Zhongyu YAO, Frank

Zhongyu YAO, Frank

PhD Student of Computer Science

City University of Hong Kong

Biography

I am a PhD student at Department of Computer Science, City University of Hong Kong under the supervision of Prof. WONG Ka-Chun. I design and develop some well-performed models/tools in machine learning/data mining-related interdisciplinary R&D. My research interests include applied machine learning, transfer learning, and bioinformatics.

Before this, I worked as a research assistant at Prof. Jiannong Cao’s Lab (IMCL) in PolyU. I received the Master’s degree under Prof. Chung Fu-Lai (Korris)’s supervision from the Hong Kong Polytechnic University in 2020, and the Bachelor’s degree under Prof. Jin Wang’s supervision from CQUPT in 2018 separately.


Always open to interesting ideas.

Interests

  • Data science
  • Machine learning
  • Bioinformatics
  • Transfer learning
  • Graph neural networks

Education

  • Ph.D. in Computer Science, 2021-2025

    City University of Hong Kong

  • M.Sc. in Information Technology, 2018-2020

    The Hong Kong Polytechnic University

  • B.Eng in Computer Science, 2014-2018

    Elite Class of Outstanding Engineers Program, CQUPT / Exchange, UC Irvine

Recent News

2022.06: One paper accepted by Gene

Our paper, The comprehensive and systematic identification of BLCA-specific SF-regulated, survival-related AS events, is accepted by Gene. In this paper, we comprehensively and systematically identified five SFs and 46 AS events.

2020.09: I was awarded as a candidate of Research Talent Hub (ITF-Funded) in HK

I was awarded as a candidate of Research Talent Hub with the funding from Innovation and Technology Commission of HKSAR from September 2020.

2020.07: One paper accepted by CIKM 2020

Our paper, Recursive Balanced k-Subset Sum Partition for Rule-constrained Resource Allocation, is accepted by CIKM 2020. This is an algorithm paper. In this paper, we proposed a new approach to rule-constrained resource allocation by regarding it as a partition problem.

2020.04: One paper published by IEEE Transactions on Big Data

Our paper, IRDA: Incremental Reinforcement Learning for Dynamic Resource Allocation, is accepted by IEEE Transactions on Big Data. This is a journal paper. We mine the task patterns from the large volume of historical allocation data and propose a reinforcement learning model termed IRDA to learn the allocation strategy in an incremental way.

2020.02: One paper accepted by DASFAA 2020

Our paper, A Big-data-driven Airport Resource Management Engine and Application Tools, is accepted by DASFAA 2020. This is a Demo paper. In this paper, we showcase our research in big data analytics for resource management.

Projects

Big-data-driven Airport Resource Management Engine

We develop a series of prediction models using big data techniques to predict unknown factors affecting resource management, and design novel allocation algorithms to efficiently manage resources.

Clothes Matching on Taobao

Analyze and model more than 1.837 million Taobao desensitization data by Java and Python. C4.5, Bayesian, KNN and TF-IDF are used to modeling. I have ranked 17 more than 2 years.

Big data analysis system for passenger flow of Guangzhou Baiyun Airport

(Provincial-level, 10%) 2nd Prize in 15th National College Student ā€œChallenge Cupā€ Contest

A-guarder

We effectively detect the Android system’s sensitive permission calls on the Android software basic framework layer code.

Recent Publications

Quickly discover relevant content by filtering publications.

The comprehensive and systematic identification of BLCA-specific SF-regulated, survival-related AS events.

Bladder urothelial carcinoma (BLCA) is a complex disease with high morbidity and mortality. Changes in alternative splicing (AS) and splicing factor (SF) can affect gene expression, thus playing an essential role in tumorigenesis.

Recursive Balanced k-Subset Sum Partition for Rule-constrained Resource Allocation.

Rule-constrained resource allocation aims to evenly distribute tasks to different processors under the constraints of a set of allocation rules. Conventional heuristic approach fails to achieve optimal solution while simple brute force method has the defects of extremely high computational complexity.
Recursive Balanced k-Subset Sum Partition for Rule-constrained Resource Allocation.

IRDA: Incremental Reinforcement Learning for Dynamic Resource Allocation.

We mine the task patterns from the large volume of historical allocation data and propose a reinforcement learning model termed IRDA to learn the allocation strategy in an incremental way. We observe that historical allocation data is usually generated from the daily repeated operations, which is not independent and identically distributed.
IRDA: Incremental Reinforcement Learning for Dynamic Resource Allocation.

A Big-data-driven Airport Resource Management Engine and Application Tools.

We develop a series of prediction models using big data techniques to predict unknown factors affecting resource management, and design novel allocation algorithms to efficiently manage resources. We demonstrate our research achievements in baggage reclaim belt management at HKIA to efficiently balance overload reclaim belts for improving Custom Service Excellent.
A Big-data-driven Airport Resource Management Engine and Application Tools.

A Sequential Attention Based Convolutional Neural Network for Anomaly Detection.

Web-attack was one of the most challenging threats with the rapid development of Internet. A piece of well-designed malicious code in a Web request could cause serious information leakages or other fatal security incidents.
A Sequential Attention Based Convolutional Neural Network for Anomaly Detection.

Experience

 
 
 
 
 

Faculty Lecturer

Huaiyin Institute of Technology

Mar 2023 ā€“ Aug 2023 Huaian, China

Responsibilities include:

  • Undertake the theoretical and practical teaching tasks of the specialty as well as other teaching tasks in computer science
  • Follow the latest research progress and participate in scientific research projects, publish scientific research papers and other scientific research tasks
  • Participate in the construction of disciplines and professional construction tasks of the university
 
 
 
 
 

Research Assistant

The Hong Kong Polytechnic University

May 2019 ā€“ Feb 2021 Hong Kong SAR

Responsibilities include:

  • Develop the back-end of big data-driven system with state-of-art machine learning algorithms, like reinforcement learning
  • Design prototypes for performance evaluation of components and for big data programming models and their context links
  • Conduct research works, including reviewing the literature, abstracting projects and writing papers
 
 
 
 
 

Director Assistant Intern

Hangzhou Taihao Science&Technology Co.Ltd.

Jul 2018 ā€“ Sep 2018 Hangzhou, China
I worked as an intern in my sister’s start-up. Participated in the company’s operations, like administration, marketing and finance affairs.
 
 
 
 
 

Consulting Intern

Deloitte

Jul 2017 ā€“ Sep 2017 Shenzhen, China

Experience include:

  • Familiar with the business logic and operation of EWM module in SAP system within one month
  • Polish design logic of the new system
  • Teach the corporate customers to operate in implementation phase of the system
  • Received approval from the whole team and got a recommend letter from the project manager of Deloitte
 
 
 
 
 

Teacher Assistant

School of Computer Science and Technology, CQUPT

Sep 2016 ā€“ Jul 2017 Chongqing, China

Experience include:

  • Administrated daily class work. Planned and organized activities between college and classes, such as promotion of exchange students program, friendship activities between classes (over 100 people), sports activities, etc
  • Tutored students English. Students examination scores improved a lot and most of them passed the CET4 after coach

Contact