Last Updated: 1/21/2004

 

Curriculum Vita

TAEK MU KWON, Ph.D.

 

 

Office Address: ECE Dept. 271 MWAH, 10 University   Dr., Duluth, MN 55812

Phone: Office (218) 726-8211; Fax: (218) 726-7267 

Citizenship: U.S.A.                  

Email: tkwon@d.umn.edu

Home Page URL: http://www.d.umn.edu/~tkwon

 

 

 

 

 

EDUCATION

 

      Dissertation: An Elementary Processor for a Digital Neural Computer.

            Thesis: Consonant Recognition Using Linear Predictive Coding.

 

PROFESSIONAL EXPERIENCE

 

 

 

 

 

Consulting

 

 

RECENT RESEARCH PROJECTS

 

US DOT IVI (Intelligent Vehicles Initiative) Specialty Vehicle Field Operational Test

 

The project team is comprised of Mn/DOT, the University of Minnesota, 3M, who provides a magnetic based lateral guidance system, Navistar, a supplier of medium and heavy duty trucks, and Altra Technologies, an Eden Prairie, MN, based provider of radar based collision warning system. The project goal is to develop an optimized user interface integrating both vehicle guidance and collision avoidance technologies and to document the safety and performance benefits associated with such systems by performing a field operational test. My role in this project is to evaluate motorist’s visibility through weather sensor network and video images collected during the test period. This project was funded by multiple agencies including US DOT, Mn/DOT and private sectors with total funding of exceeding six million dollars.

 

 

Northland Advanced Transportation Systems Research Lab (NATSRL)

 

The geographical location of the Duluth and Northern Minnesota area presents unique challenges in operating and maintaining the area-wide transportation systems, which need to provide safe and efficient travel environment under often inclement weather conditions. NATSRL was funded to address various research needs for Northland transportation systems. The research issues include efficient real-time detection of hazardous road/weather/traffic conditions, advance warning and guidance to drivers with road/weather/traffic information, winter-road and snowplow fleet management and decision support system with on-line weather/pavement information, large-scale even and tourist traffic management, and on/off-line assessment of area-wide system performance. This project was funded by US DOT TEA-21, Mn/DOT, and UMD. $3,700,000.

 

 

TMC Traffic Data Automation For Mn/DOT’s Traffic Monitoring Program

 

The Minnesota Department of Transportation (Mn/DOT) has been responsible for collecting, analyzing, and publishing traffic count data from the various roadway systems throughout the state. The traffic reporting system mainly developed by the Traffic Forecasting and Analysis Section (TFAS) of Mn/DOT has been used in several federal programs, internal Mn/DOT applications, and many private sectors.  The objective of this project is to develop computerized automation methods for the current manual effort to import, filter, and analyze the Mn/DOT TMC portion of inductive loop detector data contributed to the Mn/DOT's Traffic Monitoring System. The main research effort has been in developing multi-level data screening and analysis methods based prioritized acceptance tests and Q-K curve analysis. This project was sponsored by Mn/DOT Guide Star Program. $80,000.

 

Visibility Measurement System Based-on Imaging

 

This research project is focused on developing a practical atmospheric-visibility monitoring system based on imaging systems. Because visibility reductions due to inclement weather conditions are one of the main causes of traffic incidents, and among the primary criteria used to determine road closures in winter, accurate visibility measurement is an important area of research for transportation managers. However, accurate and reliable measurement of atmospheric visibility is difficult because it continuously changes over time and space and is influenced by a host of atmospheric conditions such as fog, rain, snow, smog, sun direction, solar radiation, etc. Measurement by human observers is unreliable due to differences in individual eyesight, perception and other biological conditions. Other techniques such as light-scatter meters exist, but do not measure true visibility. A new approach developed in this research is based on measurement of visibility through an imaging system that comprises a special video camera, an image digitizer and multiple targets specifically designed and positioned at specific distances from the camera. The images are regularly sampled and processed through image processing techniques to determine at what distance the foreground is no longer distinguishable from the background by using the contrast information of the field of view extracted from the image. This distance essentially represents the visibility. For night visibility measurement, several approaches are under investigation. Those include embedding light sources in visual and infrared spectrum to the targets and using different types of spectral filters in camera. This research was sponsored by US DOT TEA-21 and Mn/DOT.

 

 

Next-Generation Road Weather Information System: Concept and Proto Type Development

 

Traditional ways of using R/WIS (Road/Weather Information System) have been to forecast road icing before its formation for proactive winter-road maintenance. Although ice forecasting has served a significant value in deicing operations, as states plan implementation of a statewide R/WIS, they recognize that it is a large, expensive system. Moreover, due to rapidly changing technologies and associated increasing costs, implementation of R/WIS has been complex. Planners find that it is important to start with an architecture that allows easy integration of new and legacy technologies and gradual expansion to a larger system. This project develops a flexible R/WIS model that can seamlessly integrate with the existing and legacy systems and can gradually expand to a larger system. The research also focuses on new ways of utilizing the massive amount of environmental sensor data collected from R/WIS. This research was sponsored by Mn/DOT.

