Skip to content
View Nightey3s's full-sized avatar
:octocat:
B̵̞̓̀͑͐͛r̶͖̭͌͗͗͜i̴͈͖͌͐̑͜͝͝a̸͚̫͈̕͠n̷̮̼̙̬̽͐ͅ ̷̨̹̙̌̋̍͝T̵̛̮͖̲͌̒̑̆ḧ̶̭̙̠́ǻ̵̺̜ṃ̶̾̇
:octocat:
B̵̞̓̀͑͐͛r̶͖̭͌͗͗͜i̴͈͖͌͐̑͜͝͝a̸͚̫͈̕͠n̷̮̼̙̬̽͐ͅ ̷̨̹̙̌̋̍͝T̵̛̮͖̲͌̒̑̆ḧ̶̭̙̠́ǻ̵̺̜ṃ̶̾̇

Block or report Nightey3s

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Nightey3s/README.md

About Me

I am Brian Tham, an A*STAR Research Intern and Applied AI undergraduate at Singapore Institute of Technology, passionate about pushing the boundaries of AI research and its real-world applications. With a strong foundation in computer science and a keen interest in emerging technologies, I'm dedicated to developing innovative AI solutions to solve complex challenges.

Projects

Multimodal system for detecting and rephrasing profanity in both speech and text, featuring real-time analysis, automatic content refinement, and toxicity classification using advanced NLP models.

Team: Brian Tham, Hong Ziyang, Nabil Zafran, Adrian Wong, Lin Xiang Hong

Deep learning-based food detection system using YOLOv8 to identify 55 different food classes, with calorie estimation and a web interface featuring image upload and camera capture capabilities.

Team: Brian Tham, Hong Ziyang, Javier Si, Timothy Delaya

System using Wav2Vec2 to classify speech into four emotional categories (Neutral, Happy, Sad, Angry), achieving 69.02% accuracy through transformer architecture and robust data augmentation techniques.

Team: Brian Tham, Hong Ziyang

Experience

  • Overseas Immersion Programme(2025) - Tallinn, Estonia: Tallin University of Technology, Cybersecurity Summer School
  • Overseas Immersion Programme(2024)- Da Nang, Vietnam: FPT University, Developed AI models for land cover classification and won Best Accuracy award in emotion recognition hackathon
  • Created predictive machine learning models for business applications
  • Analysed ransomware attacks across industries for cybersecurity insights
  • Evaluated AI chatbot performance in natural language tasks

Technical Skills:

  • Programming: Python, C#, R
  • Machine Learning: PyTorch, TensorFlow, Scikit-learn, Keras
  • Data Analysis & Visualization: Matplotlib, RStudio, PowerBI, VBA
  • Cloud Platforms: Google Cloud Certified - Professional Machine Learning Engineer, HuggingFace ZeroGPU spaces
  • DevOps & Tools: Docker, Git
  • Web Development: HTML, CSS, JavaScript

My experience with both software and hardware, through education, and hobby, has allowed me to gain a deeper understanding of the integration between software and hardware in computer systems. You can find my portfolio here or you can take a look at some of my repositories below! Open to connecting with fellow researchers, industry professionals, and anyone passionate about the future of AI! Always excited to discuss new ideas, collaborate on projects, or explore opportunities in the rapidly evolving field of artificial intelligence.

Pinned Loading

  1. profanity-detection profanity-detection Public

    A robust multimodal system for detecting and rephrasing profanity in both speech and text, leveraging advanced NLP models to ensure accurate filtering while preserving conversational context.

    Python 3 1

  2. FoodVision FoodVision Public

    FoodVision is a deep learning-based food detection system that utilizes YOLOv8 to identify and classify various food items in images. The system is capable of detecting 55 different food classes wi…

    Jupyter Notebook 4 3

  3. Speech-Emotion-Recognition-using-Wav2Vec2 Speech-Emotion-Recognition-using-Wav2Vec2 Public

    A Speech Emotion Recognition (SER) system using Facebook's Wav2Vec2 model that classifies speech into four emotions (Neutral, Happy, Sad, Angry). Achieves 69.02% accuracy on IEMOCAP dataset using m…

    Jupyter Notebook 2 2

  4. MachineLearning-Iris MachineLearning-Iris Public archive

    Machine Learning - Iris | Unsupervised Learning

    Jupyter Notebook

  5. MachineLearning-HousingPrices MachineLearning-HousingPrices Public archive

    A jupyter notebook writen in python to determine housing prices

    Jupyter Notebook

  6. MachineLearning-Titanic MachineLearning-Titanic Public archive

    Jupyter Notebook