Anomaly Detection in Wireless Sensor Networks in a Non-Stationary Environment
IEEE Communications Surveys & TutorialsPublished 1 January 2014Open access
Colin O’Reilly, Alexander Gluhak, Muhammad Ali Imran, Sutharshan Rajasegarar
Citations129
SJR quartileQ1
SJR score14.18
SNIP13.92
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
This survey provides a comprehensive overview of approaches to anomaly detection in a WSN and their operation in a non-stationary environment.
Abstract
Anomaly detection in a WSN is an important aspect of data analysis in order to identify data items that significantly differ from normal data. A characteristic of the data generated by a WSN is that the data distribution may alter over the lifetime of the network due to the changing nature of the phenomenon being observed. Anomaly detection techniques must be able to adapt to a non-stationary data distribution in order to perform optimally. In this survey, we provide a comprehensive overview of approaches to anomaly detection in a WSN and their operation in a non-stationary environment.
Keywords
Computer Science
Encyclopedia of Statistics in Behavioral SciencePrincipal Component Analysis
14,549 Citations2005Ian T. Jolliffe
ACM Computing SurveysAnomaly detection
11,146 Citations2009Varun Chandola, Arindam Banerjee +1 more
This survey tries to provide a structured and comprehensive overview of the research on anomaly detection by grouping existing techniques into different categories based on the underlying approach adopted by each technique.
Pattern RecognitionThe use of the area under the ROC curve in the evaluation of machine learning algorithms
7,233 Citations1997Andrew P. Bradley
AUC exhibits a number of desirable properties when compared to overall accuracy: increased sensitivity in Analysis of Variance (ANOVA) tests; a standard error that decreased as both AUC and the number of test samples increased; decision threshold independent; and it is invariant to a priori class probabilities.
Computer NetworksWireless sensor network survey
6,161 Citations2008Jennifer Yick, Biswanath Mukherjee +1 more
This survey presents a comprehensive review of the recent literature since the publication of a survey on sensor networks, and gives an overview of several new applications and then reviews the literature on various aspects of WSNs.
Machine LearningSupport Vector Data Description
3,484 Citations2003David M. J. Tax, Robert P. W. Duin
The Support Vector Data Description (SVDD) is presented which obtains a spherically shaped boundary around a dataset and analogous to the Support Vector Classifier it can be made flexible by using other kernel functions.
Communications of the ACMWireless integrated network sensors
3,227 Citations2000Gregory J. Pottie, William J. Kaiser
The WINS network represents a new monitoring and control capability for applications in such industries as transportation, manufacturing, health care, environmental oversight, and safety and security, and opportunities depend on development of a scalable, low-cost, sensor-network architecture.
IEEE Circuits and Systems MagazineEnsemble based systems in decision making
2,866 Citations2006Robi Polikar
Conditions under which ensemble based systems may be more beneficial than their single classifier counterparts are reviewed, algorithms for generating individual components of the ensemble systems, and various procedures through which the individual classifiers can be combined are reviewed.
Models and issues in data stream systems
2,517 Citations2002Brian Babcock, Shivnath Babu +3 more
The need for and research issues arising from a new model of data processing, where data does not take the form of persistent relations, but rather arrives in multiple, continuous, rapid, time-varying data streams are motivated.
Mining high-speed data streams
2,180 Citations2000Pedro Domingos, Geoff Hulten
This paper describes and evaluates VFDT, an anytime system that builds decision trees using constant memory and constant time per example, and applies it to mining the continuous stream of Web access data from the whole University of Washington main campus.
Mining time-changing data streams
1,725 Citations2001Geoff Hulten, Laurie Spencer +1 more
An efficient algorithm for mining decision trees from continuously-changing data streams, based on the ultra-fast VFDT decision tree learner is proposed, called CVFDT, which stays current while making the most of old data by growing an alternative subtree whenever an old one becomes questionable, and replacing the old with the new when the new becomes more accurate.
Coverage problems in wireless ad-hoc sensor networks
1,707 Citations2002Saro Meguerdichian, Farinaz Koushanfar +2 more
This work establishes the main highlight of the paper-optimal polynomial time worst and average case algorithm for coverage calculation, which answers the questions about quality of service (surveillance) that can be provided by a particular sensor network.
Journal of Statistical Planning and InferenceImproving predictive inference under covariate shift by weighting the log-likelihood function
1,681 Citations2000Hidetoshi Shimodaira
A class of predictive densities is derived by weighting the observed samples in maximizing the log-likelihood function, effective in cases such as sample surveys or design of experiments, where the observed covariate follows a different distribution than that in the whole population.
