PROJECTS
Color Sorting Robotic Arm
| Python, OpenCV, Arduino (C), Raspberry Pi [GitHub]
• Developed a real-time color detection pipeline in Python using OpenCV on Raspberry Pi for object classification
• Implemented multi-servo robotic control in Arduino (C) to actuate base, arm, and gripper for automated sorting
• Designed a distributed control architecture with Raspberry Pi handling vision processing and Arduino handling motion
control
• Integrated serial communication between controllers to achieve synchronized detection-to-actuation workflow
• Automated boot-time execution and deployment scripts to enable fully autonomous system startup
Colour Sorting Robotic Arm.pdf :
https://pdfhost.io/v/xWdp4JbqBW_Colour_Sorting_Robotic_Arm
RESEARCH
ARTIFICIAL INTELLIGENCE IN PHYSICS: PREDICTING PHYSICAL PHENOMENA WITH MACHINE LEARNING
Artificial Intelligence (AI) has revolutionized the field of physics by providing a new paradigm for understanding and analyzing complex physical phenomena. Machine learning, a subset of AI, has emerged as a powerful tool for predicting and explaining physical phenomena, enabling physicists to uncover new insights and make accurate predictions about the behavior of matter and energy. In recent years, machine learning has been successfully applied to a wide range of problems in physics, from particle physics to condensed matter physics, and from cosmology to biophysics
One of the most significant applications of machine learning in physics is in the analysis of large datasets generated by particle colliders, such as the Large Hadron Collider (LHC). The LHC produces vast amounts of data, which are used to study the properties of subatomic particles and their interactions. Machine learning algorithms can be trained on these datasets to identify patterns and relationships between different variables, allowing physicists to make more accurate predictions about the behavior of particles and interactions
DOI: https://www.ijprems.com/uploadedfiles/paper//issue_7_july_2024/35561/final/fin_ijprems1722021901.pdf
Enhancing Data Privacy in Federated Learning Using Artificial Intelligence
This paper addresses privacy concerns in Federated Learning (FL) by proposing AI-driven optimizations for differential privacy, homomorphic encryption, and secure multiparty computation. The research demonstrates the effectiveness of these methods in enhancing data protection while maintaining model performance. Empirical studies show a significant reduction in computational overhead and improved privacy metrics, making the proposed techniques suitable for real-world applications.
New York Academy of Sciences (NYAS) - Junior Academy
Participated in the NYAS fall program on AI integration in education, leading Team Cognix to research and report on enhancing learning with AI. Developed leadership, teamwork, and research skills during the program . Accessed workshops, seminars, and networking events through NYAS membership, expanding knowledge in STEM fields. Gained insights into cutting-edge research and technology applications, shaping scientific aspirations and problem-solving abilities (2023).
