Artık Ağ Tabanlı Uygulamayla Gözlerde Bulunan Bakterilerin Sınıflandırılması

Abstract

Araştırmada, ResNet mimarisi kullanılarak TensorFlow ve Keras kütüphaneleri kullanılarak bir derin öğrenme modeli oluşturulmuştur. Çalışmada 6 farklı bakteri sınıfı için toplamda 689 adet bakteri resmi veri kümesi olarak kullanılmıştır. Yazılım tasarımı, veri ön işleme, model oluşturma ve eğitim adımlarını içermektedir. Veri ön işleme aşamasında, resimler normalize edilmiş ve boyutlandırılmıştır. Model oluşturma aşamasında, ResNet mimarisi tercih edilmiştir çünkü derin ağların daha iyi öğrenme yetenekleri sunabileceği bilinmektedir. Model eğitimi sırasında, eğitim verisi üzerinde iteratif bir yaklaşım benimsenmiş ve optimize edici işlevler kullanılarak ağın ağırlıkları ayarlanmıştır. Sonuçlar, tasarlanan yazılımın %83,33 doğruluk oranı ile bakteri resimlerini başarılı bir şekilde sınıflandırdığını göstermektedir. Bu sonuçlar, derin öğrenme tekniklerinin biyomedikal görüntü analizinde potansiyelini vurgulamaktadır. Bu çalışma, bakteri sınıflandırma konusunda daha geniş veri kümeleri ve daha gelişmiş özellik mühendisliği tekniklerinin entegrasyonunu içerecek şekilde genişletilebilir.

Keywords

• Derin öğrenme
• Makine öğrenmesi
• Sınıflandırma
• Artık ağ (residual network)
• Yapay zeka

Classification of Bacteria in Eyes with a Residual Network Based Application

Abstract

In the research, a deep learning model using the ResNet architecture was constructed using the TensorFlow and Keras libraries. A dataset comprising a total of 689 bacterial images was utilized for 6 distinct bacterial classes. The software design encompasses data preprocessing, model creation, and training steps. During data preprocessing, the images were normalized and resized. The ResNet architecture was chosen for model creation, as deep networks are known to offer enhanced learning capabilities. Throughout model training, an iterative approach was adopted on the training data, and the network's weights were adjusted using optimization functions. The results demonstrate that the designed software effectively classifies bacterial images with an accuracy rate of 83.33%. These findings underscore the potential of deep learning techniques in biomedical image analysis. This study can be expanded to encompass larger datasets and more advanced feature engineering techniques for bacterial classification.

Keywords

• Deep learning
• Machine learning
• Classification
• Residual network
• Artificial Intelligent

References

1. Samudre, P, Shende, P, & Jaiswal, V. Optimizing Performance of Convolutional Neural Network Using Computing Technique. 2019 IEEE 5th International Conference for Convergence in Technology.2019, doi:10.1109/I2CT45611.2019.9033876
2. S. S.-S. a. S. Ben-David, Understanding Machine Learning: From Theory to Algorithms, New York, NY: Cambridge University Press, 2014, pp. 5-19.
3. T. M. Mitchell, Machines Learning, McGraw-Hill Science/Engineering/Math, 1997, pp. 2-8.
4. H. Daumé III, A Course in Machine Learning, CIML License, 2012, pp.51-60.
5. L. Wu, H. Zhou, X. Ma, J. Fan, and F. Zhang, Daily reference evapotranspiration prediction based on hybridized extreme learning machine model with bio-inspired optimization algorithms: Application in contrasting climates of China, J. Hydrol, vol. 577, Oct. 2019, Art. no. 123960. https://doi.org/10.1016/j.jhydrol.2019.123960
6. Goodfellow, I, Bengio, Y, Courville, A. Deep learning (Vol. 1)Cambridge MIT press, 2016 -326-366.https://www.worldcat.org/title/deep-learning/oclc/1002916636
7. Xing, Y, Zhao, Y, & Zhong, Y. (2020). Design and Implementation of Mass Log Analysis Method Based on Deep Learning. 2020 IEEE 9th Joint International Information Technology and Artificial Intelligence Conference. doi: 10.1109/ITAIC49862.2020.9339136
8. Dong, Y, & Liang, G. (2019). Research and Discussion on Image Recognition and Classification Algorithm Based on Deep Learning. 2019 International Conference on Machine Learning, Big Data and Business Intelligence.2019 doi: 10.1109/MLBDBI48998.2019.00061

