% IMPORTANT: The following is UTF-8 encoded.  This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.

@MASTERSTHESIS{Wiersch:865946,
      author       = {Wiersch, Lisa},
      title        = {{S}ex classification from resting-state functional brain
                      networks},
      school       = {Heinrich-Heine Universität Düsseldorf},
      type         = {Masterarbeit},
      reportid     = {FZJ-2019-05212},
      pages        = {61},
      year         = {2019},
      note         = {Masterarbeit, Heinrich-Heine Universität Düsseldorf,
                      2019},
      abstract     = {Sex differences in the brain have received a wide interest
                      in neuroscientific research. Insteadof task-based group
                      comparisons, the present study employed a machine-learning
                      (ML)-approach to examine whether the resting-state
                      functional connectivity of 12 meta-analyticallydefined
                      networks carries enough information to accurately predict
                      the sex of a person. It washypothesized that especially
                      emotion-related networks should classify well. Sex
                      classificationanalyses were conducted in the datasets of the
                      healthy brain network (HBN, n = 218) theRockland Sample of
                      the enhanced Nathan Kline Institute (eNKI, n = 574), the
                      HumanConnectome Project (HCP, n = 734) and the
                      1000BRAINS-dataset (n = 995). The MLalgorithmsLASSO, LSVM,
                      Ridge and RVM were used for this classification approach.
                      Theresults showed that the eNKI- and HCP-datasets as well as
                      the algorithms LASSO and Ridgereceived on average higher
                      classification accuracies than the other datasets and
                      algorithms.The networks of autobiographical and semantic
                      memory reached the highest accuracies of allnetworks. Taken
                      together, the results did not support the initial
                      hypothesis. Instead, theresults generally displayed a strong
                      dependency on the datasets and ML-algorithms.},
      cin          = {INM-7},
      cid          = {I:(DE-Juel1)INM-7-20090406},
      pnm          = {572 - (Dys-)function and Plasticity (POF3-572)},
      pid          = {G:(DE-HGF)POF3-572},
      typ          = {PUB:(DE-HGF)19},
      url          = {https://juser.fz-juelich.de/record/865946},
}