., Trzcinski, P., Sas, L., Sumorok, B., & Borkowski, B., “Computerized classification system for the identification of soil microorganisms,” Applied Mathematics and Information Sciences, 2016, vol. 10, pp. 21-31.
Irani, T., Amiri, H., Azadi, S., Bayat, M., & Deyhim, H., “Use of a convolution neural network for the classification of E. Coli and V. Cholara bacteria in wastewater,” Environmental Research and Technology, 2022, vol. 5, Issue 1, pp. 101-110.
Talo, M., “An Automated Deep Learning Approach for Bacterial Image Classification,” 2019, International Conference on Advanced Technologies, Computer Engineering and Science (ICATCES2019).
Mehak, Er. Komal Ahuja, “Transfer Learning Model Based Bacteria Image Classification” International Journal of Emerging Technologies and Innovative Research, 2023, vol. 10, issue 6, pp. 580 -583.
Kotwal, S., Rani, P., Arif, T., Manhas, Dr., & Sharma, S., “An Automated Bacterial Classifications Using Machine Learning Based Computational Techniques: Architectures, Challenges and Open Research Issues,” Archives of Computational Methods in Engineering, 2022, vol. 29, pp. 2469-2490.
Nasip, Ö. F., & Zengin, K., “A hybrid model: Multiple feature selection approach using transfer learning for bacteria classification,” Traitement du Signal, 2022, vol. 39, no. 6, pp. 2123-2131.
Sarah, G., Andreas M, “Introduction to Machine Learning with Python”, O’Reilly, 2016, pp. 263-302.
Downloads
Published
Issue
Section
How to Cite
Accepted 2024-07-31
Published 2024-07-31
