He Wang 王赫

Postdoctoral Fellow

Institute of Theoretical Physics, CAS

Biography

I am currenly a postdoctoral researcher at the Institute of Theoretical Physics, Chinese Academy of Sciences. My research interests mainly focus on the study of theoretical modelling and the application of AI-based machine learning techniques to gravitational wave data analysis. In addition, I am also committed to related researches such as data processing methods and the development of algorithms for ground-based and space-based gravitational wave detection.

My doctoral dissertation, “Research on Data Analysis of Deep Learning in Gravitational Wave Detection”, discusses the difficulties and challenges of real-time detection and data processing of gravitational wave signals by ground-based gravitational wave detectors, and combines real gravitational wave data with traditional signal processing algorithms via deep neural network model to search for possible weak gravitational wave signals.

Interests

Gravitational Waves
Data Analysis
Machine Learning
Deep Learning
Artificial Intelligence

Education

Ph.D. in Theoretical Physics, 2020

Beijing Normal University
M.Sc. in Theoretical Physics, 2015

China West Normal University
B.Sc. in Applied Physics, 2012

Chongqing Technology and Business University

Projects

Survey4GWML

A survey on gravitational waves researches using machine learning techniques.

Code

My Dissertation [zh-CN]

Title: Research on Data Analysis of Deep Learning in Gravitational Wave Detection.

PDF Code Slides

Recent & Upcoming Talks

Presentations

Gravitational-wave Signal Recognition of LIGO Data by Deep Learning

Apr 24, 2021 2:40 PM — 3:00 PM 中国物理学会引力与相对论天体物理分会

He Wang

Project Slides

Gravitational-wave Signal Recognition of LIGO Data by Deep Learning

Dec 19, 2020 3:45 PM — 4:05 PM National Central University (Hybrid style Workshop)

He Wang, Shichao Wu, Zhoujian Cao, Xiaolin Liu, Jian-Yang Zhu

Project Slides

Gravitational-wave Signal Recognition of LIGO Data by Deep Learning

Dec 17, 2020 1:30 PM — 1:50 PM The 26th KAGRA Face-to-Face meeting - Webniar

He Wang, Shichao Wu, Zhoujian Cao, Xiaolin Liu, Jian-Yang Zhu

Project Slides

Matched-filtering Techniques & Deep Neural Networks

Dec 14, 2020 10:01 AM — 10:21 AM Apache MXNet Day - Webniar

He Wang

Project Slides

Matched-filtering Techniques & Deep Neural Networks

Matched-filtering & Deep Learning Networks

Jul 19, 2020 Chongqing University - Webniar

He Wang

Project Slides

Matched-filtering & Deep Learning Networks

See all talks

Featured Publications

He Wang, Shichao Wu, Zhoujian Cao, Xiaolin Liu, Jian-Yang Zhu

May 2020 Phys. Rev. D Gravitational-wave Detection

Gravitational-wave Signal Recognition of LIGO Data by Deep Learning

Deep learning method develops very fast as a tool for data analysis these years. Such a technique is quite promising to treat gravitational wave detection data. There are many works already in the literature which used deep learning technique to process simulated gravitational wave data. In this paper we apply deep learning to LIGO O1 data. In order to improve the weak signal recognition we adjust the convolutional neural network (CNN) a little bit. Our adjusted convolutional neural network admits comparable accuracy and efficiency of signal recognition as other deep learning works published in the literature. Based on our adjusted CNN, we can clearly recognize the eleven confirmed gravitational wave events included in O1 and O2. And more we find about 2000 gravitational wave triggers in O1 data.

DOI