Anomaly detection using LoOP: Local Outlier Probabilities, a local density based outlier detection method providing an outlier score in the range of [0,1].

Project: Unsupervised Anomaly Segmentation via Deep Feature Reconstruction

Implementation of "Bayesian Robust Attributed Graph Clustering: Joint Learning of Partial Anomalies and Group Structure".

Detecting and segmenting destructive anomalies in farmland from satellite images, improving time, efficiency, and crop yield.

Thesis project about Visual Anomaly Detection based on Self Supervised Learning. The model identifies anomalies from information acquired during training, where normality and anomaly patterns are built using syntetic data

Replicate Barberis, Jin, and Wang (2021)

Anomalies Detection in Metocean Simulation Results Framework

This repository aims to identify discords in time series data using the HOT SAX publication as a role model. The base code is result of the work of Dr. Christian Gruhl, while alterations to add the alternative to HOT are the work of this student project.

Application of anomalies detecting and imputing algorithms for improving the LightGBM regressor.

Testing out optimal magic numbers for the old fast inverse square root function.

Unsupervised anomaly detection on COCO-style masked objects, comparison of results using various state-of-the-art deep autoencoders