- Local Area Network Attack 🛡️: Detects malicious LAN activity like DDoS and sniffing using ML models. [GitHub]
- Diabetes Healthy 🔍: Predicts diabetes risk based on health metrics. [GitHub]
- Airline Passenger Satisfaction
✈️ : Predicts satisfaction using feedback and ML classification. [GitHub] - Titanic 🚢: Predicts survival using classic Titanic dataset. [GitHub]
- IBM HR Employee 📊: Predicts employee attrition from satisfaction, work-life balance, etc. [GitHub]
- Heart Disease Prediction ❤️: Predicts heart disease using key health features. [GitHub]
- Bank Loan Prediction 💳📊: Classifies loan applications using various ML models. [GitHub]
- Chest X-ray Classification 👩⚕️: Classifies chest diseases using CNNs and pre-trained models. [GitHub]
- Gender Recognition 👩🦱👨🦱: Uses CNNs to classify gender from facial features. [GitHub]
- Footwear Impression Retrieval 👟🔍:This project involves the retrieval of crime scene footwear impressions using a Siamese Network and Triplet Loss. [GitHub]
- Football Player Tracking ⚽🎯: End-to-end system for detecting, tracking, and assigning team colors using YOLOv11 + ByteTrack with custom video annotations.[GitHub]
- Car Object Detection YOLOv8 🚗🔍: Detects cars in images using YOLOv8. [GitHub]
- Gym Step Counting 🏋️♂️: Tracks steps during workouts using motion sensors. [GitHub]
- OCR License Plate Recognition 🚗🔢: Uses OCR and CV to detect and extract license plate text. [GitHub]
- Cloud Segmentation ☁️: Segments cloud regions from satellite images using CNNs. [GitHub]
- Automatic Speech Recognition 🗣️🎧: Focused on converting spoken language into text using OpenAI's Whisper model. This project leverages Whisper's capabilities for automatic speech recognition, capable of transcribing audio in multiple languages with high accuracy. [GitHub Repository]
- Machine Translation 🌐 : focused on automatically translating text from English to Spanish using deep learning techniques. This project leverages models such as Sequence-to-Sequence (Seq2Seq) and Transformer networks to handle tasks like language translation, enabling cross-language communication and content localization [GitHub Repository]
- Text Generation ✍️💬: The project trains on a large corpus of text data to generate coherent and contextually relevant text, such as story generation, text completion, or creative writing. By utilizing RNNs, LSTMs, and GRUs, the model learns the patterns and structures of language, improving the fluency and creativity of generated content. [GitHub Repository]
- Face Sketch Generation 🎨🖼️: Generates face sketches from photos using GANs (DCGAN, WGAN, VAN). [GitHub]
- Transformer Model 🧠🔍: The project applies the Transformer architecture for text classification tasks. It uses a Transformer encoder to process text data and a decoder with a contextual mask for tasks like sequence generation and contextual understanding. [GitHub Repository]
- Deafbot 🤖🦻: A project designed to help individuals with speech impairments (such as those who are mute or non-verbal) interact with Large Language Models (LLMs) like GPT or Gemini. Deafbot utilizes sign language recognition technology to translate gestures into text, enabling seamless communication with LLM bots. The system bridges the gap between users who communicate through sign language and advanced AI, facilitating real-time conversation and interaction. [GitHub Repository]
- Medical Q&A Assistant 🩺🤖: A RAG-based AI assistant that allows users to upload medical PDF documents and ask questions about their content. It combines document retrieval with powerful LLMs to provide accurate, context-aware answers. Built using LangChain, FAISS, , Streamlit API. [GitHub Repository]