 

Web-Based Pavement Condition Reporting System

 

Pavement Condition Reporting System (PCRS) is a Mn/DOT’s networked application system that tracks and reports weather circumstances that may affect the driving conditions.  The system was designed based on a database server and customized front-end programs that allow data entry and retrieval.  The main problem of this system was the customized front-end programs that require modification of codes as the windows operating systems are upgraded; consequently, the system did not work as Mn/DOT upgraded their operating system. However, even if the old software was rewritten for new operating systems with extra budget, modification of the front- end programs required reinstallation of the codes in every client workstations in order for the Mn/DOT PCRS to work properly. In order to alleviate the problems associated with the old PCRS and to further advance the PCRS technology, Mn/DOT decided to implement a new PCRS based on a World Wide Web (web) technology.  In this new approach, any Mn/DOT person having a standard web browser and a password will have access to the PCRS for all of its functions. This project was given to Dr. Kwon and his students at the University of Minnesota Duluth, and they successfully developed a new system, referred to as a web-PCRS, using the state-of-the-art dynamic web technologies. The system is driven by a web server and a central relational database, and includes various forms of pavement-condition data entry, real-time notification, instant messaging between PCRS operators and administrators, weather/permit entry, and many administrative functions. This project was funded by Mn/DOT, and the system developed was deployed statewide.

 

 

Research Interests

 

In the past, my research was mainly focused on developing algorithms in neural networks, fuzzy systems, pattern recognition, and image processing. Presently, my research is more focused on developing transportation applications using my computational and theoretical backgrounds. The topics include development of visibility measurement algorithms using image processing, next generation road weather information systems, large scaled transportation data center, large-scaled transportation data archival/retrieval systems, distributed server farm design, detector data screening and quality management, and automated bridge deicing systems.

 

PROFESSIONAL AFFILIATIONS AND ACTIVITIES

 

  Associate Editor of the International Journal on Intelligent Automation and Soft  

  Computing, Since 1997.

  Member of IEEE Computer Society

  Member of IEEE Systems, Man, and Cybernetics Society

  Member of International Neural Network Society

  Member of KSEA (Korean Scientists and Engineers Association in America)

  Reviewer of IEEE Transactions on Signal Processing

  Reviewer of IEEE Transactions on Image Processing

  Reviewer of IEEE Transactions on Neural Networks

  Reviewer of IEEE Transactions on Circuits and Systems

        Reviewer of IEEE Transactions on Fuzzy Systems  

        

HONORS

 

 

PATENTS

 

“Measurement of Motorist’s Relative Visibility Index (MRVI) Using Video Images,” US Patent Pending, 2001.

 

“Video Camera-Based Visibility Measurement system,” US Patent Pending, Docket: 600.374-US-01, 1999.

 “Artificial Neural network Based Algorithms in Detecting Financial Reporting,” with E. Feroz, U.S. Patent Pending, 1999.

 

 

TEACHING EXPERIENCE

 

A. Courses regularly taught at University of Minnesota Duluth

 

            ECE 4321 (ECE 3520):  Computer Networks

            ECE 4801 (ECE 5800):  Introduction to Artificial Neural Networks

            ECE 4315 (ECE 3515):  Multiprocessor-Based System Design

            ECE 2325 (ECE 3325):  Microcomputer System Design

 

      B. Other courses taught in the past at UMD

 

            ECE 1315        Digital System Design

            ECE 5580        Computer Fault Tolerance

            ECE 5551        Switching Theory

            ECE 3950        Design Workshop

            CpE 3040        Digital System Design

            CpE 3020        Introduction to Electronics

            CpE 3035        Analog Electronic Circuits

            CpE 3970        Senior Project I

            CpE 3971        Senior Project II

            CpE 3960        Independent Study

            CpE 5960        Independent Study 

 

   C. Courses taught at the Florida Institute of Technology (1985-1988)

           

CP 4193          Computer Systems Design

            CP 4291          Computer Interfacing Lab

            EE 4196           Electronic Circuit Lab

 

LAB MANUALS WRITTEN

 

            University of Minnesota, Duluth:

                       

            ECE 3950 Computer Construction Manual

            CpE 3040 Digital System Design Lab

            ECE 3325 Introduction to Microcomputers Lab

 

 

            Florida Institute of Technology:

 

            CP 4291 Computer Interfacing Lab

            CP 4193 Computer Systems Design Lab

 

 

 

TEACHING LAB RELATED DEVELOPMENTS

 

§         Developed Computer Networks Lab in Room 61 MWAH. The design goal of this lab was to provide students with hands-on network experiments that reflect real-world networks in a smaller scale. The lab was innovatively designed to address multi-layered architecture of computer networks covering from wiring to network operating systems. The experiments include 10M and 100M bps Ethernet wiring and wiring closet design, standard wiring conformance testing and use of testing equipments, implementation of network equipments (hubs, routers, bridges), client-server installations, network performance monitoring, remote file sharing, and server management (web, printer, database). 1999-Present. 

