Upstream repository for a custom step to generate synthetic data based on an input table, using the Synthetic Minority Oversampling TEchnique (SMOTE). SMOTE is an oversampling technique which identifies new data observations in the neighborhood of closely associated original observations.

Implementation of augmentation, SMOTE, ADASYN, AE, DGAN for oversampling image data used in detection (YOLO and others one stage detectors). Maritime flags/code scenario.

This project focuses on predicting whether a customer will default on their credit card payment in the upcoming month. Utilizing historical transaction data and customer demographics, the project employs various machine learning algorithms to distinguish between risky and non-risky customers for better credit risk management.

By analyzing the results of this project, we can identify the most effective data preprocessing techniques and classifiers, ultimately leading to the development of a highly accurate solar flare prediction model.

in this project we used image processing Technique to classify 9 class malwares our final goal is to reach an appropriate model with high accuracy and small size and computational cost

Detect fraudulent credit card transactions using machine learning models and compare their performance. This project explores various techniques, including SMOTE, to handle imbalanced data and enhance detection accuracy.

Build a machine learning model to detect fraudulent online payment transactions with high accuracy. The project includes data preprocessing, SMOTE for class imbalance correction, and deployment using Streamlit for real-time predictions.

A machine learning pipeline for classifying cybersecurity incidents as True Positive(TP), Benign Positive(BP), or False Positive(FP) using the Microsoft GUIDE dataset. Features advanced preprocessing, XGBoost optimization, SMOTE, SHAP analysis, and deployment-ready models. Tools: Python, scikit-learn, XGBoost, LightGBM, SHAP and imbalanced-learn

This project analyzes health and lifestyle factors influencing heart attack risk using statistical methods and machine learning, with Ridge Regression identified as the best predictive model.

This repository contains all the machine learning algorithms and the ml concepts.

Stroke: Statistical analysis of risk factors and creation of predictive models using machine learning

A machine learning-based system for detecting fraudulent credit card transactions, leveraging advanced techniques like SMOTE, under-sampling, and anomaly detection models. Built with Random Forest, XGBoost, and SVM for robust performance on imbalanced datasets.

Projecto para la materia de Sistemas inteligentes haciendo uso de KNN oversampling.

The advertisement click prediction wiith machine learning models.

Implementation of novel oversampling algorithms.

Streamlining the process to generate synthetic data. Just focus on the data, not the code!

Spam/Ham Classifier with SMOTE Technique

Predict how effective employee performance is through actual productivity (deployed)

This project addresses cybersecurity in aviation by developing a machine learning-enhanced intrusion detection and prevention system (IDPS) for aircraft networks. Combining YARA-based signature detection with behavior-based (ML) anomaly detection, the system mitigates cyber threats in real-time, protecting aircraft from sophisticated attacks.

These notebooks provide a comprehensive workflow, from start to finish, for processing and analyzing the SWAN-SF dataset. They include detailed steps for reading the dataset files, performing full preprocessing, and executing classification.