- Semi-Supervised Learning: manually labeled samples usually are expensive and scarce. It is economical to train classifiers (shallow or deep models) using a small amount of labeled samples and aboundant, easily available unlabeled samples.
- Deep Neural Networks: understanding brain learning mechanism and developing highly effective AI algorithms are a pair of dual problems. It is interesting to explore the foundamental neural learning rules shared across biological and artificial intelligence.
Projects & Grants
- Artificial Intelligence Course Construction and Reform, Industry-Education-Research Collaboration Funding of Ministry of Education of China (PI)
- Semi-Supervised Deep Learning Algorithms and Their Applications to Time Series Data Prediction. Natural Science Foundation Of China (NSFC) Young Scientists Fund 2021.01-2021.12 (PI)
- Deep Spiking Neural Network Model and Applications in Spatio-Temporal Data Analysis. Natural Science Foundation of Shanghai (PI)
- Startup Fund for Youngman Research at Shanghai Jiao Tong University (SFYR at SJTU) (PI)
- Construction of Heart Fiber DTI Map and Cardiac Fiber Constant Feature Detection Based on Fiber Information Joint Clustering and Sparse Registration. Natural Science Foundation Of China (NSFC), 2019.01-2021.01 (CoI)
- Graph-based k-means for nonlinear manifold clustering and representative points selection, CN103617609B
- Multi-resolution variant regional level set for image segmentation, CN102044077B
(Full Publications: Google Scholar)
- Enmei Tu, Zihao Wang, Jie Yang, and Nikola Kasabov. “Deep semi-supervised learning via dynamic anchor graph embedding in latent space.” Neural Networks (2021).
- Zihao Wang, Enmei Tu* and Zhicheng Lee. Deep Semi-Supervised Learning via Dynamic Anchor Graph Embedding Learning, 2021 International Joint Conference on Neural Networks (IJCNN 2021).
- Zihao Wang, Zhiqiang Xie, Enmei Tu*, Alex Zhong and Yingying Liu. Reinforcement Learning-Based Insulin Injection Time And Dosages Optimization, 2021 International Joint Conference on Neural Networks (IJCNN 2021).
- Zhiqiang Xie, Enmei Tu*, Hao Zheng, Yun Gu and Jie Yang. Semi-Supervised Skin Lesion Segmentation With Learning Model Confidence, 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2021).
- Zihao Wang, Enmei Tu*, and Zhou Meng. End-To-End Graph-based Deep Semi-Supervised Learning with Extended Graph Laplacian, 2020 China Automation Congress (CAC 2020).
- Tianyi Zhang, Yun Gu, Xiaolin Huang, Enmei Tu, and Jie Yang. Stereo Endoscopic Image Super-Resolution Using Disparity-Constrained Parallel Attention, The International Conference on Learning Representations (ICLR 2020, workshop paper)
- Xiao Han, Zihao Wang, Enmei Tu*, Gunnam Suryanarayana, and Jie Yang. Semi-Supervised Deep Learning Using Improved Unsupervised Discriminant Projection, International Conference on Neural Information Processing (ICONIP), 2019.
- Doborjeh Maryam, Nikola Kasabov, Zohreh Doborjeh, Reza Enayatollahi, Enmei Tu, and Amir H. Gandomi. Personalised modelling with spiking neural networks integrating temporal and static information. Neural Networks, 119 (2019): 162-177.
- Chen Mingjian, Hao Zheng, Changsheng Lu, Enmei Tu, Jie Yang, and Nikola Kasabov. Accurate breast lesion segmentation by exploiting spatio-temporal information with deep recurrent and convolutional network. Journal of Ambient Intelligence and Humanized Computing (2019): 1-9.
- Suryanarayana Gunnam, Enmei Tu, and Jie Yang. Infrared super-resolution imaging using multi-scale saliency and deep wavelet residuals. Infrared Physics & Technology, 97 (2019): 177-186.
- Chen Xingyu, Fanghui Liu, Enmei Tu, Longbing Cao, and Jie Yang. Deep-PUMR: Deep Positive and Unlabeled Learning with Manifold Regularization. International Conference on Neural Information Processing (ICONIP), 2018.
