AI-generated or real face? These Deep Learning-based models can expose digital imposters before they ghost you, so no more falling for flawless deepfake faces!!

EasyTorch is a research-oriented pytorch prototyping framework with a straightforward learning curve. It is highly robust and contains almost everything needed to perform any state-of-the-art experiments.

An example of easytorch implementation on retinal vessel segmentation.

The project provides a complete end-to-end workflow for building a binary classifier in Python to recognize the risk of housing loan default. It includes methods like automated feature engineering for connecting relational databases, comparison of different classifiers on imbalanced data, and hyperparameter tuning using Bayesian optimization.

Several small AI projects, including basic machine learning algorithms, perceptron neural networks, convolutional neural networks, and semantic segmentation.

Code and supplementary materials for the research paper titled 'Advancing Geological Image Segmentation: Deep Learning Approaches for Rock Type Identification and Classification', published in Applied Computing and Geosciences (Elsevier).

This project is an Android mobile application, written in Java programming language and implements a Recommender System using the k-Nearest Neighbors Algorithm. In this way the algorithm predicts the possible ratings of the users according to scores that have already been submitted to the system.

Pada project ini, akan dilakukan identifikasi nilai mata uang rupiah dengan menggabungkan metode ekstrasi ciri Local Binary Pattern dan metode klasifikasi Naïve Bayes. Serta untuk pengukuran akurasi identifikasi dilakukan dengan metode evaluasi K-Fold Cross Validation. Dataset yang digunakan berupa citra dengan rincian terdapat 120 citra yang terdiri dari 15 citra uang kertas Rp1.000, 15 citra uang kertas Rp2.000, 15 citra uang kertas Rp5.000, 15 citra uang kertas Rp10.000, 15 citra uang kertas Rp20.000, 15 citra uang kertas Rp50.000, 15 citra uang kertas Rp75.000, dan 15 citra uang kertas Rp100.000

Notebooks for Kaggle competition

Fuzzy Systems Assignments (Classification and Regression) - TSK

This toolbox offers 6 machine learning methods including KNN, SVM, LDA, DT, and etc., which are simpler and easy to implement.

MLB Team Runs Allowed Prediction Project (Linear Regression)

A notebook about commonly used machine learning algorithms.

Machine Learning with MATLAB

this project is sentiment analysis about about Kampus Merdeka that launched at Youtube platform using Naive Bayes Classifier with TF-IDF term weighting, also get validated using K Fold Cross Validation. The score-mean result is 91.2%, pretty good for valid score.

An explainable and interpretable binary classification project to clean data, vectorize data, K-Fold cross validate and apply classification models. The model is made explainable by using LIME Explainers.

An analysis of the factors that have affected the bleaching of coral reefs across a span of 20 years in different oceans around the globe.

No description provided.

my machine learning practices for my third year in MFCI CS department

No description provided.

This toolbox offers 7 machine learning methods for regression problems.

As part of this project, various classification algorithms like SVM, Decision Trees and XGBoost was used to classify a GPU Run as high or low time consuming process. The main purpose of this project is to test and compare the predictive capabilities of different classification algorithms

Master's Thesis project at University of Agder, Spring 2020. Classification with Tsetlin Machine on board game 'GO'.

Ad campaign performance evaluation using AB Testing

Predicted preterm birth (PTB) in early stages of pregnancy. Identified dominant PTB risk factors using Shapley Additive Explanation (SHAP).

Data Mining project : Built a classifier, trained a classifier, created clusters, performed 5-fold-cross-validation.

This repository contains a practical application of machine learning In Machine Learning Workshop at GDSC

This project aims to understand and implement all the cross validation techniques used in Machine Learning.

A Java console application that implemetns k-fold-cross-validation system to check the accuracy of predicted ratings compared to the actual ratings and RMSE to calculate the ideal k for our dataset.

Multi-class network intrusion detection using CatBoost with GPU/CPU support, handling highly imbalanced datasets. Includes stratified downsampling, K-Fold cross-validation, and explainable AI with SHAP feature importance analysis. Designed for high-performance training on large datasets with detailed evaluation metrics and visualizations.