+ All Categories
Home > Documents > Faculty Research Areas Labs/Centers Meetings

Faculty Research Areas Labs/Centers Meetings

Date post: 04-Feb-2016
Category:
Upload: declan
View: 29 times
Download: 0 times
Share this document with a friend
Description:
Faculty Research Areas Labs/Centers Meetings. Areas. Artificial Intelligence Bio-Informatics Databases Graphics, Image Processing and Multimedia Networks Pervasive Computing Software Engineering Systems and Architecture Security. Manfred Huber Farhad Kamangar Vassilis Athitsos - PowerPoint PPT Presentation
Popular Tags:
92
Fall 2010 1 Faculty Research Areas Labs/Centers Meetings
Transcript
Page 1: Faculty Research Areas Labs/Centers Meetings

Fall 2010 1

Faculty Research AreasLabs/Centers

Meetings

Page 2: Faculty Research Areas Labs/Centers Meetings

Fall 2010 2

Areas

Artificial Intelligence Bio-Informatics Databases Graphics, Image Processing and Multimedia Networks Pervasive Computing Software Engineering Systems and Architecture Security

Page 3: Faculty Research Areas Labs/Centers Meetings

Fall 2010 3

Artificial Intelligence

Manfred HuberFarhad KamangarVassilis AthitsosGian Luca Mariottini

Page 4: Faculty Research Areas Labs/Centers Meetings

Fall 2010 4

Manfred Huber

Research Projects• Personal Service Robots• Hierarchical Skill Acquisition• CONNECT - Information

Technologies for the Disabled

Contact: [email protected] (GACB114)

Page 5: Faculty Research Areas Labs/Centers Meetings

Fall 2010 5

Farhad Kamangar

Research Projects• Computer Vision• Neural Networks• Robotics• CONNECT - Information

Technologies for the Disabled

Contact: [email protected] (GACB

112)

Page 6: Faculty Research Areas Labs/Centers Meetings

Fall 2010 6

Bio-Informatics

Dr. Nikola Stojanovic301 Nedderman Hall

Phone: (817) 272-7627E-mail: [email protected]: http://ranger.uta.edu/~nick

Dr. Jean Gao338 Nedderman Hall

Phone: (817) 272-3628E-mail: [email protected]: http://crystal.uta.edu/~gao

Dr. Fillia MakedonDr. Heng HuangDr. Chris Ding

Page 7: Faculty Research Areas Labs/Centers Meetings

Fall 2010 7http://www.washbac.org/images/farside.gif

Page 8: Faculty Research Areas Labs/Centers Meetings

Fall 2010 8

What is BIOINFORMATICS? Have you ever thought that a cure for cancers could be

developed by people working at their computers?

Page 9: Faculty Research Areas Labs/Centers Meetings

Fall 2010 9

What is BIOINFORMATICS? Have you ever thought that a cure for cancers could be

developed by people working at their computers?

it will probably happen exactly that way

Page 10: Faculty Research Areas Labs/Centers Meetings

Fall 2010 10

What is BIOINFORMATICS? Have you ever thought that a cure for cancers could be

developed by people working at their computers?

Modern high-throughput technologies are generating tremendous volume of data - somebody needs to store and manipulate the data, generate reports and share them with the scientific community.

it will probably happen exactly that way

Page 11: Faculty Research Areas Labs/Centers Meetings

Fall 2010 11

What is BIOINFORMATICS? Have you ever thought that a cure for cancers could be

developed by people working at their computers?

Modern high-throughput technologies are generating tremendous volume of data - somebody needs to store and manipulate the data, generate reports and share them with the scientific community.

it will probably happen exactly that way

Page 12: Faculty Research Areas Labs/Centers Meetings

Fall 2010 12

What is BIOINFORMATICS? Have you ever thought that a cure for cancers could be

developed by people working at their computers?

Modern high-throughput technologies are generating tremendous volume of data - somebody needs to store and manipulate the data, generate reports and share them with the scientific community.

Can we turn that data into information, and eventually knowledge?

it will probably happen exactly that way

Page 13: Faculty Research Areas Labs/Centers Meetings

Fall 2010 13

What is BIOINFORMATICS? Have you ever thought that a cure for cancers could be

developed by people working at their computers?

