| |
| Home |
| People |
| Research Projects |
| Publications |
| REU Program |
| Demos |
| Senior Design Project |
| In The News |
| Photo Gallery |
| Calendar |
| Related Links |
| NSF Sponsors |
| |
|||||
| Current Research Projects | |||||
 Description: This project
addresses challenges posed by marine disasters caused by ships when
there is an accident that results in oil spills and destruction of
coastline and sea life. Oil spill prevention research is of primary
interest to the US Department of the Interior, especially after
events such as the 1989 Exxon Valdez spill, the subsequent enactment
of the Oil Pollution Act of 1990, and the BP Deepwater Horizon spill
in the Gulf of Mexico in April 2010. As the oceans’ fisheries,
biodiversity and other marine resources decrease, preventing oil
spills is a major economic issue affecting coastline communities,
offshore and natural gas development, many commercial enterprises
and the public. Read More... |
|||||
|
Software Controlled Devices for Psychological Monitoring and Rehabilitation Enhancement in Post-Stroke Depression |
|||||
|
|
|||||
|
ZPLAY: An Interactive User Interface System for Alzheimer's Intervention |
|||||
Description: Alzheimer's Disease (AD) is a neurological
affliction that impacts primarily the aged due to brain tissue
deterioration. It has been shown that this deterioration can be
slowed down by engaging the person with daily interactive activities
that include gaming, social interaction, memory exercises and
physical activity. The purpose of this project is to develop a
game-based user interface system which is designed to be web-based
and to provide intervention therapy for AD. ZPLAY has two versions:
the @lab version which is designed for diagnosis and used to measure
different brain activation responses of AD and the @home version
which is used to promote subject engagement and rehabilitation in a
home environment in-between visits to the clinic. Details |
|||||
|
CPLAY: An Intelligent HCI System for Neurological Disorder Assessment and Rehabilitation |
|||||
Description: The project will create an intelligent
human-computer interface system, CPLAY, that can be used for
assessment and rehabilitation of CP, a challenging neurological
disorder that can be greatly improved with the proposed system. CP
is one of the most common motor impairments in children caused by
injury to the developing brain from the prenatal period until age 5.
It affects motor control and coordination, making it difficult to
perform even the simplest tasks, such as standing still, breathing,
bladder and bowel control and eating. The proposed CPLAY system
offers an approach applicable to other types of neurological
disorders. Its front end is a computer game with varying levels of
complexity to provide controlled auditory and visual stimuli to
children with CP and thus facilitate a desired motor response that
can generate performance data for diagnosis and rehabilitation
treatment. Its back-end has advanced computational engines to
automate data logging (from child playing the game), data fusion,
analysis and decision support facilities. CPLAY is an open
development kit that can afford many enhancements. Details |
|||||
|
Development of a Next-Generation Multimodal Data Management Human-Sensing Instrument for Trustworthy Research Collaboration and Quality of Life Improvement.(NSF #0923494) |
|||||
|
Description: The aim of this
project is to develop an instrument (Zooscopion) that serves as an
interactive personal care and human activity monitoring center. It
allows for privacy-preserving and secure data sharing through
wireless connections with remote users in an assistive living
environment context with the aim to keep the person safe and as long
as possible at home with high quality of life. It will be composed
of interconnected modules that allow flexible development and
delivery and have a user friendly graphical interface. Different
users have different access privileges depending on their roles in
the given context. The Zooscopion (zScope) can connect devices,
humans, objects and the environment. It provides for mental and
emotional support and can connect to other assistive living
projects, thus making them interoperable. It will deliver a Digital
Library of sanitized research data and cases that have high
educational and training value.
|
|||||
|
Join Energy Project with Convia |
|||||
|
Description: The Heracliea Human
Centered Computing Laboratory and the University of Texas at
Arlington have a joint project through Facilities Management to
experiment with electrical load monitoring equipment from Convia.
(www.convia.com) The goal of the project is two-fold: First, to
investigate the technology and its software for the energy usage of
the laboratory. Second, a subset of the monitors in the laboratory
can be designated for the simulated apartment, to do an additional
energy usage project for assistive living.
|
|||||
|
Computing Infrastructure for Smart Appliance Utilization and Secure Data Sharing for Energy Consumption Optimization |
|||||
|
Description: The purpose of this
project is to build an advanced computational research
infrastructure for sustainable energy that is based on extending our
NSF-funded work in recommendation systems and provides
recommendations to users as to how to use energy. The infrastructure
includes smart metering, visualization, privacy, security and
simulation facilities. It will deliver new tools and test data for
researchers to explore energy consumption optimization further. We
call this system ENERGY ANGEL or ENAN for short. This is both a
technical and a human factor problem. To engage users, it is
important to show them alternative ways of saving energy through
smart metering and a combination of recommendation system
technologies to help them make good decisions. Smart metering works
with efficient remote mechanisms that automatically analyze
consumption data, the quality and type of energy provided, supply
interruptions and user preferences, as they fluctuate with market
changes. When a user is able to access such information, he builds
trust, wishes to collaborate and learn more about how to save energy
and money. Using easy-to-understand and clear information the user
can work with interactive user interfaces to express preferences and
also combine different user operations.
|
|||||
|
Strengthening Human-Robot Interaction by Acoustical Implicit Communication |
|||||
| Participants: Yates Yong Lin | |||||
|
Description: Speaker Recognition
is a technique originated in the 1970s. The main techniques used to
identify speakers include 1) feature selection and extraction:
Spectrum, Linear Prediction Code (LPC), Mel-Cepstrum Coefficient
(mfcc), Pitch, Prosodic, Formants, Phonetics; 2) Classification
Algorithms: DTW, VQ, GMM, HMM, SVM, LDA, etc.
