• Journal of Korea Multimedia Society
• /
• v.20 no.10
• /
• pp.1646-1654
• /
• 2017

Pupil size variation can not be controlled intentionally by the user and includes various features such as the blinking frequency and the duration of a blink, so it is suitable for understanding the user's emotional state. In addition, an ocular feature based emotion classification method should be studied for virtual and augmented reality, which is expected to be applied to various fields. In this paper, we propose a novel emotion classification based on CNN with pupil size variation signals which include not only various ocular feature information but also time information. As a result, compared to previous studies using the same database, the proposed method showed improved results of 5.99% and 12.98% respectively from arousal and valence emotion classification.

• International Journal of Highway Engineering
• /
• v.12 no.1
• /
• pp.9-20
• /
• 2010

This study was intended to identify, among various characteristics of tunnel, the relationship between the design factors comprising the driver's psychological stability, easiness and the sensitivity and then to suggest the mechanism for evaluating the tunnel view, and to that end, the study attempted to evaluate the relations between the physical elements comprising the tunnel shape and the variation of driver's emotional recognition, thereby proposing the measures to create the scenic environment. As a result of LISREL modeling to identify the characteristics of emotional recognition to tunnel view, the elements affecting tunnel view appeared to be emotional image created by the combination of elements comprising the tunnel view. Such emotional image can be explained by design elements and individual characteristics, and the effect of design element appeared to be greater than individual characteristics. The relations between individual characteristics and design element appeared to be positive (+) and the relations between the "safety" and "variability" was significant. And the "safety" have had greater effect on view recognition than "variability", indicating that the drivers tend to give more importance to "safety", but also require the "variability"on the other hand.

• Journal of Digital Contents Society
• /
• v.18 no.1
• /
• pp.87-91
• /
• 2017

Recently, several kinds of researches using IoT wearable devices are active in the field of sports, design, emotional sciences and so on. The human bio data such as blood pulse, ECG, SKT signal, and GSR Signal producing from IoT wearable devices such as Watch, Smart-band, Grass can adapt to the meaningful future applications. Using the human's emotional data and a physical status with variation and so on, we can individually get the personal status. Due to knowing the personal emotion or physical status is related and connected to the valuable wallet of customers, the approach is more important in nowadays. Therefore, the personal information can effectively adapt to the marketing of the culture industry, which deals with emotions of customers. The research shows implementation steps for explaining overall architecture of the convergence research between Art and Technologies.

• Journal of the Korea Convergence Society
• /
• v.8 no.6
• /
• pp.163-170
• /
• 2017

In this paper want to recognize competition and cooperation as a non-contact sensing method among the social emotion that are caused by interaction. Experiments were conducted in a pattern matching task divided into competition and cooperation situations. Data collection was performed by extracting the micro-movement data of 15Hz component from the upper body image. We compared and analyzed the amount and the variation and synchronization. As a result, Amount and variation are bigger in competition than cooperation. Synchronization was higher in cooperation than competition. This can be seen as the difference between two people trying to win when they are in competition and trying to breathe each other in cooperation. This study is significant in confirming the possibility of competition and cooperation through non contact sensing method based on physiological response.

• Journal of the Korean Society of Costume
• /
• v.61 no.9
• /
• pp.131-147
• /
• 2011

This study puts the significance on the trends, the characteristics, the factors and background of the typical diversification of 2000's historical dramas and of their costume in conjunction with the popular culture. We analyzed the materials like the official web-sites, the articles and promotional photos based on 47 TV historical dramas and 21 historical movies. And we, approaching the characteristics of popular culture in connection with the social, cultural, economic, emotional and technical aspects, considered the trends of the historical dramas and their connection with the paradigms of the contemporary popular culture. The results of this analysis are summarized as follows. First, the 2000's historical dramas & their costume, in the process to widen communication with the public, rose the values of popular culture, economic values, traditional values. Second, the diversification of the costumes in historical dramas, derived from the diversification of the era Genre characters and this is related to the characteristics of popular culture in 2000's such as the diversity, the nature of mixture, flexibility and the orientation of variation. Third, the new media environment and the imaging technology of 2000's raised completeness of the historical dramas and their costume. As the technical background placed the emphasis on realistic representation. Fourth, the costume of historical dramas in 2000's reflected the intention of the production in consideration with the emotional aspects of popular culture.

