• Journal of the Institute of Electronics Engineers of Korea SP
• /
• 제40권5호
• /
• pp.371-377
• /
• 2003

In this paper, comparison of feature parameters for emotion recognition using speech signal is studied. For this purpose, a corpus of emotional speech data recorded and classified according to the emotion using the subjective evaluation were used to make statical feature vectors such as average, standard deviation and maximum value of pitch and energy and phonetic feature such as MFCC parameters. In order to evaluate the performance of feature parameters speaker and context independent emotion recognition system was constructed to make experiment. In the experiments, pitch, energy parameters and their derivatives were used as a prosodic information and MFCC parameters and its derivative were used as phonetic information. Experimental results using vector quantization based emotion recognition system showed that recognition system using MFCC parameter and its derivative showed better performance than that using the pitch and energy parameters.

• Science of Emotion and Sensibility
• /
• 제25권3호
• /
• pp.127-134
• /
• 2022

This study sought to identify the voice user interface (VUI) design parameters that evoked positive user emotions. Six VUI design parameters that could affect emotional user satisfaction were considered. The moderating effects of user gender and the design parameters were analyzed to determine the appropriate conditions for user satisfaction when interacting with the VUI. An interactive VUI system that could modify the six parameters was implemented using the Wizard of OZ experimental method. User emotions were assessed from the users' facial expression data, which was then converted into a valence score. The frequency analysis and chi-square test found that there were statistically significant moderating gender and AI effects. These results implied that it is beneficial to consider the users' gender when designing voice-based interactions. Adult/male/high-tone voices for males and adult/female/mid-tone voices for females are recommended as general guidelines for future VUI designs. Future analyses that consider various human factors will be able to more delicately assess human-AI interactions from a UX perspective.

• Journal of the Korean Institute of Intelligent Systems
• /
• 제18권5호
• /
• pp.586-591
• /
• 2008

This paper studied the emotion recognition system combined with robust speech recognition system in order to improve the performance of emotion recognition system. For this purpose, the effect of emotional variation on the speech recognition system and robust feature parameters of speech recognition system were studied using speech database containing various emotions. Final emotion recognition is processed using the input utterance and its emotional model according to the result of speech recognition. In the experiment, robust speech recognition system is HMM based speaker independent word recognizer using RASTA mel-cepstral coefficient and its derivatives and cepstral mean subtraction(CMS) as a signal bias removal. Experimental results showed that emotion recognizer combined with speech recognition system showed better performance than emotion recognizer alone.

• Proceedings of the KOSOMBE Conference
• /
• 대한의용생체공학회 1997년도 춘계학술대회
• /
• pp.176-178
• /
• 1997

We are exposed to the various types of external stimuli, and many researches have been conducted to analyze the emotional changes to the stimuli quantitatively. In this paper, changes of human emotion was studied by analyzing HRV from ECG signals which were varied by the auditory stimulus. Power contents for each frequency bands were calculated from HRV waveforms. Two peak values representing autonomic nervous system status, HF and LF, were used to extract the parameters. An analysis on the normalized HF/LF to the subjective rating of the subject were performed. It was assumed that the positive emotional changes evoked by the auditory stimuli, the HF values representing activation of the parasympathetic nervous system, are increased much higher than the LF values, activation of the sympathetic nervous system. Results showed that the parasympathetic nervous system works more actively than the sympathetic nervous system to the stimuli which cause the positive emotional changes.

• Journal of Power Electronics
• /
• 제16권6호
• /
• pp.2294-2305
• /
• 2016

The introduction of a high-voltage direct-current (HVDC) system based on a modular multilevel converter (MMC) for wind farm integration has stimulated studies on methods to control this type of converter. This research article focuses on the control of the AC voltage and circulating current for a wind-farm-side MMC (WFS-MMC). After theoretical analysis, emotional learning (EL) controllers are proposed for the controls. The EL controllers are derived from the learning mechanisms of the amygdala and orbitofrontal cortex which make the WFS-MMC insensitive to variance in system parameters, power change, and fault in the grid. The d-axis and q-axis currents are respectively considered for the d-axis and q-axis voltage controls to improve the performance of AC voltage control. The practicability of the proposed control is verified under various conditions with a point-to-point MMC-HVDC system. Simulation results show that the proposed method is superior to the traditional proportional-integral controller.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• 제22권3호
• /
• pp.476-484
• /
• 2021

In this study, we analyze the relationships between long-term care workers' person-centeredness and job satisfaction, emotional labor, and service quality. Self-administered questionnaires were used to collect data from 460 long-term care workers in long-term care facilities. In the research model, person-centered care was verified using independent variables, with emotional labor (surface behavior, internal behavior) and job satisfaction applied as parameters, and service quality applied as a dependent variable. The results of this study are as follows. First, the fit of the model is good. Second, the implicit behavior of emotional labor is found to be an important factor affecting service quality. Also, emotional labor is an important mediator, improving the value of person-centered care and service quality. There is a positive correlation between internal behavior and service quality, and a negative correlation between surface behavior and service quality. Third, emotional labor (surface behavior, internal behavior) is the most influential variable in terms of service quality. The results of this study demonstrate the necessity to pay clinical and academic attention to person-centered care in terms of long-term care workers' emotional labor and service quality.

