The aim of this project is to study the behaviour of DeTraC when different hyperparameters are changed. To see the effectiveness of the algorithm in detecting COVID-19 with a high accuracy.
COVID-19 is a growing issue in society and there is a need for resources to manage the disease. This project looks at studying the effect of class decomposition in the deep convolutional neural network, called DeTraC (Decompose, Transfer and Compose). DeTraC can robustly detect and predict COVID-19 from chest X-ray images. The experimental results showed that changing the number of clusters (decomposition granularity) affected the performance of DeTraC and influenced the accuracy of the model. As the number of clusters increased, the accuracy decreased for the shallow tuning mode but increased for the deep tuning mode. This shows the importance of using suitable hyperparameter settings to get the best results from the DeTraC deep learning model. The highest accuracy obtained, in this study, was 98.33% from the deep tuning model. The finding from this study can benefit radiographers and other healthcare professionals involved in the diagnosis process improving speed care to patients.
Long term, this project will benefit radiographers and other healthcare professionals involved in the diagnosis process. Machine and Deep Learning will not replace radiologists but instead aid the work they do. By investigating the algorithms and seeing their performance is essential to determine their effectiveness and benefit patients in the long run