Nguyễn Đức Hiếu

Software Developer


Skills
  • Computer Vision
  • Data science

About Me

34

Greetings! I'm Hieu, a Computer Science & Engineering student at Vietnam Japan University, on track to graduate in 2026. My driving force is the exciting intersection of Artificial Intelligence and Robotics, and I'm determined to contribute to this field by developing practical and innovative solutions. My experience includes hands-on research projects focused on leveraging AI for diverse applications, such as analyzing fish behavior, building laser weeding robots, and creating a non-destructive durian maturity measurement system that achieved over 91% accuracy using acoustic signals. I also enjoy mobile app development and have experience integrating machine learning in robotics, like in my contributions to a football-playing robot project. Currently, I'm diving deeper into the application of machine learning by working on a project focused on accelerating heat prediction and fluid simulation in Selective Laser Melting (SLM) – a fascinating challenge at the intersection of AI and advanced manufacturing. My technical toolkit includes Python, Kotlin, Javascript, C/C++, and frameworks like Keras, PyTorch, and OpenCV. I'm eager to connect with and learn from others in the AI and robotics community, and I'm particularly interested in exploring how these technologies can be used to address complex challenges and create positive change."

Find me on

Experience and Role in AI4LI

As a dedicated member of Team V5, specializing in Computer Vision, I am driven by the opportunity to leverage the power of image processing for impactful solutions. My primary focus is on researching and developing innovative approaches to image classification, Vision-Language Models (VLMs), and object classification. These technologies are not just academic pursuits for me; they are the fundamental building blocks for creating assistive tools that can significantly improve the daily lives of individuals with disabilities. By enabling machines to "see" and interpret the visual world, we can develop systems that offer crucial support for tasks ranging from navigation and object identification to scene understanding and information retrieval. My work is ultimately geared towards fostering greater independence and convenience in everyday activities for those facing various challenges.

Contribution with AI4LI:

Updated on: March 23, 2025, 9:57 p.m.