• Journal of the Korean Institute of Intelligent Systems
• /
• v.13 no.3
• /
• pp.275-280
• /
• 2003

In this paper, we propose a method for recognizing the human s emotion using output data of image and speech. The proposed method is based on the recognition rate of image and speech. In case that we use one data of image or speech, it is hard to produce the correct result by wrong recognition. To solve this problem, we propose the new method that can reduce the result of the wrong recognition by multiplying the emotion status with the higher recognition rate by the higher weight value. To experiment the proposed method, we suggest the simple recognizing method by using image and speech. Finally, we have shown the potentialities through the expriment.

• The Journal of the Korea Contents Association
• /
• v.14 no.9
• /
• pp.476-483
• /
• 2014

The purpose of this study was to make a suitable images for korean emotional expressions. KSFI(Korean Standard Facial Image)-AUs was produced from korean standard apperance and FACS(Facial Action coding system)-AUs. For the objectivity of KSFI, the survey was examined about emotion recognition rate and contribution of emotion recognition in facial elements from six-basic emotional expression images(sadness, happiness, disgust, fear, anger and surprise). As a result of the experiment, the images of happiness, surprise, sadness and anger which had shown higher accuracy. Also, emotional recognition rate was mainly decided by the facial element of eyes and a mouth. Through the result of this study, KSFI contents which could be combined AU images was proposed. In this future, KSFI would be helpful contents to improve emotion recognition rate.

• Science of Emotion and Sensibility
• /
• v.15 no.1
• /
• pp.133-140
• /
• 2012

We designed a novel individualization process for improving personal emotion recognitions in real time. The designed individualization process was performed by a neutralization algorithm of physiological signals, a subjective emotion reflection of a user updated by personal emotion rules in real time. The physiological signals such as PPG(Photoplethysmography), GSR(Galvanic skin reflex), and SKT(Skin temperature) were measured and analyzed to estimate an emotion states of users. Regulating the emotion status using by emotion rules was performed by reflecting subjective evaluations. The agreement of emotion recognition between of individualization and non-individualization method was estimated by 10 undergraduates (5 females, mean age: $22.1{\pm}2.2$) of Sangmyung University. During the emotion recognition test, 45 images were randomly presented to each participant five times. In results, the proposed individualization process showed the agreement of 71.67 % which was five times higher than when the process was not applied. Therefore, in this study, we demonstrated that the individualization process was significantly useful for customizing emotion recognitions of personal users in real time. The individualization process will be able to improve satisfactions in various emotion related applications and services in the nearer future.

• Science of Emotion and Sensibility
• /
• v.1 no.1
• /
• pp.3-11
• /
• 1998

In an urgent situation of interdisciplinary research and method, we feel eagerly the necessity of discussing the philosophical background of ´the science of emotion and sensibility´. If human cognitive faculties lie in split dualism of sensibility and reason, it is difficult to find out the whole image of just recognition, Therfore, it is so important that we should pursue the interrelational context between reason and sensibility through the rationalization of sensibility and the sensibilization of reason. Both reason and sensibility constitute the immanant system of knowledge, The science of sensitive cognition has lower cognitive faculty in contrast to the science of logic, but commonsense plays a rloe to expand the world knowledge which the logical cognition can not fully accomplish. it is dur task to expand the problem of sensibility from the level of humanities on the ground of the communal to the scientific objecticity, which is based on the observation of natural appearances.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.05a
• /
• pp.206-209
• /
• 2003

본 논문에서는 퍼지추론과 면역 네트워크의 세 가지 메커니즘을 바탕으로 인간의 외부 자극(색상정보)에 따른 내부 감성상태를 인식할 수 있는 방법을 제안한다. 인간의 내부 감성상태는 심리학에서 많이 사용하는 색채심리를 바탕으로 추론을 하였으며 추론된 값은 색상 정보의 정도에 따른 감성상태이다. 이러한 감성상태의 값들 간에 유사성을 계산하여 면역 네트워크에 세 가지 메커니즘에 적용하여 인공적인 감성상태를 인식할 수 있는 방법을 나타내었다.

