• 한국정보과학회논문지:소프트웨어및응용
• /
• 제37권10호
• /
• pp.779-787
• /
• 2010

최근 로봇의 다양한 활용과 더불어 로봇-사람간의 상호작용에 대한 연구 또한 활발하게 진행되고 있으며, 대표적으로 자연어 처리나 대화중 제스처 생성 등의 방법이 로봇과 사람간의 의사소통에 적용되었다. 그러나 기존의 로봇-사람간의 의사소통을 위한 방법을 통해서는 정적인 의사소통만을 수행할 수 있다는 한계가 존재하며, 보다 자연스럽고 사실적인 의사소통 방법에 대한 연구가 필요하다. 본 논문에서는 보다 수준 높은 의사소통을 위해 감정형 제스처 기반 대화 관리 시스템을 제안한다. 제안하는 시스템은 베이지안 네트워크와 패턴 매칭을 이용하여 로봇과 사람간의 대화를 수행함과 동시에 로봇-사람간의 대화 도중 실시간으로 상황에 어울리는 로봇의 감정형 제스처를 생성한다 감정형 제스처 생성을 통해 로봇은 사람에게 대화를 보다 효과적으로 전달함과 더불어 사실적인 상호작용을 수행할 수 있다. 제스처 생성은 동적으로 변화하는 대화 상황에 유연하게 대처할 수 있도록 행동 네트워크를 사용하였다. 이후 제안하는 감정형 제스처 기반 시스템의 유용성을 검증하기 위해 사용성 평가를 통해 감정이니 제스처를 사용하지 않는 기존의 대화 관리 시스템과의 비교를 수행하였다.

• 한국음향학회지
• /
• 제25권6호
• /
• pp.269-276
• /
• 2006

본 논문은 이동전화 (Cellular phone)를 통해 실시간으로 습득된 음성으로부터 사람의 감성 상태를 평상 혹은 화남으로 인식할 수 있는 음성 감성인식 시스템을 제안하였다. 일반적으로 이동전화를 통해 수신된 음성은 화자의 환경 잡음과 네트워크 잡음을 포함하고 있어 음성 신호의 감성특정을 왜곡하게 되고 이로 인해 인식 시스템에 심각한 성능저하를 초래하게 된다. 본 논문에서는 이러한 잡음 영향을 최소화하기 위해 비교적 단순한 구조와 적은 연산량을 가진 MA (Moving Average) 필터를 감성 특정벡터에 적용해서 잡음에 의한 시스템 성능저하를 최소화하였다. 또한 특정벡터를 최적화할 수 있는 SFS (Sequential Forward Selection) 기법을 사용해서 제안 감성인식 시스템의 성능을 한층 더 안 정화시켰으며 감성 패턴 분류기로는 k-NN과 SVM을 비교하였다. 실험 결과 제안 시스템은 이동통신 잡음 환경에서 약 86.5%의 높은 인식률을 달성할 수 있어 향후 고객 센터 (Call-center) 등에 유용하게 사용될 수 있을 것으로 기대된다.

• 한국의류산업학회지
• /
• 제21권4호
• /
• pp.390-400
• /
• 2019

A major factor in making current hospital gowns is how to manage patients from the standpoint of hospitals. This shows that hospital gowns have not been considered as an apparel for a specific purpose with a design that considers the psychological composure of patients. This study, along with a meticulous analysis of the pattern design of domestic hospital gown suggests a design philosophy that can be of emotional help to patients. The analysis of hospital gowns in terms of motif is that the corporate identity of the hospital in question, along with the lettering symbolizing the hospital is conspicuous. The motif shown in the pattern also has a brightness contrast and two-way pattern. This study suggests hospital gown patterns as follows. First, on the basis of color dynamics, utilize repetition arrangement, camaieu arrangement and faux camaieu arrangement. Second, make use of warm colors in order to enhance trust between patients and medical staff. Last, use green color as a dominant color for the hospital to be felt of as a convenient space. Utilizing these three factors in the future design of hospital gowns will assist in the development of new hospital gowns that render a psychological composure.