Modern high-throughput technologies are generating tremendous volume of data - somebody needs to store and manipulate the data, generate reports and share them with the scientific community.

Can we turn that data into information, and eventually knowledge?

it will probably happen exactly that way

Page 14: Faculty Research Areas Labs/Centers Meetings

Fall 2010 14http://bioinformatics.ubc.ca/about/what_is_bioinformatics/

Page 15: Faculty Research Areas Labs/Centers Meetings

Fall 2010 15http://bioinformatics.ubc.ca/about/what_is_bioinformatics/

Page 16: Faculty Research Areas Labs/Centers Meetings

Fall 2010 16http://bioinformatics.ubc.ca/about/what_is_bioinformatics/

Page 17: Faculty Research Areas Labs/Centers Meetings

Fall 2010 17

Page 18: Faculty Research Areas Labs/Centers Meetings

Fall 2010 18

Biotechnology and pharmaceutical industry

Biotechnology and pharmaceutical industry revenues are estimated at hundreds of billions of dollars annually.

The industry's claim is that they spend $800 million on research & development for every new drug which receives FDA approval.

Much of the R&D efforts are pursued computationally these days.

Page 19: Faculty Research Areas Labs/Centers Meetings

Fall 2010 19

Biotechnology and pharmaceutical industry

Biotechnology and pharmaceutical industry revenues are estimated at hundreds of billions of dollars annually.

The industry's claim is that they spend $800 million on research & development for every new drug which receives FDA approval.

Much of the R&D efforts are pursued computationally these days.

This is a large and growing industry - whether in R&D or just software support, you may see yourself working for one of these companies in a few years.

Page 20: Faculty Research Areas Labs/Centers Meetings

Fall 2010 20

http://bioinformatics.uta.edu

Page 21: Faculty Research Areas Labs/Centers Meetings

Fall 2010 21

Bioinformatics lab projects Motif discovery in DNA sequences. Identification and characterization of mobile elements in

DNA. Studying structure and conservation patterns in genomic

sequences. Characterization of chromosomal recombination patterns. Studying human genetic variation and its relation to disease

susceptibility.

Page 22: Faculty Research Areas Labs/Centers Meetings

Fall 2010 22

Bioinformatics lab projects Motif discovery in DNA sequences. Identification and characterization of mobile elements in

DNA. Studying structure and conservation patterns in genomic

sequences. Characterization of chromosomal recombination patterns. Studying human genetic variation and its relation to disease

susceptibility.

Research funded by the National Institutes of Health, and preformed in collaboration with UTA Biology Department and the University of Texas Southwestern Medical Center in Dallas.

Page 23: Faculty Research Areas Labs/Centers Meetings

Fall 2010 23

UT Arlington

http://www.biotconf.org

Page 24: Faculty Research Areas Labs/Centers Meetings

Fall 2010 24

Databases

Sharma ChakravarthyRamez ElmasriLeonidas FegarasGautham DasChengkai Li

Page 25: Faculty Research Areas Labs/Centers Meetings

Fall 2010 25

Information Technology LaboratoryProf. Sharma ChakravarthyEmail: [email protected], URL: http://itlab.uta.edu/sharmaFunding Sources: NSF, Spawar, Rome Lab, ONR, DARPA, TI, MCC

Select Projects

InfoMosaic (information integration from heterogeneous sources)

MavEStream: (Event and Stream Processing)

Active Technology (Push Paradigm, pub/sub, event-driven architectures)

WebVigiL: (General Purpose Change Monitoring for the web)

Mining: Graph, Text, Assoc Rules

Prediction of Event Patterns

Information Search, Filtering, and classification

Information Security

Mobile Caching

Select Publications

1. 1. R. Adaikkalavan and S. Chakravarthy, Event Specification and Processing for Advanced Applications: Generalization and Formalization, DEXA Sep 2007

2. A. Telang, R. Mishra, and S. Chakravarthy, Ranking Issues for Information Integration, DBrank workshop (ICDE 2007), Turkey, 2007.

3. S. Savla and S. Chakravarthy, Efficient Main Memory Algorithms for Significant Episode Discovery, To appear in the Int’l Journal of Data warehousing and Mining, 2006.