• Science of Emotion and Sensibility
• /
• v.20 no.3
• /
• pp.61-70
• /
• 2017

Physiological responses have been measured to recognize emotion. Although physiological responses have been interrelated between organs, their connectivities have been less considered for emotion recognizing. The connectivities have been assumed to enhance emotion recognition. Specially, autonomic nervous system is physiologically modulated by the interrelated functioning. Therefore, this study has been tried to analyze connectivities between heart and respiration and to find the significantly connected variables for emotion recognition. The eighteen subjects(10 male, age $24.72{\pm}2.47$) participated in the experiment. The participants were asked to listen to predetermined sound stimuli (arousal, relaxation, negative, positive) for evoking emotion. The bio-signals of heart and respiration were measured according to sound stimuli. HRV (heart rate variability) and BRV (breathing rate variability) spectrum were obtained from spectrum analysis of ECG (electrocardiogram) and RSP (respiration). The synchronization of HRV and BRV spectrum was analyzed according to each emotion. Statistical significance of relationship between them was tested by one-way ANOVA. There were significant relation of synchronization between HRV and BRV spectrum (synchronization of HF: F(3, 68) = 3.605, p = 0.018, ${\eta}^2_p=0.1372$, synchronization of LF: F(3, 68) = 5.075, p = 0.003, ${\eta}^2_p=0.1823$). HF difference of synchronization between ECG and RSP has been able to classify arousal from relaxation (p = 0.008, d = 1.4274) and LF's has negative from positive (p = 0.002, d = 1.7377). Therefore, it was confirmed that the heart and respiration to recognize the dimensional emotion by connectivity.

• Science of Emotion and Sensibility
• /
• v.11 no.4
• /
• pp.637-644
• /
• 2008

Human emotion has been tried to be recognized by physiological measurements in developing emotion machine enabling to understand and react to user's emotion. This study is to find the time-dependent physiological measurements and their variation characteristics for discriminating emotions according to dimensional emotion model. Ten university students were asked to watch sixteen prepared images to evoke different emotions. Their subjective emotions and autonomic nervous responses such as ECG (electrocardiogram), PPG (photoplethysmogram), GSR (Galvanic skin response), RSP (respiration), and SKT(skin temperature) were measured during experiment. And these responses were analyzed into HR(Heart Rate), Respiration Rate, GSR amplitude average, SKT amplitude average, PPG amplitude, and PTT(Pulse Transition Time). TDPs(Time dependent parameters) defined as the delay, the activation, the half recovery and the full recovery of respective physiological signal in this study have been determined and statistically compared between variations from different emotions. The significant tendencies in TDP were shown between emotions. Therefore, TDP may provide useful measurements with emotion recognition.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2003.05b
• /
• pp.536-540
• /
• 2003

최근에 개인의 경험을 통해 얻어지는 외부의 물리적 자극에 대한 복합적인 감성을 측성 및 분석하여 공학적으로 처리함으로서 인간이 보다 편리하고 안락한 생활을 영위하도록 하는 연구가 활발히 진행되고 있다. 본 논문에서는 색채 심리를 바탕으로 한 감성을 인식할 수 있는 생리학적 퍼지 신경망은 제안하였다. 본 논문에서 제안한 생리학적 퍼지 뉴런 구조를 기반으로 하여 입력층, 퍼지 귀속 시넵스(Fuzzy Membership Synapse) 및 출력층으로 구성되며 지도 학습(supervised learning)으로 동작된다. 제안된 생리학적 퍼지 신경망을 단일 색상 정보에 따른 감성 인식에 적용한 결과, 단일 색상 정보에 따른 감성 인식에 있어서 효율적임을 확인 할 수 있었다.

• Science of Emotion and Sensibility
• /
• v.21 no.3
• /
• pp.73-82
• /
• 2018

Attempts have been made to recognize social emotion, including competition-cooperation, while designing interaction in work places. This study aimed to determine the cardiac response associated with classifying competition-cooperation of social emotion. Sixty students from Sangmyung University participated in the study and were asked to play a pattern game to experience the social emotion associated with competition and cooperation. Electrocardiograms were measured during the task and were analyzed to obtain time domain indicators, such as RRI, SDNN, and pNN50, and frequency domain indicators, such as VLF, LF, HF, VLF/HF, LF/HF, lnVLF, lnLF, lnHF, and lnVLF/lnHF. The significance of classifying social emotions was assessed using an independent t-test. The rule-base for the classification was determined using significant parameters of 30 participants and verified from data obtained from another 30 participants. As a result, 91.67% participants were correctly classified. This study proposes a new method of classifying social emotions of competition and cooperation and provides objective data for designing social interaction.

• The Journal of the Acoustical Society of Korea
• /
• v.25 no.6
• /
• pp.269-276
• /
• 2006

In this paper, we propose an emotion recognition system that can discriminate human emotional state into neutral or anger from the speech captured by a cellular-phone in real time. In general. the speech through the mobile network contains environment noise and network noise, thus it can causes serious System performance degradation due to the distortion in emotional features of the query speech. In order to minimize the effect of these noise and so improve the system performance, we adopt a simple MA (Moving Average) filter which has relatively simple structure and low computational complexity, to alleviate the distortion in the emotional feature vector. Then a SFS (Sequential Forward Selection) feature optimization method is implemented to further improve and stabilize the system performance. Two pattern recognition method such as k-NN and SVM is compared for emotional state classification. The experimental results indicate that the proposed method provides very stable and successful emotional classification performance such as 86.5%. so that it will be very useful in application areas such as customer call-center.