Detail...
|
|||||
|
Abnormal Human Activity Detection Using Wireless Sensor Networks |
|||||
| Participants: Kyungseo Park, Yong Lin, Jyothi Vinjumur | |||||
|
Description: Using wireless sensor
networks, we would like to detect abnormal human activity for the
elderly who lives alone. Related techniques include Euclidean
distance search, scoring function, top-k ranking, decision boundary,
and longest common subsequences.
Detail...
|
|||||
|
Assistive Room Activity Analyzer |
|||||
| Participants: Scott Phan, Roman Arora, Eric Becker | |||||
|
Description: The Assistive Room
Activity Analyzer (ARAA) is a tool for the development of
experiments involving event and activity recognition in assistive
environments. The application is designed to simplify the design of
assistive environment workspaces and the analysis of algorithms on
real data sets. A variety of functionality in the form of panels and
buttons is provided, which include functionality to design an
experiment, set sensor configurations, capture and record data, and
finally evaluate the results against different metrics and
algorithms.(Download: Doc)
|
|||||
|
CoroBot Speaker Recognition |
|||||
| Participants: Kapil Vyas, Yong Lin | |||||
|
Description: Speaker Recognition
algorithm developed by Lin can tell the difference between one
speaker and another to about 70% accuracy. Lin says, “The algorithm
has never been tested on a platform, and this is exactly what we
want to do.” Heracleia’s goal: show case the algorithm on Coroware’s
CoroBot. When a bunch of speakers talk to the CoroBot in
listen-mode, it will only behave to one speaker’s voice – perhaps
this could be the owner. The idea is to demo a new kind of
authentication system. One based on voice.
Detail...
|
|||||
|
Room Finder |
|||||
| Participants: Kapil Vyas, Ganesh Palaniappan | |||||
|
Description: In an Assistive
environment, the need to willfully command a robot to come to some
locality is a priority. This requires the robot to have knowledge of
its environment. Robots equipped with expensive laser range finder
(LRF) stand out from all others, in that they can build maps with a
fair amount of precision. Heracleia´s goal is to use its
PeopleBot to allow clients give orders like: “Come to the
kitchen” via voice or pressing a button. In the pre-processing
step, PeopleBot will navigate to create a floor plan. Next, users
can set room names that the robot will move to, when asked.
Detail...
|
|||||
|
Assistive Monitoring Project |
|||||
 The main purpose of
assistive monitoring is to do the lab surveillance remotely. In the
modern world, security is given foremost importance and priority.
Through this project, it is possible to capture the movement in the
lab as video during motion detection, snapshots are also taken. The
video recorded during motion detect is saved in archive for future
reference too. Both live and recorded video can be viewed remotely
through internet when logged on using authorized credentials. Detail... |
|||||
|
@Home Assistive Living Apartment |
|||||
 The @Home Ambient Assistive Living Apartment,
“@Home” or “The Apartment” for short, is a
testbed of sensors and furniture in a model apartment to develop
experiments, algorithms, and procedures for recognizing human
activity without the use of cameras. Multiple researchers are
working on various fields from programming sensor motes to
developing theoretical robotic responses for Human interaction. The
goal is to develop a deployable wireless sensor network, the
infrastructure needed to handle the data, and then to have usable
applications that has the sensor data streams as input.Detail... |
|||||
|
|
|||||
|
Open Collaboration |
|||||
|
|
|||||
|
Secure Content Exchange Negotiation System |
|||||
 Data sharing
of sensitive or highly valuable informational resources requires new
models of negotiation to promote communication with built-in
incentives, Secure authentication, new metadata standards and new
metrics of evaluation. SCENS, a Secure Content Exchange Negotiation
System, is a system we have been building to enable the exchange or
sharing of private (sensitive) multimodal digital data that reside
in distributed digital repositories. These data may include raw
data, derived data, tools, methods or services.
Detail... |
|||||
|
Localization algorithm and its application: |
|||||
|
Localization (Fig.1) provides fundamental support for
location-aware applications and protocols in wireless sensor
networks with mobile and static nodes. |
|||||
|
Privacy in Sensor Networks |
|||||
Sensor networks are used in many realtime applications for collecting information from monitored environments and objects, such as vehicle tracking, battlefield reconnaissance, and habitat monitoring. Following the increasingly wide deployment of sensor networks, privacy concerns have emerged as an obstacle. Source location protection in sensor networks becomes a very important problem when a sensor network is used in monitoring valuable assets or the source is a sensitive object.We propose a new concept, the cyclic entrapment method (CEM), to preserve the performance advantage of shortest path routing while also protecting the location of a source. |
|||||
|
Detecting Attacks in
Recommender Systems
|
|||||
|
|
|||||
| Other Research Area: | |||||
| Computational Multimedia Applications, Multimedia Authoring and Retrieval, Analysis of fMRI Brain Activations, and Electronic Commerce. | |||||
An Open Environment (OE)
is an electronic domain in which multiple entities need to interact
but do not necessarily have complete knowledge of each other. In
this setting, OC (Open Collaboration), a tool being developed to
support a variety of electronic collaboration needs, may be useful.
OC is built on the open-source JXTA toolkits. Group and role
information is propagated in a peer-to-peer fashion, and peers can
share files to any peer who is a member of an appropriate group or
role. 
Information
overload has become a problem in data sharing and collaboration: the
amount of information users must sift through has reached the point
where it is overwhelming. Recommender systems help people deal with
information overload and provide them with personalized
recommendations, content, and services. Because recommender systems
are dependent on external sources of information, they are
vulnerable to recommendation attacks. In these attacks, attackers
influence a recommender system in a manner advantageous to them by
introducing biased ratings. We have developed a series of approaches
to detect a diverse and general set of recommendation attacks and
demonstrate their effectiveness with data.