Developed a computer vision system to identify and categorize Diabetic Retinopathy stages, aiding ophthalmologists in preventing potential blindness. This system utilized standardized retina images and applied advanced preprocessing techniques, including Gaussian blur. Experiments with ResNet models achieved up to 97% accuracy….
Sentiment Analysis of Movie Review Dataset
This project focuses on analyzing sentiment in a dataset of 25,000 unique IMDB movie reviews, classifying them into Negative, Neutral, or Positive categories. The analysis involves deep understanding of the context, semantics, and sentiment expressed in the reviews. Advanced machine learning…
Voice and Large Language Models (LLM)
This project focuses on processing audio inputs using advanced speech recognition and employing large language models to extract valuable insights. It includes transcription, diarization, and analysis of recorded meetings and voice notes, generating actionable summaries and key information points. AI and…
LTV Prediction for Financial Institutions
This project develops a predictive tool for assessing loan-to-value (LTV) ratios, a critical financial metric used by banks to evaluate lending risks associated with mortgages. With high LTV ratios typically indicating higher-risk loans, the project aimed to create a sophisticated model…
P&C ChatBot
This project developed a conversational HR chatbot designed to offer instant and precise answers to common HR-related queries, enhancing accessibility and reducing the workload for HR Business Partners. The chatbot aims to streamline interactions by providing quick responses, thereby improving operational…
AI-Powered Virtual Teaching Assistant
This project involves the development of an advanced AI-based virtual teaching assistant, designed to provide interactive educational support using Meta’s LLama-3-70B-Instruct model. The assistant is engineered to assist with a range of educational activities, from delivering personalized learning content to handling…