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

TL;DR

This study enhances convolutional neural networks for pneumonia image classification by integrating AlexNet and InceptionV3, improving accuracy and efficiency while reducing computational costs.

Contribution

It proposes a novel method combining features from AlexNet and InceptionV3 with knowledge extraction to optimize pneumonia image classification.

Findings

Prediction accuracy increased by 4.25 percentage points.

Specificity and sensitivity improved by 7.85 and 2.32 percentage points.

Graphics processing usage decreased by 51%.

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.