• Proceedings of the Korea Information Processing Society Conference
• /
• 2017.11a
• /
• pp.1037-1040
• /
• 2017

현재 머신러닝과 딥러닝의 기술이 빠른 속도로 발전하면서 수많은 인공지능 음성 비서가 출시되고 있지만, 발화자의 문장 내 존재하는 단어만 분석하여 결과를 반환할 뿐, 비언어적 요소는 인식할 수 없기 때문에 결과의 구조적인 한계가 존재한다. 따라서 본 연구에서는 인간의 의사소통 내 존재하는 비언어적 요소인 말의 빠르기, 성조의 변화 등을 수치 데이터로 변환한 후, "플루칙의 감정 쳇바퀴"를 기초로 지도학습 시키고, 이후 입력되는 음성 데이터를 사전 기계학습 된 데이터를 기초로 kNN 알고리즘을 이용하여 분석한다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2001.04b
• /
• pp.259-261
• /
• 2001

가상환경을 구축하는 있어 상황은 동적인 형태로 존재한다. 즉, 어떤 객체의 등장이나 소멸, 변화 혹은 서로 다른 두 객체간의 관계에서 상황은 형성된다. 또한, 이런 상황은 시간의 흐름에 따라서 구성하는 에이전트의 행동에 의해 바꾸어 질 수 있는데, 이러한 상황은 어떠한 형태로 가상세계를 구성하며, 에이전트에 인식되어 질 것이다. 만약 에이전트의 행동에 의해 만들어지는 상황이 다른 어떤 객체에게 있어 예측할 수 없었던 상황이라면, 기존의 스크립트 기반 시스템에서는 어떻게 될 것인가\ulcorner 본 연구에서는 이런 각각의 상황을 이벤트의 구성으로 표현함과 동시에 등장 에이전트의 구성된 상황에 대한 인식과 에이전트의 내부환경요소 즉 감정요소를 도입함으로써 발생 상황에 능동적으로 대처하는 시스템에 대한 환경을 제안하고자 한다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2000.10b
• /
• pp.425-427
• /
• 2000

얼굴 표정은 사람의 감정을 표현함과 동시에 그것을 이해할 수 있는 중요한 수단이다. 최근 이러한 얼굴 표정의 자동인식과 추적을 위한 연구가 많이 진행되고 있다. 본 연구에서는 대략적인 얼굴영역을 설정하여 얼굴의 표정을 나타내는 표정요소들을 찾아낸 후, 각 요소의 특징점을 추출하고 추적하는 방법을 제시한다. 제안하는 시스템의 개요는 입력영상의 첫 프레임에서 얼굴영역 및 특징점을 찾고, 연속되는 프레임에서 반복적으로 이를 추적한다. 특징점 추출과 추적에는 템플릿 매칭과 Canny 경계선 검출기, Gabor 웨이블릿 변환을 사용하였다.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.1
• /
• pp.48-55
• /
• 2018

A framework has recently been developed to evaluate the user experience (UX) design for a virtual reality (VR) indoor bike. However, no comparative evaluation has been performed for an actual product using this framework. This paper investigates the effectiveness of the framework and identifies some problems when applying it. To validate the framework, we applied the proposed framework to a Korean VR indoor bike (KoVIB) prototype and VirZOOM, a commercial VR bike. The evaluation criteria consist of usability, emotional aspects, user values, and sense of reality. These four criteria were interpreted to evaluate prototypes and include 13, 6, 8, and 16 sub-elements, respectively. The results revealed the strengths and weakness between the Korean prototype and the commercial product, which are valuable for promotion and improvement. The framework helps to identify some problems when applied to real domains. As a result, we recommend a revised framework to compare prototypes with existing VR bikes.

• Journal of IKEEE
• /
• v.22 no.4
• /
• pp.1140-1146
• /
• 2018

Recently, a methodology for analyzing complex bio-signals using a deep learning model has emerged among studies that recognize human emotions. At this time, the accuracy of emotion classification may be changed depending on the evaluation method and reliability depending on the kind of data to be learned. In the case of biological signals, the reliability of data is determined according to the noise ratio, so that the noise detection method is as important as that. Also, according to the methodology for defining emotions, appropriate emotional evaluation methods will be needed. In this paper, we propose a wavelet -based noise threshold setting algorithm for verifying the reliability of data for multimodal bio-signal data labeled Valence and Arousal and a method for improving the emotion recognition rate by weighting the evaluation data. After extracting the wavelet component of the signal using the wavelet transform, the distortion and kurtosis of the component are obtained, the noise is detected at the threshold calculated by the hampel identifier, and the training data is selected considering the noise ratio of the original signal. In addition, weighting is applied to the overall evaluation of the emotion recognition rate using the euclidean distance from the median value of the Valence-Arousal plane when classifying emotional data. To verify the proposed algorithm, we use ASCERTAIN data set to observe the degree of emotion recognition rate improvement.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2014.11a
• /
• pp.876-878
• /
• 2014

인터넷 사용량이 급증하고 사용자들이 생성하는 데이터의 양이 증가함에 따라 사용자 데이터 분석은 객관적인 정보 탐색과 분석을 넘어 주관적인 감정을 분석하는 데까지 시도되고 있다. 이러한 감정 분석은 사업, 행정, 외교 등의 다양한 분야에 걸쳐 용용 될 수 있다. 본 연구에서는 텍스트 데이터를 주요 분석 대상으로 하여 문장 구성의 다양한 요소를 특징화하고, 특징화된 문장에 대해 다양한 서포트 벡터머신을 통한 학습을 시도함으로써 텍스트가 내포한 감정을 추측한다. 다양한 특징화 방법을 적용하되, 낮은 밀도가 될 것으로 추측되는 데이터 매트릭스의 차원 감쇄를 위해 정보엔트로피 기반의 특징 선택기법을 적용한다.

