|
Affiliations
I
am a PhD student in the Department of
Computer Science doing collaborative research with several other groups at Colorado State University, including the:
Center
for Biomedical Research in Music
Molecular,
Cellular, and Integrative Neurosciences Program
Department
of Psychology
Research
Interests
The overarching goal of my research is to
advance biomedical science by integrating advances in technology. More specifically, in most of my research I
use signal processing and machine learning to answer questions in systems,
cognitive, and clinical neuroscience. A
few examples of threads in my research include:
|
1. Identifying changes in the
human brain associated with learning. How are changes in brain physiology affected
by verbal learning strategies such as repetition and musical mnemonics? What are the implications for mitigating
the effects of neurologic deficits on learning and memory? 2.
Enhancing methods for non-invasive brain-computer interfaces. Can simple
"yes"/"no" thoughts be detected from recordings on the
scalp? Does a judicious application
of machine learning make these signals more discernible, robust over time,
and amenable for use by individuals with severely degraded lower motor
function? |
Scalp topographies of
alpha-band oscillatory power changes during verbal learning. |
||
|
3.
Diagnosing and understanding cancer through microarray
classification. In the search for genetic factors involved, how do optimal
classifier parameters depend on the number of genes considered? What are the implications for molecular
biology research and drug development? |
Classification accuracy (darker is better)
is jointly sensitive to the number of genes considered and a key parameter in
the support vector machine classifier. |
Topography figures above generated with EEGLAB (www.sccn.ucsd.edu/eeglab/). Classifier performance figure to the left based
on Figure 2 in Peterson and Thaut (2004). |
|
My
Curriculum Vitae (.pdf)
Select Publications
1. Peterson DA and Thaut MH. (in press) Music increases frontal EEG coherence during verbal learning, Neuroscience Letters.
2. Thaut MH, Peterson DA and McIntosh GC (2005) Temporal entrainment of cognitive functions: musical mnemonics induce brain plasticity and oscillatory synchrony in neural networks underlying memory, Annals of the New York Academy of Sciences, 1060: 243-54.
3.
Peterson DA, Knight JN, Kirby MJ, Anderson CW, Thaut
MH. (2005) Feature selection and blind source separation in an EEG-based
brain-computer interface. EURASIP
Journal on Applied Signal Processing; Special Issue on Trends in Brain Computer
Interfaces 2005(19): 3128-3140.
4.
Peterson DA and Thaut MH. (2004) Model and feature selection in microarray classification, Proceedings
of the IEEE Symposium on Computational Intelligence in Bioinformatics and
Computational Biology (CIBCB), 56-60.
5.
Garrett D, Peterson DA, Anderson CW, and Thaut MH.
(2003) Comparison of linear, nonlinear, and feature selection methods for EEG
signal classification. IEEE Transactions on Neural Systems and
Rehabilitation Engineering 11(2) 141-144.
Background
I have bachelor’s degrees in engineering and
business from the University of Colorado at Boulder. The engineering degree is in Electrical and Computer Engineering
with an emphasis on software engineering.
The business degree emphasis is in Finance.
I spent several years in the information technology
industry, including internships with IBM and Motorola, brief stints at small
startups, and a longer stretch at Accenture (previously Andersen
Consulting). The broad exposure
provided by the network and management consulting I did at
Andersen Consulting strongly influenced the direction of my long-term research
goals. In a simplified sense, one can
view information technology as having three components: processing, distribution, and the human
interface. While great strides have
been made over the past few decades in the first two, relatively little
progress has been made in the human interface.
We have only a very limited understanding of how information gets into,
gets processed by, and back out of the human brain.
I believe that understanding and ultimately
interfacing with the human brain will require a strongly interdisciplinary
approach. Accordingly, I began the research phase of my career with a
customized, interdisciplinary PhD program.
I have drawn upon coursework and research experiences from several
disciplines, including computer science, mathematics, engineering, statistics,
psychology and neurobiology. Other students seeking elements of a custom,
interdisciplinary program in computational cognitive neuroscience at CSU have
found it helpful to review this list of courses I took.