• Healthcare Informatics Research
• /
• v.24 no.4
• /
• pp.309-316
• /
• 2018

Objectives: Both the valence and arousal components of affect are important considerations when managing mental healthcare because they are associated with affective and physiological responses. Research on arousal and valence analysis, which uses images, texts, and physiological signals that employ deep learning, is actively underway; research investigating how to improve the recognition rate is needed. The goal of this research was to design a deep learning framework and model to classify arousal and valence, indicating positive and negative degrees of emotion as high or low. Methods: The proposed arousal and valence classification model to analyze the affective state was tested using data from 40 channels provided by a dataset for emotion analysis using electrocardiography (EEG), physiological, and video signals (the DEAP dataset). Experiments were based on 10 selected featured central and peripheral nervous system data points, using long short-term memory (LSTM) as a deep learning method. Results: The arousal and valence were classified and visualized on a two-dimensional coordinate plane. Profiles were designed depending on the number of hidden layers, nodes, and hyperparameters according to the error rate. The experimental results show an arousal and valence classification model accuracy of 74.65 and 78%, respectively. The proposed model performed better than previous other models. Conclusions: The proposed model appears to be effective in analyzing arousal and valence; specifically, it is expected that affective analysis using physiological signals based on LSTM will be possible without manual feature extraction. In a future study, the classification model will be adopted in mental healthcare management systems.

• 한국HCI학회:학술대회논문집
• /
• 2009.02a
• /
• pp.707-710
• /
• 2009

In this paper, we introduce an interface for exploring music using emotional model. First, we survey arousal-valence factors of various music and calculate a correlation between audio fefatures of music and arousal-valence factors to build an AV model. Then, various music is aligned and arranged using the AV model and the user can explore music in this interface. To select the desired music more intuitively, we introduce new fade in/out function based on the location of the user's mouse point. We also offer several mode of selecting music so user can explore music using most suitable mode of interface. With our interface, the user can find the emotionally desired music more easily.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.37 no.4
• /
• pp.1-11
• /
• 2014

This paper addresses the emotion computing model for software affective agents. In this paper, emotion is represented in valence-arousal-dominance dimensions instead of discrete categorical representation approach. Firstly, a novel emotion model architecture for affective agents is proposed based on Scherer's componential theories of human emotion, which is one of the well-known emotion models in psychological area. Then a fuzzy logic is applied to determine emotional statuses in the emotion model architecture, i.e., the first valence and arousal, the second valence and arousal, and dominance. The proposed methods are implemented and tested by applying them in a virtual training system for children's neurobehavioral disorders.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.18 no.12
• /
• pp.230-241
• /
• 2017

The main purpose of this study was to empirically investigate the effects of participation behavior and performance improvement on motivation factors of Korean university students which participated in LINC by utilizing Vroom's Expectancy Theory. Three motivation factors of valence, instrumentality, and expectancy were examined in this study. In addition, two different models (valence and force model) analyzed the causal relationships regarding participation behavior and performance improvement. 236 data were collected and findings of this study were as follows: First, comparative analysis between demographic characteristics including university, major, and residence had no significant differences in mean value. However, females had higher levels of recognition related to valence (attractiveness) relative to males. Second, valence and the force model were significant predictors of LINC participation behavior and performance improvement. Furthermore, the coefficient of determination and beta coefficient of the force model were higher compared with the valence model. Third, the level of mediation effects including direct, indirect, and total effect of the force model was higher than the valence model. LINC participation behavior had a partial mediating effect between the three motivation factors and performance improvement variable.

• Journal of Korea Society of Industrial Information Systems
• /
• v.26 no.1
• /
• pp.1-10
• /
• 2021

This study proposed a Long-Short Term Memory network to consider changes in emotion over time, and applied an attention mechanism to give weights to the emotion states that appear at specific moments. We used 32 channel EEG data from DEAP database. A 2-level classification (Low and High) experiment and a 3-level classification experiment (Low, Middle, and High) were performed on Valence and Arousal emotion model. As a result, accuracy of the 2-level classification experiment was 90.1% for Valence and 88.1% for Arousal. The accuracy of 3-level classification was 83.5% for Valence and 82.5% for Arousal.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.5
• /
• pp.200-212
• /
• 2019

