rajdip-i Goto Github PK

23m0323_llm

Season of Code 2024

application-to-display-a-grayscale-image-its-pseudo-color-display-negative-and-histogram

This application enables visualization of grayscale images with enhanced functionalities, including displaying grayscale images, transforming them into pseudo-colored representations, generating negative counterparts, and analyzing histograms with customizable scales.

assignments

Assignments of EE-769 cource

consumer-energy-management

Utilizing LSTM Neural Networks to forecast energy cosumption trends with time series analysis. Employing Collaborative Filtering with Matrix Factorization and SVD, the system suggests personalized actions based on user behavior, fostering energy conservation.Leveraging Isolation Forest to detect anomalies in consumption patterns.

covid-project

This project Integrated machine learning models including Support Vector Machine (SVM), Random Forest, k-Nearest Neighbors, and Neural Networks into a stacked ensemble for predicting potential COVID-19 infections based on the collected data, facilitating proactive healthcare interventions and management.

ev-market-segmentation

genetic-algoritham-and-neural-nets

This project Integrats the capabilities of neural networks with the optimization strength of genetic algorithms to develop a resilient image classification system. In this collaborative framework, the neural network learns to differentiate between various image classes, while the genetic algorithm refines the network’s initial weights .

geological-text-mining

iitb-faq-bot

RAG based chatbot for IITB students using Mistral 7B and FAISS.

market-segmentation

This Project includes the market segmentation for McDonalds using K-Means, Mixture of distributions and Mixture of regression models.

natural-features-detection

This project implements YOLO v8 architecture for detecting natural features like basins, bays, islands, lakes, ridges, and valleys in satellite images and Digital Elevation Models. It leveraged the power of deep learning and extensive training on the GeoimageNet dataset to achieve remarkable accuracy.

restaurant-rating-prediction

This project focuses on predicting restaurant ratings . Models including Linear Regression, Random Forest, Support Vector Machine, and XGBoost are trained ,evaluated and compared to determine their effectiveness in predicting ratings. Folium is used to create interactive maps that display the locations of restaurants for predicted ratings.

voltvision-ai

voltvisionai