Search

Your search keyword '"Wang, Chenglong"' showing total 68 results
Start Over Author "Wang, Chenglong" Publisher ieee
68 results on '"Wang, Chenglong"'

12. ADD 2022: the first Audio Deep Synthesis Detection Challenge

Author

Yi, Jiangyan, primary, Fu, Ruibo, additional, Tao, Jianhua, additional, Nie, Shuai, additional, Ma, Haoxin, additional, Wang, Chenglong, additional, Wang, Tao, additional, Tian, Zhengkun, additional, Bai, Ye, additional, Fan, Cunhang, additional, Liang, Shan, additional, Wang, Shiming, additional, Zhang, Shuai, additional, Yan, Xinrui, additional, Xu, Le, additional, Wen, Zhengqi, additional, and Li, Haizhou, additional

Published
2022
Full Text
View/download PDF

16. A Fully Deep Learning Paradigm for Pneumoconiosis Staging on Chest Radiographs.

Author

Sun, Wenjian, Wu, Dongsheng, Luo, Yang, Liu, Lu, Zhang, Hongjing, Wu, Shuang, Zhang, Yan, Wang, Chenglong, Zheng, Houjun, Shen, Jiang, and Luo, Chunbo

Subjects
DEEP learning, CHEST X rays, DUST diseases, COMPUTER-aided diagnosis, LOGNORMAL distribution, IMAGE segmentation
Abstract

Pneumoconiosis staging has been a very challenging task, both for certified radiologists and computer-aided detection algorithms. Although deep learning has shown proven advantages in the detection of pneumoconiosis, it remains challenging in pneumoconiosis staging due to the stage ambiguity of pneumoconiosis and noisy samples caused by misdiagnosis when they are used in training deep learning models. In this article, we propose a fully deep learning pneumoconiosis staging paradigm that comprises a segmentation procedure and a staging procedure. The segmentation procedure extracts lung fields in chest radiographs through an Asymmetric Encoder-Decoder Network (AED-Net) that can mitigate the domain shift between multiple datasets. The staging procedure classifies the lung fields into four stages through our proposed deep log-normal label distribution learning and focal staging loss. The two cascaded procedures can effectively solve the problem of model overfitting caused by stage ambiguity and noisy labels of pneumoconiosis. Besides, we collect a clinical chest radiograph dataset of pneumoconiosis from the certified radiologist's diagnostic reports. The experimental results on this novel pneumoconiosis dataset confirm that the proposed deep pneumoconiosis staging paradigm achieves an Accuracy of 90.4%, a Precision of 84.8%, a Sensitivity of 78.4%, a Specificity of 95.6%, an F1-score of 80.9% and an Area Under the Curve (AUC) of 96%. In particular, we achieve 68.4% Precision, 76.5% Sensitivity, 95% Specificity, 72.2% F1-score and 89% AUC on the early pneumoconiosis ‘stage-1’. [ABSTRACT FROM AUTHOR]

Published
2022
Full Text
View/download PDF

40. A Delaunay Triangulation-Based Matching Area Selection Algorithm for Underwater Gravity-Aided Inertial Navigation.

Author

Wang, Chenglong, Wang, Bo, Deng, Zhihong, and Fu, Mengyin

Abstract

The matching area selection algorithm is one of the key technologies for underwater gravity-aided inertial navigation system. Positioning accuracy and matching rate of gravity matching can be improved in high quality matching area. The traditional matching area selection algorithms usually use the statistical characteristic parameters of gravity field, which is difficult to reflect the spatial characteristics of gravity field. In order to explore more vector characteristics and spatial relation characteristics of gravity field and find more potential matching areas, the matching area selection algorithm based on Delaunay triangulation is proposed in this article. The proposed algorithm establishes the three-dimensional model and extracts spatial feature parameters to analysis gravity field. The comprehensive characteristics matrix is used to select matching area by feature extraction and cluster analysis. The experimental results show that the proposed algorithm can extract more characteristics of gravity field, and select more effective matching areas than the traditional algorithms. [ABSTRACT FROM AUTHOR]

Published
2021
Full Text
View/download PDF

43. Object Reconstruction Using the Binomial Theorem for Ghost Imaging.

Author

Yue, Cong, Chen, Ping, Lv, Xiaofeng, Wang, Chenglong, Guo, Shuxu, Song, Junfeng, Gong, Wenlin, and Gao, Fengli

Abstract

Noise term in the reconstruction matrix in ghost imaging is a major cause of blurring imaging results. To remedy this problem, we propose a new ghost imaging method based on the binomial theorem to reduce the level of noise. In our method, images with low-level noise can be generated by constructing a binomial formula using high-order imaging results that are acquired by reintroducing the reconstruction result back into the imaging formula repeatedly. Experimental and simulation results demonstrate that our method is effective in improving imaging quality and the anti-interference performance and reducing computing time, making it useful for practical applications. [ABSTRACT FROM AUTHOR]

Published
2018
Full Text
View/download PDF

46. Experimental Investigation of Iterative Pseudoinverse Ghost Imaging.

Author

Lv, Xiaofeng, Guo, Shuxu, Wang, Chenglong, Yang, Chao, Zhang, Hongwei, Song, Junfeng, Gong, Wenlin, and Gao, Fengli

Abstract

An iterative pseudoinverse ghost imaging (IPGI) method is proposed based on iterative denoising and pseudoinverse ghost imaging (PGI). The background noise in the imaging is eliminated in iterations by setting an appropriate threshold. The IPGI method provides a significantly larger enhancement of the peak signal-to-noise ratio (PSNR) than the PGI technique for binary objects. Experiments and data analyses are performed to evaluate the performance of the proposed method. Compared with conventional GI, differential GI, and PGI methods, the proposed method has the highest performance in visual effects and significantly improves the imaging quality. For a certain PSNR, the proposed method provides satisfactory performance in terms of computing time. [ABSTRACT FROM AUTHOR]

Published
2018
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results