Comparative Analysis of Lightweight Vision Transformers and CNNs for Efficient Bacterial Species Classification

M. Amirul Ghiffari; Febri Dolis Herdiani; Ishak Ariawan; Dea Aisyah Rusmawati

doi:10.35377/saucis...1777006

EN

Comparative Analysis of Lightweight Vision Transformers and CNNs for Efficient Bacterial Species Classification

Abstract

Food safety requires rapid and accurate bacterial identification to prevent disease and economic losses. This study compares three lightweight deep learning models—Tiny-ViT, ShuffleNetV2, and EfficientNet-Lite—for classifying 33 bacterial species from a combined public dataset. Models were trained using transfer learning with original and augmented data and evaluated using 5-fold cross-validation. Tiny-ViT achieved the highest performance with 99.66% accuracy and 99.70% precision, setting a new state-of-the-art for the DIBaS dataset. EfficientNet-Lite reached 99.32% accuracy with superior efficiency—threefold lower FLOPs (397.49M), fewer parameters (3.41M), and faster inference (0.90 ms/image). Comparison of per-class error rates across four models—Tiny-ViT Original, Tiny-ViT Augmented, EfficientNet-Lite Augmented, and EfficientNet-Lite Original—showed consistent stability, where each bacterial class exhibited low mean error and narrow 95% confidence intervals (CI95%), reflecting statistical reliability. These findings highlight a trade-off: Tiny-ViT offers maximum accuracy, while EfficientNet-Lite provides optimal accuracy–efficiency balance for edge-based bacterial diagnostics.

Keywords

Supporting Institution

Ministry of Higher Education, Science, and Technology (KEMDIKTI SAINTEK)

Project Number

0419/C3/DT.05.00/2025

Ethical Statement

This article contains no data or other information from studies or experiments involving human or animal subjects.

Thanks

The authors gratefully acknowledge the funding from the Ministry of Higher Education, Science, and Technology (KEMDIKTI SAINTEK) through the Hibah Dosen Pemula (PDP) scheme awarded to M. Amirul Ghiffari in 2025.

References

J. Zhang, C. Li, Y. Yin, J. Zhang, and M. Grzegorzek, “Applications of artificial neural networks in microorganism image analysis: A comprehensive review from conventional multilayer perceptron to popular convolutional neural network and potential visual transformer,” Artif. Intell. Rev., vol. 56, no. 2, pp. 1013–1070, Feb. 2023. doi: 10.1007/s10462-022-10192-7
X. Dong, A. Huang, L. He, C. Cai, and T. You, “Recent advances in foodborne pathogen detection using photoelectrochemical biosensors: From photoactive material to sensing strategy,” Front. Sustain. Food Syst., vol. 8, p. 1432555, Aug. 2024. doi: 10.3389/fsufs.2024.1432555
A. H. Havelaar et al., “World health organization global estimates and regional comparisons of the burden of foodborne disease in 2010,” PLoS Med., vol. 12, no. 12, p. e1001923, Dec. 2015. doi: 10.1371/journal.pmed.1001923
P. S. Hiremath, and P. Bannigidad, “Automatic classification of bacterial cells in digital microscopic images,” in Proc. 2nd Int. Conf. Digit. Image Process. Singapore, Singapore, Feb. 2010, p. 754613. doi: 10.1117/12.853303
S. Visitsattaponge, M. Bunkum, C. Pintavirooj, and M. P. Paing, “A deep learning model for bacterial classification using big transfer (BiT),” IEEE Access, vol. 12, pp. 15609–15621, 2024. doi: 10.1109/ACCESS.2024.3358671
B. Zieliński, A. Plichta, K. Misztal, P. Spurek, M. Brzychczy-Włoch, and D. Ochońska, “Deep learning approach to bacterial colony classification,” PLoS ONE, vol. 12, no. 9, pp. 1–14, Sep. 2017. doi: 10.1371/journal.pone.0184554
Y. LeCun, Y. Bengio, and G. Hinton, “Deep learning,” Nature, vol. 521, no. 7553, pp. 436–444, May 2015. doi: 10.1038/nature14539
A. Dosovitskiy et al., “An image is worth 16x16 words: Transformers for image recognition at scale,” arXiv, 2020. doi: 10.48550/ARXIV.2010.11929

