An Open-Source, synthetic finger anatomic dataset

Computation of training set (X^T * X) and (X^T * Y) in a cross-validation setting using the fast algorithms by Engstrøm (2024).

API to read, write, and filter DNA sequence alignment files

LiDAR processing ROS2. Segmentation: "Fast Ground Segmentation for 3D LiDAR Point Cloud Based on Jump-Convolution-Process". Clustering: "Curved-Voxel Clustering for Accurate Segmentation of 3D LiDAR Point Clouds with Real-Time Performance".

These are python codes developed to process Sentinel 2 and Field Reflectance Data

This project delves into advanced image compression methodologies leveraging Principal Component Analysis (PCA). PCA is utilized to decompose image data into orthogonal components, optimizing storage efficiency by retaining essential visual features through dimensionality reduction.

Compute various geospatial neighborhood deprivation indices

This repo contains scripts that can help you pre-process data, carry out principal component analysis (PCA) on them, and plot PCA-relevant plots.

This repository contains functions/codes related to different methods of machine learning for classification and clustering in python.

Face Recognition Using several dimensionality reduction techniques along with KNN as a classification algorithm

The FID-Evaluator is a tool to analyze how the FID behaves when the embedding space is reduced.

This tutorial provides a comprehensive walk around to performing molecular dynamics (MD) trajectory analysis using the Bio3D package in R.

The HotellingEllipse package helps draw the Hotelling's T-squared ellipse on a PCA or PLS score scatterplot by computing the Hotelling's T-squared statistic and providing the ellipse's coordinates, semi-minor, and semi-major axes lengths.

School assignments and final projects

A general purpose Snakemake workflow to perform unsupervised analyses (dimensionality reduction & cluster analysis) and visualizations of high-dimensional data.

This project analyzes tumor cell data from 550 patients using Python. It involves data cleaning, exploratory analysis, feature engineering, and machine learning to classify tumors as malignant or benign. Techniques include PCA, logistic regression, and k-fold cross-validation to ensure model accuracy and reliability.

This project predicts customer churn using machine learning. It involves data cleaning, EDA, feature engineering, and model evaluation. AdaBoostClassifier with SMOTE was optimized using GridSearchCV and validated with ROC analysis.

This includes various assignments I worked on learning Data Mining in R Studio

"This repository contains an implementation of the Principal Component Analysis (PCA) algorithm, which is one of the key techniques used for dimensionality reduction in data mining and machine learning."