• Journal of Semiconductor Engineering
• /
• v.2 no.2
• /
• pp.130-135
• /
• 2021

Recently, deep neural networks (DNNs) are actively used for action control so that an autonomous system, such as the robot, can perform human-like behaviors and operations. Unlike recognition tasks, the real-time operation is essential in action control, and it is too slow to use remote learning on a server communicating through a network. New learning techniques, such as reinforcement learning (RL), are needed to determine and select the correct robot behavior locally. In this paper, we propose an energy-efficient DNN processor with a LUT-based processing engine and near-zero skipper. A CNN-based facial emotion recognition and an RNN-based emotional dialogue generation model is integrated for natural HRI system and tested with the proposed processor. It supports 1b to 16b variable weight bit precision with and 57.6% and 28.5% lower energy consumption than conventional MAC arithmetic units for 1b and 16b weight precision. Also, the near-zero skipper reduces 36% of MAC operation and consumes 28% lower energy consumption for facial emotion recognition tasks. Implemented in 65nm CMOS process, the proposed processor occupies 1784×1784 um2 areas and dissipates 0.28 mW and 34.4 mW at 1fps and 30fps facial emotion recognition tasks.

• Journal of Korean Academy of Nursing
• /
• v.28 no.4
• /
• pp.931-940
• /
• 1998

This study was done to describe health behavior and determine affecting factors in Korean adults, based on the Health Behavior Assessment tool. The subjects were sample of 298 adults from five cities. The instrument for this study were Health Behavior Assessment tool (30 items, 4 scale). Frequency, percentage, t-test, ANOVA, cluster analysis with SPSS program were used to analyze the data. The results of the study are as follows ; 1) The average item score for health behavior was 2.56, the highest score on the subscale was limitation of liking(M=3.16), followed by stress management (M=2.98), nutrition(M=2.82), energy conservation (M=2.67). 2) A significant difference between age, sex, perception of health, and health behavior were found. 3) Pattern of health behavior among Korean adults focused on stress management in order to obtain emotional stability, and balance and harmony in dietary life, and energy conservation. Patterns of health behavior in Korean adults is unique in each individual. Therefore nursing intervention skill for health promotion have to be developed based on the health behavior in each individual.

• Journal of Haehwa Medicine
• /
• v.17 no.1
• /
• pp.157-166
• /
• 2008

1. Vertigo and dizziness is also called as Mok-hyun, Hyun-mo, Pung-hyun, Du-pung-hyun-un, Du-sun. 2. Causes and processes of Vertigo and dizziness are mainly divided into external infection and internal damage. Wind, cold, dampness and summer heat are included in the one and in the other, vital energy and blood deficiency, insufficiency of the liver and kidney, retention of phlegm and fluid, emotional disorder and so on. 3. Symptoms of vertigo and dizziness are disequilibrium, nausea, inability of hearing, vomiting, sweating and syncope. 4. Treating of vertigo and dizziness are recovery of vital energy and blood deficiency, strenthening of insufficiency of the liver and kidney, drying of dampness and removing of phlegm.

• Science of Emotion and Sensibility
• /
• v.16 no.1
• /
• pp.117-124
• /
• 2013

This study examined that how precisely MFCC, LPC, energy, and pitch related parameters of the speech data, which have been used mainly for voice recognition system could predict the vocal emotion categories as well as dimensions of vocal emotion. 110 college students participated in this experiment. For more realistic emotional response, we used well defined emotion-inducing stimuli. This study analyzed the relationship between the parameters of MFCC, LPC, energy, and pitch of the speech data and four emotional dimensions (valence, arousal, intensity, and potency). Because dimensional approach is more useful for realistic emotion classification. It results in the best vocal cue parameters for predicting each of dimensions by stepwise multiple regression analysis. Emotion categorizing accuracy analyzed by LDA is 62.7%, and four dimension regression models are statistically significant, p<.001. Consequently, this result showed the possibility that the parameters could also be applied to spontaneous vocal emotion recognition.

• Journal of Korean Society for Atmospheric Environment
• /
• v.22 no.4
• /
• pp.421-430
• /
• 2006

This paper explores a new methodology of socio-statistical survey to classify environmental perception characteristics and to quantify atmospheric environmental sensitivity of neighboring people around a large industrial complex. In order to compensate intrinsic inclination against environmental problems, Atmospheric Environmental Sensitivity Index (AESI) is proposed as the weighted-summation of four representative questions asking the current status of the local air quality, which are chosen by the factor analysis of questionnaire. Atmospheric environmental perception is tried to be classified into interest/indifference characteristics and rational/emotional perception on environmental issues, positive/negative opinion on the solution of environmental problems. According to the chi-square cross-correlation and two-way layout analyses, it was clearly shown that environmental perception is categorized into two major groups, i.e., the positive-rational group having lower AESI and the negative-emotional group having higher AESI which means more seriously senses the status of local air quality.

