C
Chao Ma
Researcher at Wuhan University
Publications - 31
Citations - 248
Chao Ma is an academic researcher from Wuhan University. The author has contributed to research in topics: Computer science & Time series. The author has an hindex of 6, co-authored 21 publications receiving 119 citations. Previous affiliations of Chao Ma include Hong Kong Polytechnic University & National University of Singapore.
Papers
More filters
Journal ArticleDOI
Tackling mode collapse in multi-generator GANs with orthogonal vectors
TL;DR: A new approach to training GAN to overcome mode collapse by employing a set of generators, an encoder and a discriminator, and a new minimax formula is proposed to simultaneously train all components in a similar spirit to vanilla GAN.
Proceedings ArticleDOI
An approach for matching communication patterns in parallel applications
TL;DR: This paper proposes a methodology to compare the communication pattern of distributed-memory programs and applies it to four applications in the NAS parallel benchmark suite and evaluates the communication patterns by studying the effects of varying problem size and the number of logical processes (LPs).
Book ChapterDOI
An Architecture for Healthcare Big Data Management and Analysis
TL;DR: Under the guidance of the proposed architecture, a prototype system constructed based on HBase, Hive, Spark MLLib and Spark Streaming is introduced for personal health problem detection and real-time vital sign monitoring.
Proceedings ArticleDOI
An Approach for Visualization and Formalization of Web Service Composition
Chao Ma,Yanxiang He +1 more
TL;DR: This paper proposes a Fast Web Service Composition Approach (FWSCA) which adopts the Extended OWL-S web service semantic description language(OWL-ES) and develops an automatic web service composition Visualization and Formalization Tool (VFT) which is able to ease the process of web service compositions for end-users.
Proceedings ArticleDOI
TSA-GAN: A Robust Generative Adversarial Networks for Time Series Augmentation
TL;DR: In this paper, the authors proposed TSA-GAN which is a robust GAN model with a self-adaptive recovering strategy to solve the problem of low quality of the generated time series.