|
|
Bimonthly Since 1986 |
ISSN 1004-9037
|
|
|
|
|
Publication Details |
Edited by: Editorial Board of Journal of Data Acquisition and Processing
P.O. Box 2704, Beijing 100190, P.R. China
Sponsored by: Institute of Computing Technology, CAS & China Computer Federation
Undertaken by: Institute of Computing Technology, CAS
Published by: SCIENCE PRESS, BEIJING, CHINA
Distributed by:
China: All Local Post Offices
|
|
|
|
|
|
|
|
|
|
Abstract
Deep learning is a new machine learning technology that plays a significant role in different classification techniques. Image classification is a very important application of the deep neural network technique. We have used a deep learning technique in this research work to classify COVID19 CT scan images. The deep learning technique plays a vital role in developing a robust model for classifying the COVID19 CT Scan images. This research work proposed a special type of deep learning technique that is a convolutional neural network (CNN) to classify the COVID19 CT scan images. The main contribtion of this reserch work is to select the relevant tuning parameter of CNN which gives better accuracy for classifying COVID19 CT scan images. We analyzed the CNN model with different tuning parameters and compared the performance of the proposed CNN model with Relu, Sigmoid, and Tanh activation functions. The proposed CNN model achieved 88.24% accuracy under the condition of the Relu activation function.
Keyword
Classification, CT Scan Image, Convolutional Neural Network, Deep Learning, Activation function.
PDF Download (click here)
|
|
|
|
|