Portfolio

My Projects

A collection of AI and machine learning projects I've built. Each project represents my passion for solving real-world problems with intelligent solutions. Disclaimer: Some projects are demos or prototypes created for experimentation purposes. They may not be production-ready but showcase my skills and creativity in AI development. Since i cannot share the code for some projects due to company policies, I have included video demos and detailed descriptions to provide insights into the project implementations and outcomes.

Agentic Chatbot System - Salesman Knoeledge Expert

NLP

Description

This is a demo for Agentic Chatbot System using Llamaindex and Vector DB. The system can perform sales knowledge analysis and generate a report for the user through Text2SQL. Also the chatbot is equipped with a vector DB to store sales knowledge and storing SQL related information to help performing Text2SQL.

Key Features

  • Chatbot
  • LLM

Technologies

  • Llamaindex
  • Vector DB
  • Transformers

Agentic Chatbot System - Fraud Analysis

NLP

Description

This is a demo for Agentic Chatbot System using Langgraph and Vector DB. The system can perform analysis on historical fraud data and generate a report for the user through Text2SQL. Also the chatbot is equipped with a vector DB to store fraud theory knowledge and storing SQL related information to help performing Text2SQL.

Key Features

  • Chatbot
  • LLM

Technologies

  • Langgraph
  • Vector DB
  • Transformers

Skin Analysis AI

Computer Vision

Description

A feature that uses DETR object detection model with a custom dataset to identify acne problems, InceptionV3 for wrinkle classification, mediapipe for facial landmark detection, and VGG16 for skin type classification. The same method for wrinkle detection is applied to detect dark circles under the eyes.

Key Features

  • Object Detection
  • Landmark Detection
  • Image Classification

Technologies

  • Flask API
  • Tensorflow

Facial Ratio Measurement AI

Computer Vision

Description

Using EfficientNetV2, the system can classify the shape of the face. It also calculates the width-to-length ratio of the face using Euclidean Distance to measure the distance between facial landmarks.

Key Features

  • Object Detection
  • Landmark Detection
  • Image Classification

Technologies

  • Flask API
  • Tensorflow

Human Tracking System for Smart Wheelchair

Computer Vision Robotics

Description

The system Leveraging YOLOv5 and byte track to create auto navigation by following human in front of the smart wheelchair captured by web camera. The system is embedded to Nvidia Jetson TX2.

Key Features

  • Object Detection
  • Object Tracking

Technologies

  • Nvidia Jetson
  • Arduino
  • Pytorch

Room Name Recognition System

Computer Vision Robotics

Description

The system contained object detection to detect the plate using YOLOv5 and read/recognize the plate character using EasyOCR, the object captured using web camera. The system is embedded to Nvidia Jetson TX2.

Key Features

  • Object Detection
  • OCR

Technologies

  • Nvidia Jetson
  • Arduino
  • Pytorch