N. E. M. Khalifa, M. H. N. Taha, and A. E. Hassanien, “Deep bacteria: Robust deep learning data augmentation design for limited bacterial colony dataset,” Int. J. Reasoning-based Intell. Syst., vol. 11, no. 3, pp. 256–264, Mar. 2019. doi: 10.1504/IJRIS.2019.102610
S. Halder, M. Rafiqul Islam, Q. Mamun, A. Mahboubi, P. Walsh, and M. Zahidul Islam, “A comprehensive survey on AI-enabled secure social industrial Internet of things in the agri-food supply chain,” Smart Agric. Technol., vol. 11, p. 100902, Aug. 2025. doi: 10.1016/j.atech.2025.100902
D. A. Rusmawati, I. Ariawan, and A. Firmanda, “Comparison of efficient deep learning architectures for lactobacillus species identification,” Karbala Int. J. Mod. Sci., vol. 10, no. 4, Nov. 2024. doi: 10.33640/2405-609X.3379
O. F. Nasip, and K. Zengin, “Deep learning based bacteria classification,” in 2018 2nd International Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT), Oct. 2018, pp. 1–5. doi: 10.1109/ISMSIT.2018.8566685
K. Simonyan, and A. Zisserman, “Very deep convolutional networks for large-scale image recognition,” arXiv, Apr. 10, 2015. doi: 10.48550/arXiv.1409.1556
A. Krizhevsky, I. Sutskever, and G. E. Hinton, “ImageNet classification with deep convolutional neural networks,” Commun. ACM, vol. 60, no. 6, pp. 84–90, May 2017. doi: 10.1145/3065386
M. Talo, “An automated deep learning approach for bacterial image classification,” arXiv, 2019. doi: 10.48550/ARXIV.1912.08765
C. Rujichan, N. Vongserewattana, and P. Phasukkit, “Bacteria classification using image processing and deep convolutional neural network,” in 2019 12th Biomedical Engineering International Conference (BMEiCON), Nov. 2019, pp. 1–4. doi: 10.1109/BMEiCON47515.2019.8990270
M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, and L.-C. Chen, “MobileNetV2: Inverted residuals and linear bottlenecks,” in 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, June 2018, pp. 4510–4520. doi: 10.1109/CVPR.2018.00474
M. A. Elaziz, K. M. Hosny, A. A. Hemedan, and M. M. Darwish, “Improved recognition of bacterial species using novel fractional-order orthogonal descriptors,” Appl. Soft Comput., vol. 95, p. 106504, Oct. 2020. doi: 10.1016/j.asoc.2020.106504
B. D. Satoto, M. I. Utoyo, R. Rulaningtyas, and E. B. Koendhori, “An auto contrast custom convolutional neural network to identifying gram-negative bacteria,” in 2020 International Conference on Computer Engineering, Network, and Intelligent Multimedia (CENIM), Nov. 2020, pp. 70–75. doi: 10.1109/CENIM51130.2020.9297964
R. Gallardo García, S. Jarquín Rodríguez, B. Beltrán Martínez, C. Hernández Gracidas, and R. Martínez Torres, “Efficient deep learning architectures for fast identification of bacterial strains in resource-constrained devices,” Multimed Tools Appl., vol. 81, no. 28, pp. 39915–39944, Nov. 2022. doi: 10.1007/s11042-022-13022-8
C. Reddy G.P., P. A. Reddy, V. R. Kanabur, D. Vijayasenan, S. D. S., and S. Govindan, “Semi-automatic labeling and semantic segmentation of gram-stained microscopic images from DIBaS dataset,” in 2023 2nd International Conference on Computational Systems and Communication (ICCSC), Mar. 2023, pp. 1–6. doi: 10.1109/ICCSC56913.2023.10142976
A. Singh, A. Kumar, H. M. Salman, N. Rawat, S. K. Jain, and A. T. Rao, “Transfer learning approach on bacteria classification from microscopic images,” in 2022 5th International Conference on Contemporary Computing and Informatics (IC3I), Uttar Pradesh, Dec. 2022, pp. 982–987. doi: 10.1109/IC3I56241.2022.10072818
