福州大学数学与计算机科学学院计算机图形学与多媒体/人工智能研究生导师介绍：甘敏

• 2025考研英语全程班 早鸟3班
• 26考研全科上岸规划营「择校▪规划▪备考」
• 福州大学2025考研专业课复习资料「真题▪笔记▪讲义▪题库」

福州大学数学与计算机科学学院计算机图形学与多媒体/人工智能研究生导师甘敏介绍如下：

个人简介

甘敏，男，博士，教授，博导。2010年获中南大学控制科学与工程专业博士学位。2010年6月至2016年10月在合肥工业大学电气与自动化工程学院工作，2016年11月至今在福州大学数学与计算机科学学院工作。2011年7月至9月在香港城市大学系统工程与工程管理学院做研究助理工作，2013年4月至12月在澳门大学科技学院做博士后工作，2015年7月至2016年5月在美国达科他州大学做博士后工作。主要研究方向为：机器学习中的优化方法、计算机视觉、系统辨识、图像处理。主持国家自然科学基金面上项目“基于核矩阵的柔性系数回归模型及其在风电场风速间歇性建模中的应用”，国家自然科学基金青年项目“基于变系数模型与函数逼近的非线性非平稳系统建模与预测”。

可招收计算机科学与技术专业博士生，计算机软件与理论、应用数学、运筹学与控制论、计算机应用，软件工程等方向的学术和专业型硕士研究生。欢迎应用数学、运筹学与控制论的学术硕士来交流。

目前我们在做计算机视觉中的超分辨率，图像处理的去模糊，机器学习中的稀疏主成分分析、低秩矩阵分解等问题。特别欢迎数学基础好，或对机器学习、系统建模、深度学习有一定基础的优秀同学，尽早联系我。期待与勤奋学习、勇于探索的同学共同进步！

电话：130557240--

邮箱： aganmin@aliyun.com

研究方向：机器学习、数据分析、图像处理 

办公室：数计学院2号楼510

主要学术论文

[1]  Jian-nan Su, Min GAN (甘敏, 通讯作者), Guang-Yong Chen, C. L. Philip Chen. Attention-Based Convolutional Neural Networks for Image Super-Resolution. Submitted to IEEE Transactions on Neural Networks and Learning System.

[2]  Min GAN (甘敏), Yu Guan, Guang-Yong Chen, C. L. Philip Chen. Recursive Variable Projection Algorithm for a Class of Separable Nonlinear Models. Submitted to IEEE Transactions on Signal Processing, Major revision.

[3]  Min GAN (甘敏), Hong-Tao Zhu, Guang-Yong Chen, C. L. Philip Chen. Weighted Generalized Cross Validation Based Regularization for Broad Learning System. Submitted to IEEE Transactions on Cybernetics.

[4]  Qiong-Ying Chen, Min GAN (甘敏, 通讯作者), Guang-Yong Chen, C. L. Philip Chen. Model Selection for RBF-ARX model. IEEE Transactions on Cybernetics, Major Revision.

[5]   Feng Zhou, Min GAN (甘敏, 通讯作者), C. L. Philip Chen. State-dependent ARX Model-based RPC with Variable Feedback Control Laws for Output Tracking, IEEE Transactions on Industrial Electronics, major revision.

[6]   Qiong-Ying Chen, Min GAN (甘敏, 通讯作者), C. L. Philip Chen. Variable projection approach based on BFGS algorithm for blind deconvolution, Submitted to IEEE Transactions on Computational Imaging.

[7]   Jia Chen, Min GAN (甘敏, 通讯作者), Guang-Yong Chen, C. L. Philip Chen. Constrained Variable Projection Optimization for a Stationary RBF-AR Model. Neurocomputing, Major revision.

[8]   Jing Chen, Min GAN, C. L. Philip Chen. Robust standard gradient descent algorithm for ARX models using Aitken acceleration technique, Submitted to IEEE Transactions on Automatic Control.

[9]  Guang-Yong Chen, Min GAN (甘敏, 通讯作者), Dong-Qing Wang, C. L. Philip Chen. Insights into Algorithms of Separable Nonlinear Least Squares Problems. Submitted to IEEE Transactions on Image Processing.

[10]  Yu Guan, Yun-zhi Huang, Guang-Yong Chen, Min GAN (甘敏, 通讯作者). A novel L2-norm noise constrained estimation for image restoration based on Gradient projection and variable projection, submitted to IEEE Signal Processing Letters.