 

§         Developed several neural network simulators for UNIX and Windows environments. The simulators include back-propagationnetwork, Kohonen's self-organizing feature map, simulated annealing, Hopfield networks, Radial Basis Function Networks, Support Vector Machines, and graphical tools. They were used in CpE 5800 and ECE4801: Introduction to Neural Networks. 1993-Present.

 

§         Developed Microcomputer Lab based on a SPARC station, a SUN Network Terminal Server (64 terminals), and single board computers (M68HC11EVBs), for basic computer engineering courses. Each station includes an interface card that was designed for various hardware and software experiments. It was used ECE 3325: Introduction to Microcomputers.

 

§         Designed Computer Interface Lab and the Computer Systems Lab at the Florida Institute of Technology. Both labs were designed using MC68000 family chips, MEX68KECBs, and many interface I/O boards. In addition, an EPROM programmer was designed and integrated to the system to provide a development environment to students. 1987.

 

§         Designed and constructed several computer systems based on MC68000 family for development of computer design courses and as a development and testing tool for microprocessor-based system designs. The system includes many types of I/O ports and an EPROM burner for testing and implementation of BIOS and I/O’s in microprocessor-embedded systems. The systems were used as a development system for CpE 3950: Design Workshop/Computer Construction at University of Minnesota Duluth, and for CP 4193: Computer Systems Design at Florida Institute of Technology. 1986-1992.

 

§         Designed and constructed a 16-bit microprocessor using bit-slice computers. It was used as an experimental station for micro-programmed computer architecture and instruction design. 1988.

 

COMMITTEES (UMD)

 

§         McKnight Professor Search Committee, Chair

§         ECE Department Merit Evaluation Policy, Chair

§         College of Science Executive Committee

§         ECE Faculty Search Committees

§         Senior Project Policy Committee

§         CSE Single Quarter Leave Committee

§         Faculty Information Record Committee, Chair

 

 

 

RESEARCH GRANTS

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

PUBLICATIONS

 

A. Books or Chapters in Books

 

 

 

 

 

 

 

 

B. Papers in Refereed Journals

 

 

 

 

 

 

 

§         T. M. Kwon and E. Feroz,  “A Multi-layered Perceptron Approach to Prediction of the SEC's Investigation Targets,” IEEE Trans. on Neural Networks, vol. 7, no. 5, pp. 1286 - 1290, Sep. 1996

 

 

§         M. J. Patyra and T. M. Kwon, “A Degenerated Fuzzy-Number Processing System Based on Artificial Neural Networks,” Information Science, vol. 86, pp. 211-226, 1995.

 

§         M. E. Zervakis, T. M. Kwon, and J. Yang ``Multiresolution Image Restoration in the Wavelet Domain,'' IEEE Trans. on Circuits and Systems II: Analog and Digital Signal Processing, vol. 42, No. 9, pp. 578-591, Sep. 1995.

 

§         M. E. Zervakis, A. K. Katsaggelos, and T. M. Kwon, ``A Class of Robust Entropic Functionals for the Enhancement of Images,'' IEEE Trans. on Image Processing, vol. 4, No 6, pp. 752-773, June, 1995.

 

§         T. M. Kwon and M. E. Zervakis, ``KWTA Networks and Their Applications,'' International Journal on Multidimensional Systems and Signal Processing, vol. 6, pp. 331-344, 1995.

 

§         T. M. Kwon, M. E. Zervakis, and A. N. Venetsanopoulos, “Design and Analysis of a Class of Self-Organizing and Trainable Fuzzy Controllers,” Journal of Intelligent and Robotic Systems, vol. 12, pp. 1-15, 1995. 

 

 

§         T. M. Kwon and M. E. Zervakis, “A Self-Organizing KNN-Fuzzy Controller and Its Neural Network Structure,” International Journal of Adaptive Control and Signal Processing, vol. 8, pp. 407-431, Jul.-Aug., 1994.

 

§         J-S Yang, M. E. Zervakis, and T. M. Kwon, “Application of the Quantitative Feedback Theory (QFT) to the Grumman F-14 Pitch Axis ControlProblem,” Computers in Education Journal, vol. IV, no. 3,  pp. 75 - 81, Jul. - Sep. 1994.

 

 

C. Conference Papers

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

§         T. M. Kwon, “Gaussian Perceptron: Experimental Results,” Proc. of the International Conference on Systems, Man, and Cybernetics, vol. 3, pp. 1593-1598, Charlottesville, VA, Oct. 1991.

 

 

 

 

 

 

 

 

 

D. Technical Manuals

 

 

 

 

 

E. Others


INVITED SEMINARS

 

           

SUPERVISION OF UNDERGRADUATE RESEARCH OPPORTUNITY PROJECTS (UROP)