2024
Large-Scale Independent Vector Analysis (IVA-G) via Coresets
Gabrielson B, Yang H, Vu T, Calhoun V, Adali T. Large-Scale Independent Vector Analysis (IVA-G) via Coresets. IEEE Transactions On Signal Processing 2024, 73: 230-244. DOI: 10.1109/tsp.2024.3517323.Peer-Reviewed Original ResearchJoint blind source separationIndependent vector analysisBlind source separationSubset selection methodJoint diagonalizationMultivariate Gaussian modelSource separationSignificant scalabilityComputational costCoresetMultiple datasetsSelection methodDatasetMeasure of discrepancyGaussian modelVector analysisNumerous extensionsScalabilityMethodConstrained Independent Vector Analysis With Reference for Multi-Subject fMRI Analysis
Vu T, Laport F, Yang H, Calhoun V, Adal T. Constrained Independent Vector Analysis With Reference for Multi-Subject fMRI Analysis. IEEE Transactions On Biomedical Engineering 2024, 71: 3531-3542. PMID: 39042541, PMCID: PMC11754528, DOI: 10.1109/tbme.2024.3432273.Peer-Reviewed Original ResearchIndependent vector analysisIndependent component analysisIVA approachesIndependent vector analysis algorithmMulti-subject functional magnetic resonance imagingHigher-order statistical informationMulti-subject dataSingle-subject mappingModel interferenceMultiple datasetsPrior informationNovel methodStatistical dependenceDatasetSeparation qualityStatistical informationComputational issuesVariable thresholdAlgorithmStatistical diversityModel matchingVector analysisQuality of separationComponent analysisInformationReproducibility and Replicability in Neuroimaging: Constrained IVA as an Effective Assessment Tool
Laport F, Dapena A, Vu T, Yang H, Calhoun V, Adali T. Reproducibility and Replicability in Neuroimaging: Constrained IVA as an Effective Assessment Tool. 2015 23rd European Signal Processing Conference (EUSIPCO) 2024, 802-806. DOI: 10.23919/eusipco63174.2024.10715160.Peer-Reviewed Original ResearchBlind source separationMatrix decomposition techniqueLinear blind source separationMulti-subject functional magnetic resonance imagingIndependent vector analysisPermutation ambiguityBSS techniquesDecomposition techniqueModel order selectionSource separationData-driven approachFunctional magnetic resonance imagingModel matchingModel orderComputational reproducibilityOrder selectionFMRI datasetsSuboptimal resultsMatchingDatasetEfficient federated learning for distributed neuroimaging data
Thapaliya B, Ohib R, Geenjaar E, Liu J, Calhoun V, Plis S. Efficient federated learning for distributed neuroimaging data. Frontiers In Neuroinformatics 2024, 18: 1430987. PMID: 39315000, PMCID: PMC11416982, DOI: 10.3389/fninf.2024.1430987.Peer-Reviewed Original ResearchFederated learningCommunication overheadsSparse modelModel sparsityClient siteTraining phaseAdolescent Brain Cognitive DevelopmentData sharingEfficient communicationLarge modelsLocal trainingResource capabilitiesDatasetCommunicationLearningSparsityActual dataOverheadsPrivacyNeuroimaging dataCognitive developmentDataScientific communitySharingLocal-structure-preservation and redundancy-removal-based feature selection method and its application to the identification of biomarkers for schizophrenia
Xing Y, Pearlson G, Kochunov P, Calhoun V, Du Y. Local-structure-preservation and redundancy-removal-based feature selection method and its application to the identification of biomarkers for schizophrenia. NeuroImage 2024, 299: 120839. PMID: 39251116, PMCID: PMC11491165, DOI: 10.1016/j.neuroimage.2024.120839.Peer-Reviewed Original ResearchConceptsSelection methodClassification accuracy gainsGraph-based regularizationHigh-dimensional dataFeature selection methodLocal structural informationSparse regularizationAblation studiesFeature subsetPublic datasetsFeature selectionClassification accuracyExperimental evaluationAccuracy gainsSelection techniquesNetwork connectivityData transformationSuperior performanceDatasetConvergence analysisStructural informationClassificationRegularizationFeaturesDisorder predictionEvaluating Augmentation Approaches for Deep Learning-based Major Depressive Disorder Diagnosis with Raw Electroencephalogram Data*
