Loading [MathJax]/extensions/MathMenu.js
Research on Deep Learning Model of Feature Extraction Based on Convolutional Neural Network | IEEE Conference Publication | IEEE Xplore

Research on Deep Learning Model of Feature Extraction Based on Convolutional Neural Network


Abstract:

Neural networks with relatively shallow layers and simple structures may have limited ability in accurately identifying pneumonia. In addition, deep neural networks also ...Show More

Abstract:

Neural networks with relatively shallow layers and simple structures may have limited ability in accurately identifying pneumonia. In addition, deep neural networks also have a large demand for computing resources, which may cause convolutional neural networks to be unable to be implemented on terminals. Therefore, this paper will carry out the optimal classification of convolutional neural networks. Firstly, according to the characteristics of pneumonia images, AlexNet and InceptionV3 were selected to obtain better image recognition results. Combining the features of medical images, the forward neural network with deeper and more complex structure is learned. Finally, knowledge extraction technology is used to extract the obtained data into the AlexNet model to achieve the purpose of improving computing efficiency and reducing computing costs. The results showed that the prediction accuracy, specificity, and sensitivity of the trained AlexNet model increased by 4.25 percentage points, 7.85 percentage points, and 2.32 percentage points respectively. The graphics processing usage has decreased by 51% compared to the InceptionV3 mode.
Date of Conference: 28-30 June 2024
Date Added to IEEE Xplore: 15 October 2024
ISBN Information:
Conference Location: Shenyang, China

I. Introduction

In the past diagnosis of pneumonia, the determination of images mostly relied on doctors with rich clinical practice experience, and this difference could not be guaranteed to be correct due to artificial experience. In recent years, computer-assisted imaging (CCAD) has been gradually applied in the imaging field [1], and has become an important basis for doctors to evaluate image quality [2]. Researchers have classified the images of pneumonia images and given the corresponding algorithms [3]. Researchers have used a 121-level convolutional neural network to perform experiments on 112,120 labeled lung X-ray images, and found that 11 of them achieved results comparable to or better than imaging diagnoses by radiographers [4].

References

References is not available for this document.