General

Fengzhen Tang


Shenyang Institute of Automation,
Chinese Academy of Sciences
Email: tangfengzhen@sia.cn 
Telephone: +86-24-23970211
Address: No.114 Nanta Street, Shenyang, Liaoning Province, China
Postcode:  110016

Research Areas

 Machine Learning,Artifical Intelligence, Intelligent Robotics, Computational Neuroscience


Recruiting research staff related to above research areas. Please send me your CV to my email box tangfengzhen@sia.cn.

You can also check the following links for detailed information: 

中国科学院沈阳自动化研究所2023-2024年招聘岗位需求(进行中)--中国科学院沈阳自动化研究所 (cas.cn)  (神经计算课题组)

中国科学院沈阳自动化研究所2023-2024年招聘简章--中国科学院沈阳自动化研究所 (cas.cn)



Education

  • 2015 PhD in Computer Science,University of Birmingham, School of Computer Science, Birmingham,UK (Supervisor: Prof. Peter Tino; Second supervisor: Prof. Huanhuan Chen)

  • 2011 M.Sc in Computer Science and Technology,Northeastern University, Software College, Shenyang, China (Supervisor: Prof. Huiyan Jiang)

  • 2009 BEng in Software Engineering,Northeastern University , Software College, Shenyang, China

Experience

   
Work Experience

  • 2023 until present:Researcher in State Key Laboratory of Robotics, Shenyang Insitute of Automation Chinese Academy of Sciences, Shenyang, China

  • 2018 until 2022: Associate Researcher in State Key Laboratory of Robotics, Shenyang Insitute of Automation Chinese Academy of Sciences, Shenyang, China

  • 2015- 2017: Assistant Researcher in State Key Laboratory of Robotics, Shenyang Insitute of Automation Chinese Academy of Sciences, Shenyang, China

Teaching Experience

In Shenyang Institute of Automation, Chinse Academy of Science

  • Sep 2017 - Jan 2018. Lecturer. Course : Academic English for Postgraduates

In School of Computer Science, The University of Birmingham, UK.

  • Jan 2015 - May 2015. Teaching Associate. Course : Foundations of Computer Science and MSc/ICY Java Workshop.
  • Sep 2014 - Dec 2014. Demonstrator. Course : Mathematical Techniques for Computer Science and MSc/ICY Java Workshop.
  • Feb 2014 - May 2014. Demonstrator. Course : Introduction to Mathematics for Computer Science.
  • Sep 2013 - Dec 2013. Demonstrator. Course : Mathematical Techniques for Computer Science.
  • Jan 2012 - Mar 2013. Demonstrator. Course : Foundations of Computer Science
  • Sep 2012 - Dec 2012. Demonstrator. Course : Mathematical Techniques for Computer Science

In Software College, Northeastern University, Shenyang, China

  • 2009-2011 Teaching Assistant of Program Practice (IV)(Network Application Programming Based on TCP/IP)



Publications


Journal Papers

[25]  Zhihui Zhang, Fengzhen Tang*, Yiping Li, Xisheng Feng.A spatial transformation-based CAN model for information integration within grid cell modules.Cognitive Neurodynamics,https://doi.org/10.1007/s11571-023-10047-z, 2024.(SCI, 3区)

[24]Chenchen Wu, Ruming Zhang, Fengzhen Tang, Mengling Fan. Vibration optimization of cantilevered bistable composite shells based on machine learning.Engineering Applications of Artificial Intelligence,126:1-10,2023 (SCI, 2区Top)

[23] Zirui Zhang, Yinan Guo, Fengzhen Tang*.  Dimension Selection for EEG Classification in the SPD Riemannian Space Based on PSO. Knowledge-Based Systems, 279:110933,2023. (SCI, 1区Top)

[22] D Xu, F Tang, Y Li, Q Zhang, X Feng. FB-CCNN: A Filter Bank Complex Spectrum Convolutional Neural Network with Artificial Gradient Descent Optimization,Brain Sciences 13 (5), 780 (SCI, 3区)

[21]   Zhihui Zhang, Fengzhen Tang*, Yiping Li, Xisheng Feng. Modeling the grid cell activity based on cognitive space transformation. Cognitive Neurodynamics. https://doi.org/10.1007/s11571-023-09972-w, 2023 (SCI, 3区)

[20] Dongcen Xu, Fengzhen Tang, Yiping Li, Qifeng Zhang and Xisheng Feng. An Analysis of Deep Learning Models in SSVEP-Based BCI: A Survey. Brain Sciences. 13(3):1-23, 2023 (SCI, 3区)

