• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2007.11a
• /
• pp.11-14
• /
• 2007

인간과 컴퓨터간의 상호교류 하는데 있어서 감정 인식은 필수라 하겠다. 그래서 본 논문에서는 음성 신호 및 얼굴 영상을 BL(Bayesian Learning)과 PCA(Principal Component Analysis)에 적용하여 5가지 감정 (Normal, Happy, Sad, Anger, Surprise) 으로 패턴 분류하였다. 그리고 각각 신호의 단점을 보완하고 인식률을 높이기 위해 결정 융합 방법과 특징 융합 방법을 이용하여 감정융합을 실행하였다. 결정 융합 방법은 각각 인식 시스템을 통해 얻어진 인식 결과 값을 퍼지 소속 함수에 적용하여 감정 융합하였으며, 특정 융합 방법은 SFS(Sequential Forward Selection)특정 선택 방법을 통해 우수한 특정들을 선택한 후 MLP(Multi Layer Perceptron) 기반 신경망(Neural Networks)에 적용하여 감정 융합을 실행하였다.

• MALSORI
• /
• no.62
• /
• pp.19-32
• /
• 2007

This study investigated the perception of emotional voices by transplanting some or all of the prosodic aspects, i.e. pitch, duration, and intensity, of the utterances produced with emotional voices onto those with normal voices and vice versa. Listening evaluation by 24 raters revealed that prosodic effect was greater than segmental & vocal quality effect on the preception of the emotion. The degree of influence of prosody and that of segments & vocal quality varied according to the type of emotion. As for fear, prosodic elements had far greater influence than segmental & vocal quality elements whereas segmental and vocal elements had as much effect as prosody on the perception of happy voices. Different amount of contribution to the perception of emotion was found among prosodic features with the descending order of pitch, duration and intensity. As for the length of the utterances, the perception of emotion was more effective with long utterances than with short utterances.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.8 no.1
• /
• pp.31-42
• /
• 2013

Considerations of how to facilitate aging-in-place(AIP) are becoming increasingly pertinent as care-givers are overwhelmed by an aging population. Aging friendly home-care services combined with IT can satisfy the needs of the elderly suffer from chronic diseases such as depression and dementia. Therefore, we propose future smart phone services and application technologies which can estimate emotional states of the aged and respond to the desire to be happy with mental health, connectedness and consolation from peoples. Firstly, we introduce depression measurement techniques to estimate the severity of depression using multiple sensors. At second, the emotional responding services are categorized to four parts and the details are described. Lastly, we propose the process to implement emotional communication and the application techniques(services) to fulfill the emotional satisfaction and mental healthcare for AIP using smart phone as a mediator.

• 한국HCI학회:학술대회논문집
• /
• 2006.02a
• /
• pp.555-558
• /
• 2006

감정을 포함하고 있는 음성은 청자로 하여금 화자의 심리상태를 파악할 수 있게 하는 요소 중에 하나이다. 음성신호에 포함되어 있는 감정을 인식하여 사람과 로봇과의 원활한 감성적 상호작용을 위하여 특징을 추출하고 감정을 분류한 방법을 제시한다. 음성신호로부터 음향정보 및 운율정보인 기본 특징들을 추출하고 이로부터 계산된 통계치를 갖는 특징벡터를 입력으로 support vector machine (SVM) 기반의 패턴분류기를 사용하여 6가지의 감정- 화남(angry), 지루함(bored), 기쁨(happy), 중립(neutral), 슬픔(sad) 그리고 놀람(surprised)으로 분류한다. SVM에 의한 인식실험을 한 경우 51.4%의 인식률을 보였고 사람의 판단에 의한 경우는 60.4%의 인식률을 보였다. 또한 화자가 판단한 감정 데이터베이스의 감정들을 다수의 청자가 판단한 감정 상태로 변경한 입력을 SVM에 의해서 감정을 분류한 결과가 51.2% 정확도로 감정인식하기 위해 사용한 기본 특징들이 유효함을 알 수 있다.

