This project is an image classification project using a deep-learning based on Convolutional Neural Networks (CNNs) with Keras. The Dogs vs. Cats is a classic problem for anyone who wants to dive deeper into deep-learning.

Graphs, plots and maps made using python.

Better multi-class confusion matrix plots for Scikit-Learn, incorporating per-class and overall evaluation measures.

The aim of this project is to predict whether a credit card transaction is fraudulent or not, based on the transaction amount, time and other transaction related data.It aims to track down credit card transaction data, which is done by detecting anomalies in the transaction data.

In simple, a Loan (borrowing money from a bank) is the sum of money that you borrow from the bank or lending financial institution in order to meet needs. These needs could result from planned or unplanned events, and by borrowing, you incur a debt that you have to pay within the agreed duration on your contract.

Objective: Build a CNN classifier that will be able to accurately predict the species of plant seedling based on an image of that seedling taken from the top.

An LSTM model to label articles into 5 categories.

Deep learning application for term deposit prediction on imbalanced dataset

This repository contains a Convolutional Neural Network which classifies whether a person is suffering from COVID-19 or not with the help of Chest X-rays.

ML_Logistic_Regression

In this project, we aimed to develop a deep learning model for accurately classifying X-ray images as either pneumonia or COVID cases. The objective was to compare accuracy of different types of CNN, where we used two: DenseNet and MobileNetV2 and acheived an accuracy of something close to 54.5% and later using feature scaling it came close to 85%.

Streamlit application to predict risk of cardiovascular disease

This research work summarized different machine learning algorithms to create models for predicting diabetes patients utilizing the Diabetes Dataset (PIDD) from the UCI repository. The classifiers were K-Nearest Neighbors, Naïve Bayes, Support Vector, Decision Tree, Random Forest, Logistic Regression and Ensemble Model using a voting classifier.

A human activity recognizer based on accelerometer data using a decision tree classifier and a feature extractor (TSFEL).