• Proceedings of the Korean Society for Emotion and Sensibility Conference
• /
• 2000.04a
• /
• pp.144-148
• /
• 2000

A new paradigm is urgently needed to create the textile product that appeal to human Kansei or Gosei. A future of textiles depends heavily on this new paradigm. In order to create new paradigm Kansei color designs by pleasant sound are tried. These computing color designs are treated by the method of Fast fourier Transformation. As several result good color designs are given in forms of ring color patterns and band. But these judgments depend finally on human kansei. These new technology give us good hints in order to create new paradigm that appeal to Kansei goods. This new concept should be developed to higher level by additional improvements.

• Proceedings of the Korean Society for Emotion and Sensibility Conference
• /
• 2003.11a
• /
• pp.141-142
• /
• 2003

본 논문에서는 이성간의 대화에서 여성을 상대로 이성에 대하여 관심이 있을 경우와 관심이 없을 경에 따른 성문 특성변화를 비교 연구하였다. 대화내용을 녹음한 음성신호의 분석을 거쳐 얻어낸 결과로부터 보면 여성은 자신이 관심을 갖지 않는 상대에 대하여서는 17.2％ 미만의 응답을 보여주는 반면 관심이 있는 상대에 대하여서는 45.1％ 좌우 또는 그 이상의 응답을 보여주고 있다. 대화 내용의 음성신호를 스펙트로그램으로 표현 하였을 경우 성문 특성의 변화는 매우 뚜렷하다. 주파수 측면으로부터 보면 여성은 관심 있는 이성과 대화할 경우 200Hz에서 450Hz 좌우의 기본 주파수 폭을 이루게 되지만 관심이 없는 상대에 대해서는 200Hz에서 320Hz 정도의 기본 주파수 폭을 나타내게 된다. 따라서 이성간 대화에서 이러한 성문 특성의 변화를 이용하여 상대방 호감도를 측정할 수 있는 제품 개발에도 본 논문에서의 연구내용이 용이하게 쓰일 것으로 예상하고 있다.

• Proceedings of the Korean Society for Emotion and Sensibility Conference
• /
• 1998.11a
• /
• pp.65-69
• /
• 1998

진화 연산을 이용하여 최적화 문제를 푸는데 있어서 가장 잘 알려져 있는 문제 중의 하나는 미완숙 수렴이다. 일반적인 제한 최적화 문제를 푸는 기법으로서 제안된 하이브리드 진화프로그래밍(EP), 이상 EP(TPEP), Evolian 등과 같은 알고리즘도 첫 번째 상에서 이와 같은 문제점을 내포하고 있다. 본 논문에서는 이같은 문제점을 극복하기 위해서 Evolian 알고리즘에 공유 함수 기법을 적용하고 다음 상들을 위해서는 다중 라그랑지안 승수를 사용하고자 한다. 부개체군 영역에서 각각의 라그랑지안 승수들을 설정하고 병렬적으로 갱신해 나가면서 전역적인 최적해를 병렬적으로 찾아나간다. 컴퓨터 모의 실험을 통해서 제안된 공유 기법 및 다중 라그랑지안 승수 기법의 유용성을 보인다.

• Science of Emotion and Sensibility
• /
• v.13 no.3
• /
• pp.429-440
• /
• 2010

It is known that as many as 1 in 91 children are diagnosed with an autistic spectrum disorder, and the incidence rate of the autistic spectrum disorder is much higher than that of cancer in Korea. It is necessary to develop a novel technology to sense their emotional status and give proper psychological diagnosis and therapy, since the children with autistic spectrum disorder usually do not express their own emotional status. This article presents the state-of-the-arts on the affective computing technologies that include recognition of emotional status through bio-sensing and virtual affective agent modeling, and then proposes a novel system architecture for diagnosis and therapy of autistic spectrum disorder. The diagnosis and therapy system of autistic spectrum disorder is composed of bio-sensing module, virtual environment module with affective agents, and haptic interface module. The architecture proposed in this paper will enhance the objectivity to diagnose autism spectrum disorders, and enable continuous treatment in daily life.

• The Journal of the Acoustical Society of Korea
• /
• v.25 no.2E
• /
• pp.74-78
• /
• 2006

This paper proposes an effective method for classifying emotions of the music from its acoustical signals. Two feature sets, timbre and tempo, are directly extracted from the modified discrete cosine transform coefficients (MDCT), which are the output of partial MP3 (MPEG 1 Layer 3) decoder. Our tempo feature extraction method is based on the long-term modulation spectrum analysis. In order to effectively combine these two feature sets with different time resolution in an integrated system, a classifier with two layers based on AdaBoost algorithm is used. In the first layer the MDCT-driven timbre features are employed. By adding the MDCT-driven tempo feature in the second layer, the classification precision is improved dramatically.