M. F. Amri et al., “Bacterial classification using deep structured convolutional neural network for low resource data,” J. Elektron. dan Telekomun., vol. 23, no. 1, p. 47, Aug. 2023. doi: 10.55981/jet.533
K. Kristensen, L. M. Ward, M. L. Mogensen, and S. L. Cichosz, “Using image processing and automated classification models to classify microscopic gram stain images,” Comput. Methods Programs Biomed. Update, vol. 3, p. 100091, 2023. doi: 10.1016/j.cmpbup.2022.100091
B. Wang, H. Wang, X. Lu, X. Zheng, and Z. Yang, “Recent advances in electrochemical biosensors for the detection of foodborne pathogens: current perspective and challenges,” Foods, vol. 12, no. 14, p. 2795, Jul. 2023. doi: 10.3390/foods12142795
D.-T. Mai, and K. Ishibashi, “Small-scale depthwise separable convolutional neural networks for bacteria classification,” Electronics, vol. 10, no. 23, p. 3005, Dec. 2021. doi: 10.3390/electronics10233005
R. Gallardo-García, S. Jarquín-Rodríguez, B. Beltrán-Martínez, and R. Martínez, “Deep learning for fast identification of bacterial strains in resource constrained devices,” Aplicaciones Científicas y Tecnológicas de las Ciencias Computacionales, pp. 67–78, 2020.
M. (Behdad) Jamshidi, S. Sargolzaei, S. Foorginezhad, and O. Moztarzadeh, “Metaverse and microorganism digital twins: A deep transfer learning approach,” Appl. Soft Comput., vol. 147, p. 110798, Nov. 2023. doi: 10.1016/j.asoc.2023.110798
J. Deng, W. Dong, R. Socher, L.-J. Li, Kai Li, and Li Fei-Fei, “ImageNet: A large-scale hierarchical image database,” in 2009 IEEE Conference on Computer Vision and Pattern Recognition, June 2009, pp. 248–255. doi: 10.1109/CVPR.2009.5206848
K. Wu et al., “TinyViT: Fast pretraining distillation for small vision transformers,” arXiv, 2022. doi: 10.48550/ARXIV.2207.10666
N. Ma, X. Zhang, H.-T. Zheng, and J. Sun, “ShuffleNet V2: Practical guidelines for efficient cnn architecture design,” in Computer Vision – ECCV 2018, vol. 11218, V. Ferrari, M. Hebert, C. Sminchisescu, and Y. Weiss, Eds., in Lecture Notes in Computer Science, vol. 11218., Cham: Springer International Publishing, 2018, pp. 122–138. doi: 10.1007/978-3-030-01264-9_8
M. N. Ab Wahab, A. Nazir, A. T. Zhen Ren, M. H. Mohd Noor, M. F. Akbar, and A. S. A. Mohamed, “Efficientnet-lite and hybrid CNN-KNN implementation for facial expression recognition on raspberry pi,” IEEE Access, vol. 9, pp. 134065–134080, 2021. doi: 10.1109/ACCESS.2021.3113337
Z. Chen, J. Yang, L. Chen, and H. Jiao, “Garbage classification system based on improved ShuffleNet v2,” Resour. Conserv. Recycl., vol. 178, p. 106090, Mar. 2022. doi: 10.1016/j.resconrec.2021.106090
P. Upadhyay, B. Garg, A. Tyagi, and A. Tyagi, “Face recognition using EfficientNet,” in Proceedings of International Conference on Recent Trends in Computing, vol. 600, R. P. Mahapatra, S. K. Peddoju, S. Roy, and P. Parwekar, Eds., in Lecture Notes in Networks and Systems, vol. 600, 2023, pp. 679–692. doi: 10.1007/978-981-19-8825-7_58
B. A. Mohamed, and H. M. Afify, “Automated classification of bacterial images extracted from digital microscope via bag of words model,” in 2018 9th Cairo International Biomedical Engineering Conference (CIBEC), Dec. 2018, pp. 86–89. doi: 10.1109/CIBEC.2018.8641799
K. Chaudhury, Math and Architectures of Deep Learning. Shelter Island: Manning Publications, 2023.
I. Naz, J. H. Shah, M. H. U. Rehman, M. Rafiq, and G. S. Choi, “Quantum mechanism-based convolution model for the classification of pathogenic bacteria,” IEEE Access, vol. 11, pp. 137747–137757, 2023. doi: 10.1109/ACCESS.2023.3339127