4. R. Balachandran, S. Padmanabhan, S. Chakravarthy Enhanced DB-Subdue: Supporting Subtle Aspects of Graph Mining Using a Relational approach in PAKDD, 2006

5. A. Srinivasan, D. Bhatia, and S. Chakravarthy, Discovery of Interesting episodes in Sequence Data, in 21st ACM SAC, Data Mining Track, 2006.

6. M. Aery, S. Chakravarthy: eMailSift: Email Classification Based on Structure and Content in IEEE ICDM 2005

7. H. Kona, S. Chakravarthy, and A. Arora, SQL-Based Approach to Incremental Association Rule Mining, in ADBIS Workshop on DMKD, 2005.

8. Q. Jiang, R. Adaikkalavan and S. Chakravarthy, NFMi: An Inter-domain Network Fault Management System. IEEE ICDE, 2005.

9. R. Adaikkalavan, and S. Chakravarthy: Active Authorization Rules for Enforcing Role-Based Access Control and its Extensions, PDM Workshop, IEEE ICDE, 2005.

10. L. Elkhalifa, R. Adaikkalavan, and S. Chakravarthy, InfoFilter: A System for Expressive Pattern Specification and Detection Over Text Streams, ACM SAC, 2005.….

People

PhD Students –

Mr. Aditya Telang (Adi)Ms. Roochi Mishra

Masters Students –

Mr. Mayur MotgiMr. Supreet ChakravarthyMr. Aamir Syed

Group Meeting:

1 Pm to 2 Pm on Fridays in NH 232

Page 26: Faculty Research Areas Labs/Centers Meetings

Fall 2010 26

…Ground controller 1 Ground controller 2 Ground controller n

uav1

uav2 uav3

uav4

uav5

uav6

A Distributed Middleware-Based Architecture for Fault-Tolerant Computing Over Distributed repositories

Semi-joins Compression Replication Smart Routing

Page 27: Faculty Research Areas Labs/Centers Meetings

Fall 2010 27

Network of computing nodes:Unmanned vehicles, Sensors, Robots, PCs ,

Servers, Ground Controlling devices

Fault Tolerance Services

Fault Tolerance Services

Context/ Knowledge

Base

Context/ Knowledge

Base

Local fusion/Materiali

zation

Local fusion/Materiali

zation

Publish Subscribe Capability

Publish Subscribe Capability

Query Capability

Query Capability Raw Data / fused

data /data from other nodes

Queries, Tasks, Requests, Continuous Queries Publish/Subscribe

SOA Distributed MiddlewareTask planning Join computationComposition pub/subContext-aware NotificationResource Management Data management

Limited ResourcesMobilityHeterogeneityDisconnections

Page 28: Faculty Research Areas Labs/Centers Meetings

Fall 2010 28

Ramez ElmasriProfessor

DatabasesDistributed XML Querying and Caching

Object-Oriented DatabasesKeyword-based XML Query Processing

Sensor NetworksEnergy-Efficient Querying of Sensor

NetworksCombining RFID and Sensor Networks

Indexing of Sensor Networks Data

BioinformaticsModelling Complex Bioinformatics and

Biomedical DataMediators for Accessing Heterogeneous Data

Sources

Page 29: Faculty Research Areas Labs/Centers Meetings

Fall 2010 29

Leonidas FegarasAssociate Professor(PhD: UMass 1993)

Areas of interest: Databases

Web Databases and XML Object-Oriented Databases Query Processing and Optimization Data Management on Peer-to-Peer Systems

Programming Languages Functional Programming Program Optimization

Page 30: Faculty Research Areas Labs/Centers Meetings

Fall 2010 30

Research Review Gautam Das

Database Exploration Web/Information Retrieval searching techniques in

databases OLAP, Data Warehouse, Approximate Query Processing

Data Mining Clustering, Classification, Similarity models, Time-

Series Analysis Algorithms

Graph Algorithms, Computational Geometry

More information available athttp://ranger.uta.edu/~gdas/website/research.htm

Page 31: Faculty Research Areas Labs/Centers Meetings

Chengkai LiAssistant Professor http://ranger.uta.edu/~cli [email protected] The Innovative Database and Information Systems Research (IDIR) Lab

http://idir.uta.edu , GeoScience 237Jared Ashman, Avinash Bharadwaj, Ebrahim Cutlerywala, Sunny Hasan, Naeemul Hassan, Angus Helm, Nandish Jayaram, Pat Jangyodsuk, Xiaonan Li, Vikramark Singh, Ning Yan

