Search results for "algorithm"

showing 10 items of 4887 documents

Clustering categorical data: A stability analysis framework

2011

Clustering to identify inherent structure is an important first step in data exploration. The k-means algorithm is a popular choice, but K-means is not generally appropriate for categorical data. A specific extension of k-means for categorical data is the k-modes algorithm. Both of these partition clustering methods are sensitive to the initialization of prototypes, which creates the difficulty of selecting the best solution for a given problem. In addition, selecting the number of clusters can be an issue. Further, the k-modes method is especially prone to instability when presented with ‘noisy’ data, since the calculation of the mode lacks the smoothing effect inherent in the calculation …

Computer sciencebusiness.industrySingle-linkage clusteringCorrelation clusteringConstrained clusteringcomputer.software_genreMachine learningDetermining the number of clusters in a data setData stream clusteringCURE data clustering algorithmConsensus clusteringData miningArtificial intelligenceCluster analysisbusinesscomputer2011 IEEE Symposium on Computational Intelligence and Data Mining (CIDM)
researchProduct

Detection of TV commercials

2004

This paper presents a system that labels TV shots either as commercial or program shots. The system uses two observations: logo presence and shot duration. These observations are modeled using HMMs, and a Viterbi decoder is finally used for shot labeling. The system has been tested on several hours of real video, achieving more than 99% correct labeling.

Computer sciencebusiness.industrySpeech recognitionShot (filmmaking)ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONViterbi algorithmsymbols.namesakeComputingMethodologies_PATTERNRECOGNITIONViterbi decoderPattern recognition (psychology)symbolsComputer visionArtificial intelligenceHidden Markov modelbusinessDecoding methods2004 IEEE International Conference on Acoustics, Speech, and Signal Processing
researchProduct

Advances in the statistical methodology for the selection of image descriptors for visual pattern representation and classification

1995

Recent advances in the statistical methodology for selecting optimal subsets of features (image descriptors) for visual pattern representation and classification are presented. The paper attempts to provide a guideline about which approach to choose with respect to the a priori knowledge of the problem. Two basic approaches are reviewed and the conditions under which they should be used are specified. References to more detailed material about each one of the methods are given and experimental results supporting the main conclusions are briefly outlined.

Computer sciencebusiness.industryVisual descriptorsVisual patternsRepresentation (systemics)A priori and a posterioriPattern recognitionArtificial intelligencebusinessMachine learningcomputer.software_genrecomputerSelection (genetic algorithm)
researchProduct

Periodic Variance Maximization using Generalized Eigenvalue Decomposition applied to Remote Photoplethysmography estimation

2018

International audience; A generic periodic variance maximization algorithm to extract periodic or quasi-periodic signals of unknown periods embedded into multi-channel temporal signal recordings is described in this paper. The algorithm combines the notion of maximizing a periodicity metric combined with the global optimization scheme to estimate the source periodic signal of an unknown period. The periodicity maximization is performed using Generalized Eigenvalue Decomposition (GEVD) and the global optimization is performed using tabu search. A case study of remote photoplethysmography signal estimation has been utilized to assess the performance of the method using videos from public data…

Computer sciencebusiness.industry[INFO.INFO-TS] Computer Science [cs]/Signal and Image Processing0206 medical engineeringFeature extraction[INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]02 engineering and technologyMaximizationVariance (accounting)020601 biomedical engineeringSignalTabu searchPeriodic function[INFO.INFO-CV] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV][INFO.INFO-TS]Computer Science [cs]/Signal and Image ProcessingMetric (mathematics)0202 electrical engineering electronic engineering information engineering020201 artificial intelligence & image processingArtificial intelligencebusinessGlobal optimizationAlgorithm
researchProduct

