On-Line Unsupervised Outlier Detection Using Finite Mixtures with Discounting Learning Algorithms

By Kenji Yamanishi, Jun'ichi Takeuchi, Graham J. Williams, Peter Milne. Knowledge Discovery and Data Mining, 2000

718 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Civil and Structural Engineering

View Paper: https://www.semanticscholar.org/paper/ec5d26aaf2e6902ca28effa0f94c9556571160b8

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Civil and Structural Engineering

Citations in the corpus

Change-Point Detection in Time-Series Data by Direct Density-Ratio Estimation (2009, background): “This problem is referred to as change-point detection [34, 16, 22] or event detection [13], and covers a broad range of real-world problems such as fraud detection in cellular systems [24, 3], intrusion detection in computer networks [35], irregular-motion detection in vision systems [20], signal se”
Outlier Detection for Temporal Data: A Survey (2014, methodology): “[102], [103] present SmartSifter which employs an online discounting learning algorithm to incrementally learn the probabilistic mixture model, with a decay factor to account for drift.”
Fast Outlier Detection in High Dimensional Spaces (2002, neutral): “In [ 20 ] a Gaussian mixture model to represent the normal behaviors is used and each datum is given a score on the basis of changes in the model.”
Learning Discriminative Reconstructions for Unsupervised Outlier Removal (2015, methodology): “Statistical methods [6, 27, 11] fit parametric distributions on data, and outliers are identified as those having low probability under the learned distributions.”
An Analysis of the 1999 DARPA/Lincoln Laboratory Evaluation Data for Network Anomaly Detection (2003, methodology): “The network traffic from the 1998 data set was also used to develop the 1999 KDD cup machine learning competition [21], which had 25 participants, and which continues to be used to test intrusion detection methods [22-23].”
Anomaly Detection in Time Series: A Comprehensive Evaluation (2022, neutral): “[91] SubsequenceLOF [22] Data Mining TwoFinger[90] NorM[14] DissimilarityAlgo[6] STOMP [164] Series2Graph [16] HOTSAX [70] STAMP [156] MERLIN[97] DAD[154] BoehmerGraph[13] GrammarViz [120] TARZAN [71] NormA-SJ [15] NormA-smpl[15] KnorrSeq2[102] TSBitmap [144] ILOF[108] VALMOD [82] SurpriseEncoding[2”
Parzen-window network intrusion detectors (2002, background): “Many network intrusion detection methods have been proposed in the research community, e.g., [2] [3] [6] [8] [9] [10] [11] [14] [17] [18].”
A comparative study of RNN for outlier detection in data mining (2002, methodology): “We follow the experimental technique employed in [18] to construct suitable datasets for outlier detection and to rank all data points with an outlier measure.”
A unifying framework for detecting outliers and change points from time series (2006, background): “IDENTIFICATION of outliers in a data stream has been one ofthe most exciting topics in data mining (e.g., [11], [3], [16]) and in statistics (e.g., [2]) since it can lead to the discovery of unexpected and interesting knowledge.”
HRN: A Holistic Approach to One Class Learning (2020, background): “Early work in statistics [4] was mainly based on probabilistic modeling of the distribution of the normal data and regard data points with low probabilities in the distribution as anomalies [4, 87, 22, 86].”
Anomaly detection: A survey (2009, neutral): “…and have been used to detect strains in airframe data [Hickinbotham and Austin 2000a; Hollier and Austin 2002], to detect anomalies in mammographic image analysis [Spence et al. 2001; Tarassenko 1995], and for network intrusion detection [Yamanishi and ichi Takeuchi 2001; Yamanishi et al. 2004].”
A Survey of Stealth Malware Attacks, Mitigation Measures, and Steps Toward Autonomous Open World Solutions (2016, background): “Thresholding density estimates from Gaussian mixture models (GMMs) is a popular parametric approach to novelty detection with a similar functional form to KDE [147]–[151].”
A review of novelty detection (2014, methodology): “This approach was first proposed in [118] for data mining, specifically in fraud detection, network intrusion detection, or network monitoring.”
Unsupervised learning techniques for an intrusion detection system (2004, methodology): “A discounting learning algorithm has been used in the Smart Sifter prototype [32], and should combine a smooth running time with good detection rates.”
DeepAnT: A Deep Learning Approach for Unsupervised Anomaly Detection in Time Series (2019, methodology): “This data set is also used as described in [55].”