Research AreasDatabases, Web Data Management, Information Retrieval, Data Mining

Specific Topics Data Retrieval and Exploration, Ranking and Top-k Queries; Web

Search/Mining/Integration, Web Databases, Query Processing and Optimization, OLAP and Data Warehousing, Cloud Computing, Database Testing, XML

Projects: Search the Database and Query the Web Computational Journalism DBTest: Database Application Testing Entity-Centric Enterprise Information Management BestCloud: Query Optimization for Cloud Computing RankSQL: Ranking and Top-k Queries, Database Exploration SetQuery: Set-Oriented OLAP Queries WebEQ: Querying and Exploring Structured Information on the Web

31

Page 32: Faculty Research Areas Labs/Centers Meetings

Two Demos from WebEQ project

Facetedpediahttp://idir.uta.edu/facetedpedia/

Entity-Relationship Querieshttp://idir.uta.edu/erq/

32

Page 33: Faculty Research Areas Labs/Centers Meetings

Fall 2010 33

Graphics Image Proc., Multimedia

Ishfaq AhmadMultimedia Authoring, Compression, CommunicationVideo Processing, Next Generation TVNetwork SecurityParallel Algorithms

Dr. Gutemberg Guerra-Filho

Computer Vision, Animation, and Humanoid Robotics

Page 34: Faculty Research Areas Labs/Centers Meetings

Fall 2010 34

Dr. Ahmad works closely with federal agencies, Arlington police and multimedia industry.

Several projects in power-aware video compression, multimedia systems, next generation TV are being pursued in his lab.

Prof. Ishfaq Ahmad

Page 35: Faculty Research Areas Labs/Centers Meetings

Fall 2010 35

High-Performance

Ishfaq Ahmad Resources Management in Parallel and Distributed SystemsPower Management in Data Center and Distributed Systems

Page 36: Faculty Research Areas Labs/Centers Meetings

Fall 2010 36

http://www.iris.uta.edu/

Institute for Research in Security (IRIS)

Ishfaq AhmadA Multi-disciplinary center focusing on infrastructure, people, and environmental security

Page 37: Faculty Research Areas Labs/Centers Meetings

Fall 2010 37

Networks

Sajal DasMohan KumarGergley ZarubaHao CheYonghe Liu

Page 38: Faculty Research Areas Labs/Centers Meetings

Fall 2010 38

Sajal K. DasCenter for Research in Wireless Mobility

and Networking (CReWMaN)

Sajal K. Das, Mohan Kumar Yonghe Liu, Hao Che

[email protected]

URL: http://crewman.uta.eduWoolf Hall 411,413,

Tel: 2-7409[Networking, Mobile Computing and Parallel Computing Research Group]

Page 39: Faculty Research Areas Labs/Centers Meetings

Fall 2010 39

Pervasive Computing Middleware Service creation, composition and deployment Prototype development Sensor networks and smart environments Information Fusion in pervasive/sensor environments

Uniform Information Access in Distributed, mobile and pervasive systems Caching, prefetching, and broadcasting Data management

Peer-to-Peer (P2P) Systems Information and service sharing Efficient communication and collaboration Security and privacy

Active and Overlay Networking Novel protocols Role in mobile, pervasive and P2P computing

Mohan KumarPervasive and Mobile ComputingSensor Systems

Recommended courses before

starting thesis work:

CSE5311, CSE5346,CSE5306 and CSE5347/5355

Directed Study

Page 40: Faculty Research Areas Labs/Centers Meetings

Fall 2010 40

Gergely Zaruba

Research Projects

Personal Area Networks

Heterogeneous Wireless NetworksArchitecture, Admission Control and Handoff

Optical NetworksOptical Burst Switching, Routing, QoS Provisioning

Traffic Modelling

Contact: [email protected] (GACB 112)

Page 41: Faculty Research Areas Labs/Centers Meetings

Fall 2010 41

Hao Che Embedded hardware/software design for NG

network processors Traffic engineering

Implementation issues and software development

MPLS path protection and fast rerouting Routing redundancy Traffic modeling for wireless networks

Contact: http://crystal.uta.edu/~hche/ [email protected]