- Chen Mingjian, Hao Zheng, Changsheng Lu, Enmei Tu, Jie Yang, and Nikola Kasabov. A Spatio-Temporal Fully Convolutional Network for Breast Lesion Segmentation in DCE-MRI. International Conference on Neural Information Processing (ICONIP), 2018.
- Wang Lu, Chao Ma, Enmei Tu, Jie Yang, and Nikola Kasabov. Discrete Sparse Hashing for Cross-Modal Similarity Search. In International Conference on Neural Information Processing (ICONIP), 2018.
- Enmei Tu, Guanghao Zhang, Lily Rachmawati et al. Exploiting AIS Data For Intelligent Maritime Navigation: A Comprehensive Survey, IEEE Transactions on Intelligent Transportation System, 2018, 19(5): 1559-1582.
- Mao Shangbo, Enmei Tu, Guanghao Zhang, Lily Rachmawati, Eshan Rajabally, and Guang-Bin Huang. An automatic identification system (AIS) database for maritime trajectory prediction and data mining. In Proceedings of ELM-2016, pp. 241-257. Springer, Cham, 2018.
- Zhang Guanghao, Enmei Tu, and Dongshun Cui. Stable and improved generative adversarial nets (GANS): A constructive survey. IEEE International Conference on Image Processing (ICIP), pp. 1871-1875. 2017.
- Enmei Tu, Guanghao Zhang, Lily Rachmawati, Eshan Rajabally, Shangbo Mao, and Guang-Bin Huang. A theoretical study of the relationship between an ELM network and its subnetworks. International Joint Conference on Neural Networks (IJCNN), pp. 1794-1801. IEEE, 2017.
- Enmei Tu, Yaqian Zhang, Lin Zhu, Jie Yang, Nicola Kasabov. A Graph-Based Semi-Supervised $k$ Nearest-Neighbor Method for Nonlinear Manifold Distributed Data Classification, Information Scieces: 2016, 367, 673- 688
- Nikola Kasabov, Nathan Matthew Scott, Enmei Tu, Stefan Marks, Neelava Sengupta, Elisa Capecci, Muhaini Othman et al. Evolving spatio-temporal data machines based on the NeuCube neuromorphic framework: design methodology and selected applications. Neural Networks 78 (2016): 1-14.
- Enmei Tu. Graph Based Machine Learning Algorithms Design and Its Application in Neural Network Research, PhD Thesis (In Chinese), Shanghai Jiao Tong University:2014
- Enmei Tu, Nikola Kasabov, Jie Yang. Mapping Temporal Variables Into the NeuCube for Improved Pattern Recognition, Predictive Modeling, and Understanding of Stream Data, IEEE Transactions on Neural Networks and Learning Systems:2016
- Enmei Tu, Jie Yang, Nicola Kasabov, Yaqian Zhang. Posterior Distribution Learning (PDL): A Novel Supervised Learning Framework Using Unlabeled Samples to Improve Classification Performance, Neurocomputing: 2015, 157, 173–186
- Enmei Tu, Longbing Cao, Jie Yang, Nicola Kasabov. A novel Graph-based K-means for Nonlinear Manifold Clustering and Representative Selection, Neurocomputing: 2014, 143, 109–122
- Enmei Tu, Jie Yang, Zhenghong Jia, Nicola Kasabov. Posterior Distribution Learning (PDL): A Novel Supervised Learning Framework, Neural Information Processing: 2014, 86–94
- Enmei Tu, Nikola Kasabov, Marini Othman, Yuxiao Li, Susan Worner, Jie Yang, Zhenghong Jia. Neucube (st) for Spatio-Temporal Data Predictive Modelling with a Case Study on Ecological Data, International Joint Conference on Neural Networks (IJCNN):2014, 638–645
- Enmei Tu, Jie Yang, Jiangxiong Fang, Zhenghong Jia, Nikola Kasabov. An Experimental Comparison of Semi-supervised Learning Algorithms for Multispectral Image Classification, Photogrammetric Engineering & Remote Sensing: 2013, 79(4), 347–357