Rohith Vishnu Teja Gupta Thommandru

Driven and ambitious computer science professional dedicated to advancing expertise and fostering innovation within the technology sector. With a keen eye for detail and exceptional communication and project management skills, excels at handling multiple tasks efficiently in fast-paced environments. Proactive approach to problem-solving allows to identify and address issues while optimizing processes and supporting team objectives.

• Java Scripts from SRM Axis Intellects
• Basics of Python from Infosys Springfield
• Machine Learning & Big Data using Python and Data Science with R language

•  Attended the 5th International Conference on Intelligent Sustainable Systems (ICISS 2022).

• Attended the International Conference on Advanced Computing and Communication Technology (ICACCT'23).

• Mandala art
• Volley Ball
• Swimming

• Real time detection of train track cracks using Deep Learning, presented an innovative approach utilizing deep learning techniques for the real-time identification of cracks in train tracks. Our methodology leverages Convolution Neural Networks (CNNs) to classify track segments as cracked or non-cracked. Through this project, we demonstrate the effectiveness of CNNs and deep learning in swiftly detecting track defects. I hold a team lead position in this project.

• IoT-Powered Smart Home Automation Systems, conducted a  cutting-edge home automation system seamlessly integrated with Internet of Things (IoT) technology. This groundbreaking solution leverages robust C++ algorithms to deliver a flawless and efficient automation experience, enhancing the functionality of modern homes. Through continuous refinement and rigorous testing, we have not only improved the system but also demonstrated its real-world effectiveness.

• Enhancing Breast Cancer Detection Using Advanced Machine Learning Techniques,Utilized a comprehensive Kaggle dataset to develop and evaluate models, including K-Nearest Neighbors (KNN), Random Forest (RF), and Deep Neural Networks (DNN). Implemented rigorous data preprocessing methods, such as Principal Component Analysis (PCA) and SMOTE to address class imbalances. Achieved a remarkable accuracy of 98% with the Random Forest model, highlighting its effectiveness in complex pattern recognition. This project underscores the transformative potential of machine learning in medical diagnostics and sets the stage for future clinical applications.