one-class-svm

anomaly detection by one-class SVM

Fast Incremental Support Vector Data Description implemented in Python

PySVM : A NumPy implementation of SVM based on SMO algorithm. Numpy构建SVM分类、回归与单分类，支持缓存机制与随机傅里叶特征

A one class svm implementation to detect the anomalies in network.

Code for paper 'Avoid touching your face: A hand-to-face 3d motion dataset (covid-away) and trained models for smartwatches'

This demo shows how to detect the crack images using one-class SVM using MATLAB.

A curated list of awesome resources dedicated to One Class Classification.

Detect outliers with 3 methods: LOF, DBSCAN and one-class SVM

Reproducible Python tutorials and benchmarks for outlier detection using statistical methods, machine learning, ensembles, autoencoders, tests, exercises, and CI.

Anomaly Detection in Optical Networks

Canned estimators and pre-trained models converted for TensorFlow.

OCS-WAF: a Web Application Firewall based on anomaly detection using One-Class SVM classifier

Anomaly detection for Sequential dataset

This project consists of comparative algorithm analysis between six machine learning algorithms to identify the optimum ML algorithm for intrusion detection.

DDoS detection using anomaly detection in high-speed ITP networks. Comparing Autoencoder, Isolation Forest, Local Outlier Factor, and One-Class SVM across real ITP datasets, different aggregation windows, and feature selections using Pearson’s correlation coefficient.

Anomaly detection using IF, LOF, OC-SVM, Autoencoder.

One-Class SVMs for Document Classification

Anomaly detection (also known as outlier analysis) is a data mining step that detects data points, events, and/or observations that differ from the expected behavior of a dataset. A typical data might reveal significant situations, such as a technical fault, or prospective possibilities, such as a shift in consumer behavior.

Empowering Sustainable Energy with Artificial Intelligence. 🍃🌍 An intelligent IoT & Machine Learning platform that transforms raw environmental and mechanical sensor data into real-time diagnostics. By predicting everything from optimal operations to critical emergencies before they happen, we are making renewable energy smarter, safer, and more

Constraint-enforcing synthetic IoT packet generation. Two methods: statistical learning (PCA + dual OCSVM/IF gating, ~1,091 pkts/sec) and a genetic algorithm (composite fitness, ~5.7 pkts/sec, 0.62% anomaly). Amplifies the 5-sample ARP Spoofing class by 200x. All 12 ACI-IoT-2023 categories pass independent validators. ICCCN 2026 submission.