💻 Tech Stack

🌐 Socials

📑 Publications

A Dynamic Embedding Method for Passenger Flow Estimation

• Wei-Yi Chung, Yen-Nan Ho, Yu-Hsuan Wu, Jheng-Long Wu
  
• In 2021 10th International Congress on Advanced Applied Informatics (IIAI-AAI)
• Paper

Sentiment-based masked language modeling for improving sentence-level valence–arousal prediction

• Jheng-Long Wu, Wei-Yi Chung
  
• Applied Intelligence, 2022
• Paper

A Dimensional Valence-Arousal-Irony Dataset for Chinese Sentence and Context

• Sheng-Wei Huang, Wei-Yi Chung, Yu-Hsuan Wu, Chen-Chia Yu, and Jheng-Long Wu
  
• In Proceedings of the 34rd Conference on Computational Linguistics and Speech Processing, 2022
• Paper

Factor Detection Task of Cyberbullying Using the Deep Learning Model

• Yu-Hsuan Wu, Sheng-Wei Huang, Wei-Yi Chung, Chen-Chia Yu, and Jheng-Long Wu
  
• 2022 IEEE International Conference on Big Data
• Paper

A Chinese Dimensional Valence-Arousal-Irony Detection on Sentence-level and Context-level Using Deep Learning Model

• Jheng-Long Wu, Sheng-Wei Huang, Wei-Yi Chung, Yu-Hsuan Wu, Chen-Chia Yu
  
• Computational Linguistics and Chinese Language Processing, Vol. 27, No. 2, December 2022
• Paper

💻 Projects

Parking Spaces Prediction and Dynamic Programming of Taipei city

• Intro: Using time series model to estimate the remanning parking space to guide the people who is waiting for parking space
• Language: Python, HTML, CSS, JavaScript
• Keywords: Machine Learning, Time Series Model, Flask, Dynamic Programming
• Tool: LSTM, Flask, Pytorch

Hybrid Movie Recommandation System by description and category

• Intro: Recommend favorite movies based on user input description and favorite movie category
• Language: Python, HTML, CSS, JavaScript
• Keywords: Machine Learning, BERT, Flask, NLP, Word2Vec, TF-IDF, Recommandation System
• Tool: Transformer, Flask, Pytorch

Airbnb New Uesr Booking Prediction

• Intro: Kaggle competition. Our proposed using Hierarchical XGBoosting model to predict the target country of customer preference
• Language: Python
• Keywords: Machine Learning, XGBoost, Statistic
• Tool: XGBoost

Company Fraud Detection Website (Cooperate with KPMG)

• Intro: Detection of fraud in four different aspect and visulize in website
• Language: Python, HTML, CSS, JavaScript
• Keywords: BERT, Crawler, NLP, Node, Fraud
• Tool: Selenium, Networkx, Plotly

Data Annotaion System for valence-arousal-irony

• Intro: PTT Data Annotation system written by php, javascript, html and deploy on Heroku
• Language: SQL, HTML, CSS, JavaScript, PHP
• Keywords: Data Annotation, Login, DataBase
• Tool: Crawler, MySQL, Apache

Gogoro Feasibility Analysis

• Intro: Gogoro Feasibility Analysis in Taiwan
• Language: HTML, CSS, JavaScript, CanvasJS
• Keywords: Website, Analysis, Visulization
• Tool: HTML, Webhook

🏫 Experience

• 2022.12 - Software Engineer at ASUS AICS
  

• 2020.9 ~ 2022.1 - Research Assistant in NLP Lab(@DS.SCU)
  

  • Invented a combination model of neural network and statistic method for co-reference resolution. Improved F1-score from 78.3 to 79.2.
  • Built and trained a multi-topic GPT2 model, and improved the model performance by model tuning and spelling corrections handling.
  • Developed a hierarchical attention network (HAN) model to learn the three different aspect of hope, trigger event and arousal from society community post. Improved the F1-score from 0.58 to 0.86 on the prediction of depression.
  • Invented a dynamic MRT station embedding model for passenger flow prediction. Replaced the traditional station embedding model Node2Vec and improved MAE from 1.47 to 0.93, 36% increased.

• 2019.9 ~ 2020.6 - Data Analysis Intern at Deloitte
  

  • Completed the deployment of machine learning model on the Django platform for economic indicator trend prediction.
  • Researched the practical application of OCR in financial statements and achieved a digital recognition rate of 86%.
  • Maintained news and social web crawlers, and developed robotic process automation (RPA) programs to handle unstructured data.

• 2019.7 ~ 2019.8 - Automatic Speech Recognition Intern at Delta Electronics
  

  • Annotated noise span in recordings and modified the speech recognition models to detection noise.
  • Developed a noise detection deep learning model and deployed on the internal system with Flask. The model is stacked the CNN model with soft-attention mechanism and LSTM as prediction model. Achieved 89% accuracy rate in noise span.

• 2018.3 ~ 2019.6 - Research Assistant in Information Fusion Lab
  

  • Developed a micro-expression recognition model to identify readers’ investment styles, and combined recommendation systems to recommend suitable financial articles for readers. Achieved 91% F1-score.
  • Deployed the financial recognition APP on Zenbo robot, combined with personalized dashboard to present financial information exclusive to users. This APP earned Honorable Mention in HNCB Fintechers competitions.

• 2016.9 ~ 2020.7 - Bachelor student in SCU (@DS.SCU)