• 대한간호학회지
• /
• 제29권1호
• /
• pp.61-71
• /
• 1999

Sleep is a necessity for survival. Disruption of sleep leads to numerous adverse physiological and psychological consequences. These could be particularly undesirable for older patients, who are subject to many additional factors. But there is limited research related to hospitalized elderly in Korea. The purpose of the study is to explore sleep patterns and disturbing factors of before and after hospitalization, in order to present basic information regarding elderly sleep to develop nursing intervention. The sample consisted of 32 elderly men and women between the ages of n and 87 years. Data collection was done from September to November 1997. Measures of sleep patterns and related factors were obtained from self-reported sleep questionnaires. Analysis of data was done by use of t-test, paired t-test, ANOVA, and Pearson Correlation Coefficient. The results of this study were summarized as follows : 1. In comparision between before and after admission of their sleep pattern, “sleep onset” tends to be delayed and nocturnal sleep time was significantly reduced. So, hospitalized elderly reported less total sleep time than before admission. 2. Regarding the sleep disturbing factors, medication(hypnotics ; 37.5%), physiological factor (snoring ; 59.4%) environmental factor (pillow ; 78.1%), emotional factor(anxiety related to disease ; 37.5%), and illness factor(fatigue ; 34.7%) were reported. 3. Significant differences in gender were found. Men had more disturbances in sleep than women owing to difficulty in falling a sleep and lack of nocturnal sleep. Women consumed more sleep inducing drugs. Significant increase was reported in napping during the day with increasing age. 4. Significant differences between good sleepers and poor sleepers were found for the following variables : nocturnal sleep time, total sleep time, bed time, sleep onset latency time, sleep latency time after nocturnal awakening, time spent in bed upon arousal, environmental factors, and emotional factors. In conclusion, it was found that the quantity and quality of sleep were significantly altered in hospitalized elderly, but adequate strategies for better sleep were not practiced. Further research is needed to develop Intervention strategies to promote sleep and to prevent sleep problems.

• 한국의류산업학회지
• /
• 제15권3호
• /
• pp.347-357
• /
• 2013

The nursery active-wear uniform designs of Internet shopping malls are simple and similar; however, the latest children's wear trends (mostly composed of training jumpers and pants) do not reflect these qualities. Children's folklore plays (widely used in child education) have an instructive value for the emotional and intellectual development of a child. Nursery active-wear uniform designs applied to children's folklore's plays could be positive for the emotional development and specialized cultural education of children. We designed three nursery active-wear uniforms with three different design concepts (casual, semi-formal and sporty) regardless of sex. The main color of the three nursery active-wear uniforms was yellow. We used three different chroma and values of yellow through three design concepts: Design I of a nursery active-wear uniform (a training suit style with a good activity), Design II of a nursery active-wear uniform (a semi suit style), and Design III of a nursery active-wear uniform (a sportswear style that reflected a sport wear trend). We expressed children's folklore plays in the pattern of a nursery active-wear uniform. The pattern was characterized as a pair of bears flying kites. This pattern was utilized in three nursery active-wear uniforms with the logo and name of the nursery. We modified the designs of active-wear nursery uniforms based on an evaluation of 33 special panels. We made three nursery active-wear uniforms for five-year olds.

• 한국감성과학회:학술대회논문집
• /
• 한국감성과학회 2000년도 춘계 학술대회 및 국제 감성공학 심포지움 논문집 Proceeding of the 2000 Spring Conference of KOSES and International Sensibility Ergonomics Symposium
• /
• pp.366-369
• /
• 2000

This paper examines three algorithms to recognize speaker's emotion using the speech signals. Target emotions are happiness, sadness, anger, fear, boredom and neutral state. MLB(Maximum-Likeligood Bayes), NN(Nearest Neighbor) and HMM (Hidden Markov Model) algorithms are used as the pattern matching techniques. In all cases, pitch and energy are used as the features. The feature vectors for MLB and NN are composed of pitch mean, pitch standard deviation, energy mean, energy standard deviation, etc. For HMM, vectors of delta pitch with delta-delta pitch and delta energy with delta-delta energy are used. We recorded a corpus of emotional speech data and performed the subjective evaluation for the data. The subjective recognition result was 56% and was compared with the classifiers' recognition rates. MLB, NN, and HMM classifiers achieved recognition rates of 68.9%, 69.3% and 89.1% respectively, for the speaker dependent, and context-independent classification.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2006년 학술대회 논문집 정보 및 제어부문
• /
• pp.214-216
• /
• 2006