Ellis C, Miller R, Calhoun V. Evaluating Augmentation Approaches for Deep Learning-based Major Depressive Disorder Diagnosis with Raw Electroencephalogram Data*. Annual International Conference Of The IEEE Engineering In Medicine And Biology Society (EMBC) 2024, 00: 1-5. PMID: 40039441, DOI: 10.1109/embc53108.2024.10782103.Peer-Reviewed Original ResearchConceptsAugmented training setData augmentationTraining setDA methodsDeep learning methodsDA approachNeuropsychiatric disorder diagnosisModel performanceTraining dataDeep learningEEG datasetDataset sizeLearning methodsAugmentation approachImprove model performanceDepressive disorder diagnosisDA efficacyDatasetDisorder diagnosisCompare performanceMajor depressive disorder diagnosisPerformanceBaseline setDeepChannelCGDM-GAN: An Adversarial Network Approach with Self-supervised Learning for Site Effect Removal
Cui X, Zhi D, Yan W, Calhoun V, Zhuo C, Sui J. CGDM-GAN: An Adversarial Network Approach with Self-supervised Learning for Site Effect Removal. Annual International Conference Of The IEEE Engineering In Medicine And Biology Society (EMBC) 2024, 00: 1-4. PMID: 40039732, DOI: 10.1109/embc53108.2024.10782176.Peer-Reviewed Original ResearchConceptsSelf-supervised learningIntrinsic image propertiesGeneralization of modelsSynthetic datasetsClassification performanceGenerative modelDiscrepancy minimizationImage dataNetwork approachDatasetData harmonizationImaging propertiesLearningNeuroimaging classificationCycleGANData harmonization methodsAdversaryABCD datasetAcquisition protocolsPerformanceEffective wayDataTaskExploring Schizophrenia Classification in fMRI Data: A Common Spatial Patterns(CSP) Approach for Enhanced Feature Extraction and Classification
Esfahani M, Miller R, Calhoun V. Exploring Schizophrenia Classification in fMRI Data: A Common Spatial Patterns(CSP) Approach for Enhanced Feature Extraction and Classification. Annual International Conference Of The IEEE Engineering In Medicine And Biology Society (EMBC) 2024, 00: 1-4. PMID: 40040201, DOI: 10.1109/embc53108.2024.10782387.Peer-Reviewed Original ResearchConceptsImplementation of deep learning modelsNetwork connectivityUnsupervised dimensionality reduction techniquesTime-varying network connectivityEnhanced feature extractionDimensionality reduction techniquesDeep learning modelsMotor imagery tasksFeature extractionElectroencephalogram signalsTransformation of signalsEEG signalsPrincipal component analysisLearning modelsData typesCSP methodApplication of CSPSchizophrenia classificationFMRI datasetsReduction techniquesImagery tasksDatasetCSPDataClassificationCross-Sampling Rate Transfer Learning for Enhanced Raw EEG Deep Learning Classifier Performance in Major Depressive Disorder Diagnosis
Ellis C, Miller R, Calhoun V. Cross-Sampling Rate Transfer Learning for Enhanced Raw EEG Deep Learning Classifier Performance in Major Depressive Disorder Diagnosis. 2024, 00: 1-5. DOI: 10.1109/isbi56570.2024.10635743.Peer-Reviewed Original ResearchTransfer learningDeep learning classifier’s performanceEarly convolutional layersConvolutional neural networkDeep learning modelsDeep learning studiesConvolutional layersClassifier performanceDiagnosis tasksExplainability analysisNeural networkSleep datasetsRaw electroencephalographyLearning modelsIncreased robustnessDatasetChannel lossSampling rateModel accuracyMDD modelLearningRepresentationTaskLearning studiesElectroencephalographyA Robust and Scalable Method with an Analytic Solution for Multi-Subject FMRI Data Analysis
Vu T, Yang H, Laport F, Gabrielson B, Calhoun V, Adalı T. A Robust and Scalable Method with an Analytic Solution for Multi-Subject FMRI Data Analysis. 2024, 00: 1831-1835. DOI: 10.1109/icassp48485.2024.10447397.Peer-Reviewed Original ResearchJoint blind source separationSource separationMulti-subject functional magnetic resonance imagingBlind source separationLatent sourcesSeparation of sourcesDemixing vectorsComputational complexityCompetitive performanceMultiple datasetsEstimation performanceDatasetSource templateMulti-subjectNumerical resultsEfficient methodRuntimeComponent analysisScalable methodPerformanceAlgorithmAnalytical solutionMethodOptimizationImplementationMaximum Classifier Discrepancy Generative Adversarial Network for Jointly Harmonizing Scanner Effects and Improving Reproducibility of Downstream Tasks