Cooperative compressive power spectrum estimation in wireless fading channels

2017

This paper considers multiple wireless sensors that cooperatively estimate the power spectrum of the signals received from several sources. We extend our previous work on cooperative compressive power spectrum estimation to accommodate the scenario where the statistics of the fading channels experienced by different sensors are different. The signals received from the sources are assumed to be time-domain wide-sense stationary processes. Multiple sensors are organized into several groups, where each group estimates a different subset of lags of the temporal correlation. A fusion centre (FC) combines these estimates to obtain the power spectrum. As each sensor group computes correlation esti…

Computer sciencebusiness.industrycorrelation lagSub-Nyquist samplingEstimatorSpectral densityfading020206 networking & telecommunicationsmulticoset sampling02 engineering and technologypower spectrumSignalwide-sense stationarycooperative estimationComputer Science::Networking and Internet Architecture0202 electrical engineering electronic engineering information engineeringWireless020201 artificial intelligence & image processingFadingUniquenessNyquist ratebusinessAlgorithmWireless sensor network2017 International Conference on Electrical Engineering and Informatics (ICELTICs)
researchProduct

Subpixel determination of imperfect circles characteristics

2008

This article deals with the problem of the determination of characteristics of imperfect circular objects in discrete images, namely the radius and center coordinates. To limit distortion, a multi-level method based on active contours was developed. Its originality is to furnish a set of geometric envelopes in one pass, with a correspondence between grayscale and a regularity scale. The adequacy of this approach was tested with several methods, among them is the Radon-based method. More particularly, this study indicates the relevance of the use of active contours combined with a Radon transform-based method which was improved using a fitting considering the discrete implementation of the R…

Computer sciencechemistry.chemical_elementRadonImage processingGeometryGeometric noise010103 numerical & computational mathematics02 engineering and technology01 natural sciencesGrayscaleEdge detectionArtificial IntelligenceDistortion[ INFO.INFO-TI ] Computer Science [cs]/Image Processing0202 electrical engineering electronic engineering information engineering0101 mathematicsComputingMilieux_MISCELLANEOUSRadon transformActive contour modelRadon transformActive contoursDiscrete circlesSubpixel renderingchemistry[INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV]Signal Processing020201 artificial intelligence & image processingComputer Vision and Pattern RecognitionModel fittingAlgorithmSoftware
researchProduct

A methodology to assess the intrinsic discriminative ability of a distance function and its interplay with clustering algorithms for microarray data …

2013

Abstract Background Clustering is one of the most well known activities in scientific investigation and the object of research in many disciplines, ranging from statistics to computer science. Following Handl et al., it can be summarized as a three step process: (1) choice of a distance function; (2) choice of a clustering algorithm; (3) choice of a validation method. Although such a purist approach to clustering is hardly seen in many areas of science, genomic data require that level of attention, if inferences made from cluster analysis have to be of some relevance to biomedical research. Results A procedure is proposed for the assessment of the discriminative ability of a distance functi…

Computer sciencecomputer.software_genreBiochemistrysymbols.namesakeDiscriminative modelStructural BiologyCluster AnalysisRelevance (information retrieval)Cluster analysisMolecular BiologyOligonucleotide Array Sequence AnalysisClustering discriminative ability of a distance function external validation indicesSettore INF/01 - InformaticaResearchApplied MathematicsMutual informationPearson product-moment correlation coefficientComputer Science ApplicationsHierarchical clusteringEuclidean distanceRange (mathematics)Metric (mathematics)symbolsData miningTranscriptomecomputerAlgorithmsBMC Bioinformatics
researchProduct

Indexing a sequence for mapping reads with a single mismatch

2014

Mapping reads against a genome sequence is an interesting and useful problem in computational molecular biology and bioinformatics. In this paper, we focus on the problem of indexing a sequence for mapping reads with a single mismatch. We first focus on a simpler problem where the length of the pattern is given beforehand during the data structure construction. This version of the problem is interesting in its own right in the context of the next generation sequencing. In the sequel, we show how to solve the more general problem. In both cases, our algorithm can construct an efficient data structure in time and space and can answer subsequent queries in time. Here, n is the length of the s…

