Asee peer logo

Optimized Signal/Image Feature Recognition For Machine Learning

Download Paper |

Conference

2002 Annual Conference

Location

Montreal, Canada

Publication Date

June 16, 2002

Start Date

June 16, 2002

End Date

June 19, 2002

ISSN

2153-5965

Conference Session

NSF Grantees Poster Session

Page Count

10

Page Numbers

7.902.1 - 7.902.10

DOI

10.18260/1-2--10625

Permanent URL

https://peer.asee.org/10625

Download Count

178

Request a correction

Paper Authors

author page

Sunanda Mitra

Download Paper |

Abstract
NOTE: The first page of text has been automatically extracted and included below in lieu of an abstract

Main Menu

Experimentation and Laboratory-Oriented Studies Division (DELOS), session number 1526. ID#2002-1954

ASEE Abstract Title: Optimized signal/image feature recognition for Machine Learning. NSF AWARD # 9980296, CRCD: Machine Learning: A Multidisciplinary Computer Engineering Graduate Program. Sunanda Mitra, Department of Electrical and Computer Engineering, Texas Tech University, Lubbock, Texas 79409. E-mail: Sunanda.Mitra@coe.ttu.edu.

Abstract

This paper describes some of the research projects, facilitating machine learning, completed by graduate students supported by the NSF-CRCD AWARD # 9980296 entitled “Machine Learning: A Multidisciplinary Computer Engineering Graduate Program ” to Texas Tech University. The program is now under development in parallel at Texas Tech and The University of Missouri at Rolla. As part of the curriculum development, courses were taught in adaptive optimization for signal processing, optimization in information theory and coding, adaptive pattern recognition, neural network s and adaptive critics, and mathematical methods and algorithms for signal processing. Thirty-five graduate students and twelve undergraduate students were significantly involved in both the research and educational activities associated with the program. Research activities were wide-ranging, and included optimized design of lossless and lossy compression for medical images, adaptive pattern recognition, segmentation, adaptive critic designs, Q-learning, optimized blind source separation, fuzzy modeling, and vector quantization. Three specific doctoral level projects involving optimization methods in signal/image processing leading to machine learning have been chosen for this paper since these projects included additional students at Master’s and senior undergraduate levels in Electrical and Computer Engineering demonstrating a successful pyramid learning structure using a top down approach. Significant collaboration with federal laboratories, industries, and other universities were developed during the design and development of the projects described in the paper.

Introduction

The design and development of three specific projects, on optimization in signal/image processing and providing significant contribution to machine learning through a pyramid l earning structure from senior undergraduate to doctoral level students involved in the projects, will be presented as a part of the NSF Showcase at the ASEE2002 annual meeting. The three chosen projects are:

1. Vadim Kustov, Ph.D. Dissertation, “Adaptive Filter Banks for Digital Signal Processors”, December, 2000.

2. Shuyu Yang, Ph.D. Dissertation, “Performance Analysis From Rate Distortion Theory of Wavelet Domain Vector Quantization Encoding”, December, 2002.

3. Zhanyu Ge, Ph.D. Dissertation, “ Automated Object Recognition by Reinforcement Learning ”, May 2002.

A number of Master’s degree candidates in Electrical Engineering, and B.S.E.E candidates were involved in each of the above doctoral dissertation projects.

Main Menu

Mitra, S. (2002, June), Optimized Signal/Image Feature Recognition For Machine Learning Paper presented at 2002 Annual Conference, Montreal, Canada. 10.18260/1-2--10625

ASEE holds the copyright on this document. It may be read by the public free of charge. Authors may archive their work on personal websites or in institutional repositories with the following citation: © 2002 American Society for Engineering Education. Other scholars may excerpt or quote from these materials with the same citation. When excerpting or quoting from Conference Proceedings, authors should, in addition to noting the ASEE copyright, list all the original authors and their institutions and name the host city of the conference. - Last updated April 1, 2015