时光,男,计算机科学与技术系副教授,数学专业理学博士,统计学科博士后,香港中文大学访问学者。
主讲课程:算法设计与分析,编译原理
主要研究方向:深度学习,空气污染预测、时空关系建模、遥感图像目标检测等。
近年发表论文
[1]Guang Shi,Yee Leung, Jiangshe Zhang, Yu Zhou*,Modeling the air pollution process using a novel multi-site and multi-scale method with adaptive utilization of spatio-temporal information.Chemosphere, doi:10.1016/j.chemosphere.2023.140799. (2023) (TOP期刊,中科院2区,影响因子8.8)
[2]Guang Shi,Yee Leung, Jiangshe Zhang, Tung Fung, Fang Du, Yu Zhou: A novel method for identifying hotspots and forecasting air quality through an adaptive utilization of spatio-temporal information of multiple factors.Science of The Total Environment,759:14513 (2021). (TOP期刊,中科院2020升级版1区,影响因子:7.963)
[3]Guang Shi,Jiangshe Zhang, Junming Liu, Chunxia Zhang, Changsheng Zhou and Shuyun Yang: Global Context-Augmented Objection Detection in VHR Optical Remote Sensing Images.IEEE Transactions on Geoscience and Remote Sensing,59(12): 10604-10617 (2021). (TOP期刊,中科院2区,影响因子:5.6)
[4]Guang Shi,Jiangshe Zhang, Chunxia Zhang, Junying Hu: A distributed parallel training method of deep belief networks.Soft Computing, 24: 13357–13368 (2020). (中科院3区,影响因子:3.643)
[5]Guang Shi,Jiangshe Zhang, Nannan Ji, Changpeng Wang: A New Variant of Restricted Boltzmann Machine with Horizontal Connections.Neural Computing and Applications, 31(10): 6521-6533 (2019). (中科院2区,影响因子:5.606)
[6]Guang Shi,Jiangshe Zhang, Huirong Li, Changpeng Wang: Enhance the performance of deep neural networks via L2 regularization on the input of activations.Neural Processing Letters, 50(1): 57-75 (2019). (中科院3区,影响因子:2.908)
主持的项目:
[1]基于相关关系信息增强的遥感图像小目标快速检测算法研究(国家自然科学基金青年项目, 2022.1—2024.12)
[2]基于空间注意力与有效感受野匹配的遥感图像小目标自监督检测算法(陕西省科技厅青年项目,2018.1—2020.12)
授权专利:
[1]一种基于注意力机制的遥感图像目标检测方法,专利号:ZL 201910457637.6,证书号第4512216号,授权公告号:CN110276269 B
[2]一种基于贝叶斯迁移学习的光学遥感图像目标检测方法,专利号:ZL 201910457619.8,证书号第4612467号,授权公告号:CN 110245587 B
邮箱:gshi@xpu.edu.cn