• Journal of Power Electronics
• /
• 제14권1호
• /
• pp.74-81
• /
• 2014

In this study, a brain emotional learning-based intelligent controller (BELBIC) is developed for the speed control of an interior permanent magnet synchronous motor (IPMSM). A novel and simple model of the IPMSM drive structure is established with the intelligent control system, which controls motor speed accurately without the use of any conventional PI controllers and is independent of motor parameters. This study is conducted in both real time and simulation with a new control plant for a laboratory 3 ph, 3.8 Nm IPMSM digital signal processor (DSP)-based drive system. This DSP-based drive system is then compared with conventional BELBIC and an optimized conventional PI controller. Results show that the proposed method performs better than the other controllers and exhibits excellent control characteristics, such as fast response, simple implementation, and robustness with respect to disturbances and manufacturing imperfections.

• Proceedings of the Korean Society for Emotion and Sensibility Conference
• /
• 한국감성과학회 1998년도 추계학술발표 논문집
• /
• pp.143-147
• /
• 1998

Autonomic and EEG responses of 38 college students were studied during 60-sec long presentation of International Affective Picture System (IAPS )slides evoking, according to subjective reports, negative (disgust, sadness, surprise) and positive (happiness, exciting) emotional. states. Observed were significant heart rate (HR) deceleration, large skin conductance responses (SCR), moderate respiration frequency slowing, reduction of frontal (F 3, F 4 ) and occipital (O 1, O 2 ) fast alpha, and increases of theta, delta and beta relative spectral power values during the first 30 sec of exposure of IAPS pictures. Analysis carried out to differentiate emotion categories according to autonomic responses indicated that observed HR deceleration was larger in magnitude in surprise and sadness than in disgust, SCR amplitude higher in sadness than in disgust. EEC showed significant differences in theta (F 3, F 4 ) and delta (O 1) power increase in disgust vs. happiness, fast alpha (F 3, F 4 ) power was lower in surprise than in happiness, and slow beta power higher. in happiness than in disgust (0 1). Despite some differences. observed within discrete emotion conditions, overall responses pattern of monitored parameters exhibited similar profiles with few variations, most. obvious. in disgust state, which suggests that affective visual stimulation elicits stereotypical responses in a given passive viewing paradigm. However, the magnitude of physiological responses may vary to certain extent across discrete emotional states making it possible to differentiate among particular experimentally-induced emotional states, e.g., disgust vs. sadness by ANS responses or disgust vs. happiness by EEG measures.

• Proceedings of the Korean Society for Emotion and Sensibility Conference
• /
• 한국감성과학회 1998년도 추계학술발표 논문집
• /
• pp.225-229
• /
• 1998

The purpose of the current study was comparative analysis of autonomic and electrocortical responses to passive and active touch of the tektites with different subjective emotional preference. Perspective goal of the project is development of a template for classification of tactile stimuli according to subjective comfort and associated physiological manifestations. The study was carried out on 36 female college students. Physiological signals were acquired by Grass and B10PAC 100 systems with AcqKnowledge III software. Frontal, parietal and occipital EEG (relative power spectrum /percents/ of EEG bands - delta, theta, slow and fast alpha, low and fast beta), and autonomic variables, namely heart rate (HR), respiratory sinus arrhythmia (RSA), pulse transit time (PTT), respiration rate (RSP) and skin conductance parameters (SCL, amplitude, rise time and number of SCRs) were analyzed for rest baseline and stimulation conditions. Analysis of the overall pattern of reaction indicated that autonomic response to tactile stimulation was manifested in a form of moderate HR acceleration, RSP increase, RSA decrease (lowered vagal tone), decreased n and increased electrodermal activity (increased SCL, several SCRs) that reflects general sympathetic activation. Parietal EEG effects (on contra-lateral side to stimulated hand) were featured by short-term alpha-blocking, slightly reduced theta and significantly increased delta and enhanced fast beta activity with few variations across stimuli. The main finding of the study was that most and least preferred textures exhibited significant differences in autonomic (HR, RSP, PTT, SCR, and at less extent in RSA and SCL) and electrocortical responses (delta, slow and fast alpha, fast beta relative power). These differences were recorded both in passive and active stimulation modes, thus demonstrating reproducibility of distinction between most and least emotionally preferred tactile stimuli, suggesting influence of psychological factors, such as emotional property of stimulus, on physiological outcome. Nevertheless, development of sufficiently sensitive .and reliable template for classification of emotional responses to tactile stimulation based on physiological response pattern may require more extensive empirical database.

• Journal of Internet Computing and Services
• /
• 제10권4호
• /
• pp.55-70
• /
• 2009

Vision-based Human computer interaction is an emerging field of science and industry to provide natural way to communicate with human and computer. In that sense, inferring the emotional state of the person based on the facial expression recognition is an important issue. In this paper, we present a novel approach to recognize facial expression from a sequence of input images using emotional specific HMM (Hidden Markov Model) and facial motion tracking based on optical flow. Conventionally, in the HMM which consists of basic emotional states, it is considered natural that transitions between emotions are imposed to pass through neutral state. However, in this work we propose an enhanced transition framework model which consists of transitions between each emotional state without passing through neutral state in addition to a traditional transition model. For the localization of facial features from video sequence we exploit template matching and optical flow. The facial feature displacements traced by the optical flow are used for input parameters to HMM for facial expression recognition. From the experiment, we can prove that the proposed framework can effectively recognize the facial expression in real time.