• Journal of East-West Nursing Research
• /
• v.22 no.2
• /
• pp.138-147
• /
• 2016

Purpose: This study aimed to explore the experiences of participation in community leisure programs among older adults. Methods: Data were collected using face-to-face interviews with nine older adults participated in community leisure programs and analyzed using a qualitative content analysis. Results: Seven themes emerged from the data: 1) A deep regret not learned, 2) unboring life, 3) living together, 4) having a happy life, 5) gaining recognition from family members, 6) cherishing their own lives, and 7) living for others. Conclusion: Findings indicate that there is a need for health professionals to understand meanings of participation in community leisure programs before planning community senior programs. More studies are needed to develop community leisure programs for older adults' health promotion in community health centers.

• IE interfaces
• /
• v.15 no.2
• /
• pp.172-181
• /
• 2002

Customer satisfaction is undoubtedly one of the top strategic issues in the new decade. Today, many organizations are rushing to become more customer focused. A key component of many initiatives is the implementation of customer satisfaction software. In this paper, we provide a case study for customer satisfaction management in a city gas company. The three issues include the plan for giving premiums and the development of a happycall system and a web-based measurement system for customer satisfaction.

• 전기의세계
• /
• v.30 no.5
• /
• pp.252-262
• /
• 1981

The Institute of Electrical Engineers of Japan (JIEE) was founded far back in 1888, in the very dawn period of the electric power utilities, For the past 93 years since its establishment, the JIEE has been contributing much, in the same manner as you, towared technological progress and industrial growth in many fields of electrical engineering in Japan. Now, I am very happy to say that it will certainly be a matter of great significance for the Institute of Electrical Engineers in both countries to exert their cooperative efforts for establishment of new technologies towared the future. Today I would like to introuduce you the current status fo electrical power engineering in the Japanese electric utilities and to refer to the future R and D tasks coping with the severe energy situation.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2005.11a
• /
• pp.179-184
• /
• 2005

Recently, studying on modeling the emotion of a robot has become issued among fields of a humanoid robot and an interaction of human and robot. Especially, modeling of the motivation, the emotion, the behavior, and so on, in the robot, is hard and need to make efforts to use our originality. In this paper, new modeling using mathematical formulations to represent the emotion and the behavior selection is proposed for the software robot with virtual sensor modules. Various Points which affect six emotional states such as happy or sad are formulated as simple exponential equations with various parameters. There are several experiments with seven external sensor inputs from virtual environment and human to evaluate this modeling.

• Journal of Korean Society for Quality Management
• /
• v.28 no.3
• /
• pp.145-154
• /
• 2000

Effective management of knowledge is essential to keep up with demands of this challenging information age. The first step for this kind of management would be to define indicators to evaluate the quality of knowledge. In this paper, we use five latent variables (intrinsic quality, representational quality, ease of use of quality, maintainable quality, usage of quality) as basis for a preliminary path analysis for knowledge management. Preliminary study results showed that high intrinsic quality does not necessarily guarantee high frequency of use. A modified questionnaire is made and is used for SERVQUAL. The result of SERVQUAL shows that customers are not relatively happy about both intrinsic quality and its ease of use. Additional path analyses are done for both expected and observed quality indicators. The path model based on the expectation indicated that the presentation method of knowledge would induce its easy maintenance while that based on observation did not back up the same phenomenon.

• MALSORI
• /
• no.56
• /
• pp.173-183
• /
• 2005

We propose a speech emotion recognition method for affective human-robot interface. In the Proposed method, emotion is classified into 6 classes: Angry, bored, happy, neutral, sad and surprised. Features for an input utterance are extracted from statistics of phonetic and prosodic information. Phonetic information includes log energy, shimmer, formant frequencies, and Teager energy; Prosodic information includes Pitch, jitter, duration, and rate of speech. Finally a pattern classifier based on Gaussian support vector machines decides the emotion class of the utterance. We record speech commands and dialogs uttered at 2m away from microphones in 5 different directions. Experimental results show that the proposed method yields $48\%$ classification accuracy while human classifiers give $71\%$ accuracy.