Page 42: Faculty Research Areas Labs/Centers Meetings

Fall 2010 42

Yonghe Liu Sensor network and security

Prototyping and experimental study Theoretic design and analysis

Cross layer optimization Channel dependent performance

Software security Design and analysis

In need of Strong mathematic skill (probability/signal processing/number

theory/etc), or Strong programming skill (hardware/software)

Contact: http://ranger.uta.edu/~yonghe/

Page 43: Faculty Research Areas Labs/Centers Meetings

Fall 2010 43

Software Engineering

David KungYu LeiDr. Christoph CsallnerDavid Levine

Page 44: Faculty Research Areas Labs/Centers Meetings

Fall 2010 44

David Kung

Agent-Oriented Software Engineering Testing Object-Oriented Software Expert System for Design Patterns Formal Methods for Quality Assurance Fault Tolerance and Automatic Recovery

Using Dynamic Class Diversity

Contact: http://ranger.uta.edu/~kung/kung.html

Page 45: Faculty Research Areas Labs/Centers Meetings

Fall 2010 45

Yu Lei Concurrent and real-time software

systems Race analysis, Deterministic Execution

Environment, Reachability Testing, State Exploration-Based Verification

Automated software testing Object-Oriented Testing, Component-Based

Testing, Combinatorial Testing

Contact: http://ranger.uta.edu/~ylei

Page 46: Faculty Research Areas Labs/Centers Meetings

Fall 2010 46

David Levine, CSE@UTAProjects: (Computers applied to:) High Energy Physics, Bioinformatics, Medical Informatics, People with Disabilities, Streaming Processing, other..

David Levine High Throughput Computational Science: Clusters and Grids::

Page 47: Faculty Research Areas Labs/Centers Meetings

Fall 2010 47

Software EngineeringResearch Center

Faculty members:Dr. Christoph Csallner

Dr. Dave KungDr. Jeff Lei

Check out the lab: NH 246

Page 48: Faculty Research Areas Labs/Centers Meetings

Fall 2010 48

Page 49: Faculty Research Areas Labs/Centers Meetings

Fall 2010 49

Software Engineering

Software has become pervasive in modern society Directly contributes to quality of life Malfunctions cost billions of dollars every

year, and have severe consequences in a safe-critical environment

All about building quality software, especially for large-scale development Requirements, design, coding, testing,

maintenance, configuration, documentation, deployment, and etc.

Page 50: Faculty Research Areas Labs/Centers Meetings

Fall 2010 50

THE Best Job in America

What is the 2nd best job?

Go for a PhD in Software Engineering!!

Page 51: Faculty Research Areas Labs/Centers Meetings

Fall 2010 51

Great Impact

Page 52: Faculty Research Areas Labs/Centers Meetings

Fall 2010 52

Quotes from Dr. Parnas

Extracted from his ACM Fellow Profilehttp://www.sigsoft.org/SEN/parnas.html

Page 53: Faculty Research Areas Labs/Centers Meetings

Fall 2010 53

Current Research Projects

Object-Oriented Software Analysis and Testing (Dr. Kung)

Software Security Analysis and Testing (with Drs. Kung and Liu)

Pervasive Context-Aware Computing (with Dr. Kumar)

Formal Testing and Verification of Concurrent Software Systems (with GMU)

Automated Combinatorial Testing for Software (with National Institute of Standards and Technology)

Interaction Testing of Web Applications (with UMBC)

Page 54: Faculty Research Areas Labs/Centers Meetings

Fall 2010 54

Current Research Projects

Hybrid static-dynamic program analyses Automatic test case generators

JCrasher, Check ‘n’ Crash, DSD-Crasher New: Testing of database-centric applications

OrmCheck with ToDo: Support complex languages like UML

New: Dynamic symbolic invariant detector Pex/DySy with ToDo: Scale analysis to large applications ToDo: Add static knowledge to dynamic inference

Page 55: Faculty Research Areas Labs/Centers Meetings

Fall 2010 55

Page 56: Faculty Research Areas Labs/Centers Meetings

Fall 2010 56

If you want to improve..

