About

Work Experience

• internship, CodeAlpha

  Apr, 2026 - May, 20261 month

  Selected for a competitive Machine Learning internship program at CodeAlpha, focusing on practical, real-world applications of AI and data science.

  • Built and implemented machine learning models using Python, applying algorithms such as classification and regression. Performed data preprocessing, feature engineering, and exploratory data analysis (EDA) to improve model performance.

  • Evaluated models using metrics like accuracy, precision, recall, and confusion matrix. Gained hands-on experience with libraries such as NumPy, Pandas, Scikit-learn, and Matplotlib. Worked on structured projects, enhancing problem-solving skills and understanding of end-to-end ML pipelines. Strengthened knowledge in model optimization, validation techniques, and performance tuning.

• Summer intern, Minders

  Jul, 2025 - Sep, 20252 months

  I had the chance to attend an AI workshop at Minders, where I explored practical applications of Artificial Intelligence and its impact on real-world problems.

  • This experience helped me broaden my perspective on the field and gain hands-on insights that will support my journey in Computer Science.

Projects Experience

• Traffic sign Image classifier

  - Present

  Developed an intelligent Traffic Sign Recognition system capable of automatically classifying road traffic signs using both classical machine learning techniques and deep learning models. The project was built using the German Traffic Sign Recognition Benchmark (GTSRB) dataset containing 43 traffic sign classes.

  The workflow started with data exploration and visualization to understand class distribution and inspect sample images. Images were then preprocessed and flattened to prepare them for classical machine learning algorithms. Since each image contains a large number of features, Principal Component Analysis (PCA) was applied to reduce dimensionality while retaining 95% of the important information.

  Multiple classical machine learning models were trained and evaluated, including K-Nearest Neighbors (KNN) and Naive Bayes, to establish baseline performance.

  To improve accuracy and leverage modern computer vision techniques, a Deep Learning approach was implemented using MobileNetV2, a pretrained convolutional neural network. The model was fine-tuned to classify 43 traffic sign categories, enabling efficient feature extraction and improved classification accuracy.

Skills

Education

Certificates

Awards

Interests