Z
Zeng-Shun Zhao
Researcher at Shandong University of Science and Technology
Publications - 35
Citations - 268
Zeng-Shun Zhao is an academic researcher from Shandong University of Science and Technology. The author has contributed to research in topics: Competitive learning & Support vector machine. The author has an hindex of 7, co-authored 35 publications receiving 232 citations. Previous affiliations of Zeng-Shun Zhao include Shandong University & Chinese Academy of Sciences.
Papers
More filters
Journal ArticleDOI
Improved Rao-Blackwellized Particle Filter by Particle Swarm Optimization
Zeng-Shun Zhao,Xiang Feng,Yan-yan Lin,Fang Wei,Shi-Ku Wang,Tong-Lu Xiao,Maoyong Cao,Zeng-Guang Hou,Min Tan +8 more
TL;DR: The experimental results demonstrate that this novel algorithm is more efficient than the standard RBPF, and the particle swarm optimization (PSO) is applied to drive all the particles to the regions where their likelihoods are high in the nonlinear area.
Journal ArticleDOI
Solving one-class problem with outlier examples by SVM
TL;DR: In this paper, a new algorithm "SVM-SVDD" is proposed, in which both Support Vector Machine (SVM) and SVDD are used to solve data description problem with negative examples, and the experimental results illustrate that SVM-sVDD outperforms SVDd-neg on both training time and accuracy.
Journal ArticleDOI
Evolved neural network ensemble by multiple heterogeneous swarm intelligence
Zeng-Shun Zhao,Xiang Feng,Yan-yan Lin,Fang Wei,Shi-Ku Wang,Tong-Lu Xiao,Maoyong Cao,Zeng-Guang Hou +7 more
TL;DR: This paper combines NNE and multi-population swarm intelligence to construct the improved neural network ensemble (INNE), and demonstrates that the proposed novel INNE algorithm is superior to existing popular NNE in function prediction.
Journal ArticleDOI
Letters: Gabor face recognition by multi-channel classifier fusion of supervised kernel manifold learning
TL;DR: A face recognition framework under the multi-channel fusion strategy for Gabor wavelet endows the algorithm in a similar way as the human visual system, to represent face features, and the manifold learning is applied to model the nonlinear labeled intrinsic structure.
Journal ArticleDOI
Compression artifacts reduction by improved generative adversarial networks
Zeng-Shun Zhao,Zeng-Shun Zhao,Zeng-Shun Zhao,Qian Sun,Haoran Yang,Heng Qiao,Zhigang Wang,Dapeng Oliver Wu +7 more
TL;DR: An improved generative adversarial network (GAN) for image compression artifacts reduction task (artifacts reduction by GANs, ARGAN) that not only learns an end-to-end mapping from input degraded image to corresponding restored image, but also learns a loss function to train this mapping.