Wiley series in probability and statisticsPrincipal Component Analysis
1,669 Citations2002Alvin C. Rencher
Machine LearningLearning in the Presence of Concept Drift and Hidden Contexts
1,432 Citations1996Gerhard Widmer, Miroslav Kubát
A family of learning algorithms that flexibly react to concept drift and can take advantage of situations where contexts reappear are described, including a heuristic that constantly monitors the system's behavior.
IEEE Transactions on Signal ProcessingProjection approximation subspace tracking
1,257 Citations1995Bin Yang
A novel interpretation of the signal subspace as the solution of a projection like unconstrained minimization problem is presented, and it is shown that recursive least squares techniques can be applied to solve this problem by making an appropriate projection approximation.
Introduction to Multivariate Statistical Analysis in Chemometrics
1,221 Citations2010Курт Вармуза, Peter Filzmoser
Machine LearningLearning in the presence of concept drift and hidden contexts
988 Citations1996Gerhard Widmer, Miroslav Kubát
A family of learning algorithms that flexibly react to concept drift and can take advantage of situations where contexts reappear are described, including a heuristic that constantly monitors the system's behavior.
The problem of concept drift: definitions and related work
945 Citations2004Alexey Tsymbal
This paper considers different types of concept drift, peculiarities of the problem, and gives a critical review of existing approaches to the problem.
IEEE Transactions on Neural NetworksIncremental Learning of Concept Drift in Nonstationary Environments
898 Citations2011Ryan Elwell, Robi Polikar
An ensemble of classifiers-based approach for incremental learning of concept drift, characterized by nonstationary environments (NSEs), where the underlying data distributions change over time, which indicates that Learn++.NSE can track the changing environments very closely, regardless of the type of concept Drift.
LOCI: fast outlier detection using the local correlation integral
848 Citations2004Spiros Papadimitriou, Hiroyuki Kitagawa +2 more
Experiments show that LOCI and aLOCI can automatically detect outliers and micro-clusters, without user-required cut-offs, and that they quickly spot both expected and unexpected outliers.
IEEE Communications Surveys & TutorialsOutlier Detection Techniques for Wireless Sensor Networks: A Survey
793 Citations2010Yang Zhang, Nirvana Meratnia +1 more
This survey provides a comprehensive overview of existing outlier detection techniques specifically developed for the wireless sensor networks and presents a technique-based taxonomy and a comparative table to be used as a guideline to select a technique suitable for the application at hand based on characteristics such as data type, outlier type,outlier identity, and outlier degree.
ACM Computing SurveysSurvey of network-based defense mechanisms countering the DoS and DDoS problems
759 Citations2007Tao Peng, Christopher Leckie +1 more
This survey analyzes the design decisions in the Internet that have created the potential for denial of service attacks and the methods that have been proposed for defense against these attacks, and discusses potential countermeasures against each defense mechanism.
Models and issues in data stream systems
746 Citations2002Brian Babcock, Shivnath Babu +3 more
Statistical ScienceClassifier Technology and the Illusion of Progress
710 Citations2006David J. Hand
This paper argues that simple methods typically yield performance almost as good as more sophisticated methods, to the extent that the di!erence in performance may be swamped by other sources of uncertainty that generally are not considered in the classical supervised classification paradigm.
Computer NetworksSpatio-temporal correlation: theory and applications for wireless sensor networks
665 Citations2004Mehmet C. Vuran, Özgür B. Akan +1 more
A theoretical framework is developed to model the spatial and temporal correlations in WSN to enable the development of efficient communication protocols which exploit these advantageous intrinsic features of the WSN paradigm.
IEEE Journal on Selected Areas in CommunicationsStatistical en-route filtering of injected false data in sensor networks
532 Citations2005Fan Ye, Haiyun Luo +2 more
Analysis and simulations show that SEF is able to drop 80/spl sim/90% injected false reports by a compromised node within 10 forwarding hops, and reduce energy consumption by 50% or more in many cases.
Sensor deployment strategy for target detection
375 Citations2002Thomas Clouqueur, Veradej Phipatanasuphorn +2 more
This paper presents an approach for sequential deployment in steps and illustrates that the cost of deployment can be minimized to achieve the desired detection performance by appropriately choosing the number of sensors deployed in each step.
