Key Skills

Software

Roboflow

Top Subject Matter

No subject matter listed

Top Data Types

Image

Top Label Types

Bounding Box

Object Detection

Data Collection

Freelancer Overview

I am an IT professional with hands-on experience in data annotation and AI training data, particularly in computer vision projects. During my work on the VigiWheel Drowsiness Detection & Driver Behavior Monitoring System, I annotated over 20,000 images using Roboflow to train a phone detection model, gaining in-depth knowledge of the data labeling process and the importance of high-quality datasets for machine learning. I am skilled in Python, React, and various tools like AWS, Figma, and Looker Studio, and have contributed to both the development and design of web and mobile applications. My background in building real-time dashboards and integrating analytics further strengthens my ability to support AI and data-driven projects. I am eager to apply my technical skills and attention to detail to deliver accurate and reliable training data for AI systems.

Labeling Experience

Data Annotation for Phone Detection Model (Computer Vision)

RoboflowImageBounding BoxObject Detection

An academic project (thesis/capstone) focused on monitoring driver behavior, particularly indicators related to drowsiness, where phone usage was identified as a contributing factor. An object detection model was trained specifically to detect phone usage, supported by the annotation of over 20,000 images from a custom driving dataset using Roboflow. The resulting model achieved 96% detection accuracy, demonstrating the effectiveness of the dataset preparation and labeling process. The project successfully met all academic requirements and passed evaluation, highlighting the importance of high-quality data annotation in developing reliable machine learning systems.

An academic project (thesis/capstone) focused on monitoring driver behavior, particularly indicators related to drowsiness, where phone usage was identified as a contributing factor. An object detection model was trained specifically to detect phone usage, supported by the annotation of over 20,000 images from a custom driving dataset using Roboflow. The resulting model achieved 96% detection accuracy, demonstrating the effectiveness of the dataset preparation and labeling process. The project successfully met all academic requirements and passed evaluation, highlighting the importance of high-quality data annotation in developing reliable machine learning systems.

2024 - 2025

Education

Work History