bayesgm: An AI-powered versatile Bayesian Generative Modeling Framework

Fill your data. A Multiverse Imputation Method powered by Topology 🍩

CUR-Estimator integrates interval-aware temporal modeling into neural imputation and suppresses unrealistic prediction drift via statistical interpolation constraints. The effectiveness is validated on simulated engine data, real civil aero-engine datasets, and wind turbine datasets.

Reproducibility code for the MethodsX paper: Percentile-Based Slope-Constrained Linear Interpolation for Robust Imputation of Highly Volatile PM2.5 Time Series. DOI: https://doi.org/10.1016/j.mex.2026.103859

Generate missing modalities from available data (e.g., sound from video, images from text) using advanced generative models

Basic neural matrix factorization for missing data imputation

[KDD 2024] "ImputeFormer: Low Rankness-Induced Transformers for Generalizable Spatiotemporal Imputation"

This project is a CSV Data Preprocessing Pipeline that automates the cleaning of sales data. It reads multiple CSV files from a specified directory, processes them, and saves the cleaned outputs with dynamically generated filenames based on the year found in the input filenames.

This project implements a machine learning-based triage system for emergency rooms, which classifies patients based on their symptoms and vitals using a Random Forest Classifier. The system features real-time patient data integration, a user-friendly GUI built with Tkinter, and secure patient data encryption using Fernet from the cryptography lib

The Growth Rate Data Imputation Tool is designed to handle datasets with missing values by using implied or artificial linear growth rates.

LLM4HRS:A LLM-based Spatio-temporal Imputation Model for Highly-sparse Remote Sensing Data

Binary classification algorithm that predicts which passengers are transported to an alternate dimension

Basic ML Algorithm that uses advanced regression techniques to predict the price of a house

Missing data imputation using the exact conditional likelihood of Deep Latent Variable Models

Data imputation is used when there are missing values in a dataset. It helps fill in these gaps with estimated values, enabling analysis and modeling. Imputation is crucial for maintaining dataset integrity and ensuring accurate insights from incomplete data.

Imputation-based Time-Series Anomaly Detection with Conditional Weight-Incremental Diffusion Models, KDD 2023

Repository for paper 'Truncated tensor Schatten p-norm based approach for spatiotemporal traffic data imputation with complicated missing patterns'.

Data Science stroke prediction project

[Nature-SR'22] DINI: Data Imputation using Neural Inversion

Code and Datasets for the paper "Identifying Sepsis Subphenotypes via Time-Aware Multi-ModalAuto-Encoder", published on KDD 2020.