Journal of Network and Computer ApplicationsAnomaly detection in wireless sensor networks: A survey
349 Citations2011Miao Xie, Song Han +2 more
The key design principles relating to the development of anomaly detection techniques in WSNs are discussed in particular and a brief discussion towards the potential research areas in the near future and conclusion are discussed.
ACM Transactions on Sensor NetworksSensor faults
339 Citations2010Abhishek Sharma, Leana Golubchik +1 more
This work explores and characterize four qualitatively different classes of fault detection methods, and finds that time-series-analysis-based methods are more effective for detecting short duration faults than long duration ones, and incur more false positives than the other methods.
IEEE Wireless CommunicationsAnomaly detection in wireless sensor networks
304 Citations2008Sutharshan Rajasegarar, Christopher Leckie +1 more
The state of the art in anomaly detection techniques for wireless sensor networks is analyzed, some open issues for research are discussed, and some ideas for future directions are discussed.
Environmental Modelling & SoftwareAnomaly detection in streaming environmental sensor data: A data-driven modeling approach
296 Citations2009David Hill, Barbara Minsker
The results indicate that a multilayer perceptron model of the data stream, coupled with replacement of anomalous data points, performs well at identifying erroneous data in this data stream.
ACM Transactions on Sensor NetworksSensorScope
283 Citations2010François Ingelrest, Guillermo Barrenetxea +4 more
The overall hardware and software architectures and especially focus on the sensor network itself are described and the importance of simple code, well suited to the application, as well as the value of close interaction with end-users in planning and running the network and finally exploiting the data are indicated.
Machine Learning in Non-Stationary Environments: Introduction to Covariate Shift Adaptation
268 Citations2012Masashi Sugiyama, Motoaki Kawanabe
IEEE Transactions on Pattern Analysis and Machine IntelligenceConstructing boosting algorithms from SVMs: an application to one-class classification
244 Citations2002Gunnar Rätsch, Mika Sirén +2 more
This work shows via an equivalence of mathematical programs that a support vector algorithm can be translated into an equivalent boosting-like algorithm and vice versa, and exemplifies this translation procedure for a new algorithm: one-class leveraging, starting from the one- class support vector machine (1-SVM).
The impact of changing populations on classifier performance
225 Citations1999Mark G. Kelly, David J. Hand +1 more
Examples of population drift are given, the nature of such population drift is examined, how the impact of population Drift depends on the chosen measure of classification performance, and a strategy for dynamically updating classification rules is proposed.
The MIT Press eBooksMachine Learning in Non-Stationary Environments
208 Citations2012Masashi Sugiyama, Motoaki Kawanabe
This book focuses on a specific non-stationary environment known as covariate shift, in which the distributions of inputs and outputs change but the conditional distribution of outputs is unchanged, and presents machine learning theory, algorithms, and applications to overcome this variety of non-stationarity.
International Journal of Distributed Sensor NetworksIntrusion Detection for Routing Attacks in Sensor Networks
197 Citations2006Chong Eik Loo, Mun Yong Ng +2 more
This paper extends a sensor network simulator to generate routing attacks in wireless sensor networks and demonstrates that the intrusion detection scheme is able to achieve high detection accuracy with a low false positive rate for a variety of simulated routing attacks.
IEEE Signal Processing LettersFast orthonormal PAST algorithm
196 Citations2000Karim Abed‐Meraim, A. Chkeif +1 more
An orthonormal version of the PAST algorithm for fast estimation and tracking of the principal subspace or/and principal components of a vector sequence and guarantees the orthonormality of the weight matrix at each iteration is elaborated on.
International Journal of Geographical Information SystemsStatistics-based outlier detection for wireless sensor networks
179 Citations2012Y. Zhang, Nicholas Hamm +4 more
It is concluded that the incorporation of tools for outlier detection in WSNs can be based on current statistical methodology, which provides a usable and important tool in a novel scientific field.
Quarter Sphere Based Distributed Anomaly Detection in Wireless Sensor Networks
176 Citations2007Sutharshan Rajasegarar, Christopher Leckie +2 more
This work uses sensor data from the Great Duck Island Project to demonstrate that a distributed approach to anomaly detection is energy efficient in terms of communication overhead while achieving comparable accuracy to a centralised scheme.
Lecture notes in computer scienceEffective learning in dynamic environments by explicit context tracking
175 Citations1993Gerhard Widmer, Miroslav Kubát
By explicitly storing old hypotheses and re-using them to bias learning in new contexts, the method possesses the ability to utilize experience from previous learning, which greatly increases the system's effectiveness in environments where contexts can reoccur periodically.
