1. Curriculum Vitae
Colleen Pam Chen, MS Computational Science
(714) 417-0409
ColleenPamChen@gmail.com
Education
San Diego State University San Diego, CA 2014
Masters in Computational Science with a focus in machine learning and data analytics
GPA: 3.83
University of San Diego San Diego, CA 2011
Professional Certification: ABA Approved Paralegal Certificate Program
GPA: Honors in Business Litigation Specialty
University of California San Diego San Diego, CA 2010
B.A. Political Science; History minor
GPA: 3.6; Provost Honors
Pi Sigma Alpha (National Political Science Honor Society); Phi Alpha Delta
Freie Universität Berlin, Germany 2010
UC Educational Abroad Program: German linguistics, European Business Culture,
European Legal Traditions
Relevant Graduate Coursework
Computational Science
Computational Methods
Computational Imaging
Computational Genomics
Statistical Learning Methods
Bioinformatics
Brain Computer Interface
Scientific databases
Technical Skills
Data analysis: R, Matlab, Mathematica
Programming languages: PERL, C, C++, Python, HTML, MySQL, Fortran
OS & Scripting Languages: LINUX, OSX, Shell Script
Neuroimaging Software: AFNI, FSL, FreeSurfer, dicom3tools, GroupICA Toolbox (GIFT),
MRIConvert, mricron, nipype, nibabel, Resting State fMRI data analysis Toolkit (REST), SPM8
Parallel Computing: MPI and CUDA
2. Journal Publications
• Chen, C.P., Keown, C., Jahedi, A., Nair, A., Pflieger, M., Bailey, B., & Müller R.-A. (2015)
Diagnostic classification of intrinsic functional connectivity highlights somatosensory, default
mode, and visual regions in autism. Neuroimage Clinical, 20. DOI:10.1016/j.nicl.2015.04.002
• Chen, C.P., Keown, C., & Müller R.-A. (2013) Towards Understanding Autism Risk Factors: a
Classification of Brain Images with Support Vector Machines, International Journal of Semantic
Computing. Vol. 7, No. 2. 205–213.
• Nair A, Carper RA, Abbott AE, Chen CP, Solders S, Nakutin S, Datko MC, Fishman I, Müller R-A
(2015) Regional Specificity Of Aberrant Thalamocortical Connectivity In Autism. Human Brain
Mapping, in press.
• Stewart, C.R., Sanchez, S.S., Grenesko, E.L., Brown, C.M., Chen, C.P., Keehn, B., Velasquez, F.,
Lincoln, A.J. & Müller, R.-A. (2015) Sensory Symptoms and Processing of Nonverbal Auditory
and Visual Stimuli in Children with Autism Spectrum Disorder. Journal of Autism and
Developmental Disorders.
MANUSCRIPTS IN PREPARATION
Chen, C.P., Bailey, B., & Müller R.-A. Towards autism subtypes? Unsupervised machine learning
using fcMRI features (2015)
Research Experience
Research Assistant, Brain Development Imaging Laboratory, Department of Psychology,
San Diego State University Research Foundation (2015-present)
Research Assistant investigating atypical functional connectivity patterns of Autism using
machine learning methods.
Using machine learning methods including classifiers and clustering algorithms to
diagnose autism based on imaging data as well as discover subtypes within the
autism spectrum, both tasks are important for early diagnosis and personalization
of treatment
Utilizing statistical models to quantify how functional MRI preprocessing steps
designed to correct for noise (e.g. motion) impact data quality with the goal of
explaining varied findings in current autism literature.
Examining the synchronization of networks in autism compared to typically
developing subjects, using independent component analysis to detect networks and
graph theory to model their interactions in the temporal domain, and results
suggested noisy communication between networks in autism.
Implementing graph theoretical metrics to quantify both local and regional patterns
of aberrant connectivity in autism spectrum disorders, finding evidence of both
over- and underconnectivity in comparison with typically developing children.
3. Research Assistant, Source Signal Imaging Inc., multimodal imaging analysis software, La
Mesa (2013-2015)
SBIR project, "Data-driven detection and estimation of BOLD-related EEG signal:
computational theory."
Developed data-driven computational method for detecting neuroelectric-
hemodynamic couplings associated with specific EEG frequencies and fMRI brain
signals of interest using concurrently collected EEG-fMRI data.
Used FreeSurfer software to generate head model for computational modeling of
EEG source signals.
Graduate Research Assistant, Dr. Ralph-Axel Müller, Cognitive Neuroscience Neuroimaging
Lab, San Diego State University (2012 – 2015)
Implemented machine learning methods including classifiers and clustering algorithms to
diagnose autism based on imaging data as well as discover subtypes within the autism
spectrum, both tasks are important for early diagnosis and personalization of treatment
Utilized statistical models to quantify how functional MRI preprocessing steps designed to
correct for noise (e.g. motion) impact data quality with the goal of explaining varied
findings in current autism literature.
Examined the synchronization of networks in autism compared to typically developing
subjects, using independent component analysis to detect networks and graph theory to
model their interactions in the temporal domain, and results suggested noisy
communication between networks in autism.
Implemented graph theoretical metrics to quantify both local and regional patterns of
aberrant connectivity in autism spectrum disorders, finding evidence of both over- and
underconnectivity in comparison with typically developing children.
AWARDS & GRANTS
• Jun 2015 Award: Organization of Human Brain Mapping Abstract Merit Award
• Jun 2013 Award: Organization of Human Brain Mapping Trainee Travel Award
ORAL PRESENTATIONS
Chen, C.P., Bailey, B., & Müller R.-A. Towards autism subtypes? Unsupervised machine
learning using fcMRI features. 2015. Organization of Human Brain Mapping Conference,
Honolulu, HI.
Chen, C.P., C. L. Keown, & Müller R.-A.: High Diagnostic Prediction Accuracy for ASD
Using Functional Connectivity MRI Data and Random Forest Machine Learning. 2014.
International Meeting for Autism Research, Atlanta, GA.
Chen, C.P., Keown, C., & Müller R.-A. Diagnostic classification of autism using particle
swarm optimization for fMRI feature selection. 2013. Organization of Human Brain
Mapping Conference, Seattle, WA.
4. Chen, C.P., Keown, C., & Müller R.-A. Classification of Autism Neuroimaging Data using Machine
Learning Algorithm. 2013. San Diego State University Student Research Symposium, San Diego,
CA.
PROFESSIONAL MEMBERSHIPS
IEEE Computational Intelligence (2012-2014)
Organization of Human Brain Mapping (2013-2015)
International Society for Autism Research (2014-2015)
Society for Neuroscience (2013-2014)
PROFESSIONAL EXPERIENCE
*Refer to Professional Resume