Yan W, Fu Z, Jiang R, Sui J, Calhoun V. Maximum Classifier Discrepancy Generative Adversarial Network for Jointly Harmonizing Scanner Effects and Improving Reproducibility of Downstream Tasks. IEEE Transactions On Biomedical Engineering 2024, 71: 1170-1178. PMID: 38060365, PMCID: PMC11005005, DOI: 10.1109/tbme.2023.3330087.Peer-Reviewed Original ResearchDownstream tasksPerformance of downstream tasksOriginal feature spaceState-of-the-artAdversarial generative networkGAN generatorAdversarial networkFeature spaceOriginal imageGeneration networksClassification performanceSmall-sample problemTask objectivesGenerative modelImproved performanceTaskHarmony frameworkAnatomical layoutNetworkHarmonious methodsMulti-site collaborationSimulated dataLayoutScanner effectsDatasetImproving Age Prediction: Utilizing LSTM-Based Dynamic Forecasting For Data Augmentation in Multivariate Time Series Analysis
Gao Y, Ellis C, Calhoun V, Miller R. Improving Age Prediction: Utilizing LSTM-Based Dynamic Forecasting For Data Augmentation in Multivariate Time Series Analysis. 2024, 00: 125-128. DOI: 10.1109/ssiai59505.2024.10508611.Peer-Reviewed Original ResearchLong short-term memoryDeep learning modelsData augmentationPerformance deep learning modelsLearning modelsMultivariate time series dataAge prediction taskShort-term memoryPrediction taskAugmented datasetDynamical forecastsComponent networksMultivariate time series analysisDatasetNeuroimaging datasetsRobust solutionTime series dataOriginal dataValidation frameworkTime series analysisSeries dataNetworkNeuroimaging fieldDataModel performanceA Multi-dimensional Joint ICA Model with Gaussian Copula
Agcaoglu O, Silva R, Alacam D, Calhoun V. A Multi-dimensional Joint ICA Model with Gaussian Copula. Lecture Notes In Computer Science 2024, 14366: 152-163. DOI: 10.1007/978-3-031-51026-7_14.Peer-Reviewed Original ResearchIndependent component analysisBivariate distributionMarginal distributionsGaussian copulaLogistic distributionJoint ICAImage data miningSuper-Gaussian distributionImage datasetsFunctional magnetic resonance imaging datasetsInfomax principleAlzheimer's Disease Neuroimaging InitiativeProposed algorithmData miningIdentical marginalsMagnetic resonance imaging datasetICA modelMultimodal versionICA methodJoint independent component analysisCopulasDatasetMaximum likelihoodMixing matrixNeuroimaging dataIdentifying the Relationship Structure Among Multiple Datasets Using Independent Vector Analysis: Application to Multi-Task fMRI Data
Lehmann I, Hasija T, Gabrielson B, Akhonda M, Calhoun V, Adali T. Identifying the Relationship Structure Among Multiple Datasets Using Independent Vector Analysis: Application to Multi-Task fMRI Data. IEEE Access 2024, 12: 109443-109456. DOI: 10.1109/access.2024.3435526.Peer-Reviewed Original ResearchIndependent vector analysisTask datasetMultiple datasetsFeature extraction approachUser-defined thresholdsHigher-order statisticsMulti-task fMRI dataExtraction approachRelationship structureDatasetSimulation resultsHierarchical clusteringInterpretable componentsVector analysisFMRI-dataFMRI dataEffective wayMethodTaskDataActivated brain regionsHypothesis testingDistributional assumptionsInformationMode Coresets for Efficient, Interpretable Tensor Decompositions: An Application to Feature Selection in fMRI Analysis
Gabrielson B, Yang H, Vu T, Calhoun V, Adali T. Mode Coresets for Efficient, Interpretable Tensor Decompositions: An Application to Feature Selection in fMRI Analysis. IEEE Access 2024, 12: 192356-192376. DOI: 10.1109/access.2024.3517338.Peer-Reviewed Original ResearchTensor decompositionSize of modern datasetsRank-1 tensorsComputational complexity scalesCore tensorTucker decompositionFeature selectionComputational complexitySelection schemeData tensorMultidimensional arraysRank-1CoresetTensor dataMatrix decompositionModern datasetsMassive sizeMyriad of applicationsMethod efficiencyDatasetSelection abilityComplexity scalesMeasure of discrepancyWell-approximatedDecomposition method