IEEE Transactions on Instrumentation and MeasurementMonitoring in Industrial Systems Using Wireless Sensor Network With Dynamic Power Management
164 Citations2009Fabiano Salvadori, Maurício De Campos +6 more
A digital system for energy usage evaluation, condition monitoring, diagnosis, and supervisory control for electric systems applying wireless sensor networks (WSNs) with dynamic power management (DPM).
IEEE Transactions on Information Forensics and SecurityCentered Hyperspherical and Hyperellipsoidal One-Class Support Vector Machines for Anomaly Detection in Sensor Networks
156 Citations2010Sutharshan Rajasegarar, Christopher Leckie +2 more
This paper proposes a distributed anomaly detection algorithm for sensor networks using a one-class quarter-sphere support vector machine (QSSVM), and evaluation of the distributed algorithm using QSSVM reveals that it detects anomalies with comparable accuracy and less communication overhead than a centralized approach.
IEEE Transactions on Neural NetworksJust-in-Time Adaptive Classifiers—Part I: Detecting Nonstationary Changes
153 Citations2008Cesare Alippi, Manuel Roveri
This paper addresses the change detection aspect leaving the design of just-in-time adaptive classification systems to a companion paper, and two completely automatic tests for detecting nonstationarity phenomena are suggested.
IEEE Transactions on Parallel and Distributed SystemsScalable Hypergrid k-NN-Based Online Anomaly Detection in Wireless Sensor Networks
131 Citations2013Miao Xie, Jiankun Hu +2 more
A new kNN-based AD scheme based on hypergrid intuition is proposed for WSN applications to overcome the lazy-learning problem and is able to work successfully in any environment without human interventions.
Ad Hoc NetworksDistributed online outlier detection in wireless sensor networks using ellipsoidal support vector machine
130 Citations2012Yang Zhang, Nirvana Meratnia +1 more
This paper takes into account the correlation between sensor data attributes and proposes two distributed and online outlier detection techniques based on a hyperellipsoidal one-class support vector machine (SVM) and takes advantage of the theory of spatio-temporal correlation to identify outliers.
Learning Concept Drift with a Committee of Decision Trees
129 Citations2003Kenneth O. Stanley
The results indicate that using a committee to track drift has several advantages over traditional window-based approaches.
TechnometricsControlling the Standard Deviation by Cusums and Warning Lines
113 Citations1963E. S. Page
EURASIP Journal on Wireless Communications and NetworkingDevelopment of a Testbed for Wireless Underground Sensor Networks
102 Citations2010Agnelo R. Silva, Mehmet C. Vuran
This is the first work that proposes guidelines for the development of an outdoor W USN testbed with the goals of improving the accuracy and reducing of time for WUSN experiments.
IEEE NetworkSWATS: Wireless sensor networks for steamflood and waterflood pipeline monitoring
99 Citations2011SunHee Yoon, Wei Ye +3 more
A wireless sensor network system that detects, identifies, and localizes major anomalies such as blockage and leakage that arise in steamflood and waterflood pipelines in oilfields by utilizing multimodal sensing and multisensor collaboration, and exploiting temporal and spatial patterns of the sensed phenomena.
IEEE Transactions on Systems Man and Cybernetics Part B (Cybernetics)Distributed Visual-Target-Surveillance System in Wireless Sensor Networks
98 Citations2009Xue Wang, Sheng Wang +1 more
A multiview visual-target-surveillance system in WSN that can autonomously implement target classification and tracking with collaborative online learning and localization and the P2P-based progressive data-fusion paradigm can improve the energy efficiency and robustness of target surveillance.
Information FusionReal-time data mining of non-stationary data streams from sensor networks
91 Citations2005Lior Cohen, Gil Avrahami-Bakish +3 more
A new real-time data-mining algorithm called IOLIN (incremental on-line information network), which saves a significant amount of computational effort by updating an existing model as long as no major concept drift is detected.
Design and Implementation of a Real Time Video Surveillance System with Wireless Sensor Networks
85 Citations2008Wen-Tsuen Chen, Po‐Yu Chen +2 more
A real time video surveillance system consisting of many low cost sensors and a few wireless video cameras that is adaptable to variant environments and provides real time information of the monitored environment is proposed.
IEEE Sensors JournalDiagnosing Anomalies and Identifying Faulty Nodes in Sensor Networks
75 Citations2007Vassilis Chatzigiannakis, Symeon Papavassiliou
An anomaly detection approach that fuses data gathered from different nodes in a distributed sensor network is proposed and evaluated and allows the integration of results from neighboring network areas to detect correlated anomalies/attacks that involve multiple groups of nodes.
