Projects

LED Defect Detection (With Oriented Bounding Box) 2024

In-progress project: developing AI chat app for hospital group info, utilizing Language Model (LLM) tech, exploring LLM chaining, agent-based methods, and prompt engineering for accuracy.

Artificial Intelligence Machine Learning Deep Learning Large Language Model Natural Language Processing Python SQL PyTorch Langchain Scikit-Learn Matplotlib

Read More
Multilabel Video Classification 2023

Reproduced FrameExit paper's SOTA results in video recognition using HVU dataset, overcoming challenges with existing models, achieving 49.28% mAP.

Artificial Intelligence Machine Learning Deep Learning Object Detection Multi-label classification Computer Vision Python PyTorch OpenCV Scikit-Learn Matplotlib Scipy

Read More
LED Defect Detection (With Oriented Bounding Box) 2023

Developed AI system to detect LED defects on PCBs, adapting model to generate oriented bounding boxes for tilted LEDs. Established baseline and improved it.

Artificial Intelligence Machine Learning Deep Learning Oriented Object Detection Computer Vision Python PyTorch OpenCV Scikit-Learn Matplotlib Scipy

Read More
PCB Defect Classification 2023

Replicated SOTA paper on PCB defect classification, augmented dataset, fine-tuned models, enhancing results. Detailed results available in portfolio.

Artificial Intelligence Machine Learning Deep Learning Image Classification Image Augmentation Computer Vision Python PyTorch OpenCV Scikit-Learn Matplotlib Scipy

Read More
Enhance Existing Automatic Speech Recognition Model 2023

Focused on long-term maintenance and improvement of Automatic Speech Recognition (ASR) model, updating with new datasets, training acoustic and language models iteratively.

Artificial Intelligence Machine Learning Deep Learning Automatic Speech Recognition Digital Signal Processing Speech-to-Text Noise Reduction Python MATLAB C/C++ PyTorch Scipy Scikit-Learn Matplotlib Scipy

Read More
Design a noise robust VAD algorithm 2022

Implemented novel Voice Activity Detection (VAD) algorithm using digital signal processing (DSP) techniques, reducing computational costs without deep learning models.

Artificial Intelligence Machine Learning Deep Learning Automatic Speech Recognition Digital Signal Processing Speech-to-Text Noise Reduction Speech Enhancement Python MATLAB C/C++ PyTorch Scipy Scikit-Learn Matplotlib Scipy

Read More
Design a wake-up word algorithm 2021

Implemented wake-up word feature for ASR applications, defining trigger phrases and experimenting with speech features like MFCC and PLP.

Artificial Intelligence Machine Learning Deep Learning Automatic Speech Recognition Digital Signal Processing Speech-to-Text Feature Selection Feature Extraction Python MATLAB C/C++ PyTorch Scipy Scikit-Learn Matplotlib Scipy

Read More
Preprocessing System for Speech Enhancement 2020

Developed preprocessing methods for speech signal enhancement: noise removal, dereverberation, and speaker separation, utilizing AI models for effectiveness.

Artificial Intelligence Machine Learning Deep Learning Automatic Speech Recognition Digital Signal Processing Speech-to-Text Noise Reduction Speech Enhancement Python MATLAB C/C++ PyTorch Scipy Scikit-Learn Matplotlib Scipy

Read More
Auto-Parts Counter System 2019

Developed advanced auto-parts counter using object detection and tracking, aiming to replace weight-scaling method, showing promising results.

Artificial Intelligence Machine Learning Deep Learning Object Detection Object Tracking Computer Vision Python Keras Tensorflow OpenCV Scikit-Learn Matplotlib Scipy

Read More
Paper Document Information Extraction 2019

Developing automated document information extraction system for handwritten and computer-generated text, employing segmentation, AI models, and OCR techniques.

Artificial Intelligence Machine Learning Deep Learning Object Detection Computer Vision Tesseract OCR Python Keras Tensorflow OpenCV Scikit-Learn

Read More
Blood Cell Detection and Localization 2019

Focused on long-term maintenance and improvement of Automatic Speech Recognition (ASR) model, updating with new datasets, training acoustic and language models iteratively.

Artificial Intelligence Machine Learning Deep Learning Object Detection Computer Vision Python Keras Tensorflow OpenCV Scikit-Learn Matplotlib Scipy

Read More
AI-based Automatic Visual Inspection Machine 2019

A responsive web application for travel planning that my team developed in ICS 415.

Artificial Intelligence Machine Learning Deep Learning Object Detection Computer Vision Python Keras Tensorflow OpenCV Scikit-Learn Matplotlib Scipy

Read More