SURYA TEJA

Skilled Java Developer with experience in designing, developing, and maintaining robust Java applications. Strong background in object-oriented programming, software development life cycle (SDLC), and Agile methodologies. Demonstrated the ability to collaborate with cross-functional teams to deliver high-quality software solutions on time. Adept at problem-solving, optimizing code for performance, and ensuring scalability and reliability in complex systems. Committed to continuous learning and professional growth.

1. Worked on an Internship Project: Predicting the Quality of Wine using Machine Learning with Python.

• Developed and implemented a machine learning model to predict the quality of wine based on its chemical properties. Utilized Python and key libraries such as Pandas, and NumPy to preprocess data, perform exploratory data analysis, and build predictive models.
• Applied various machine learning algorithms, including Random Forest, Decision tree, KNN algorithm and Gradient Boosting, to identify the most accurate model. Deployed the final model and created visualizations using Matplotlib and Seaborn to interpret and present findings effectively.

2. In my Bachelor’s degree, I worked on a project called Real-Time Sign Language Gesture Recognition, which helps to interpret sign language gestures in real-time with Machine Learning using Python.

• Implemented a machine learning and Python-based real-time sign language gesture recognition system. Used computer vision techniques and libraries such as OpenCV for hand tracking and gesture detection. Preprocessed and augmented image data to enhance model training.
• Built and trained convolutional neural networks (CNNs) using TensorFlow and Keras to accurately classify gestures. Integrated the model into a real-time application, achieving high accuracy and low latency. Demonstrated expertise in deep learning, computer vision, and real-time system integration.

3. Worked on the Identification of Fake Currency project using Machine Learning with Python.

• Developed an advanced system for identifying counterfeit currency using Convolutional Neural Networks (CNNs) in Python. Used libraries such as TensorFlow and Keras to design, train, and optimize deep learning models capable of distinguishing between genuine and fake currency notes. Utilized image processing techniques and OpenCV for data preprocessing and augmentation to enhance model robustness.
• Achieved high accuracy in detection by fine-tuning the CNN architecture and implementing model evaluation. Successfully integrated the trained model into a user-friendly application, providing real-time currency verification. Used various machine learning algorithms, including Random Forest, Decision tree, KNN algorithm and Gradient Boosting, to identify the most accurate model.