454 Robert H. Flarsheim Hall,
5100 Rockhill Road
Kansas City, MO 64110
Our research group in 454 FH (CIBIT Lab) conducts research in biomedical signal analysis,
biometrics (physical and psychophysiological), and physiological system identification
using computational intelligence paradigms such as artificial neural networks.
Some recent projects include noninvasive brain computer interfacing, a new patented
biometric modality based on vasculature on the white of the eye, data-driven modeling
of human joints, and non-obtrusive psychophysiological pattern recognition using postural
and ocular dynamics. Please visit related pages for more information.
Some of the current projects in the CIBIT Lab are as follows.
Noninvasive brain computer interfacing
Jesee Sherwood ...
This project is funded by ...
Conjunctival Vascular Biometrics:
Conjunctiva is a thin, transparent, and moist tissue that covers the
white shell of the human eyeball and houses a wealth of fine
vasculature. For the first time, we have devised a patent-pending
biometrics modality based on these rich visible patterns. We have
introduced a new, convenient modality for eye-based biometrics.
Besides its ability as a standalone biometric system, conjunctival
vascular captures have the immediate benefit of adding precision and
security to the existing iris biometric systems. We conducted a
successful proof of the concept study, and we are currently in
process of studying the long term analysis on a larger population to
further study time-invariance, uniqueness, and universality of these
Pavan Tankasala is the graduate research assistant on this project.
Dynamic Simulation of Joints Using Multi-Scale Modeling, with Dr. Trent Guess (PI):
Dynamic loading of the knee is believed to play a significant
role in the development and progression of tissue wear disease and
injury. Macro level rigid body joint models provide insight into
joint loading, motion, and motor control. The computational
efficiency of these models facilitates dynamic simulation of
neuromusculoskeletal systems, but a major limitation is their
simplistic (or non-existent) representation of the non-linear, rate
dependent behavior of soft tissue structures. This limitation
prevents holistic computational approaches to investigating the
complex interactions of knee structures and tissues, a limitation
that hinders our understanding of the underlying mechanisms of knee
injury and disease.
The objective of this project is to develop validated neural
network models that reproduce the dynamic behavior of menisci-tibio-femoral
articulations and to demonstrate the utility of these models in a
musculoskeletal model of the leg. The specific aims of this study
Aim 1: Develop finite element (FE) models from micro-structure based
constitutive methods that bridge the nano-micro scale behavior at
the tissue level .
Aim 2: Develop neural network (NN) based models that learn from FE
simulation of dynamic behavior of menisci-tibio-femoral
Aim 3: Validate the NN models within a rigid body dynamic model of
a natural knee placed within a dynamic knee simulator.
Aim 4: Demonstrate the utility of the NN models by placing them
within a dynamic musculoskeletal model of the leg to study the
interdependencies of the menisci and other knee tissues.
Aim 5: Distribute the validated NN models of menisci-tibio-femoral
dynamic response and contact pressure for use in any rigid body
model of the knee or leg .
This project is funded by NSF.
Achieving Retention, Recruitment and Outreach With STEP (ARROWS), with Dr. Khosrow Sohraby (PI):
The School of Computing and Engineering (SCE) is an urban computer
science and engineering school at the University of Missouri-Kansas
City. The school lies within a school district with an 86% minority
student population, is 3 miles from a district where 89% of its
graduates attend 2 or 4 year postsecondary school and is five miles
from a school district with a 70% minority student population. What
do all of these school districts have in common? Few of their
students know that within a few miles of their high school is a
professional computer science and engineering school. All of these
districts have talented students, many of whom are enrolled in
technology related coursework.
Achieving Retention, Recruitment and Outreach With STEP (ARROWS) was
conceived after meeting with curriculum specialists at four local
school districts. These meetings identified a number of common needs
across the districts and resulted in the identification of several
objectives. These goals are mutually beneficial for all parties
involved and will be effective in increasing undergraduate
recruitment and retention in undergraduate engineering and computer
science programs at SCE. ARROWS is primarily a pre-college program
that will provide students and teachers a terrific overview of the
many varied careers computer scientists and engineers can pursue and
connects their curriculum with engineering application. Along with
School of Education co-investigators Drs. Arthur Odom and Donna
Russell, participating SCE faculty: Drs. Reza Derakhshani, Trent
Guess, Ganesh Thiagarajan, and Prem Uppuluri, have developed
integrated laboratory modules for use in this program.
This project is funded by NSF.
Brain Computer Interfacing and EEG
We are analyzing the performance of Time Delay Neural Networks
(TDNN) and Hidden Markov Models (HMM) for Electroencephalogram (EEG)
signal classification. The specific focus of this study is
Brain-Computer Interfacing (BCI), where near-real time detection of
underlying mental tasks during a multichannel EEG recording is
desired. We have found that HMM and TDNN to be better than the
rigid, one-size-fits-all methods of the more traditional EEG signal
classifiers. In a comparative study of our classifiers with the
reported best results on the BCI 2003 EEG benchmark dataset, our
HMM-based classifier surpassed the best reported results on dataset
Our other research efforts and interests include:
-Noninvasive liveness detection for biometrics
-Detection of affective-cognitive states from EEG and eye dynamics for computer emotional intelligence, biometrics, and deception detection
-Time series modeling for market prediction
-Theory of machine learning and hybrid intelligent systems
| || |