黑龙江科技大学学报2024，Vol.34Issue(3)：457-462,6.DOI:10.3969/j.issn.2095-7262.2024.03.019
深度学习的煤矿尘肺病图像识别
Image recognition of pneumoconiosis of miners based on deep learning
摘要
Abstract
This paper is aimed at addressing the low manual diagnosis rate and big diagnosis error of pneumoconiosis in mine.The study consists of using neural network model to assist in diagnosis of pneumo-coniosis CT map;proposing an image classification method based on the improved ResNet model by compa-ring the existing ResNet original model,DenseNet model and MC-CNN model training result;embeding GN regularization into the model to change the regular convolution to involution in the residual network model.The experimental results show that the ResNet101 model has a stronger integrity,with the accuracy rate of 93.2%and the accuracy rate of 93.8%,the recall rate of 93.6%,and the F1 of 93.7%.This image rec-ognition model verified by using deep learning algorithms and fusing the advantages of regularization is fea-sible.关键词
煤矿/深度学习/残差网络/正则化Key words
coal mine/deep learning/residual network/regularization分类
矿业与冶金引用本文复制引用
刘丹丹,刘玉秋,李德文,郭胜均,汤春瑞..深度学习的煤矿尘肺病图像识别[J].黑龙江科技大学学报,2024,34(3):457-462,6.基金项目
国家重点研发计划项目(2017YFC0805208) （2017YFC0805208）