Details

Primary Language

English

Subjects

Computing Applications in Life Sciences

Journal Section

Research Article

Authors

M. Amirul Ghiffari
0000-0002-4441-661X
Indonesia

Febri Dolis Herdiani
0000-0003-2203-1943
Indonesia

Ishak Ariawan ^*
0000-0002-7378-7540
Indonesia

Dea Aisyah Rusmawati
0009-0005-3734-6368
Indonesia

Early Pub Date

March 15, 2026

Publication Date

March 15, 2026

Submission Date

September 4, 2025

Acceptance Date

November 15, 2025

Published in Issue

Year 2026 Volume: 9 Number: 1

DOI

https://doi.org/10.35377/saucis...1777006

IZ

https://izlik.org/JA45TC75SK

Cite

RIS / Bibtex

APA

Ghiffari, M. A., Dolis Herdiani, F., Ariawan, I., & Rusmawati, D. A. (2026). Comparative Analysis of Lightweight Vision Transformers and CNNs for Efficient Bacterial Species Classification. Sakarya University Journal of Computer and Information Sciences, 9(1), 105-118. https://doi.org/10.35377/saucis...1777006

AMA

1.Ghiffari MA, Dolis Herdiani F, Ariawan I, Rusmawati DA. Comparative Analysis of Lightweight Vision Transformers and CNNs for Efficient Bacterial Species Classification. SAUCIS. 2026;9(1):105-118. doi:10.35377/saucis.1777006

Chicago

Ghiffari, M. Amirul, Febri Dolis Herdiani, Ishak Ariawan, and Dea Aisyah Rusmawati. 2026. “Comparative Analysis of Lightweight Vision Transformers and CNNs for Efficient Bacterial Species Classification”. Sakarya University Journal of Computer and Information Sciences 9 (1): 105-18. https://doi.org/10.35377/saucis. 1777006.

EndNote

Ghiffari MA, Dolis Herdiani F, Ariawan I, Rusmawati DA (March 1, 2026) Comparative Analysis of Lightweight Vision Transformers and CNNs for Efficient Bacterial Species Classification. Sakarya University Journal of Computer and Information Sciences 9 1 105–118.

IEEE

[1]M. A. Ghiffari, F. Dolis Herdiani, I. Ariawan, and D. A. Rusmawati, “Comparative Analysis of Lightweight Vision Transformers and CNNs for Efficient Bacterial Species Classification”, SAUCIS, vol. 9, no. 1, pp. 105–118, Mar. 2026, doi: 10.35377/saucis...1777006.

ISNAD

Ghiffari, M. Amirul - Dolis Herdiani, Febri - Ariawan, Ishak - Rusmawati, Dea Aisyah. “Comparative Analysis of Lightweight Vision Transformers and CNNs for Efficient Bacterial Species Classification”. Sakarya University Journal of Computer and Information Sciences 9/1 (March 1, 2026): 105-118. https://doi.org/10.35377/saucis. 1777006.

JAMA

1.Ghiffari MA, Dolis Herdiani F, Ariawan I, Rusmawati DA. Comparative Analysis of Lightweight Vision Transformers and CNNs for Efficient Bacterial Species Classification. SAUCIS. 2026;9:105–118.

MLA

Ghiffari, M. Amirul, et al. “Comparative Analysis of Lightweight Vision Transformers and CNNs for Efficient Bacterial Species Classification”. Sakarya University Journal of Computer and Information Sciences, vol. 9, no. 1, Mar. 2026, pp. 105-18, doi:10.35377/saucis. 1777006.

Vancouver

1.M. Amirul Ghiffari, Febri Dolis Herdiani, Ishak Ariawan, Dea Aisyah Rusmawati. Comparative Analysis of Lightweight Vision Transformers and CNNs for Efficient Bacterial Species Classification. SAUCIS. 2026 Mar. 1;9(1):105-18. doi:10.35377/saucis. 1777006

Öz

Comparative Analysis of Lightweight Vision Transformers and CNNs for Efficient Bacterial Species Classification

Abstract

Keywords

Supporting Institution

Project Number

Ethical Statement

Thanks

References

Details

Primary Language

Subjects

Journal Section

Authors

Early Pub Date

Publication Date

Submission Date

Acceptance Date

Published in Issue

DOI

IZ

Cite