..come talk to us

Page 57: Faculty Research Areas Labs/Centers Meetings

Fall 2010 57

Embedded Systems :: Roger Walker

Embedded Systems for Transportation Applications: Real-time Multi-core Systems for Embedded

Applications Stochastic Modeling From Sensor

Measurements Development of Special Measurement

Systems for Transportation Related Applications

Contact: http://ranger.uta.edu/~walker/

Page 58: Faculty Research Areas Labs/Centers Meetings

Design and Development of a Mobile Bridge

Monitoring/Measurement System

Integrate Data

Profiler

Gyroscope

ScanningLaser

Video

Video

VideoSurface

Data

SurfaceData

StructureData

Design and Development of a Mobile Bridge Monitoring/Measurement

System

Page 59: Faculty Research Areas Labs/Centers Meetings

Design and Development of Portable Real-Time Embedded Measure and Control Systems

Current Research Projects supported by Texas Department of Transportation, Federal Highway Administration, & Intel

Page 60: Faculty Research Areas Labs/Centers Meetings

Fall 2007 60

Donggang LiuMatt Wright

Information Security

Page 61: Faculty Research Areas Labs/Centers Meetings

Fall 2007 61

Jobs in Infosec

Page 62: Faculty Research Areas Labs/Centers Meetings

Fall 2007 62

One aspect of security

Operational Security Classified material can be

leaked based on how it’s used or through side effects

Domino’s Pizza Anyone?Last Wednesday, he adds, "we got a lot of orders, starting around midnight. We figured something was up." This time the news arrived quickly: Iraq's surprise invasion of Kuwait. "And Bomb the Anchovies", Time, p. 13,

8/13/90

Page 63: Faculty Research Areas Labs/Centers Meetings

Fall 2007 63

Border Security with WSNs

Website: http://isec.uta.edu/borde

r/

PIs: Donggang Liu, Sajal K. Das, Matthew WrightPost-Doc: Jun-Won HoStudents: Andy Fox, Na Li, Nabila Rahman, Mayank Raj, Kartik SiddhabathulaFunded in part by the National Science Foundation

Goal Intruder tracking

Intruders Corrupt many

sensors Jam wireless

channels Destroy key

infrastructure Seek gaps in the

sensing coverage

Page 64: Faculty Research Areas Labs/Centers Meetings

Fall 2007 64

Wireless and System Security :: Donggang LiuSecurity in wireless sensor

networks key management, security of services

such as localization, routing, clustering etc.

Integrity of wireless embedded devices Code integrity, tamper-resistant

techniques

Software and system security Security testing, detection of malicious

code

Contact: http://ranger.uta.edu/~dliu

Page 65: Faculty Research Areas Labs/Centers Meetings

Fall 2007 65

Matthew Wright

Internet Privacy

Robust P2P

Distributed Twitter

Sensors/Mobile/Social/Ubicomp …

Contact: http://isec.uta.edu/mwright

Page 66: Faculty Research Areas Labs/Centers Meetings

Fall 2010 66

Computer Science and Engineering DepartmentThe University of Texas at Arlington

Assist Laboratory

F. Kamangar, M. Huber, D. Levine, G. Zaruba

Page 67: Faculty Research Areas Labs/Centers Meetings

Fall 2010 67

Information Technologies for Persons with Disabilities and Health Care

• Assistance for Persons with Disabilities

• Communication devices and technologies• Intelligent assistive devices• IT for improved care

• Information Technologies for Healthcare and Aging

• Automatic health monitoring• Intelligent environments• IT to improve uniform communication needs

Page 68: Faculty Research Areas Labs/Centers Meetings

Fall 2010 68

Connect - Intelligent Communication Technologies for Disability & Health Care

ClientsHuman Service Providers

Technical support

Servers, Databases, Web pages

Wireless CommunicationProvider

Internet

ClientsHuman Service ProvidersHuman Service Providers

Technical supportTechnical support

Servers, Databases, Web pagesServers, Databases, Web pages

Wireless CommunicationProvider

Internet

• Intelligent communication services connect individuals with care providers and with important information • Seamlessly connected devices• Adaptive interfaces• Universal underlying

software architecture• Intelligent information

analysis and interpretation• Seamless, omnipresent

access to information

Page 69: Faculty Research Areas Labs/Centers Meetings

Fall 2010 69

Assistive Technologies

• Computer Technologies Can Enhance Assistive Devices• Ayuda – Intelligent wheelchair