The purpose of this study is to examine the motivational factors of university graduates participating in 'Youth Technology Transfer Specialist Training Project(Youth TLO)' by applying Vroom's expectancy theory. Moreover, it is verified that the effect of actual participation behavior and individual performance improvement for the university graduates in Gyeonggi-do, Busan regions. The motivation factors were consisted of valence, instrumentality, and expectancy. An empirical analysis was conducted of the effects on the verification of the demographic characteristics of the target, the behaviour of personal business participation in the Valence and Force model, and the improvement of performance. Three results were inferred from 322 collected data as follows; First, comparative analysis about expectancy, which related to work experience, according to demographic characteristics such as gender, residence, age, and employment period revealed no significant differences in mean value, except career duration. Especially, the university graduates in 'Youth TLO' who had internship experience had the highest level of recognition for the expectancy. Second, both of valence and force model had influence on participation behavior and performance improvement. Notably, determination of coefficient for the valence model were higher than those for the force model. Third, level of mediation effects for the valence model were higher than those for the force model in respect of direct, indirect, and the total. Moreover, it was verified that the three motivation factors could improve individual performance and participation behavior had partial mediation effect.

• Science of Emotion and Sensibility
• /
• v.17 no.3
• /
• pp.57-64
• /
• 2014

In this paper, we verify the relation between elements (active and inactive) of Russell's emotional dimension ("A Circumplex Model") to propose a new representing method. Russell's emotional dimension expresses emotional words (happy, joy, sad, nervous, etc.) as a point on the two dimensions (Arousal and Valence). It is most commonly used in many filed such as Science of Emotion & Sensibility, Human-Computer Interaction (HCI), and Psychology etc. But other researchers have insisted that Russell's emotional dimension have to be modified because of its inherent problems. Such problems included the possibility of mixed feelings, the difference of emotion and sensibility, and the difference of Arousal axis and Valence axis. Therefore, we verify relationship of A Circumplex Model's elements (active and inactive) and find how to people express their Arousal feelings using survey. We finally propose new method to express emotion in Russell's emotional dimension. Using this method, we can solve Russell's problems and compensate other researches.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.35 no.2
• /
• pp.64-70
• /
• 2012

This paper presents a statistical analysis method for the selection of electroencephalogram (EEG) electrode positions and spectral features to recognize emotion, where emotional valence and arousal are classified into three and two levels, respectively. Ten experiments for a subject were performed under three categorized IAPS (International Affective Picture System) pictures, i.e., high valence and high arousal, medium valence and low arousal, and low valence and high arousal. The electroencephalogram was recorded from 12 sites according to the international 10~20 system referenced to Cz. The statistical analysis approach using ANOVA with Tukey's HSD is employed to identify statistically significant EEG electrode positions and spectral features in the emotion recognition.

• Journal of Digital Convergence
• /
• v.15 no.3
• /
• pp.107-117
• /
• 2017

This study examined the conditional indirect effect of EEG (electroencephalogram) arousal on the relationship among affective valence, visual attention, perceived self-relevance, and attitudes toward campaign issues in the context of public service announcements (PSAs). Using SPSS macro (No. 14) of conditional process model, the findings in this current study indicated that the perceived self-relevance mediates the relationship between affective valence of PSA and attitudes toward issues and, in turn, is moderated by EEG arousal, indicating goodness-of-fit of the moderated mediation of psychophysiological arousal on PSAs. The results suggested that management of PSAs should be considered the strategic combination between affective valence and perceived self-relevance in advertising appeals.

• Science of Emotion and Sensibility
• /
• v.26 no.2
• /
• pp.25-38
• /
• 2023

Among the discussions on affective representation, the first is to explain the affective representation in the dimensions, and the second is to explain the affective representation according to the modality. In previous studies, to explain affective representation, valence models (signed valence, unsigned valence) and Modality-generality models (modality-general, modality-specific) were presented. In this study, we compared models presented in the previous study using the recently published ASMR to confirm which models explain affective representation well. The data used in this study were behavioral rating values collected by Kim & Kim (2022), and these were obtained for ASMR stimuli that were divided into three affective types (negative, neutral, and positive) and two modalities (auditory and audiovisual). Then, a multidimensional scaling, a representational similarity analysis with a two-way repeated measures ANOVA, and a multiple regression analysis with a two-way repeated measures ANOVA were performed. The results revealed that signed valence and modality-general distinguished between affective types of stimuli better than unsigned valence and modality-specific. Similar to the results of multidimensional scaling, the results of a representational similarity analysis and a multiple regression also showed that the signed valence and modality-general significantly explained affective representation better than the unsigned valence and the modality-specific. These results suggest that the model in which positive and negative are located at the opposite ends of the one dimension explains the affective representation of ASMR well, and that the affective representation was consistent regardless of modality.