Online outlier detection in sensor data using non-parametric models

By Sharmila Subramaniam, Themis Palpanas, Dimitris Papadopoulos, Vana Kalogeraki, Dimitrios Gunopulos. Very Large Data Bases Conference, 2006

506 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/afa2c668482af7e5c23bb55f64111ae5a413a99c

How researchers see this paper

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

Citations in the corpus

Outlier Detection for Temporal Data: A Survey (2014, background): “[117] propose the Multi Granularity Deviation Factor (MDEF) metric.”
MacroBase: Prioritizing Attention in Fast Data (2016, background): “A considerable subset of these techniques operates over data streams [6, 18, 65, 75].”
Classification and Novel Class Detection in Concept-Drifting Data Streams under Time Constraints (2011, background): “Finally, Section 6 concludes with directions to future works.”
Data Cleaning: Overview and Emerging Challenges (2016, unknown): “Attribute Error Value Imputation [57, 72, 8, 81, 62, 23] [75, 52, 43, 24] Data Repairing [1, 57, 8, 37] [75, 52] Duplication Error Entity Resolution [39, 24, 81, 69] [35, 37] Relevance Error Error/Outlier Removal [27, 70, 28, 15, 34] [52]”
Detection of false data injection attacks in smart-grid systems (2015, methodology): “Figure 5 shows the simulation results when applying our FDI-detection approach and the state-of-the-art distanced-based (DB) solution proposed in 2013 [9] [10].”
Robust Spectral Filtering and Anomaly Detection (2018, unknown): “Further, we should like to point to the closely related problems of deviation [27], or (on-line, complex) event [40] detection, outlier analysis [2], detection [33], or pursuit [39], foreground detection [8] and the complementary background subtraction or background maintenance, or even dynamic anom”
High-dimensional and large-scale anomaly detection using a linear one-class SVM with deep learning (2016, methodology): “In each experiment, 80% of records are randomly selected for training and 20% for testing, and then, respectively, mixed with 5% and 20% anomalous records, randomly drawn from Uð0;1Þ [50].”
MacroBase: Analytic Monitoring for the Internet of Things (2016, background): “tection (leveraging a variety of classiﬁers and techniques) [14,64], and industrial automation and predictive maintenance [8, 56]. A considerable subset of these techniques operates over data streams [6,18,65,75]. At stream volumes in the hundreds of thousands or more events per second, statistical ”
Quarter Sphere Based Distributed Anomaly Detection in Wireless Sensor Networks (2007, methodology): “Palpanas et al. [8] and Subramanium et al. [ 9 ] have proposed the use of kernel density estimators for online distributed outlier detection in streaming data in sensor networks.”
Progress in Outlier Detection Techniques: A Survey (2019, background): “[136] propose a novel idea for the one-time query of outliers in data streams that is different from the continuous queries approach presented by authors in [137], [138].”
Anomaly Detection in Time Series: A Comprehensive Evaluation (2022, unknown): “[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”
Outlier Analysis (2013, background): “Outlier detection has also been studied extensively in the context of sensor data [3, 86, 76, 170, 427, 502].”
A review of novelty detection (2014, methodology): “[93] use kernel density estimators in a framework that computes an approximation to multidimensional data distributions in order to enable complex applications in resource-constrained sensor networks.”
Density-based clustering for real-time stream data (2007, background): “Density-based clustering has been long proposed as another major clustering algorithm [14, 15].”
Learning model trees from evolving data streams (2010, methodology): “Subramaniam et al. (2006) propose a distributed streaming algorithm for outlier and change detection that uses kernel methods in the context of sensor networks.”
Outlier Detection Techniques for Wireless Sensor Networks: A Survey (2008, background): “[2] further extend the work of Palpanas et al.”