• Journal of Distribution Science
• /
• v.14 no.7
• /
• pp.63-70
• /
• 2016

Purpose - The purpose of this study was to examine the variations in emotions during vacation and to explore if such variations depend on psychological distance perceived by vacationers. We proposed that there are changes in affect balance during the course of vacation as well as the mental construal of psychological distance. Research Design, Data, and Methodology - Repeated measures ANOVA was used to examine the variation in emotion and psychological distance of 66 holiday makers who were traveling to different destination for vacation. Data were collected in 2 months with the help of a travel agency. Results - We find that there are variations in emotions during the vacation at different points in time as well as perceived psychological distance. Also we find some evidence that suggests emotional happiness does depend on perceived mental distance to some extent. Conclusion - Our study replicates the findings of previous studies in a novel way and illustrates the robustness of the nature of emotions during vacation and indicates certain time points where the happiness of vacationers can be enhanced. Perceived psychological distance do have an effect on how happy an individual feels during the vacation.

• Journal of Korea Multimedia Society
• /
• v.16 no.11
• /
• pp.1325-1337
• /
• 2013

Music affects sensitivity and emotion of human, emotional power of the music has been applied to various fields. Especially, to visualize as well as listen to music is able to create various atmosphere. In this paper, we proposed sensitivity control system for interaction with people to merge music and lighting. Because existing FT(Fourier Transform) has not information about the time, to analyze information of changed signal according to the time is difficult. In order to solve such a problem, we use STFT(Short Time Fourier Transform) method to analyze music signal. and also, we classified music for three genre and compared the frequency characteristics according to genre, and control the color, brightness of LED light based on the frequency components within analysis range. Unlike existing LED lighting control study using music, we had color control of emotional lighting and brightness control using variation amount of music signal in this paper. Proposed lighting control system will be able to utilize various industry fields as well as emotional lighting.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.22 no.6
• /
• pp.681-686
• /
• 2012

This paper studied the speech parameters less affected by the human emotion for the development of the robust emotional speech recognition system. For this purpose, the effect of emotion on the speech recognition system and robust speech parameters of speech recognition system were studied using speech database containing various emotions. In this study, mel-cepstral coefficient, delta-cepstral coefficient, RASTA mel-cepstral coefficient, root-cepstral coefficient, PLP coefficient and frequency warped mel-cepstral coefficient in the vocal tract length normalization method were used as feature parameters. And CMS (Cepstral Mean Subtraction) and SBR(Signal Bias Removal) method were used as a signal bias removal technique. Experimental results showed that the HMM based speaker independent word recognizer using frequency warped RASTA mel-cepstral coefficient in the vocal tract length normalized method, its derivatives and CMS as a signal bias removal showed the best performance.

• Information Systems Review
• /
• v.23 no.1
• /
• pp.23-43
• /
• 2021

Recently, many studies have been conducted to increase the accuracy of stock price prediction by analyzing candlestick charts using artificial intelligence techniques. However, these studies failed to consider the time-series characteristics of candlestick charts and to take into account the emotional state of market participants in data learning for stock price prediction. In order to overcome these limitations, this study produced input data by combining volatility index and candlestick charts to consider the emotional state of market participants, and used the data as input for a new method proposed on the basis of combining variantion autoencoder (VAE) and attention mechanisms for considering the time-series characteristics of candlestick chart. Fifty firms were randomly selected from the S&P 500 index and their stock prices were predicted to evaluate the performance of the method compared with existing ones such as convolutional neural network (CNN) or long-short term memory (LSTM). The results indicated the method proposed in this study showed superior performance compared to the existing ones. This study implied that the accuracy of stock price prediction could be improved by considering the emotional state of market participants and the time-series characteristics of the candlestick chart.

• Journal of the Korean Society of Fashion and Beauty
• /
• v.2 no.2 s.2
• /
• pp.59-70
• /
• 2004

The purpose of this study were to find out appeal types and variation of make-up image and make-up style in cosmetics advertising. The research of this study were collected from cosmetics advertisement printed in Amole Pacific Cosmetic industry from $1970{\sim}2004$. The results were as follow: 1. A cosmetics advertisement appeal were three types. it were models and products appeal advertisement as emotional appeal, products-appeal and mixed appeal advertisement. 2. A variation of make-up image were different by the time. In the 1970s make-up were model empersis eye-line and colorful make-up were classic and active make-up image. From the 1980s various color make-up were used and persuited of individuality and started to appeal that were romantic and elegance image. In the 1990s multi-color make-up image were manish and modern used ambivalence and multi-message, and in the $2000{\sim}2004$ natural and romantic-sexy remarkable make-up image were used of new concept of beauty.