[11]  Shu-qiang Wang, Xiang-yu Wang, Yan-yan Shen, Zhi-le Yang, Min GAN (甘敏, 通讯作者), Bai-ying Lei. Diabetic Retinopathy Diagnosis using Multi-channel Generative Adversarial Network with Semi-supervision, IEEE Transactions on Automation Science and Engineering, Conditionally Accept.

[12]  Dong-Qing Wang, Suo Zhang, Min GAN (甘敏), and Jian-long Qiu, "A novel EM identification method for Hammerstein systems with missing output data," IEEE Transactions on Industrial Informatics, 2019, acceptable for publication, DOI: 10.1109/TII.2019.2931792.

[13]  Min GAN (甘敏), Guang-Yong Chen, Long Chen, C. L. Philip Chen. Term selection for a class of nonlinear separable models. IEEE Transactions on Neural Networks and Learning Systems, acceptable for publication, 2019, DOI (identifier) 10.1109/TNNLS.2019.2904952.

[14]  Guang-Yong Chen, Min GAN (甘敏, 通讯作者), C. L. Philip Chen, Han-Xiong Li. Basis Function Matrix based Flexible Coefficient Autoregressive Models: A Framework for Time Series and Nonlinear System Modeling. IEEE Transactions on Cybernetics, acceptable for publication, DOI (identifier) 10.1109/TCYB.2019.2900469, 2019, in press.

[15]  Guang-Yong Chen, Shu-Qiang Wang, Dong-Qing Wang, Min GAN (甘敏, 通讯作者). Regularization Methods for Separable Nonlinear Models. Nonlinear Dynamics, 2019, 98: 1287–1298.

[16]  Min GAN (甘敏), Xiao-xian Chen, Ding Feng, Guang-Yong Chen, C. L. Philip Chen. Adaptive RBF-AR Models Based on Multi-innovation Least Squares Method. IEEE Signal Processing Letters, 2019, 26(8): 1182-1186.

[17]  Guang-Yong Chen, Min GAN (甘敏, 通讯作者), Feng Ding, C. L. Philip Chen. Modified Gram-Schmidt Method Based Variable Projection Algorithm for Separable Nonlinear Models. IEEE Transactions on Neural Networks and Learning System, 2019, 30(8): 2410-2418. (ESI高被引论文，hot topic论文)

[18]  Guang-Yong Chen, Min GAN (甘敏, 通讯作者), C. L. Philip Chen, Han-Xiong Li. A Regularized Variable Projection Algorithm for Separable Nonlinear Least Squares Problems. IEEE Transactions on Automatic Control, 2019, 64(2): 526 – 537.  (长文，ESI高被引论文，hot topic论文)

 [19]  Guang-Yong Chen, Min GAN (甘敏, 通讯作者), C. L. Philip Chen, Long Chen. A Two-Stage Estimation Algorithm Based on Variable Projection Method for GPS Positioning. IEEE Transactions on Instrumentation & Measurement, 2018, 67 (11): 2518 - 2525.

[20]  Min GAN (甘敏), C. L. Philip Chen, Guang-Yong Chen, Long Chen. On some separated algorithms for separable nonlinear squares problems [J]. IEEE Transactions on Cybernetics, 2018, 48(10): 2866-2874. (ESI高被引论文，hot topic论文)

[21] Guang-Yong Chen, Min GAN (甘敏, 通讯作者). Generalized Exponential Autoregressive Models for Nonlinear Time Series: Stationarity, Estimation and Applications. Information Sciences, 2018，438：46-57.

[22]  Min GAN(甘敏), Long Chen, C. Y. Zhang, Hui Ping “A Self-Organizing State Space Type Microstructure Model for Financial Asset Allocation”. IEEE Access, 2016, 4: 8035-8043.

[23]  Min GAN(甘敏), C. L. Philip Chen, Long Chen, Chun-yang Zhang. Exploiting the Interpretability and Forecasting Ability of the RBF-AR Model for Nonlinear Time Series [J]. International Journal of Systems Science, 2016, 47(8): 1868-1876.

[24]  Min GAN(甘敏), Han-Xiong Li, C. L. Philip Chen, Long Chen. A Potential Method for Determining Nonlinearity in Wind Data [J], IEEE Power and Energy Technology Systems Journal, 2015, 2(2): 74-81.

[25]  Min GAN(甘敏), C. L. Philip Chen, Han-Xiong Li, Long Chen. Gradient radial basis function based varying-coefficient Autoregressive Model for nonlinear and nonstationary time series [J]. IEEE Signal Processing Letters, 2015, 22(7): 809-812.