PIK - Praxis der Informationsverarbeitung und KommunikationIntrusion Detection in Unlabeled Data with Quarter-sphere Support Vector Machines
73 Citations2004Pavel Laskov, Christin Schäfer +2 more
This contribution investigates the application of a modern machine learning technique – one-class Support Vector Machines (SVM) – for anomaly detection in unlabeled data and proposes a novel formulation of this technique which is particularly suited for the data typical for intrusion detection systems.
ACM Transactions on Sensor NetworksElliptical anomalies in wireless sensor networks
65 Citations2009Sutharshan Rajasegarar, James C. Bezdek +2 more
A novel distributed anomaly detection algorithm is proposed that can detect elliptical anomalies with exactly the same accuracy as that of a centralized scheme, while achieving a significant reduction in energy consumption in the network.
Lecture notes in computer sciencePrincipal Component Analysis for Distributed Data Sets with Updating
65 Citations2005Zheng‐Jian Bai, Raymond H. Chan +1 more
A new method to compute the principal component analysis without incurring local approximation errors is introduced and the situation of updating the PCA when new data arrive at the various locations is considered.
Technische Universität Dortmund Eldorado (Technische Universität Dortmund)Intrusion detection in unlabeled data with quarter-sphere Support Vector Machines
64 Citations2004Pavel Laskov, Christin Schäfer +1 more
Separating the wheat from the chaff: practical anomaly detection schemes in ecological applications of distributed sensor networks
59 Citations2007Luís M. A. Bettencourt, Aric Hagberg +1 more
Expert Systems with ApplicationsEnsemble based sensing anomaly detection in wireless sensor networks
56 Citations2012Daniel-Ioan Curiac, Constantin Voloşencu
An efficient ensemble of five classifiers to detect sensor anomalies by modeling the correct operation of sensors not by one, but by five different dynamical models, acting synergically to provide a reliable solution.
Anomaly detection by clustering ellipsoids in wireless sensor networks
50 Citations2009Masud Moshtaghi, Sutharshan Rajasegarar +2 more
A distributed algorithm for anomaly detection in wireless sensor networks, which reduces the amount of data that needs to be communicated through the network, and introduces a method to cluster these ellipsoids at a global level in order to model normal behaviour in the network.
Lecture notes in computer scienceSeparating the Wheat from the Chaff: Practical Anomaly Detection Schemes in Ecological Applications of Distributed Sensor Networks
48 Citations2007Luís M. A. Bettencourt, Aric Hagberg +1 more
A practical, distributed algorithm to detect events, identify measurement errors, and infer missing readings in ecological applications of wireless sensor networks that is more storage-efficient, learns faster, and is more robust in the face of non-stationary phenomena.
Histogram-Based Online Anomaly Detection in Hierarchical Wireless Sensor Networks
40 Citations2012Miao Xie, Jiankun Hu +1 more
A simple estimating approach to detect anomalies with the histogram is introduced, which takes account into the distributed manner and online manner at the same time and proves the error caused by the new estimate is very small, through a theoretical analysis.
International Journal of Sensor NetworksEnsuring high sensor data quality through use of online outlier detection techniques
40 Citations2010Yang Zhang, Nirvana Meratnia +1 more
This paper proposes outlier detection techniques based on one-class quarter-sphere support vector machine meeting constraints and requirements of WSNs, and takes advantage of spatial and temporal correlations that exist between sensor data to reduce the false alarm rate while increasing the detection rate.
International Conference for Internet Technology and Secured TransactionsDistributed PCA-based anomaly detection in wireless sensor networks
39 Citations2010Mohammad Ahamdi Livani, Mahdi Abadi
This paper uses distributed principal component analysis (DPCA) and fixed-width clustering (FWC) in order to establish a global normal profile and to detect anomalies in sensed data in a WSN.
IEEE Transactions on Instrumentation and MeasurementRobust Recursive Eigendecomposition and Subspace-Based Algorithms With Application to Fault Detection in Wireless Sensor Networks
38 Citations2012S. C. Chan, H. C. Wu +1 more
Computer simulation and experimental results on WSN data show that the proposed fault detection approach, which combines the aforementioned robust subspace tracking algorithms with the robust detection criteria, is able to achieve better performance than other conventional approaches.