• Journal of Information Technology Services
• /
• v.11 no.sup
• /
• pp.123-138
• /
• 2012

Healthcare and wellness industries have become more promising as the interests on healthy living increase. Not only the medical care oriented services for the patients done by medical centers but also the psychological and emotional healthgiving services for the people who are normal have been being stressed. The psychological and emotional healthgiving services should be executed in an agile and timely manner to maximize its effects. This paper aims to propose an emotion healing service spaces which are able to provide the normal people with psychological care services. To achieve the goals, we invented the tripot approach : the ubiquitous computing technology for context-aware and intelligent estimation of psychological index, LED technology to implement emotional atmosphere and wellness healthcare technology. The proposed architecture has been implemented in an actual site.

• Journal of Information Processing Systems
• /
• v.11 no.1
• /
• pp.76-94
• /
• 2015

For different reasons, many viewers like to watch a summary of films without having to waste their time. Traditionally, video film was analyzed manually to provide a summary of it, but this costs an important amount of work time. Therefore, it has become urgent to propose a tool for the automatic video summarization job. The automatic video summarization aims at extracting all of the important moments in which viewers might be interested. All summarization criteria can differ from one video to another. This paper presents how the emotional dimensions issued from real viewers can be used as an important input for computing which part is the most interesting in the total time of a film. Our results, which are based on lab experiments that were carried out, are significant and promising.

• Annual Conference on Human and Language Technology
• /
• 2019.10a
• /
• pp.519-521
• /
• 2019

최근 소셜 메신저를 통해 많은 사람들이 의사소통을 주고받음에 따라, 텍스트에서 감정을 파악하는 것이 중요하다. 따라서, 감정이 태깅된 데이터가 필요하다. 하지만, 기존 연구는 감정이 태깅된 데이터의 양이 많지가 않다. 이는 텍스트에서 감정을 파악하는데 성능 저하를 야기할 수 있다. 이를 해결하기 위해, 본 논문에서는 단어 매칭 방법과 형태소 매칭 방법을 이용하여 많은 양의 한국어 감정 태깅 데이터셋인 EmoNSMC 를 구축하였다. 구축한 데이터셋은 네이버 영화 감상 리뷰 데이터 (NSMC)에 디스턴트 수퍼비전 방법 (distant supervision) 방법을 적용하여 weak labeling을 진행하였고, 이 과정에서 한국어 감정 어휘 사전 (KTEA) 을 이용하였다. 구축된 데이터셋의 감정 분포 결과, 형태소 매칭 방법을 통해 구축한 데이터셋이 좀 더 감정 분포가 균등한 것을 확인할 수 있었다. 해당 데이터셋은 공개되어 있다.

• Journal of the Institute of Convergence Signal Processing
• /
• v.24 no.4
• /
• pp.221-228
• /
• 2023

Physical and mental changes caused by emotions can affect various behaviors, such as driving or learning behavior. Therefore, recognizing these emotions is a very important task because it can be used in various industries, such as recognizing and controlling dangerous emotions while driving. In this paper, we attempted to solve the emotion recognition task by implementing a multimodal model that recognizes emotions using both audio and video data from different domains. After extracting voice from video data using RAVDESS data, features of voice data are extracted through a model using 2D-CNN. In addition, the video data features are extracted using a slowfast feature extractor. And the information contained in the audio and video data, which have different domains, are combined into one feature that contains all the information. Afterwards, emotion recognition is performed using the combined features. Lastly, we evaluate the conventional methods that how to combine results from models and how to vote two model's results and a method of unifying the domain through feature extraction, then combining the features and performing classification using a classifier.

• Journal of Digital Contents Society
• /
• v.19 no.4
• /
• pp.821-827
• /
• 2018

Affective computing has gained increasing interest in the recent years with the development of potential applications in Human computer interaction (HCI) and healthcare. Although momentous research has been done on human emotion recognition, however, in comparison to speech and facial expression less attention has been paid to physiological signals. In this paper, Electroencephalogram (EEG) signals from different brain regions were investigated using modified wavelet energy features. For minimization of redundancy and maximization of relevancy among features, mRMR algorithm was deployed significantly. EEG recordings of a publically available "DEAP" database have been used to classify four classes of emotions with Multi class Support Vector Machine. The proposed approach shows significant performance compared to existing algorithms.