• Proceedings of the KOSOMBE Conference
• /
• v.1997 no.11
• /
• pp.455-458
• /
• 1997

We are exposed to the various external stimuli input from the environment, which cause emotional changes based on the characteristics of the stimuli. Unfortunately, there are no quantitative results on relationship between human sensibility and the characteristics of physiological signals. The objective of this study was to quantify EEG signals evoked by visual stimulation based on the assumption that the analysis of the variability on the characteristics of the EEG waveform may provide the significant information regarding changes in psychological states of the subject. Seven university students were participated in this study. The experiment was devised with eleven experimental conditions, which are control and ten different types of visual stimulation based on IAPS (International Affective Picture Systems). Wavelet transformation was employed to analyze the EEG signals. Most positive and negative emotional response were compared in pairs. The results showed that the reconstructed signals at the decomposition level revealed the different energy value on the EEG signals. Also, general patterns of EEG signals in rest state compare with positive and negative stimulus were found. This study could be extended to establish an algorithm which distinguishes psychophysiological states of the subjects exposed to the visual stimulation.

• Proceedings of the ESK Conference
• /
• 1997.10a
• /
• pp.477-481
• /
• 1997

We are exposed to the various external stimuli input from the environment, which cause emotional changes based on the characteristics of the stimuli. Unfortunately, there are noquantitative results on relationship between human sensibility and the characteristics of physiological signals. The objective of this study was to quantify EEG signals evoked by visual stimulation based on the assumption that the analysis of the variability on the characteristics of the EEG waveform may provide the significant information regarding changes in psychological states of the subject. Seven university students were participated in this study. The experiment was devised with eleven experimental conditions, which are control and ten different types of visual stimulation based on IAPS(International Affective Picture Systems). Seven subjects were used to obtain EEGs while introducing visual stimulation. Wavelet transformation was employed to analyze the EEG signals. Most Positive and negative emotional response were pairely compared. The results showed that the reconstructed signals at the decomposition level revealed the different energy value on the EEG signals. Also, general patterns of EEG signals in rest state compare with negative and positive stimulus were found. This study could be extended to estabish an algorithm which distinguishes psychophysiological states of the subjects exposed to the visual stimulation.

• Research in Community and Public Health Nursing
• /
• v.6 no.2
• /
• pp.212-233
• /
• 1995

Cerebrovascular diseases in Korea is an important health problem since mortality and mobidity have been increasing rapidly. Cerebrovascular diseases marked the 2nd rank of cause specific death rate in 1993. The ploblem of emotion after a stroke has received very little attention from the nursing profession until recently. Even the frequency of the emotional disorder after stroke is uncertain, and there has been very little research. Emotional disorder after stroke was related to limited social function, guilty conscience, helplessness, hopelessness, powerlessness, alienation, and damage of self-image. In the stroke patient, hope may be related to a rehabilitation or enhancing physical condition. Inspiring hope is necessary when stroke patients are unable to mobilize energy on their own behalf and perceive limited or no person choices available. Inspiring hope is an intervention that can be used with many nursing diagnoses, especially when feelings of helplessness, hopelessness, powerlessness, and depression are present. The nurse can inspire hope by understanding the hoping process. On the basis of this literature review, the following suggestions are prosed. 1) Qualitative studies on hope have been done to indentify variables that affect maintenance of hope in the chronically ill patients. 2) In the development of an instrument to measure hope, the validity, reliability, and cultural property of the hope have been estabilished.

• 한국태양에너지학회:학술대회논문집
• /
• 2009.11a
• /
• pp.205-210
• /
• 2009

Generally, the building's windows and ventilation for the purpose of mining and the vista and windows by emotional engineering design area is a growing trend. According to the flow of energy is lost from the building, will be achieved through the walls and roof and windows. Among these, the window through the loss of about 45% of the entire building is big enough to rate. In addition, the building regulation U-value Limitation of window is $3.3W/m^2$ K in southern regions, while U-value Limitation of wall is $0.35{\sim}0.58W/m^2$ K. It means that the energy loss through windows is six times more than it through wall. Therefore, the purpose of this study is to evaluate the environmental performance of the super window system by verification experiment. The results of this study are as follows; 1)Thermal performance of insulated Super Window measured as $1.44W/m^2$ $^{\circ}C$ 2)Required energy for heating was cut down about 5.3% from 266.99 $MJ/m^2$ yr to 252.85 $MJ/m^2$ yr 3)Super Window's reduction rates increased 4.1% from 31.48% to 35.58% when it is compared to normal windows. 4)Building energy efficiency rating elevated from 2nd rating to 1st rating.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.40 no.5
• /
• 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.