所属学科专业：计算机科学与技术，电子信息
导师简介
时光，男，数学专业理学博士，统计学科博士后，副教授，香港中文大学访问学者。担任Expert Systems with Applications, Neurocomputing, IEEE TGRS等多个国际期刊的审稿人，近5年来，在Chemosphere，IEEETGRS、ScienceofTotalEnvironment、Neural Computing and Applications等国际期刊发表论文十余篇。
主要研究方向：
空气污染的时空关系建模、遥感图像目标检测等。
科研项目：
1.国家自然科学基金委，青年项目，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，2022.01至2024.12，主持
2.西安交通大学，基本科研业务费自由探索与创新项目，基于认知匹配的遥感图像少样本目标检测方法研究，2022.6至2024.12，主持
3.陕西省科技厅，青年项目，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，2021.01至2022.12，主持
4.中国电子科技集团公司第十研究所，横向项目，多模态数据深度协同学习理论与方法研究，2021.4至2021.12，参与（第二）
5.国家自然科学基金委，重点项目，模型与数据双驱动的无监督多源数据特征学习方法研究，2021.01至2024.12，参与（第三）
6.中国科学院生物物理研究所，重大项目，神经网络模型泛化性与可解释性理论研究，2020.11至2023.10，参与（项目骨干）
7.中国石油集团东方地球物理勘探有限责任公司，横向项目，东方物探—西安交大数学与油气智能探测技术研究中心项目：数学与油气智能探测技术，2020.09至2022.12，参与（第八）
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
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：9.8)
[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：8.2)
[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)
[7] Shuyun Yang,Guang Shi. An efficient approach to attribute reductions of quantitative dominance-based neighborhood rough sets based on graded information granules. Artificial Intelligence Review.57, 6 (2024).(中科院1区，影响因子12.0)
[8] Shuyun Yang, Hongying Zhang,Guang Shi, Yingjian Zhang: Attribute reductions of quantitative dominance-based neighborhood rough sets with A-stochastic transitivity of fuzzy preference relations. Applied Soft Computing. 134: 109994 (2023) (中科院1区，影响因子8.7)
[9] Changpeng Wang, Jiangshe Zhang, Tianjun Wu, Meng Zhang,Guang Shi: Semi-supervised nonnegative matrix factorization with positive and negative label propagations. Appl. Intell. 52(9): 9739-9750 (2022)
[10] Shuyun Yang, Hongying Zhang, Bernard De Baets, Moriba K. Jah,Guang Shi:Quantitative Dominance-Based Neighborhood Rough Sets via Fuzzy Preference Relations.IEEE Transactions on Fuzzy Systems. 29(3): 515-529 (2021) (中科院1区，影响因子：12.029)
[11] Junmin Liu, Zhuangzhuang Xie, Chunxia Zhang,Guang Shi: A novel method for Mandarin speech synthesis by inserting prosodic structure prediction into Tacotron2. International Journal of Machine Learning and Cybernetics. 12(10): 2809-2823 (2021). (中科院2区，影响因子：4.012)
[12] Changsheng Zhou, Jiangshe Zhang, Junmin Liu, Chunxia Zhang,Guang Shi, Junying Hu: Bayesian Transfer Learning for Object Detection in Optical Remote Sensing Images. IEEE Transactions on Geoscience and Remote Sensing. 58(11): 7705-7719 (2020). (中科院2区，影响因子：5.6)
[13] Jiangshe Zhang, Cong Ma, Junmin Liu,Guang Shi: Penetrating the influence of regularizations on neural network based on information bottleneck theory. Neurocomputing. 393: 76-82 (2020). (中科院2区，影响因子5.719)
[14] Changpeng Wang, Jiangshe Zhang,Guang Shi: Discriminative low-rank representation with Schatten-p norm for image recognition. Multimedia Tools and Applications. 78(16): 23075-23095 (2019). (中科院4区，影响因子2.757)
[15] Zhengjie Song, Jiangshe Zhang,Guang Shi, Junmin Liu. Fast Inference Predictive Coding: A Novel Model for Constructing Deep Neural Networks. IEEE Transactions on Neural Networks and Learning Systems, 99: 1-16 (2018). (中科院1区，影响因子：10.451)
[16] Fang Du, Jiangshe Zhang, Nannan Ji,Guang Shi, Chunxia Zhang, An effective hierarchical extreme learning machine based multimodal fusion framework. Neurocomputing, 322: 141-150 (2018). (中科院2区，影响因子5.719)
[17] Changpeng Wang, Jiangshe Zhang, Fang Du,Guang Shi. Symmetric low-rank representation with adaptive distance penalty for semi-supervised learning. Neurocomputing, 316:376-385 (2018). (中科院2区，影响因子5.719)
[18] Huirong Li, Jiangshe Zhang,Guang Shi, Junmin Liu: Graph-based discriminative nonnegative matrix factorization with label information. Neurocomputing, 266: 91-100(2017). (中科院2区，影响因子5.719)
联系方式: gshi@xpu.edu.cn,shiguang116@126.com
