Deriving the relationship between user satisfaction on engine sounds and affective variable sets based on classification algorithms

• Published in: 2014 IEEE International Conference on Industrial Engineering and Engineering Management pp. 1310 - 1313
• Main Authors: Kim, W. J., Kim, G. W., Lee, Y. S., Yun, M. H.
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.12.2014
• Subjects: Accuracy; classification algorithm; Classification algorithms; Emotion prediction; engine sounds; Engines; Logistics; Neurons; Prediction algorithms; product sounds; user satisfaction; Vehicles
• DOI: 10.1109/IEEM.2014.7058850
• ISSN: 2157-3611

This study aims to extract the most relevant set consisted of affective variables to the level of user satisfaction on engine sounds using classification algorithm. The affective variables for engine sounds were defined by three axes, and two classification algorithms were used to determine the prediction accuracy for those affective axes. The study was consisted of three phases: 1) extracting sets of affective variables and the level of satisfaction on engine sounds, 2) preprocessing of engine sounds and experiment design, and 3) analysis of the most relevant sets of affective variables to user satisfaction. As a result, PA (Powerful-Affective) variable set showed the highest prediction accuracy of user satisfaction compared to other sets. Predicting the level of satisfaction based on classification algorithm could help to generalize the relationship between user satisfaction and affective variables more easily, beyond the limitation with a small size of subjects.