[26]  Min GAN(甘敏), Han-Xiong Li, Hui Peng. A variable projection approach for efficient Estimation of RBF-ARX model [J]. IEEE Transactions on Cybernetics, 2015, 45(3): 476-485.

[27]  Chun-yang Zhang, C. L. Philip Chen, Long Chen, Min Gan(甘敏). Fuzzy Restricted Boltzmann Machine to Enhance Deep Learning [J]. IEEE Transactions on Fuzzy Systems, 2015, 23(6): 2163-2173.

[28]  Min GAN(甘敏), Han-xiong LI. An Efficient Variable Projection Formulation for Separable Nonlinear Least Squares Problems [J]. IEEE Transactions on Cybernetics, 2014, 44(5): 707-711.

[29]  Chun-yang Zhang, C. L. Philip Chen, Min Gan(甘敏). Predictive Deep Boltzmann Machine for Multi-Period Wind Speed forecasting [J]. IEEE Transactions on sustainable energy, 2015, 6(4): 1416-1425.

[30]  Min Gan(甘敏), Yu Cheng, Kai Liu, Gang-lin Zhang. Seasonal time series prediction based on a quasi-linear autoregressive model [J]. Applied Soft Computing, 2014, 24(1): 13-18.

[31]  Geng Zhang, Han-Xiong Li, Min GAN(甘敏). Design a Wind Speed Prediction Model Using Probabilistic Fuzzy System [J], IEEE Transactions on Industrial Informatics, 2012, 8(4): 819-827.

[32]  Min GAN(甘敏), Yun-zhi Huang, Ming Ding, Xue-ping Dong. Testing for nonlinearity in solar radiation time series by a fast method of surrogate data [J]. Solar Energy, 2012, 86(9): 2893-2896.

[33]  Min Gan(甘敏), Hui Peng, Liyuan Chen. A Global-local Approach to Parameter Optimization of RBF-type Models [J]. Information Sciences, 2012, 197(15): 144-160.

[34]  Min Gan(甘敏), Hui Peng, Xueping Dong. A hybrid algorithm to optimize RBF network architecture and parameters for nonlinear time series modeling [J]. Applied Mathematical Modelling, 2012, 36(7): 2911-2919.

[35]  Min Gan(甘敏), Hui Peng. Stability analysis of RBF-network based state-dependent autoregressive model for nonlinear time series [J]. Applied Soft Computing, 2012, 12(1): 174-181.

[36]  Min Gan(甘敏), Ming Ding, Yun-zhi Huang, Xueping Dong. The effect of different state sizes on Mycielski approach for wind speed prediction [J]. Journal of Wind Engineering & Industrial Aerodynamics, 2012, 109:89-93. 

[37]  Min Gan(甘敏), Hui Peng, et al. A locally linear RBF network-based state-dependent AR model for nonlinear time series modeling [J]. Information Sciences, 2010, 180: 4370~4383.

[38]  Min Gan(甘敏), Hui Peng, et al. An Adaptive Decision Maker for Constrained Evolutionary Optimization [J]. Applied Mathematics and Computation, 2010, 215(12): 4172~4184.

[39]  甘敏，丁明，董学平. 基于改进的Mycielski方法的风速时间序列预测[J]. 系统工程理论与实践，2013, 33(4) : 1084-1088.

[40]  甘敏，彭辉，黄云志，董学平. 自组织状态空间模型参数初始分布搜索算法[J].自动化学报，2012, 38(9): 1538-1543.

[41]  甘敏，彭辉，陈晓红. 基于金融市场微结构模型和进化算法的动态资产分配[J].系统工程学报. 2011，26(3): 314-321.

[42]  甘敏，彭辉，陈晓红. RBF-AR模型在非线性时间序列预测中的应用[J].系统工程理论与实践. 2010，30(6)：1055~1061.

[43]  甘敏，彭辉，王勇. 多目标优化与适应惩罚的混合约束优化进化算法[J]. 控制与决策, 2010, 25(3): 378~382.

[44]  甘敏，彭辉.不同基函数对RBF-ARX 模型的影响研究[J].中南大学学报. 2010, 41(6): 2231~2235.

[45]  甘敏，彭辉. 基于带回归权重的RBF-AR模型的混沌时间序列预测[J]. 系统工程与电子技术， 2010，32(4)：820~824.

[46]  甘敏，彭辉. RBF神经网络参数优化的两种混合优化算法[J]. 控制与决策, 2009, 24(8): 1172~1176.