9. Sharma, O. (2019). Deep Challenges Associated with Deep Learning. 2019 International Conference on Machine Learning, Big Data, Cloud and Parallel Computing, doi:10.1109/COMITCon.2019.8862453
10. Dong, C, Loy, C.C, He, K. and Tang, X, 2014, September. Learning a deep convolutional network for image super-resolution.In European conference on computer vision (pp. 184-199). Springer,Cham, https://doi.org/10.1007/978-3-319-10593-2_13
11. Min, S, Lee, B and Yoon, S, 2017. Deep learning in bioinformatics. Briefings in bioinformatics, 18(5), pp.851-869, https://doi.org/10.1093/bib/bbw068
12. Keke Huang a , Shuo Li a , Wenfeng Deng a , Zhaofei Yu b,c , Lei Ma c,d,(2021), Structure inference of networked system with the synergy of deep residual network and fully connected layer network, The Official Journal of the International Neural Network Society, European Neural Network Society & Japanese Neural Network Society, https://doi.org/10.1016/j.neunet.2021.10.016
13. A. Krizhevsky, I. Sutskever, and G. E. Hinton, Imagenet classification with deep convolutional neural networks, in Advance
14. Szegedy, Christian, et al. Going deeper with convolutions. Proceedings of the IEEE conference on computer vision and pattern recognition. 2015.
15. Dodge, Samuel, and Lina Karam. Understanding how image quality affects deep neural networks. Quality of Multimedia Experience (QoMEX), 2016 Eighth International Conference on. IEEE, 2016.
16. yu, C, Liu, Z, & Yu, L. (2019). Block-sparsity recovery via recurrent neural network. Signal Processing, 154, 129–135. https://doi.org/10.1016/j.sigpro.2018.08.014
17. Rahadian, R, & Suyanto, S. (2019). Deep Residual Neural Network for Age Classification with Face Image. 2019 International Seminar on Research of Information Technology and Intelligent Systems (ISRITI). doi:10.1109/ISRITI48646.2019.9034664
18. Lin Dong, Kohei Inoue (2021), Super-resolution reconstruction based on two-stage residual neural network, Department of Communication Design Science, Kyushu University, 4-9-1, Shiobaru, Minami-ku, Fukuoka, 815-8540,Japan. https://doi.org/10.1016/j.mlwa.2021.100162
19. Yılmaz, A., Karaca, A., Aydın, M. E., Arslan, M., & Özgür, U. (2023, August 22). Bacteria classification using image processing and residual neural network (ResNet). Journal of Biomedical Engineering and Informatics, 1(1), 1-10.
20. Amano, M., Mai, D.-T., Sun, G., Vu, T. N., Hoi, L. T., Hoa, N. T., & Ishibashi, K. (2022, July). Deep Learning Approach for Classifying Bacteria types using Morphology of Bacterial Colony. In 2022 43rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) (pp. 2165-2168). IEEE.
21. Khan, M. A., Saleem, M. A., Ali, W., Sharif, M. S., & Akhtar, N. (2023, Haziran 20). Fingerprint Classification Using Deep Neural Network Model Resnet50. International Journal of Advanced Computer Science and Applications, 1(1), 1-6.
22. Sivaprasad, S., Ghosh, A., Kundu, S., & Ghosh, S. K. (2022, Mayıs 10). Bacterial Image Classification Using Convolutional Neural Networks. Biomedical Signal Processing and Control, 57, 1-10.
23. Zhang, Y., Liu, Y., Wang, Q., Zhang, H., & Ding, X. (2022, Nisan 20). Deep Convolutional Neural Network for Microscopic Bacteria Images Classification. IEEE Transactions on Biomedical Engineering, 69(4), 3024-3033.
24. Aparna Vidyasagar, Stephanie Pappas published October 14, 2021. What are bacteria?, https://www.livescience.com/51641-bacteria.html
25. Mahir E. (2019). Gözümüzde Yaşayan Yararlı Bakteriler, https://bilimgenc.tubitak.gov.tr