Incremental Elliptical Boundary Estimation for Anomaly Detection in Wireless Sensor Networks
38 Citations2011Masud Moshtaghi, Christopher Leckie +4 more
This paper presents an efficient online model construction algorithm that captures the normal behavior of the Wireless Sensor Networks system and is capable of tracking changes in the data distribution in the monitored environment.
Lecture notes in computer scienceIncremental Learning of Variable Rate Concept Drift
32 Citations2009Ryan Elwell, Robi Polikar
Preliminary results on the ability of the incremental learning algorithm to accommodate addition or subtraction of classes over time are presented, and comparative results of a variation of the algorithm that employs an error-based pruning in cyclical environments are presented.
Wireless Communications and Mobile ComputingStreaming analysis in wireless sensor networks
23 Citations2012Masud Moshtaghi, James C. Bezdek +5 more
Two new incremental models for online anomaly detection in data streams at nodes in wireless sensor networks are discussed and one of the new models has a mechanism that enables graceful degradation of inputs in the distant past fading memory.
Lecture notes in computer scienceCombining Online Classification Approaches for Changing Environments
22 Citations2008Juan J. Rodríguez, Ludmila I. Kuncheva
A classifier ensemble using Winnow, using the nearest neighbour with a fixed size window and two methods with a learning rate, which indicates that the combination works better than each strategy on its own.
Observing the unobservable : distributed online outlier detection in wireless sensor networks
22 Citations2010Yang Zhang
The main research objective is to design and implement effective and efficient outlier detection techniques for WSNs to identify outliers in an online and distributed manner and distinguish between errors and events with high accuracy and low false alarm, while maintaining the communication, computation and memory complexity low.
Combined multiclass classification and anomaly detection for large-scale Wireless Sensor Networks
22 Citations2013Alistair Shilton, Sutharshan Rajasegarar +1 more
A new form of SVM is presented that combines multiclass classification and anomaly detection into a single step to improve performance when data contains vectors from classes not represented in the training set.
Differential Kullback-Leibler Divergence Based Anomaly Detection Scheme in Sensor Networks
17 Citations2012Guorui Li, Ying Wang
This paper proposes a Differential Kullback-Leibler Divergence based anomaly detection scheme, which first partitions the whole sensor network into several clusters in which the sensors in each cluster are physically close to each other and have the similar sensed values.
Distributed training of multiclass conic-segmentation support vector machines on communication constrained networks
14 Citations2010Sutharshan Rajasegarar, Alistair Shilton +3 more
A distributed algorithm for training multiclass conic-segmentation support vector machines (CS-SVMs) on communication-constrained networks to obtain classifiers at each node which closely approximate the optimal (centralised) classifier.
Online anomaly rate parameter tracking for anomaly detection in wireless sensor networks
14 Citations2012Colin O’Reilly, Alex Gluhak +2 more
This paper proposes an adaptive algorithm that can dynamically adjust the anomaly rate parameter, which can be represented by a model parameter of a one-class quarter-sphere support vector machine, and operates in an online, iterative manner producing an optimal model for a training set, which is presented sequentially.
IBM Journal of Research and DevelopmentAnomaly detection in information streams without prior domain knowledge
12 Citations2011Mandis Beigi, Shih‐Fu Chang +2 more
The proposed approach simultaneously monitors and analyzes the data stream at multiple temporal scales and learns the evolution of normal behavior over time in each time scale and is applicable in various domains and applications.
Hardware implementation of a Kullback-Leibler Divergence based signal anomaly detector
10 Citations2009Mostafa Afgani, Sinan Sinanović +1 more
A field-programmable gate array (FPGA) based implementation of the Kullback-Leibler Divergence (KLD) algorithm for real-time detection of anomalies in periodic signals and an optimised, application specific, differential-equation version of theKLD equation are proposed.
Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications EngineeringA Framework for Resource Selection in Internet of Things Testbeds
7 Citations2012Michele Nati, Alexander Gluhak +3 more
This paper presents a framework for resource selection in large scale and heterogeneous Internet of Things testbeds, in order to support the experimenter with an increased understanding of available testbed resources, their expected behavior and topological relationships in the experimentation environment.
Muti-scale temporal segmentation and outlier detection in sensor networks
5 Citations2009Mandis Beigi, Shih‐Fu Chang +2 more
This work segments the temporal data stream and identifies the potential event bearing candidates by comparing the present and past statistical behavior of the data, and demonstrates the effect of optimum bin width selection on accuracy and the range of allowable window sizes and therefore time scales.
…