Projects

My research project

Motor Imagery Classification

We proposed some bilinear dimensionality reduction methods and designed related classifiers for motor imagery BCI system. The more details are shown in demo.

Hyperspectral image classification

The low dimensional embedding is learned from the high dimensional hyperspectral image by a group local Riemannian embedding (GLRE) algorithm.

Speech to Singing

The fundamental frequency of voice was extraced by the TANDEM-STRAIGHT tools. And the frequency of speech was changed to the singing. The more details are shown in demo.

Image Segmentation 2D/3D

The proposed Random Walks algorithm was applied to extract the objective from original 2D/3D image. The more details are shown in demo.

Journal Publications

In this paper, we construct a Riemannian graph to incorporate the information of training and test data into processing. The adjacency and weight in Riemannian graph are determined by the geodesic distance of Riemannian manifold. Then, a new graph embedding algorithm, called bilinear regularized locality preserving (BRLP), is derived upon the Riemannian graph for addressing the problems of high dimensionality frequently arising in BCIs.
IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2018

Considering a special case of SPD space, a simple yet efficient bilinear sub-manifold learning (BSML) algorithm is derived to learn the intrinsic sub-manifold by identifying a bilinear mapping that maximizes the preservation of the local geometry and global structure of the original manifold. Two BSML-based classification algorithms are further proposed to classify the data on a learned intrinsic sub-manifold.
IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2016

arXiv & Conference

(2018). Bilinear Fuzzy Discriminant Analysis and Locality Preserving Embedding Learning for Motor Imagery Classification. Submit to Journal of Neural Engineering.

arXiv

(2013). Numerical Analysis of Parkinson’s Disease in a Basal Ganglia Network Model. Advances in Cognitive Neurodynamics (III) pp 833-841.

Article Link

Contact