COVID-19 teşhisi için farklı normalizasyon algoritmaları kullanılan derin öğrenme modelinin FPGA gerçeklemesi

Year 2024, Volume: 13 Issue: 3, 905 - 916, 15.07.2024

Merve Zirekgür Barış Karakaya

https://doi.org/10.28948/ngumuh.1427827

Abstract

Normalizasyon, veri setindeki aykırı değerleri ortadan kaldırmak ve ağ yanlılığını gidermek için kullanılmaktadır. Bu çalışmada, COVID-19 hastalığının teşhisi için kullanılan Konvolüsyonel Sinir Ağları (CNN) tabanlı Derin Öğrenme (DL) modeli ile farklı kombinasyonlarda Mean-Variance-Softmax-Rescale (MVSR) ve Min-Max normalizasyonları kullanılarak ağın doğruluğunun artırılması amaçlanmıştır. Bu amaçla, CNN modeli Google Colab ortamında oluşturulmuş ve COVID-19 için göğüs X-ray görüntülerini içeren açık bir veri seti ile eğitilmiştir. Veri seti, model doğruluğunu karşılaştırmak için MVSR ve Min-Max normalizasyon algoritmalarının farklı kombinasyonlarıyla normalize edilmiştir. Her eğitilmiş model, bir .h5 dosyası olarak kaydedilmiş ve ardından test aşaması için Kria KV260 Vision AI Starter Kit FPGA kartına yüklenmiştir. En yüksek doğruluk sonuçları, MVSR ve Min-Max normalizasyonlarının birlikte uygulandığı senaryo ile elde edilmiştir. En iyi performansı veren senaryo, COVID-19 ve normal X-ray görüntüleri ile FPGA yapılandırmasında tekrar test edilmiştir. En yüksek doğruluk, MVSR+Min-Max senaryosuyla deneysel olarak gerçekleştirilmiş ve %93 olarak elde edilmiştir. Modelin kesinliği, duyarlılığı ve F1-Skor değerleri sırasıyla 0.91, 0.96 ve 0.93 olarak belirlenmiştir.

Keywords

Yapay Zekâ, Derin Öğrenme, Görüntü İşleme, Normalizasyon

FPGA implementation of deep learning model utilizing different normalization algorithms for COVID-19 diagnosis

Abstract

Normalization is utilized to remove outliers from the dataset and address network bias. In this research, Mean-Variance-Softmax-Rescale (MVSR) and Min-Max normalizations are employed in various combinations for the diagnosis of COVID-19 using a Convolutional Neural Network (CNN)-based Deep Learning (DL) model, aimed at enhancing network accuracy. To accomplish this, the CNN model is developed within the Google Colab environment and trained using a publicly available dataset consisting of chest X-ray images related to COVID-19. The dataset is normalized using different combinations of the MVSR and Min-Max normalization algorithms to compare model accuracy. Each normalized dataset is used for model training, and subsequently, each trained model has been saved as a .h5 file and loaded into the Kria KV260 Vision AI Starter Kit FPGA for the testing phase. The most accurate results are obtained when MVSR and Min-Max normalizations are applied simultaneously. This high-performing scenario is re-evaluated with COVID-19 and normal X-ray images on FPGA configuration. Experimentally, the highest accuracy is achieved in real-time with the MVSR+Min-Max scenario, reaching 93%. The model's precision, recall, and F1-Score values are determined as 0.91, 0.96, and 0.93, respectively.

Keywords

Artificial Intelligence, Deep Learning, Image Processing, Normalization

References

• M. Riva, Batch Normalization in convolutional neural networks. Baeldung, San Francisco, 2023.
• An intro to Convolutional Neural Networks (CNN), https://lamiae-hana.medium.com/an-intro-to-convolutional-neural-networks-cnn, Accessed 20 March 2023.
• I., Rothe, H., Susse and K., Voss, The method of normalization to determine invariants. IEEE Transactions on Pattern Analysis and Machine Intelligence, 18(4), 366-376, 1996.
• S., Ioffe and C., Szegedy, Batch normalization: Accelerating deep network training by reducing internal covariate shift. International Conference on Machine Learning (pp. 448-456), 2015.
• J. L., Ba, J. R., Kiros and G. E., Hinton, Layer normalization. arXiv preprint arXiv:1607.06450, 2016.
• Y., Wu and K., He, Group normalization. Proceedings of the European Conference on Computer Vision (ECCV) (pp. 3-19), 2018.
• X., Wu, H., Hui, M., Niu, L., Li, L., Wang, B., He and Y., Zha, Deep learning-based multi-view fusion model for screening 2019 novel coronavirus pneumonia: a multicentre study. European Journal of Radiology, 128, 109041, 2020.
• R. M., Pereira, D., Bertolini, L. O., Teixeira, C. N., Silla Jr. and Y. M., Costa, COVID-19 identification in chest X-ray images on flat and hierarchical classification scenarios. Computer Methods and Programs in Biomedicine, 194, 105532, 2020.
• T., Rahman, A., Khandakar, Y., Qiblawey, A., Tahir, S., Kiranyaz, S. B. A., Kashem and M. E., Chowdhury, Exploring the effect of image enhancement techniques on COVID-19 detection using chest X-ray images. Computers in Biology and Medicine, 132, 104319, 2021.
• S., Yaman, B., Karakaya, and Y., Erol, A novel normalization algorithm to facilitate pre-assessment of COVID-19 disease by improving accuracy of CNN and its FPGA implementation. Evolving Systems, 1-11, 2022.
• M. E. H., Chowdhury, T., Rahman, A., Khandakar, R., Mazhar, M. A., Kadir and A. Emadi, Can AI help in screening viral and COVID-19 pneumonia?. IEEE Access, vol. 8, pp. 132665-132676, 2020, doi: 10.1109/ACCESS.2020.3010287.
• T., Rahman, A., Khandakar, Y., Qiblawey, A., Tahir, S., Kiranyaz, S. B. A., Kashem and M. E. Chowdhury, Exploring the effect of image enhancement techniques on COVID-19 detection using chest X-ray images. Computers in Biology and Medicine, 132, 104319, 2021.
• AMD, Kria KV260 Vision AI Starter Kit data sheet (DS986). California, 2022.
• COVID-19 Radiography Database, https://www.kaggle.com/datasets/tawsifurrahman/COVID19-radiography-database, Accessed 8 April 2024.
• M., Canesche, L., Bragança, O. P. V., Neto, J. A., Nacif and R., Ferreira, Google Colab CAD4U: Hands-on cloud laboratories for digital design. 2021 IEEE International Symposium on Circuits and Systems (ISCAS) (pp. 1-5) IEEE, 2021.
• The Standard Normal Distribution Calculator, Examples & Uses, https://www.scribbr.com/statistics/standard-normal-distribution/, Accessed 18 July 2023.
• J. McEwen, A Gentle introduction to min-max data normalization. Texas, 2022.
• D., Singh, B., Singh, Investigating the impact of data normalization on classification performance. Appl Soft Comput 97:105524, 2020.
• M., Sokolova, N., Japkowicz and S., Szpakowicz, Beyond accuracy, F-score and ROC: a family of discriminant measures for performance evaluation. In AI 2006: Advances in Artificial Intelligence: 19th Australian Joint Conference on Artificial Intelligence, Proceedings 19 (pp. 1015-1021), Springer Berlin Heidelberg, Hobart, Australia, December 4-8 2006.
• Z. C., Lipton, C., Elkan and B. Narayanaswamy, Thresholding classifiers to maximize F1-Score. arXiv preprint arXiv:1402.1892, 2014.