Litcius/Paper detail

Deep-Shallow Metaclassifier with Synthetic Minority Oversampling for Anomaly Detection in a Time Series

Mohammadhossein Reshadi, Wen Li, Wenjie Xu, Precious Omashor, Albert Dinh, Jun Xiao, Scott Dick, Yuntong She, Michael Lipsett

2024Algorithms10 citationsDOIOpen Access PDF

Abstract

Anomaly detection in data streams (and particularly time series) is today a vitally important task. Machine learning algorithms are a common design for achieving this goal. In particular, deep learning has, in the last decade, proven to be substantially more accurate than shallow learning in a wide variety of machine learning problems, and deep anomaly detection is very effective for point anomalies. However, deep semi-supervised contextual anomaly detection (in which anomalies within a time series are rare and none at all occur in the algorithm’s training data) is a more difficult problem. Hybrid anomaly detectors (a “normal model” followed by a comparator) are one approach to these problems, but the separate loss functions for the two components can lead to inferior performance. We investigate a novel synthetic-example oversampling technique to harmonize the two components of a hybrid system, thus improving the anomaly detector’s performance. We evaluate our algorithm on two distinct problems: identifying pipeline leaks and patient-ventilator asynchrony.

Topics & Concepts

Anomaly detectionComputer scienceOversamplingAnomaly (physics)Artificial intelligenceDeep learningPipeline (software)Series (stratigraphy)Machine learningTime seriesPattern recognition (psychology)GeologyBandwidth (computing)Computer networkPaleontologyPhysicsProgramming languageCondensed matter physicsAnomaly Detection Techniques and ApplicationsNetwork Security and Intrusion DetectionData Stream Mining Techniques
Deep-Shallow Metaclassifier with Synthetic Minority Oversampling for Anomaly Detection in a Time Series | Litcius