个人简介
宋承云,博士(博士后),重庆理工大学计算机学院副教授,硕士生导师。2017年12月于电子科技大学获得博士学位;2018年1月入职重庆理工大学计算机学院,讲师;2021年12月获得计算机科学技术副教授职称;2022年1月-2024年5月在长安汽车股份有限公司博士后工作站从事车库环境下车位号识别算法的研究;2024年9月-2025年6月为中国科学技术大学访问学者。在国内外重要专业学术期刊上发表SCI检索论文30余篇,主持国家自然科学基金1项,重庆市教委科学技术研究项目1项,参与重庆市科委科学技术项目2项。目前担任国家自然科学基金评审专家,多个国内外期刊评审专家。
联系方式:Email: scyer123@163.com
学术主页:https://scholar.google.com/citations?user=qadXsegAAAAJ&hl=zh-CN
个人主页:https://stonesonglucky.github.io/Homepage/
研究领域
1. 智能信号分析:主要研究基于人工智能算法来分类时间序列信号,解决信号维度高,信息难以挖掘的问题。并通过开展交叉学科应用的研究,培养学生的创新能力。
Qiu, Lianpeng, Cuipeng Qiu, and Chengyun Song. "ESDTW: Extrema-based shape dynamic time warping." Expert Systems with Applications 239 (2024): 122432. (SCI,JCR一区)
QIU, Lianpeng, and Chengyun SONG. "Noise robust dynamic time warping algorithm." Journal of Computer Applications 43.6 (2023): 1855. (中文核心)
Song, Chengyun, et al. "Dynamic subwindow matching: A new similarity measure for seismic facies analysis." Geophysical Prospecting 70.7 (2022): 1129-1142. (SCI,JCR三区)
Song, Chengyun, et al. "Robust K-means algorithm with weighted window for seismic facies analysis." Journal of Geophysics and Engineering 18.5 (2021): 618-626. (SCI,JCR三区)
Song, Chengyun, et al. "Application of Dynamic Time Warping in Weighted Stacking of Seismic Data." IEEE Geoscience and Remote Sensing Letters 19 (2021): 1-5. (SCI,JCR二区)
2. 聚类分析:研究基于Graph来表征数据,进而开展聚类分析的任务;研究基于深度学习的聚类算法,提升特征提取的鲁棒性和聚类结果的准确度。
Li, Lin, Xiang Chen, and Chengyun Song. "A self-adaptive graph-based clustering method with noise identification." Pattern Analysis and Applications 26.3 (2023): 907-916. (SCI,JCR四区,CCF推荐期刊)
Zhang, Kai, Chengyun Song, and Lianpeng Qiu. "Self-paced deep clustering with learning loss." Pattern Recognition Letters 171 (2023): 8-14. (SCI,JCR三区,CCF推荐期刊)
Li, Lin, Xiang Chen, and Chengyun Song. "NonPC: Non-parametric clustering algorithm with adaptive noise detecting." Intelligent Data Analysis 27.5 (2023): 1347-1358. (SCI,JCR四区,CCF推荐期刊)
Li, Lin, Xiang Chen, and Chengyun Song. "A robust clustering method with noise identification based on directed K-nearest neighbor graph." Neurocomputing 508 (2022): 19-35. (SCI,JCR二区,CCF推荐期刊)
3. 图像去噪:研究自监督的去噪算法,构建有效的训练样本,在保持图像边缘细节的情况下,尽可能的抑制图像中的随机噪声,提升图像的清晰度。
Song, Chengyun, et al. "Regularized deep learning for unsupervised random noise attenuation in poststack seismic data." Journal of Geophysics and Engineering 21.1 (2024): 60-67. (SCI,JCR三区)
Xiong, Chuanchao, et al. "Self-supervised deep learning for multi-profile seismic data denoising." International Conference on Computer, Artificial Intelligence, and Control Engineering (CAICE 2023). Vol. 12645. SPIE, 2023. (国际会议)
4. 计算机视觉:研究车载的轻量级车位号识别方法研究,可以在车库环境下实时识别车位号,提供给用户便于寻车。
Zhang, Yin, Chengyun Song, and Minglong Xue. "Psnd: A robust parking space number detector." 2022 26th International Conference on Pattern Recognition (ICPR). IEEE, 2022. (CCF推荐国际会议)