Expressive face and human body gestures are among the main non-verbal communication channels in human-human interaction. Understanding human emotions through body gesture is one of the necessary skills both for humans and also for the computers to interact with their human counterparts. Gesture analysis is consisted of several processes such as detecting of hand, extracting feature, and recognizing emotions. Skin color information for tracking hand gesture is obtained from face detection region. We have revealed relationships between paricular body movements and specific emotions by using HMM(Hidden Markov Model) classifier. Performance evaluation of emotional human body recognition has experimented.

• 제어로봇시스템학회논문지
• /
• 제13권8호
• /
• pp.754-759
• /
• 2007

In this paper, we proposed the Bi-Modal Sensor Fusion Algorithm which is the emotional recognition method that be able to classify 4 emotions (Happy, Sad, Angry, Surprise) by using facial image and speech signal together. We extract the feature vectors from speech signal using acoustic feature without language feature and classify emotional pattern using Neural-Network. We also make the feature selection of mouth, eyes and eyebrows from facial image. and extracted feature vectors that apply to Principal Component Analysis(PCA) remakes low dimension feature vector. So we proposed method to fused into result value of emotion recognition by using facial image and speech.

• 한국병원경영학회지
• /
• 제15권3호
• /
• pp.17-32
• /
• 2010

The purpose of this study is to analyze the influence of DISC behavior pattern, stress-managing method, and the stress level on job attitude of hospital Employees, and to provide suggestions for effective human resources management in hospital settings. First, the research suggested emotional or aversive stress-managing method had significant influence to the stress level, whereas DISC behavior patterns did not. Second, to the job satisfaction, Influence, Compliance and Steadiness of DISC behavior patterns, challenging or aversive stress-managing method, and the stress level showed immediate meaningful effect. Third, for the system immersion, challenging or emotional ress-managing method as well as the job satisfaction showed direct influence. Especially, the challenging method had not only a direct but an indirect effect through mediating job satisfaction.

• 한방비만학회지
• /
• 제8권2호
• /
• pp.63-72
• /
• 2008

Objectives We aimed to explore obesity pattern among overweight and obese Korean adult women using oriental obesity pattern identification questionnaire. Methods This survey was performed using data of 83 overweight and obese women aged from 20 to 55 yrs (BMI ${\geq}\;23\;kg/m^2$ : n=18, BMI ${\geq}\;25\;kg/m^2$ :ｎ=65) in Seoul, from 2007 to 2008. Subjects were given written consent and this study was performed under the permission of institutional review board of Kyung-Hee East-west Neo Medical Center. Results 1. The distribution of oriental obesity pattern identification did not show any differences between obese and overweight group(p>0.05). 2. The ratio of significantly-scored oriental pattern identification was ordered by Stagnation of the liver Qi(肝欝, 21.7%) > Indigestion(食積, 18.1%) > Spleen deficiency(脾虚, 16.9%) > Yang deficiency(陽虚, 14.5%) (n=83). 3. The frequency of top-scored oriental obesity pattern was ordered by Stagnation of the liver Qi(肝欝, 36.1%) > Indigestion(食積, 24.1%) > Yang deficiency (陽虚, 15.7%) (n=83). 4. The frequency of oriental obesity pattern identification was ordered by Stagnation of the liver Qi(肝欝, 41.7%) > Indigestion(食積, 29.2%) > Yang deficiency(陽虚, 12.5%) > Stagnation of the liver Qi and Yang deficiency(肝欝兼陽虚, 8.3%) (n=24). Conclusions In Korean adult overweight and obese women, Stagnation of the liver Qi(肝欝), Indigestion(食積), and Yang deficiency (陽虚) were found to be the main pathology based on oriental obesity pattern identification questionnaire. It suggests that not only physical status but also general condition and emotional problem should be concerned in treatment of obesity. This study could play a role as a preliminary data of oriental obesity pattern identification.