Hi, I'm Manas, . I am a student, studying Artificial Intelligence & Machine Learning at Guru Gobind Singh Indraprastha University, New Delhi, India I’m a skilled and innovative developer with expertise in software development, image processing, and machine learning. I’ve built impactful projects which blend technical precision with practical problem-solving.
With a strong foundation in Python, AI tools, and web technologies, I focus on creating efficient and scalable solutions. I’m passionate about using technology to drive meaningful impact and deliver real-world value.
  • Education
  • Experience
  • Projects
B.Tech. in Artificial Intelligence & Machine Learning GGSIP University 2022 - 2026
Work Experience
•
Intern iMax Global Ventures Ltd
Jul 2024 - Aug 2024 1 mos
•
Data analyst GGSIP University
Jan 2024 - Feb 2024 1 mos
Weigh-Bridge Fraud Detection This project focused on using image processing to detect fraudulent activities on a weighbridge in warehouses. The software ensured that trucks were positioned correctly on the weighbridge while also verifying that no other objects or people were present, thus preventing manipulation of weight readings. Additionally, we utilized a neural network to detect any adverse objects present on the weighbridge, thereby eliminating the probability of fraud and enhancing the system's reliability. Python, OpenCV, TensorFlow / Keras, NumPy, Pillow, Pixellib, Tkinter
Dynamic Traffic Light Optimizer This project aimed to improve traffic flow at intersections by calculating dynamic green light timing based on real-time vehicle counts. Using computer vision techniques like YOLO for object detection and active image segmentation for identifying vehicles in images, the system dynamically adjusted signal timings to prioritize traffic with higher congestion, ensuring smoother traffic movement and reducing wait times. The segmentation process also leveraged results from the RCNN paper to implement an effective and accurate method for vehicle detection and counting in real time. Python, OpenCV, TensorFlow / Keras, NumPy
Audio to Text & Summarization The Audio to Text & Summarization project converts spoken language into text and generates concise summaries, enabling quick insights from audio content. It was designed to offer an efficient way to process and summarize large volumes of audio data. Python, FastAPI, Hugging Face, Google Cloud Speech-to-Text API, JWT Authentication, MongoDB, Firebase