2024
Improving 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 performance
2023
Improving Explainability for Single-Channel EEG Deep Learning Classifiers via Interpretable Filters and Activation Analysis*
Ellis C, Miller R, Calhoun V. Improving Explainability for Single-Channel EEG Deep Learning Classifiers via Interpretable Filters and Activation Analysis*. 2023, 00: 2474-2481. DOI: 10.1109/bibm58861.2023.10385647.Peer-Reviewed Original ResearchDeep learning methodsLearning methodsContext of automated sleep stage classificationDeep learning classifierSleep stage classificationAutomated feature extractionMachine learning methodsImprove explainabilityLearned featuresFeature extractionExplainability methodsAwake samplesLearning classifiersRaw electroencephalographyIncrease model performanceLayer filtersExplainabilityModeling activitiesModel performanceFilterStage classificationClassifierFiltering activityElectroencephalographyFrequency filteringEvaluating Trade-Offs in IVA of Multimodal Neuroimaging using Cross-Platform Multidataset Independent Subspace Analysis
Li X, Khosravinezhad D, Calhoun V, Silva R. Evaluating Trade-Offs in IVA of Multimodal Neuroimaging using Cross-Platform Multidataset Independent Subspace Analysis. 2023, 00: 1-5. DOI: 10.1109/isbi53787.2023.10230492.Peer-Reviewed Original ResearchIndependent vector analysisMultimodal neuroimaging datasetDeep latent variable modelBlind source separation methodMulti-network architectureIndependent Subspace AnalysisNeuroimaging datasetsSource separation methodPerformance trade-offsLatent spaceSubspace analysisTrade-offsPyTorch modulesLoss functionCross-platformMultiple datasetsLatent variable modelsDatasetCritical performance trade-offsOriginal frameworkVariable modelSimulation settingsModel performanceMultiple configurationsPlatformEffective Training Strategy for NN Models of Working Memory Classification with Limited Samples
Suresh P, Ray B, Thapaliya B, Farahdel B, Kazemivash B, Chen J, Duan K, Calhoun V, Liu J. Effective Training Strategy for NN Models of Working Memory Classification with Limited Samples. 2023, 00: 1-4. DOI: 10.1109/isbi53787.2023.10230722.Peer-Reviewed Original ResearchTraining strategyNeural networkData-hungry techniquesNN modelImage featuresSets of hyperparametersMachine learning methodsMachine learning modelsTrained NN modelModel performanceHigh memory capacityImbalanced samplesLearning methodsMemory capacityBrain imaging featuresSuboptimal solutionLearning modelsNetwork configurationEffective training strategyEfficient reuseWorking memory capacityTask-specificData conditionsBiomedical imagingNetwork