[19] Kai He, Wenxue Wang, Gang Li, Peng Yu, Fengzhen Tang, LianqingLiu. Knowledge-based hybrid connectionist models for morphologic reasoning. Machine Vision and Applications, 34(2):1-13,2023 (EI,SCI, 4区)

[18] Changbo Zhu, Ke Zhou, Fengzhen Tang, Yandong Tang, Xiaoli Li, Bailu Si. A Hierarchical Bayesian Model for Inferring and Decision Making in Multi-Dimensional Volatile Binary Environments. Mathematics. 10(24):1-35,2022 (SCI, 4区)

[17] Bingjie Zhang, Xiaoling Gong, Jian Wang∗, Fengzhen Tang*, Kai Zhang, Wei Wu. Nonstationary Fuzzy Neural Network Based on FCMnet Clustering and a Modified CG Method with Armijo-type Rule, Information Sciences, 608:313-338,2022, https://doi.org/10.1016/j.ins.2022.06.071. (SCI, 1区Top)

[16] F. Tang, P. Tiňo and H. Yu, "Generalized Learning Vector Quantization With Log-Euclidean Metric Learning on Symmetric Positive-Definite Manifold," in IEEE Transactions on Cybernetics,53(8):5178-5190,2023. (SCI, 1区Top)

[15] M. Fan, F.Tang*, et al. Riemannian Dynamic Generalized Space Quantization Learning. Pattern Recognition, 132:108932,2022. (SCI, 1区Top)

[14] Yinan Guo,Botao Jiao, Ying Tan,Pei Zhang,Fengzhen Tang*, “A Transfer Weighted Extreme Learning Machine for Imbalance Classification[J]”. International Journal of Intelligent System 1-22,2022 (SCI)

[13] Yazhou Hu, Fengzhen Tang, Jun Chen,Wenxue Wang. Quantum‑enhanced reinforcement learning for control: a preliminary study. Control Theory and Technology,19:455-464,2021 (SCI)

[12] F. Tang, H. Feng, P. Tino, B. Si, D. Ji: Probabilistic Learning Vector Quantization on Manifold of Symmetric Positive Definite Matrices.Neural Networks, 142105-118, 2021. (c) Elsevier [arXiv]codehttps://github.com/sonnatang/RiemannianPLVQ/  (SCI, 1区Top)

[11] Y. Guo, Z. Zhang, F. Tang*: Kernelized Multiclass Support Vector MachinePattern Recognition, 117107988, 2021.  (SCI, 1区Top)

[10] Y. Guo, B. Jiao, J. Cheng, L. Yang, S. Yang and F. Tang: A Novel Oversampling Technique Based on the Manifold Distance for Class Imbalance Learning, International Journal of Bio-Inspired Computation, 18(3): 131-142, 2021. (SCI)

[9]    F. Tang, M. Fan, P. Tino: Generalized Learning Riemannian Space Quantization: A Case Study on Riemannian Manifold of SPD MatricesIEEE Transactions on Neural Networks and Learning Systems, 1 (32), pp. 281-292, 2021.  codehttps://github.com/sonnatang/RiemannianGLVQ/ (SCI, 1区Top)

[8]    T. Zeng, F. Tang, D. Ji, B. Si : NeuroBayesSLAM: Neurobiologically inspired Bayesian integration of multisensory information for robot navigation, Neural Networks, 126: 21–35, 2020 (SCI, 1区Top)

[7]    Dongye Zhao, F. Tang* , Bailu Si, Xisheng Feng. Learning joint space-time-frequency features for EEG decoding on small labeled data. Neural Networks,114: 67-77, 2019 (IF: 7.197, SCI 一区Top )

[6]     M. Jiang, S. Song, F. Tang, Y. Li, J. Liu, X. Feng: Scan registration for underwater mechanical scanning imaging sonar using symmetrical Kullback-Leibler divergence, Journal of Electronic Imaging, 28(1):013026-1-11, 2019 (SCI)

[5]     F. TangL. Adam, B. Si: Group Feature Selection with Multiclass Support Vector Machine. Neurocomputing, 317:42–49, 2018. (SCI, 2区Top)

[4]    F. Tang, P. Tino: Ordinal Regression based on Learning Vector Quantization, Neural Networks  93 : 76-88, 2017.(SCI,1区Top) 

[3]     F. Tang, P. Tino, P. A. Gutierrez, H. Chen: The Benefits of Modeling Slack Variables in SVMs. Neural Computation, 27: 954–981, 2015 (SCI)

[2]    H. Jiang ,F. Tang, L. Zou, Y.-W. Chen: Data De-noising Based on PCA-KNN Algorithm in Billet Surface Temperature Measurement. Applied Mathematics & Information Sciences, 7(2L): 455-458, 2013. 

