ITTC Project


Robust Classification Of Radar And Speech Signals Using A Fault-Tolerant Feed-Forward Neural Network

Project Award Date: 0000-00-00



Description

Over the past few years, feed-forward artificial neural networks (FANN) with large number of interconnections between the nodes in the adjacent layers have been successfully used in system classification problems. In this investigation, the performance of the FANN is tested in the presence of both system faults using noisy radar and speech signals. In the first part of the investigation, realistic time domain responses from five different aircraft are simulated, and a FANN is trained using the spectral samples of these responses. The network is then tested with noisy spectral samples as the links between the nodes get increasingly disconnected. It is found that the network can provide 94% success rate at a 10 dB SNR, even when 10% of its interconnections failed. A similar investigation is performed with the speech signal where a speaker is allowed to speak five different words, and the LPC coefficients of the time series are used to train a FANN. It is found that the network can provide 98% success at a SNR of 20 dB, even when 10% of its interconnections get disconnected. Thus, it appears that a properly trained FANN might be able to perform as a robust classifier in the presence of failures of its components.


Investigators




Partner with ITTC

The Information and Telecommunication Technology Center at the University of Kansas has developed several assistance policies that enhance interactions between the Center and local, Kansas, or national companies. 

ITTC assistance includes initial free consulting (normally one to five hours). If additional support is needed, ITTC will offer one of the following approaches: 

Sponsored Research Agreement

Individuals and organizations can enter into agreements with KUCR/ITTC and provide funds for sponsored research to be performed at ITTC with the assistance of faculty, staff and students.

Licensing and Royalty/Equity Agreement

An ITTC goal is the development of investment-grade technologies for transfer to, and marketing by, local, Kansas, and national businesses. To enhance this process, the Center has developed flexible policies that allow for licensing, royalty, and equity arrangements to meet both the needs of ITTC and the company.

Commercialization Development

Companies with a technology need that can be satisfied with ITTC's resources can look to us for assistance. We can develop a relationship with interested partners that will provide for the development of a technology suited for commercialization.

ITTC Resource Access

ITTC resources, including computers and software systems, may be made available to Kansas companies in accordance with the Center's mission and applicable Regents and University policies.

ITTC Calendar
There are no upcoming events at this time.