Computer sciencegenome sequenceGeneral Mathematics[INFO.INFO-DS]Computer Science [cs]/Data Structures and Algorithms [cs.DS]General Physics and AstronomyContext (language use)algorithmscomputer.software_genrePattern matchingSequenceSearch engine indexingGeneral EngineeringWildcard characterArticlescomputer.file_formatConstruct (python library)Data structuremapping readspattern matchingComputingMethodologies_DOCUMENTANDTEXTPROCESSINGData mining[INFO.INFO-BI]Computer Science [cs]/Bioinformatics [q-bio.QM]Focus (optics)mismatchcomputerAlgorithmindexingPhilosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences
researchProduct

Assessment of Deep Learning Methodology for Self-Organizing 5G Networks

2019

In this paper, we present an auto-encoder-based machine learning framework for self organizing networks (SON). Traditional machine learning approaches, for example, K Nearest Neighbor, lack the ability to be precisely predictive. Therefore, they can not be extended for sequential data in the true sense because they require a batch of data to be trained on. In this work, we explore artificial neural network-based approaches like the autoencoders (AE) and propose a framework. The proposed framework provides an advantage over traditional machine learning approaches in terms of accuracy and the capability to be extended with other methods. The paper provides an assessment of the application of …

Computer scienceintrusion detection5G-tekniikka02 engineering and technologyIntrusion detection systemself-organizing networks (SON)Machine learningcomputer.software_genrelcsh:Technologyk-nearest neighbors algorithmself-organizing networkslcsh:Chemistryautoencoder (AE)deep learning (DL)mobility load balancing0202 electrical engineering electronic engineering information engineeringGeneral Materials ScienceInstrumentationlcsh:QH301-705.5Fluid Flow and Transfer ProcessesautoencoderArtificial neural networkbusiness.industrylcsh:Tmobility load balancing (MLB)Process Chemistry and TechnologyDeep learningGeneral Engineeringdeep learning020206 networking & telecommunicationsSelf-organizing networkLoad balancing (computing)021001 nanoscience & nanotechnologyAutoencoderlcsh:QC1-999Computer Science Applicationscell outage detectionlcsh:Biology (General)lcsh:QD1-999lcsh:TA1-2040Cellular networkArtificial intelligence0210 nano-technologybusinesslcsh:Engineering (General). Civil engineering (General)computerlcsh:Physics5G
researchProduct

An Online Observer for Minimization of Pulsating Torque in SMPM Motors.

2015

A persistent problem of surface mounted permanent magnet (SMPM) motors is the non-uniformity of the developed torque. Either the motor design or the motor control needs to be improved in order to minimize the periodic disturbances. This paper proposes a new control technique for reducing periodic disturbances in permanent magnet (PM) electro-mechanical actuators, by advancing a new observer/estimator paradigm. A recursive estimation algorithm is implemented for online control. The compensating signal is identified and added as feedback to the control signal of the servo motor. Compensation is evaluated for different values of the input signal, to show robustness of the proposed method.

Computer sciencelcsh:Medicine02 engineering and technologyBioinformaticsInfographics01 natural sciences0202 electrical engineering electronic engineering information engineeringlcsh:Science010302 applied physicsMultidisciplinaryFourier AnalysisPhysicsApplied MathematicsSimulation and ModelingClassical MechanicsSignal Processing Computer-AssistedEquipment DesignSignal FilteringRotorsPhysical SciencesMagnetsEngineering and TechnologyGraphsAlgorithmsResearch ArticleComputer and Information SciencesObserver (quantum physics)Materials ScienceServomotorResearch and Analysis MethodsOnline SystemsFeedbackMagneticsMotionRobustness (computer science)Control theory0103 physical sciencesTorqueEnginesMaterials by AttributeMechanical EngineeringData Visualization020208 electrical & electronic engineeringlcsh:RMotor controlModels TheoreticalBandpass FiltersVibrationTorqueDirect torque controlMagnetSignal Processinglcsh:QActuatorMathematicsPLoS ONE
researchProduct