[1]    X. Liu, H. Jiang, F. Tang: Parameters Optimization in SVM Based-on Ant Colony Optimization algorithm, International Conference on Advances in Computer Science and Engineering, 2010. Advanced Materials Research Vols. 121-122 pp.470-475, 2010

Conference Papers

    

[13] Mengling Fan, Fengzhen Tang, Xigang Zhao. Shrinkage Estimator based Riemannian dynamic generalized space quantization learning for Multi-Class Motor Imagery Classification. YAC 2023 (EI), accepted

[12] Zhihui Zhang, Fengzhen Tang, Yiping Li, Xisheng Feng. MVSOP: A new framework for integrating MVS into SLAM based on ORB and PF. YAC 2023 (EI), accepted

[11]Mengling Fan, Fengzhen Tang, Xigang Zhao. Prototype Based Linear Sub-Manifold Learning. IJCNN 2023. (EI, CCF 推荐C类)

[10] Fei Song, Jinyu Li, Fengzhen Tang, Yandong Tang, Bailu Si*,  Reexaming Indoor Mobile Robots from a Cognitive Perspective, ICRCV, 2023

[9] Jianjun Xu, Nanya Yan, Fengzhen Tang. An Improvement of Loop Closure Detection Based on BoW for RatSLAM, YAC2022, (EI)

[8]     D. Zhao, B. Si, F. Tang: Unsupervised Feature Learning for Visual Place Recognition in Changing Environments, IJCNN, 2019

[7]      F. Tang, B. Si, D, Ji: A Prey-Predator Model for Efficient Robot Tracking, 2017 IEEE International Conference on Robotics and Automation (ICRA 2017), 2017

[6]     G. Huang, B. Si, F. Tang: Model Learning based on Grid Cell Representations, ROBIO, 2017 

[5]     H. Chen, F. Tang, P. Tino, A. G. Cohn and X. Yao. Model metric co- learning for time series classification. IJCAI, 2015.(录用率28.8%) 

[4]     F. Tang, P. Tino and H. Chen: Learning Deterministically Constructed Echo State Networks . International Joint Conference on Neural Networks (IJCNN), 2014, pp. 77 - 83

[3]    F. Tang, P. Tino, P. A. Gutierrez and H. Chen: Support Vector Ordinal Regression using Privileged Information. In Proceedings of the 2014 European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (ESANN), pp. 253-258 

[2]     H. Chen, F. Tang, P. Tino, X. Yao: Model-based Kernel for Efficient Time Series Analysis. 19th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), Accepted for oral presentation, 2013.(录用率14.6%) 

[1]     H. Jang, F. Tang, X. Zhang: Liver Cancer Identification Based on PSO-SVM Model. ICARCV 2010


Paper In Chinese

[6] 赵杭飘,徐剑君,李涛,唐凤珍*:多机协同的类脑定位建图方法,机器人,接收. 一级学报

[5] 王运梦,李涛, 徐剑君, 唐凤珍, 崔龙, 刘钊铭, 刘连庆, 微型仿生爬虫机器人类脑环境感知方法,科学通报, 68:3095-3106, 2023.一级学报

[4] 徐剑君,商亮,唐凤珍*:基于快速增量式视觉感知的类脑 SLAM ,信息与控制, 51(1):542-553. 2022. 一级学报

Xu Jianjun, SHANG Liang, TANG Fengzhen, Brain-inspired SLAM Based on Fast Incremental Visual Perception. Information and Control, 51(1):542-553. 2022 (Chinese)

[3]张驰,唐凤珍*:基于自适应编码的脉冲神经网络,计算机应用研究,39(2):593-597. 2022. 中文核心

 Chi Zhang,Fengzhen Tang* : Self-adaptive coding for spiking neural network, Application Research of Computers 39(2): 593-597, 2022 (Chinese)

[2]张晓铖,唐凤珍*:基于对数欧氏度量学习的概率黎曼空间量化方法,计算机应用研究,39(3):662-680.中文核心

Xiaochen Zhang, Fengzhen Tang*:Probabilistic Riemannian quantization method on manifold with log-Euclidean metric learning, Application Research of Computers 39(3):661-680,2022 (Chinese)

[1] 冯海峰,唐凤珍*:基于超参数学习的概率黎曼空间量化算法,计算机应用研究,38:45-48,2021. 中文核心


Research Interests

Statistical machine learning, deep learning, metric learning, feature selection

Time series analysis, EEG signal decoding, Brain-computer interface, Autonomous robots