Zeheng Bai M1 Student Department of Computer Science The University of Tokyo Mail：

Profile: English Version 中文

News

1. I will start a brand new campus life in the University of Tokyo to pursue my Master Degree. (2021-04-01)
2. Today I received the official acceptance from the University of Tokyo, so from October I will be the Research Student of Imoto Lab, Human Genome Center, Institute of Medical Science, the University of Tokyo. (2020-07-03)
3. Recently I have graduated from School of Statistics, Renmin University of China. (2020-06-30)
4. I have finished my graduation thesis and you can read it from RUC Library. I should say thank you to my advisor, Prof. Yang Li. Moreover, Prof. Feifei Wang, Prof. Danlin Yu and Prof. Yaozhong Zhang also gave me lots of help. Thank you for your efforts.(2020-04-17)

Background

Education:
Master Degree, Department of Computer Science, Graduate School of Information Science and Technology, the University of Tokyo　　　 2021 - 2023
Research Student, Graduate School of Information Science and Technology & Institute of Medical Science, the University of Tokyo　　　 2020 - 2021
Bachelor Degree, (Mathematical) Statistics, School of Statistics, Renmin University of China　　　 2016 - 2020
Graduated from Beijing Experimental High School Attached to Beijing Normal University　　　 2013 - 2016

Organizations:
Student Member, Japanese Association for Medical Artifical Intelligence

Research Interests

Bioinformatics, Machine Learning & Deep Learning, Biostatistics, Mathematical Statistics

Publications

White Papers on Chinese Medicine Big Data Industry Development 2019, White Papers on Big Data Industry Development in Chinese Medicine Editorial Committee, In 2019 World TCM Big Data Industry Summit and Annual Meeting of TCM Big Data Industry Branch of World Federation of Chinese Medicine Societies

Research Experience

Test and improvements for VIBRANT　　　Oct 2020 - Present

The University of Tokyo, Tokyo, Japan

Research assistant, Advisor:

Prof. Seiya Imoto, Professor of Human Genome Center, Institute of Medical Science, The University of Tokyo
Prof. Yaozhong Zhang, Associate Professor of Human Genome Center, Institute of Medical Science, The University of Tokyo
Made deep understanding of whole pipline of VIBRANT by using Docker and Ubuntu
Made familiar with popular tools or models for recognizing the category of genome, such as VirSorter, VirFinder, MARVEL, VIBRANT
Ran some example to test VIBRANT by using supercomputer
Made some assumptions try to improve VIBRANT, like using XGBoost or XLNet

The Relationship between Air Quality and Epidemic Diseases in Taiwan　　　Nov 2018 - Jul 2020

Renmin University of China, Beijing, China

Research assistant, Advisor:

Prof. Yang Li, Vice Dean of School of Statistics, Renmin University of China
Prof. Ben-Chang Shia, Vice Precident, Fu Jen Catholic University
Prof. Feifei Wang, Lecturer of School of Statistics, Renmin University of China
Got the each-hour data of the climate of Taiwan from 2010 to 2018 by web crawler using Python and joined the data of the climate and air quality of Taiwan according to the same watch points using R
Found outliers by the rules we had made before, change them to K-means value by close-time data
Got the everyday and every-month data of each district of Taiwan from 2010 to 2018 calculated by the each-hour data of the climate of Taiwan based on Kriging using R
Made heat maps of the everyday and every-month data of each district of Taiwan, density plots of data of the climate of each district of Taiwan, and correlation scatter plots between the climate and air quality
Found the relationship between air quality and respiratory diseases using disease mapping and variable coefficient regression
Taught the new members about data visualization make some improvements of the codes and make great progress of the coding ability; We could finish the whole task of data cleaning and data visualization in only one day

White Papers on Chinese Medicine Big Data Industry Development 2019　　　Jul 2019 - Nov 2019

Peking University, Beijing, China

Research assistant, Supervisor:

Prof. Xiaohua Zhou, Director of Department of Biostatistics, Peking University, Director of TCM Big Data Center
Dr. Xinting Huang, Assistant Director of TCM Big Data Center
Got the data of the programs about Traditional Chinese Medicine Big Data carried on by Chinese companies by web crawler using Python
Improved and corrected them, and made further understanding about the situation of Traditional Chinese Medicine Big Data by surveys using email
White Papers on Chinese Medicine Big Data Industry Development 2019: Enterprise Chapter

Active Healthy Living and the Aging Population in China　　　Jun 2019 - Jul 2019

Renmin University of China, Beijing, China

Research assistant, Supervisor:

Prof. Xiaojun Wang, Dean of School of Statistics, Renmin University of China
Prof. Feifei Wang, Lecturer of School of Statistics, Renmin University of China
Got the data about people’s feeling towards the Active Healthy Living and the Aging Population in China by Distributed Web Crawler using Python
Proposed an improved emotion analysis model which was more suitable for our project based on LDA Model

Internships

Meituan Co. LTD　　　Beijing, China　　　Oct 2020 - Feb 2021

Data Product Manager Intern

Standardized the naming and definition of metrics
Provided data sheets for the company leaders
Completed iteration of data products
Guaranteed the timeliness of the output of daily newspapers and standardized the procedures about the process of guarantee

Xiaomi Technology Co. LTD　　　Beijing, China　　　Nov 2019 - Feb 2020

Data Analyst Intern

To be in charge of the data about the Xiaomi Overseas App Store (GetApps)
To save those data by Hive, whose codes are similar to SQL
To make the reports on the strategies this can increase our income from Mi App Store
I also make some attempts on other approaches, like LSTM, and I also improved some codes on Mi Data Factory System.

China Railway Construction Investment Fund Management Co., Ltd.　　　Beijing, China　　　Jan 2019 - Feb 2019

Software Engineer Intern, Section of Technology and Development

Got familiar with the functions of the APP (China Railway Construction Financial Services)
Tried to understand the codes of the APP
Helped them to find the errors about the APP by running it on several kinds of smart phones

Overseas Exchange

Summer Session 2018, University of California, Berkeley　　　Jul 2018 - Aug 2018

Did great work during the exchange program and got high scores:
Probability and Statistics in Biology and Public Health (A+) Introduction to Neuroscience (A+)

More

Programming Skills & Software

Visual Basic(Basic), C(Mastered), Python(Proficient), R(Proficient), MySQL(Proficient), HiveSQL(Proficient), SPSS(Proficient), Stata(Proficient), Office(Proficient)

Languages

Mandarin Chinese(Native), English (Fluent), Japanese(Basic)

Personal Interests

Photography: I like taking photos by camera. I have a SONY a7m3
Orienteering: I was assistant captain of the orienteering team when I was in high school
Esports: I am the fan of Shanghai Dragons and I also made some assistance for them before

---