Y
Ye Cai
Researcher at Shenzhen University
Publications - 15
Citations - 43
Ye Cai is an academic researcher from Shenzhen University. The author has contributed to research in topics: Cache-only memory architecture & Non-uniform memory access. The author has an hindex of 3, co-authored 15 publications receiving 32 citations. Previous affiliations of Ye Cai include Chinese Academy of Sciences.
Papers
More filters
Journal ArticleDOI
Sparse feature learning for multi-class Parkinson’s disease classification
TL;DR: Experimental results indicate that the proposed framework to construct a least square regression model based on the Fisher’s linear discriminant analysis (LDA) and locality preserving projection (LPP) outperforms state-of-the-art methods.
Patent
One-by-one support point data dividing method in metric space
TL;DR: In this article, a one-by-one support point data dividing method in a metric space is proposed, in which during index building, data to be processed are intercepted from a data set according to starting and end positions.
Journal ArticleDOI
Joint regression and classification via relational regularization for Parkinson's disease diagnosis.
TL;DR: The proposed joint regression and classification scheme for PD diagnosis using baseline multi-modal neuroimaging data is proposed and can greatly improve the performance in clinical scores prediction and outperforms the state-of-art methods as well.
Book ChapterDOI
Analyzing the Characteristics of Memory Subsystem on Two Different 8-Way NUMA Architectures
TL;DR: Two NUMA architectures with different memory subsystems are experimentally analyzed and it is found that LS 3A is not such sensitive to remote access, compared with E5620, so there will be no obvious performance degradation caused by non-local memory access.
Journal ArticleDOI
Algorithms designed for compressed-gene-data transformation among gene banks with different references.
TL;DR: A set of transformation algorithms to cope with the problem that the data from different gene banks can’t merge directly and share information efficiently and are an order of magnitude faster than traditional decompression-and-recompression workflow.