• Culinary science and hospitality research
• /
• v.22 no.3
• /
• pp.166-182
• /
• 2016

This study intended to verify the impact of non-verbal communication of servers in the service industry on the affective path among customer's positive emotion, self-identification, and loyalty(behavioral and attitudinal loyalty). The data of 397 customers of typical fast food restaurants in Busan and Gyeongsangbuk-do area were analyzed with SPSS and AMOS, and the hypotheses were verified through structural equation model after frequency analysis, as well as exploratory and confirmatory factor analysis. According to the empirical analysis, all three components of server non-verbal communication in the service industry, body language, pseudo language, and body appearance, in respective order, had positive (+) influences on the positive emotion of customers. In addition, customer emotion had a positive (+) influence on brand self-identification. Finally, self-identification had a positive (+) influence on behavior loyalty and attitudinal loyalty. This study suggested practical implications and logical implications in the course of developing emotional loyalty for restaurant companies.

• Journal of Korea Entertainment Industry Association
• /
• v.13 no.6
• /
• pp.211-220
• /
• 2019

It helps to wisely abstain from errors of the a priori subjective emotions related to human emotions, and orders emotions to make rational choices. These emotional happiness of human and moral sensitivities work directly or indirectly in rational choice of rational thought and reason. Abraham would have been troubled by the divine mandate to sacrifice a son who was only one, and a son who had been healed. Was his reason reasonable at this time? In rational reason, it can be said that the act of dedicating his son is an appropriate act, but is it possible in the human mind? Aristoteles also called human virtue virtue in good for human beings. Because happiness is also a mental activity, we have to know a certain degree about the mind. This ψυχή(psyche, spirit) spirit is an irrational element that is invisible but an intervention in rational principles. Also C. G. Jung states that all human beings have four dynamic psychological functions that are not visible, and that the mind is driven by these four functional dimensions. This means that the elements of S, Sensing, N, Intuition, T, Thinking, and Feeling are combined. David Hume also emphasized the principle of empathy, asserting that morality can not be derived from reason, and Max Ferdinand Scheler, before grasping the visual characteristics of a person, has already captured the whole feeling of the person, And that the value given to this feeling is the value, and that the function of emotion that is elevated to the perceived object by grasping the value through this process and the value is always preceded by the reason. Emmanuel Levinas states that emotional emotions of love are ahead of reason and that emotions precede human reasoning and rationality is the inability of emotional control that we need rational thought and rational and wise action as reason of control and temperance. As part of human emotional education, in the 7th curriculum, Bloom's cognitive, perceptive, and behavioral domain, which is a person with integrated thinking, is trying to be a moral practitioner. It focuses on how to act according to the direction of emotions for virtuous acts and how to develop emotions for emotions on behalf of vicious acts. We can design the possibility and direction of cultivating human emotions and emotional happiness and happy sensitivities by the principle of strengthening virtue and the principle of elimination of ill feeling.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.10 no.1
• /
• pp.51-55
• /
• 2010

Tele-marketing service has been provided through voice media in a several places such as modern call centers. In modern call centers, they are trying to measure their service quality, and one of the measuring method is a extracting speaker's feeling information in their voice. In this study, it is proposed to analyze speaker's voice in order to extract their feeling information. For this purpose, a person's feeling is categorized by analyzing several types of signal parameters in the voice signal. A person's feeling can be categorized in four different states: joy, sorrow, excitement, and normality. In a normal condition, excited or angry state can be major factor of service quality. In this paper, it is proposed to select a conversation with problems by extracting the speaker's feeling information based on pitches and amplitudes of voice.

• The Journal of the Korea Contents Association
• /
• v.9 no.11
• /
• pp.1-9
• /
• 2009

In virtual environments, such as computer game and animation, we need to enhance naturalness of crowd simulation. So, we propose a method to generate dynamically moving crowd patterns by applying emotional factors to the individual characters of a crowd in the determination of their behavior. The proposed method mimics human behavior and controls each character in a group to decide its own path according to its individual status. And it is able to generate various moving patterns as a result of letting the individuals go to another group depending upon their conditions. In this paper, some temperament and feeling factors are defined and determination rules for calculating the emotional status are also proposed. Moreover we use a fuzzy theory for accurate representation of the ambiguous expressions such as feeling bad, feeling good and so on. Our experiments show that the suggested method can simulate virtual crowd in more natural and diverse ways.