Deep Speaker - Speaker Recognition System (CNN+LSTM)

The primary goal of deep speaker recognition is to identify or verify the identity of a speaker based on their unique vocal characteristics, often referred to as speaker voiceprints or biometric signatures. It is a form of biometric authentication(security systems, access control, authentication).

Identification of Medicinal Plants

A deep learning model for classifying Indian medicinal plant leaves using ResNet50 and Keras. Trained on 80+ plant species with image augmentation and transfer learning.

Real-Time Queue Detection and Management using YOLO-v8 Object Detection

Developed a real-time queue management system leveraging YOLO object detection to identify and count people in queues from live video feeds, providing actionable insights via a web interface.

Voice-controlled Wheelchair

This project demonstrates a voice-controlled wheelchair system using a Raspberry Pi. The system allows physically challenged individuals to navigate their wheelchair using simple voice commands, enhancing mobility and independence.

Credit Card Fraud Detection

Developed a deep learning model to detect fraudulent credit card transactions using precise data. The project involved analyzing transaction patterns to accurately identify potential fraud, enhancing security and reducing financial risk.

Stock Price Prediction using LSTM

In this project, I ventured into the exciting world of time series analysis and deep learning to build a robust Stock Price Prediction model using Long Short-Term Memory (LSTM) networks. Along this journey, I gained invaluable insights and knowledge.

CO2 Emission Prediction in Rwanda

This project centers around conducting a comprehensive exploratory data analysis (EDA) to uncover meaningful insights and patterns within a diverse dataset. The primary objective is to build a foundation for developing accurate predictive models for CO2 emissions.

Car Sales Price Prediction

Developed an Artificial Neural Network (ANN) model to predict car sales prices with high accuracy using precise data. This project demonstrates the use of advanced machine learning techniques to estimate vehicle prices based on various features.

Zomato Sales Analysis

Conducted a sales analysis of Zomato data using Power BI, analyzing over 100,000 transactions to identify key trends and growth opportunities. Created interactive dashboards that improved data-driven decision-making, leading to a 15% increase in targeted sales strategies.

Music App using React.js

Produced a user-friendly music streaming app using React, featuring a library of over 10,000 songs with seamless streaming and playlist creation. Optimized front-end performance and executed responsive design, while seamlessly integrating the Spotify API for a vast music library.

Identifying Patterns and Trends in Campus Placement Prediction

the solution that aims to leverage machine learning techniques to gain valuable insights from campus placement data. By analyzing student attributes, academic performance, technical skills and domain interests, we seek to unravel patterns influencing placement success.

Vegetable Mandi Price Prediction

Harnessed the power of data to create models that forecast the prices of various vegetables in mandis (markets), helping stakeholders make informed decisions.

IMDB Movies Rating Prediction

This project involves predicting IMDB movie ratings using a Support Vector Regressor (SVR). By analyzing precise data, the model accurately estimates ratings, showcasing the application of machine learning in predicting audience reception.

Titanic Survival Prediction

Titanic Survival Prediction is my first project in the domain of Data Science and Machine Learning. In this project, we delve into the fascinating realm of data analysis and machine learning to predict the survival outcomes of passengers aboard the legendary Titanic.