A neural network approach to the automated detection of acoustic annoyance in hard disk drives /

"Annoyance" in this research is defined as the reduction of

Bibliographic Details
Main Author: Faulkner, Darren Ray, 1970-
Format: Thesis eBook
Language:English
Published: [Place of publication not identified] : [publisher not identified] ; 1994.
Subjects:
Online Access:Link to OAKTrust copy
Description
Summary:"Annoyance" in this research is defined as the reduction of
analyzed and characterized using both time and frequency
annoyance in hard disk drives. The aim is to be able to
could not be found to predict the level of annoyance from
detect excessive annoyance as a quality test while still in
discussion is presented comparing the two methods and their
domain analysis. Literature suggested that magnitude, time
environment. This paper describes an artificial neural
equipment also brings added noise to the environment.
groups of annoying and not annoying. The Learning Vector
In order to increase efficiency, computing equipment in the
increase in efficiency is not optimized since the added
network based approach for automating the detection of
office environment is increasing rapidly. However, the
productivity due to the acoustic disturbance in the office
quantitative domain. First, the hard disk drive sounds were
Quantization and the Back Propagation algorithms were both
research is how to map subjective information to a
the effect of annoyance; however, a deterministic method
the manufacturing environment. The true question of this
this information. The hard drives were divided into two
training results.
used to train networks to perform this decision function. A
variance, and frequency combinations were all contributors to
Item Description:"Major subject: Electrical Engineering".
Vita.
Physical Description:x, 50 leaves : illustrations ; 28 cm.
Also available online.
Bibliography:Includes bibliographical references.