劉又瑋 YU-WEI LIU

Phone : 0952020607

Email : [email protected]

兵役 : 役畢 (2020.7)

Education  

National Central University, Electrical Engineering(2015.09 ~ 2019.07)

National Taiwan University, Biomechatronics Engineering (2020.09 ~ 2022.09)

Skill

Programming

  • Python
  • C
  • C ++
  • Verilog

Machine learning

  • Pytorch
  • Tensorflow
  • Keras

Backend and Database

  • Django
  • MySQL

Others

  • Git
  • Linux

Correlated curriculum 

Machine Learning, Deep Learning for Computer Vision, Data Structure and Algorithm, Operation System

Computer Organization, Digital Systems Design, Digital Signal processor

Digital Image Processing, Bioinformatics Algorithms, Biomedical Data Mining,

Work experience

Algorithm Engineer  •  Gomore

Feb 2023 - Jul 2023

  • Analyzing physiological signals(PPG) and implement physiological algorithms.
  • Using C language to implement to wearable devices.
  • Validation the modules in the group.

Database and Backend Engineer PT •  MISSMI INTELLIGENCE

Sep 2021 - Jan 2022

  • Bioinformatics data integration and presentation
  • Backend API developm to APP


Teaching Assistant •  National Taiwan University

Feb 2021 - Jul 2021

  • Electronics and Laboratory 
    • Integrate course information
    • Design electronic experiments, using oscilloscopes, power supplies, signal generators and Pspice to simulate various circuits
    • Homework problem solving, following class to solve classmates' problems

July 2021 - Sep 2021

  • Bioinformatics algorithm
    • Designed assignments related to bioinformatics information.
    • Integrate course information
    • Assist in classroom report submission content evaluation

:Thesis title:Using deep learning to predict T-cell receptors binding specificity

  • Using the Transfer learning and ProBert protein language model to predict pMHI-I binding of T-cell receptor.
  • Compared to existing paper, we have higher accuracy and faster inference.

Project Experience 

Python, Pytorch

Skull fracture detection ( Faster R-CNN ):

  • This project works with Inventec in Deep Learning for Computer Vision
  • Train a neural network to detect whether the patient has skull fractures and where they are by utilizing data annotated by physicians.
  • We used Faster R-CNN to implement object detection to predict where they are by utilizing data annotated by physicians.

Python, Django

Costco notice of goods

  • Design a crawler to notify the customer when the item in stock.
  • Using Django to build a Linebot


Web backend API Design 

Verilog

  • Single Cycle implementation


Other Projects

C++

  • Greedy snake design 

Verilog

  • Gobang in FPGA 
  • Single Cycle implementation

Python

  • Data structure algorithm implementation 
  • Image processing implementation

Pytorch

  • Image Classification ( CNN, Semi-Supervised learning, Self-Supervised learning, VIT, ACGAN )
  • Sequence to Sequence( Transformer, BERT )
  • Semantic segmentation ( FCN, U-net)
  • Face and Digit Generation ( SC-GAN)
  • Lunar Lander Game ( Reinforcement Learning )
  • Skull fracture detection ( Faster R-CNN )

Django

  • Web backend API Design 
  • Costco notice of goods

Linux

  • Simple shell script design and server administration