Y
Yuan Yan Tang
Researcher at University of Macau
Publications - 674
Citations - 15632
Yuan Yan Tang is an academic researcher from University of Macau. The author has contributed to research in topics: Wavelet & Wavelet transform. The author has an hindex of 58, co-authored 647 publications receiving 12835 citations. Previous affiliations of Yuan Yan Tang include Hong Kong Community College & Southwest Baptist University.
Papers
More filters
Journal ArticleDOI
Multi-Level Downsampling of Graph Signals via Improved Maximum Spanning Trees
Xianwei Zheng,Xianwei Zheng,Xianwei Zheng,Yuan Yan Tang,Jiantao Zhou,Jianjia Pan,Shouzhi Yang,Youfa Li,Patrick S. P. Wang +8 more
TL;DR: A novel and efficient method to detect and reduce the downsampling unbalance generated by the MST-based method is proposed and results on synthetic and real-world social network data show that downsamplings unbalance can be efficiently detected and then reduced by this method.
Proceedings ArticleDOI
A hybrid swarm optimization for neural network training with application in stock price forecasting
Jianjia Pan,Yuan Yan Tang,Yulong Wang,Xianwei Zheng,Huiwu Luo,Haoliang Yuan,Patrick S. P. Wang +6 more
TL;DR: The proposed method overcomes some of the drawbacks of SSO and improves its ability to train the weight of ANN, and is employed to train fuzzy wavelet neural network (FWNN) forecasting model to predict the prices of Hong Kong Hang Seng Index.
Journal ArticleDOI
Linear complexity of generalized cyclotomic binary sequences of order 2d and length 2pm
TL;DR: Two new cyclotomic binary sequences of order 2d and length 2pm are constructed which include the sequences constructed by Ke et al. in 2012 and their linear complexity is computed.
Book ChapterDOI
Learning Deep Feature Fusion for Group Images Classification
TL;DR: An end-to-end network is designed which accepts variable number of images as input and fuses features extracted from them for classification, and demonstrates the effectiveness of the method.
Posted Content
User-item matching for recommendation fairness: a view from item-providers.
TL;DR: The framework of the constrained recommendation scenario coupled with the MCMF user-item matching priority strategy still has a several-to-one advantage in the coverage fairness, while its recommendation precision is more than 90% of the best value of all the enhanced algorithms.