Advertisement
Published in:
24-07-2023
Optimized convolutional neural network for the classification of lung cancer
Published in: The Journal of Supercomputing | Issue 2/2024
Log inActivate our intelligent search to find suitable subject content or patents.
Select sections of text to find matching patents with Artificial Intelligence. powered by
Select sections of text to find additional relevant content using AI-assisted search. powered by
Abstract
Convolutional neural networks (CNN) have made significant strides in the field of image processing recently by solving a variety of previously unsolvable issues. However, the efficacy of this system depends on the selected hyper-parameters, and it is hard to physically adjust these hyper-parameters. As a result, an optimized convolution neural network is suggested in this study and is then employed to identify the kind of lung cancer. By employing an appropriate encoding strategy, the approach has used a gray wolf optimization algorithm to optimize hyper-parameters of CNN. By contrasting the model’s performance with that of conventional CNN on the NIH/NCI Lung Image Database Consortium data set, the model’s efficacy is confirmed. According to simulation findings, the suggested model can generate testing accuracy up to 98.21%, which is higher than CNN. Similarly, the suggested model’s testing loss is around 0.10%, less than CNN. The test data conclusively show that the suggested model outperforms the conventional CNN.