• Autonomous navigation capabilities

• Environment sensing• Integration of computer control

and user instructions • Force feedback technologies to

enhance interaction capabilities for persons with physical disabilities

Page 70: Faculty Research Areas Labs/Centers Meetings

Fall 2010 70

Health Monitoring and Intelligent Environments for Aging in Place

• Wirelessly Connected Sensors Provide Health Information and can Improve Quality of Life• Health sensors can monitor conditions

and detect problems• Wireless communications permit

continuous monitoring• Prediction and modeling technologies

facilitate automatic analysis of the data• Communication technologies allow

connectivity to physician

• Sensors in the environment allow automation of important functions and assistance

• Monitoring and assistance for Aging in Place

Page 71: Faculty Research Areas Labs/Centers Meetings

Fall 2010 71

Computer Science and Engineering DepartmentThe University of Texas at Arlington

AI and Robotics Laboratory

M. Huber, F. Kamangar

Page 72: Faculty Research Areas Labs/Centers Meetings

Fall 2010 72

Adaptation and Learning in Robots and Computer Systems

• Personal Service Robots• Service robots have to interact with people• Programmability by unskilled users• Robustness in real world situations

• Variable Autonomy• Robots have to be easy to program • Robots should understand any kind of user command

• Cognitive Development• Computer systems have to learn how

to act and reason in the world

Page 73: Faculty Research Areas Labs/Centers Meetings

Fall 2010 73

Robot Imitation – Programming by Demonstration

• Learning to Sense• Imitating robots have to be able to interpret their observations

• Learning to Relate Human Demonstrations to Robot Actions

• Learning to extract the important aspects of human actions • Translating human actions into corresponding robot controls

• Learning to Interpret Task Requirements

• Robots have to be able to learn to ignore dangerous commands

Page 74: Faculty Research Areas Labs/Centers Meetings

Fall 2010 74

Hierarchical Skill Learning / Cognitive Development

• Learning Behavioral Strategies• Adaptation to unknown

conditions• Automatic extraction of

subtasks

• Hierarchical Learning• Learning with abstract actions• Learning using state

abstractions• Facilitation of incrementally

more complex behavior

Page 75: Faculty Research Areas Labs/Centers Meetings

Fall 2010 75

Robot Activities and Platforms

• Robot Soccer (RoboCup)• Autonomous robotic soccer with

robot dogs • Student team

• Computer Game Trials• UCT – Urban Combat Testbed

Page 76: Faculty Research Areas Labs/Centers Meetings

Fall 2010 76

The HERACLEIA Human Centered Computing Lab

HERACLEIA was a thriving outpost of Hellenic culture south of the Black Sea. Symbolizes a world where technologies are placed at the service of humans, esp. those needing special help, and bringing out the human side of technology.

Vicon Motion Capture System

Bioloid Robot

Vicon Camera

Peoplebot

SunSPOT Wireless

Sensor Node

Page 77: Faculty Research Areas Labs/Centers Meetings

Fall 2010 77

The HeracleiansFillia Makedon (Director)Professor Chair of Computer Science and Engineering Current work: Computational Multimedia Applications, Multimedia Authoring and Retrieval, Analysis of fMRI Brain Activations, and Electronic Commerce

Zhengyi Le (Assistant Director) Research Assistant ProfessorCurrent work: Security, Privacy, and Collaboration System

Kyungseo Park Academic Interests: Data Mining in Wireless Sensor Networks

Page 78: Faculty Research Areas Labs/Centers Meetings

Fall 2010 78

Some of our Security Work

Mobile Device Protection against Loss and Capture (PETRA09) Our forward secure two-party signature scheme provides stronger

device authentication to make it work against impersonation Privacy-Enhanced Opportunistic Networks (PSPAE09)

group mobile nodes together to randomly detour the traffic to protect from timing traffic analysis (which leads to privacy leakage)

Providing Location Privacy (PETRA08) use dynamic zone to mix some location records of some moving objects

to protect against tracking Source Location Privacy (SecureCom08)

hide event messages into maintenance messages so that an attacker can not track where an event is happening (if source location information is sensitive)

Preventing Unofficial Information Propagation (ICICS07) use short-lived certificates with forward secure signatures to make the information on a

certificate not verifiable shortly after usage Challenges

how to apply expensive (resource consuming) cryptosystems in mobile, portable, assistive devices (computationally limited)

faster encryption methods that a light mobile device can afford. anti-data-mining mechanisms and privacy preserving

technologies to address the increasing public concerns on privacy information leakage.

