2021
Multiple-Shooting Adjoint Method for Whole-Brain Dynamic Causal Modeling
Zhuang J, Dvornek N, Tatikonda S, Papademetris X, Ventola P, Duncan J. Multiple-Shooting Adjoint Method for Whole-Brain Dynamic Causal Modeling. Lecture Notes In Computer Science 2021, 12729: 58-70. DOI: 10.1007/978-3-030-78191-0_5.Peer-Reviewed Original ResearchOrdinary differential equationsAdjoint methodNoisy observationsMultiple shooting methodNon-linear systemsLarge scale continuous systemsLarge-scale systemsParameter value estimationDifferential equationsAccurate gradient estimationExpectation-maximization algorithmNon-linear modelParameter estimationBayesian frameworkGradient estimationContinuous systemToy exampleLarge systemsReal fMRI dataEstimationValue estimationAlgorithmGood accuracyCausal modelingModel changes
2020
A flexible framework for simulating and fitting generalized drift-diffusion models
Shinn M, Lam NH, Murray JD. A flexible framework for simulating and fitting generalized drift-diffusion models. ELife 2020, 9: e56938. PMID: 32749218, PMCID: PMC7462609, DOI: 10.7554/elife.56938.Peer-Reviewed Original ResearchConceptsDrift-diffusion modelArbitrary user-defined functionsImportant decision-making modelFokker-Planck equationEfficient numerical methodDecision-making mechanismUser-defined functionsDrift diffusion model frameworkFlexible frameworkSoftware packageGDDMHuman datasetsNumerical methodDecision-making modelResponse time distributionsDecision-making taskLatest methodologiesModel formGood accuracyFrameworkMaximum likelihoodModel innovationTime distributionDDM parametersModel frameworkA study of entity-linking methods for normalizing Chinese diagnosis and procedure terms to ICD codes
Wang Q, Ji Z, Wang J, Wu S, Lin W, Li W, Ke L, Xiao G, Jiang Q, Xu H, Zhou Y. A study of entity-linking methods for normalizing Chinese diagnosis and procedure terms to ICD codes. Journal Of Biomedical Informatics 2020, 105: 103418. PMID: 32298846, DOI: 10.1016/j.jbi.2020.103418.Peer-Reviewed Original ResearchConceptsBM25 algorithmConcept rankingConcept generationConvolutional neural network approachNeural network approachRanking-based methodRanking methodSupport vector machineProcedure termsBetter performanceVector machineDifferent algorithmsMedical codingNetwork approachAlgorithmICD codesBERTExtended versionGood accuracyKnowledgebaseDisease termsClinical termsMatch criteriaCodeChinese diagnosisAdaptive Checkpoint Adjoint Method for Gradient Estimation in Neural ODE.
Zhuang J, Dvornek N, Li X, Tatikonda S, Papademetris X, Duncan J. Adaptive Checkpoint Adjoint Method for Gradient Estimation in Neural ODE. Proceedings Of Machine Learning Research 2020, 119: 11639-11649. PMID: 34308361, PMCID: PMC8299461.Peer-Reviewed Original ResearchNeural ordinary differential equationsComputation graphImage classification tasksClassification taskPyTorch implementationBenchmark tasksTraining timeAdaptive checkpointsNeural ODEAutomatic differentiationNaive methodTime series modelingRedundant componentsGradient estimation methodError rateGood accuracyPhysical knowledgeEmpirical performanceGraphGradient estimationTaskAccuracyODE solverSolverResNet
2019
Secure and Differentially Private Logistic Regression for Horizontally Distributed Data
Kim M, Lee J, Ohno-Machado L, Jiang X. Secure and Differentially Private Logistic Regression for Horizontally Distributed Data. IEEE Transactions On Information Forensics And Security 2019, 15: 695-710. DOI: 10.1109/tifs.2019.2925496.Peer-Reviewed Original ResearchPrivacy-preserving modelHomomorphic encryption techniqueDifferential privacy methodReal-world datasetsPrivacy methodsPrivate dataSensitive dataEncryption techniqueSecurity methodsDifferential privacyInformation leakageNaive solutionPrivacyNatural wayGood accuracyScientific collaborationData analysisEncouraging resultsMajor concernSecurityDatasetPotential leakageComputationScenariosPracticability
2018
Inferring phenotypes from substance use via collaborative matrix completion
Lu J, Sun J, Wang X, Kranzler H, Gelernter J, Bi J. Inferring phenotypes from substance use via collaborative matrix completion. BMC Systems Biology 2018, 12: 104. PMID: 30463556, PMCID: PMC6249733, DOI: 10.1186/s12918-018-0623-5.Peer-Reviewed Original ResearchConceptsRecent statistical methodsMatrix completion techniqueMatrix completionStatistical modelingStatistical methodsPhenotype imputationSpeed 20 timesBi-linear modelImputation methodsParallel algorithmSequential algorithmMultiple scalesSimilar genetic determinantsGood accuracyAlgorithmNew approachCompletion techniquesSample sizeAccuracyModel
2013
Dynamic assessment of head motion compensation for the HRRT
Jin X, Mulnix T, Gallezot J, Carson R. Dynamic assessment of head motion compensation for the HRRT. 2011 IEEE Nuclear Science Symposium Conference Record 2013, 2867-2872. DOI: 10.1109/nssmic.2012.6551654.Peer-Reviewed Original ResearchMotion-free referenceEvent motion correctionMotion correction methodIntra-frame motionMotion compensationActual motion dataMotion correctionHead motion compensationCorrection methodHuman head motionFrame-based methodsSubject motionWide rangeSystem resolutionMotionMotion dataGood accuracyPrevious simulation studiesImage reconstructionSimulation studyDynamics studyCompensationHead motionRangeMethod
2009
Maximum-Likelihood Model Averaging To Profile Clustering of Site Types across Discrete Linear Sequences
Zhang Z, Townsend JP. Maximum-Likelihood Model Averaging To Profile Clustering of Site Types across Discrete Linear Sequences. PLOS Computational Biology 2009, 5: e1000421. PMID: 19557160, PMCID: PMC2695770, DOI: 10.1371/journal.pcbi.1000421.Peer-Reviewed Original ResearchConceptsInformation criterionModel averagingBayesian information criterionMaximum likelihood methodModel likelihoodModel uncertaintyModel selectionDescription of clustersLevel of clusteringPrecision of estimationAkaike information criterionParameter rangeCluster countsLikelihood methodComputational biologyCluster sizeGood accuracyConquer strategyAveragingClusteringModelHierarchical clusteringClustersStatisticsEstimation
This site is protected by hCaptcha and its Privacy Policy and Terms of Service apply