Online ISSN: 2515-8260

Keywords : Transfer Learning

Implementation of Deep Learning for Automatic Classification of Covid-19 X-Ray Images

Muhammad Shofi Fuad; Choirul Anam; Kusworo Adi; Muhammad Ardhi Khalif; Geoff Dougherty

European Journal of Molecular & Clinical Medicine, 2021, Volume 8, Issue 2, Pages 1650-1662

Background:Reading radiographic images for Covid-19 identification by an expert radiologist requires significant time, therefore the development of an automated analysis system to assisting and saving time in diagnosing Covid-19 is important.
Objective: The purpose of this study is to implement the GoogleNet architecture with various epochs in hope achieving higher level of accuracy in Covid-19 detection.
Methods: We retrospectively used 813 images, i.e. 409 images indicating Covid-19 and 404 normal images. The deep TL model with GoogleNet architecture was implemented.The training was carried out several times to get the best acquisition value with a learning rate of 0.0001 for all levels. The network training was carried out with different epochs, i.e. 12, 18, and 24 epochs, and each epoch with 65 iterations.
Results: It was found that accuracy was determined by changes in the number of epochs. The classification accuracy was 96.9% in epoch 12, 98.2% in epoch 18, and 99.4% in epoch 24.
Conclusion: An increase in the number epochs increases the accuracy in the detection of Covid-19. In this study, the accuracy of the method reached 99.4%. These results are promising for the automation of Covid-19 detection from radiographic images.


Dr.C. ANNADURAI; Dr. I. Nelson

European Journal of Molecular & Clinical Medicine, 2020, Volume 7, Issue 11, Pages 5228-5241

Underwater image processing has always been a promising and thrilling task due to the natural condition and the lighting effect for taking the image requires good artificial lights. While taking underwater images lots of difficulties are faced by photographers such as the shadows, non-uniform lighting, color shading, etc. Recognizing the object underwater is very difficult in order to the environmental condition. Man-made object recognition was made with underwater optical sensors to capture underwater images that have gained more attention from the users. Deep learning methods have demonstrated impressive performance in object recognition tasks from natural images. Anyhow it is hard to collect all the labelled underwater optical images for training the model. It is possible to acquire labelled images. Based on the assumption that it is possible to acquire sufficient labeled in-air images, the proposed work leverages a combination of deep learning and transfer learning to develop a novel recognition system for the man-made object from underwater optical images. The extracted features from the proposed network have high representative power and demonstrate robustness in both in-air and underwater imaging modalities. Therefore, our proposed framework has the ability to recognize underwater man-made objects using only labeled in-air images. The results of experiments on simulated data demonstrate that the proposed method outperforms traditional deep learning methods in the task of underwater man-made object recognition.