TY - JOUR
T1 - GA-optimized support vector regression for an improved emotional state estimation model
AU - Ahn, Hyunchul
AU - Kim, Seongjin
AU - Kim, Jae Kyeong
N1 - Copyright:
Copyright 2014 Elsevier B.V., All rights reserved.
PY - 2014/6/27
Y1 - 2014/6/27
N2 - In order to implement interactive and personalized Web services properly, it is necessary to understand the tangible and intangible responses of the users and to recognize their emotional states. Recently, some studies have attempted to build emotional state estimation models based on facial expressions. Most of these studies have applied multiple regression analysis (MRA), artificial neural network (ANN), and support vector regression (SVR) as the prediction algorithm, but the prediction accuracies have been relatively low. In order to improve the prediction performance of the emotion prediction model, we propose a novel SVR model that is optimized using a genetic algorithm (GA). Our proposed algorithm-GASVR-is designed to optimize the kernel parameters and the feature subsets of SVRs in order to predict the levels of two aspects-valence and arousal-of the emotions of the users. In order to validate the usefulness of GASVR, we collected a real-world data set of facial responses and emotional states via a survey. We applied GASVR and other algorithms including MRA, ANN, and conventional SVR to the data set. Finally, we found that GASVR outperformed all of the comparative algorithms in the prediction of the valence and arousal levels.
AB - In order to implement interactive and personalized Web services properly, it is necessary to understand the tangible and intangible responses of the users and to recognize their emotional states. Recently, some studies have attempted to build emotional state estimation models based on facial expressions. Most of these studies have applied multiple regression analysis (MRA), artificial neural network (ANN), and support vector regression (SVR) as the prediction algorithm, but the prediction accuracies have been relatively low. In order to improve the prediction performance of the emotion prediction model, we propose a novel SVR model that is optimized using a genetic algorithm (GA). Our proposed algorithm-GASVR-is designed to optimize the kernel parameters and the feature subsets of SVRs in order to predict the levels of two aspects-valence and arousal-of the emotions of the users. In order to validate the usefulness of GASVR, we collected a real-world data set of facial responses and emotional states via a survey. We applied GASVR and other algorithms including MRA, ANN, and conventional SVR to the data set. Finally, we found that GASVR outperformed all of the comparative algorithms in the prediction of the valence and arousal levels.
KW - Emotional state estimation
KW - Genetic Algorithm
KW - Support Vector Regression
UR - http://www.scopus.com/inward/record.url?scp=84903542920&partnerID=8YFLogxK
U2 - 10.3837/tiis.2014.06.014
DO - 10.3837/tiis.2014.06.014
M3 - Article
AN - SCOPUS:84903542920
SN - 1976-7277
VL - 8
SP - 2056
EP - 2069
JO - KSII Transactions on Internet and Information Systems
JF - KSII Transactions on Internet and Information Systems
IS - 6
ER -