Page 79: Faculty Research Areas Labs/Centers Meetings

Fall 2010 79

Data Sharing: Open CollaborationSupport: Group, Role, File Sharing, Recommendation

Groups, Roles, Files Recommendations Group Operations

Files andaccesspolicies

Top 10 recommendations

Group name, Description andExpiration date

Roles andRequiredattributes

Page 80: Faculty Research Areas Labs/Centers Meetings

Fall 2010 80

Behavioral Markers: Making Genotype-Phenotype Correlations

Certain genetic anomalies lead to certain diseases/disabilities (phenotype is any demonstration of the conditions, such as a scan).

Understanding Genotype-Phenotype correlations may help create more effective treatments.

Challenges: How to correlate certain medical conditions with

observable behaviors or physiological conditions. How to use correlations to enhance decision making. How to analyze the effects of medical

treatments and adapt to patient

condition.

Deletion 9q34.3 syndrome 80

Page 81: Faculty Research Areas Labs/Centers Meetings

Fall 2010 81

@Home Apartment

Page 82: Faculty Research Areas Labs/Centers Meetings

Fall 2010 82

Active Service Robots

Approach: • robot investigates and prompts human to respond by keyboard, touch screen, or voice. • Human cancels/confirms alarm or no action. • Then robot makes a decision based on the available streams of sensor and human information using partial order Markov decision processes. Challenges: • Setting up the hierarchy of decision making to determine what level of action is appropriate by funneling the events of four different data streams into the partial order Markov decision process.• Able to access additional sensors to confirm the status of the human• Evaluating and testing the correctness of the decisions.

Yong Lin, Eric Becker, Kyungseo Park, Zhengyi Le, Fillia Makedon Decision Making in Assistive Environments using Multimodal Observations Proceedings of the 2nd International Conference on Pervasive Technologies Related to Assistive Environments (PETRA'09), Corfu, Greece, June 9-13, 2010.

Problem: When abnormal event occurs, how can a robot decide what to do?

Page 83: Faculty Research Areas Labs/Centers Meetings

Fall 2010 83

Conference Proceedings: ACM will be the publisher of the proceedings of the PETRA conference Selected papers will be in invited to the International Journal of Functional Informatics and Personalized Medicine, eJeta, and Journal of Personal and Ubiquitous Computing

WWW.PETRAE.ORGPETRA 2010

Page 84: Faculty Research Areas Labs/Centers Meetings

Fall 2010 84

Research at the Vision-Learning-Mining Lab

Vassilis Athitsos

University of Texas at Arlington

Page 85: Faculty Research Areas Labs/Centers Meetings

Fall 2010 85

American Sign Language

0.5-2 million users in the US. Complete and independent language.

Not a signed version of English.

Page 86: Faculty Research Areas Labs/Centers Meetings

Fall 2010 86

Looking Up a Sign

It is easy to go from an English word to ASL.

Page 87: Faculty Research Areas Labs/Centers Meetings

Fall 2010 87

Looking Up a Sign

It is easy to go from an English word to ASL.

It is hard to look up the meaning of a sign.

Page 88: Faculty Research Areas Labs/Centers Meetings

Fall 2010 88

Looking Up a Sign Our goal: automated

sign lookup. Input: video of a sign.

The user performs the sign in front of a camera.

Output: best matches in a database of 3000 signs.

Page 89: Faculty Research Areas Labs/Centers Meetings

Fall 2010 89

Research Directions

Challenging problems in vision, learning, database indexing. Large-scale motion-based video retrieval.

Need for developing novel atabase indexing methods

Efficient large-scale multiclass recognition.How can a computer learn to recognize 3000 signs?

Learning complex patterns from few examples.

Page 90: Faculty Research Areas Labs/Centers Meetings

Fall 2010 90

Object Detection

Page 91: Faculty Research Areas Labs/Centers Meetings

Fall 2010 91

Object Detection

Page 92: Faculty Research Areas Labs/Centers Meetings

Fall 2010 92

Parsing Satellite Images

Research goals: Accuracy. Efficiency.


Recommended