2023
Improving Multichannel Raw Electroencephalography-based Diagnosis of Major Depressive Disorder via Transfer Learning with Single Channel Sleep Stage Data*
Ellis C, Sattiraju A, Miller R, Calhoun V. Improving Multichannel Raw Electroencephalography-based Diagnosis of Major Depressive Disorder via Transfer Learning with Single Channel Sleep Stage Data*. 2023, 00: 2466-2473. DOI: 10.1109/bibm58861.2023.10385424.Peer-Reviewed Original ResearchDeep learning methodsLearning methodsTransfer learningEEG datasetManually engineered featuresTransfer learning approachDeep learning modelsDeep learning performanceMachine learning methodsClassification datasetsLearned representationsElectroencephalography classifierDeep learningEEG classificationResting-state electroencephalographyDiagnosis of major depressive disorderRaw electroencephalographyLearning approachLearning modelsMajor depressive disorder diagnosisMajor depressive disorderLearning performanceClassifierDatasetEngineering featuresREGRESSION-ASSISTED INDEPENDENT VECTOR ANALYSIS: A SOLUTION TO LARGE-SCALE FMRI DATA ANALYSIS
Yang H, Gabrielson B, Calhoun V, Adali T. REGRESSION-ASSISTED INDEPENDENT VECTOR ANALYSIS: A SOLUTION TO LARGE-SCALE FMRI DATA ANALYSIS. 2023, 00: 1443-1447. DOI: 10.1109/ieeeconf59524.2023.10476796.Peer-Reviewed Original ResearchConstrained Independent Component Analysis Based on Entropy Bound Minimization for Subgroup Identification from Multi-subject fMRI Data
Yang H, Ghayem F, Gabrielson B, Akhonda M, Calhoun V, Adali T. Constrained Independent Component Analysis Based on Entropy Bound Minimization for Subgroup Identification from Multi-subject fMRI Data. 2023, 00: 1-5. DOI: 10.1109/icassp49357.2023.10095816.Peer-Reviewed Original ResearchIndependent vector analysisSynthetic dataConstrained independent component analysisEntropy bound minimizationComputational complexity limitationsDemixing matrixIndependent component analysisComputational costOrthogonality requirementData identificationAlgorithmFunctional networksNetworkComponent analysisDatasetFMRI dataComputerTaskEntropyOrthogonalitySubgroup identificationVector analysisBrain networksDensity modelCoupled CP Tensor Decomposition with Shared and Distinct Components for Multi-Task Fmri Data Fusion
Borsoi R, Lehmann I, Akhonda M, Calhoun V, Usevich K, Brie D, Adali T. Coupled CP Tensor Decomposition with Shared and Distinct Components for Multi-Task Fmri Data Fusion. 2023, 00: 1-5. DOI: 10.1109/icassp49357.2023.10096241.Peer-Reviewed Original ResearchCP tensor decompositionTensor factorization approachDataset-specific featuresTensor-based frameworkPost-processing stepExtract featuresFunctional magnetic resonance imagingHyperparameter selectionTensor decompositionData fusionMulti-taskingDiscover componentsMultiple datasetsTaskCoupling matrixFunctional magnetic resonance imaging dataHyperparametersDatasetFeaturesGroup differencesFactor approachDecompositionFusionIndependent Vector Analysis with Multivariate Gaussian Model: a Scalable Method by Multilinear Regression
Gabrielson B, Sun M, Akhonda M, Calhoun V, Adali T. Independent Vector Analysis with Multivariate Gaussian Model: a Scalable Method by Multilinear Regression. 2023, 00: 1-5. DOI: 10.1109/icassp49357.2023.10096698.Peer-Reviewed Original ResearchJoint blind source separationIndependent vector analysisMultivariate Gaussian sourcesBlind source separationOverall estimation performanceGaussian sourceMultivariate Gaussian modelSource separationComputational costJoint decompositionEstimation performanceDatasetCost functionEstimated sourcesGaussian modelIntractable problemVector analysisMultilinear regressionEfficient methodScalable methodRegressorsFMRI dataMethodMultilinear
This site is protected by hCaptcha and its Privacy Policy and Terms of Service apply