Work

Intelligent Systems Approaches to Product Sound Quality Analysis

Year: 2013
Type: article
Abstract: As a product market becomes more competitive, consumers become more discriminating in the way in which they differentiate between engineered products.The consumer often makes a purchasing decision based on the sound emitted from the product during operation, by using the sound to judge quality or annoyance.Therefore, in recent years, many sound quality analysis tools have been developed to evaluate the consumer preference as it relates to a product sound and to quantify this preference based on objective measurements.This understanding can be used to direct a product design process in order to help differentiate the product from competitive products or to establish an impression on consumers regarding a product's quality or robustness.The sound quality process is typically a statistical tool that is used to model subjective preference, or merit score, based on objective measurements, or metrics.In this way, new product developments can be evaluated in an objective manner without the laborious process of gathering a sample population of consumers for subjective studies each time.The most common model used today is the Multiple Linear Regression (MLR), although recently non-linear Artificial Neural Network (ANN) approaches are gaining popularity.This dissertation will review publicly available published literature and present additional intelligent systems approaches that can be used to improve on the current sound quality process.The focus of this work is to address shortcomings in the current paired comparison approach to sound quality analysis.This research will propose a framework for an adaptive jury analysis approach as an alternative to the current Bradley-Terry model.The adaptive jury framework uses statistical hypothesis testing to focus on sound pairings that are most interesting and is expected to address some of the restrictions required by the Bradley-Terry model.It will also provide a more amicable framework for an intelligent systems approach.Next, an unsupervised jury clustering algorithm is used to identify and classify subgroups within a jury who have conflicting preferences.In addition, a nested Artificial Neural Network (ANN) architecture is developed to predict subjective preference based on objective sound quality metrics, in the presence of non-linear preferences.Finally, statistical decomposition and correlation algorithms are reviewed that can help an analyst establish a clear understanding of the variability of the product sounds used as inputs into the jury study and to identify correlations between preference scores and sound quality metrics in the presence of non-linearities.
Language: English
Open Access status: green
OpenAlex ID: W2520997425
FWCI: 0.511
Cites: 110
Cited by: 3
Related to: 10