• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제11권2호
• /
• pp.124-128
• /
• 2011

Music emotion recognition is currently one of the most attractive research areas in music information retrieval. In order to use emotion as clues when searching for a particular music, several music based emotion recognizing systems are fundamentally utilized. In order to maximize user satisfaction, the recognition accuracy is very important. In this paper, we develop a new music emotion recognition system, which employs a multilabel feature selector and multilabel classifier. The performance of the proposed system is demonstrated using novel musical emotion data.

• 한국멀티미디어학회논문지
• /
• 제25권2호
• /
• pp.215-220
• /
• 2022

Emotion recognition is one of the most important and challenging areas of computer vision. Nowadays, many studies on emotion recognition were conducted and the performance of models is also improving. but, more research is needed on emotion recognition and sentiment analysis of video viewers. In this paper, we propose an emotion analysis system the includes a sentiment analysis model and an interest prediction model. We analyzed the emotional patterns of people watching popular and unpopular videos and predicted the level of interest using the emotion analysis system. Experimental results showed that certain emotions were strongly related to the popularity of videos and the interest prediction model had high accuracy in predicting the level of interest.

• Journal of Multimedia Information System
• /
• 제1권1호
• /
• pp.55-67
• /
• 2014

Image topic and emotion analysis is an important component of online image retrieval, which nowadays has become very popular in the widely growing social media community. However, due to the gaps between images and texts, there is very limited work in literature to detect one image's Topics and Emotions in a unified framework, although topics and emotions are two levels of semantics that often work together to comprehensively describe one image. In this work, a unified model, Joint Topic/Emotion Multi-Modal Hierarchical Latent Dirichlet Allocation (JTE-MMHLDA) model, which extends previous LDA, mmLDA, and JST model to capture topic and emotion information at the same time from heterogeneous data, is proposed. Specifically, a two level graphical structured model is built to realize sharing topics and emotions among the whole document collection. The experimental results on a Flickr dataset indicate that the proposed model efficiently discovers images' topics and emotions, and significantly outperform the text-only system by 4.4%, vision-only system by 18.1% in topic detection, and outperforms the text-only system by 7.1%, vision-only system by 39.7% in emotion detection.

• 대한인간공학회지
• /
• 제22권3호
• /
• pp.1-11
• /
• 2003

The objective of this research is the development of the Automatic Subjective Assessment System (ASAS). The proposed subjective assessment system is designed to evaluate human emotion and sensibility (or "gamsung" in Korean terminology) with subjective responses of volunteers about the experiment of emotion and sensibility. Once volunteers enter their subjective responses about the experiment into the developed system, the proposed system can automatically generate statistical results of human emotion and sensibility using Statistical Package for the Social Sciences (SPSS). Then, the system stores the statistical results in the database which will be open to public through internet. The proposed system will be integrated into the universal" gamsung" assessment system for evaluation of human emotion and sensibility.

• 한국융합학회논문지
• /
• 제8권7호
• /
• pp.323-330
• /
• 2017

유아시기 정서발달은 전반의 발달에 중요한 의미를 갖는다. 지속적인 마음 상태인 정서는 일시적인 마음상태인 감정의 인식과 처리가 핵심 자원이 되어 발달한다. 본 연구의 목적은 정서발달에 중요한 유아시기 감성인식 기술을 이용한 교사의 효율적인 감정코칭을 제안하며, 그 효과의 유의성을 정량적으로 검증하고자 한다. 교사2명, 유아 42명 피험자를 대상으로 기준 무자극, 행동코칭, 감정코칭, 감성인식 시스템 피드백 감정코칭 자극을 제시하였고 영상기반 집단의 행동 양과 유아 개별의 주관평가 그리고 Heart Math Tools을 이용하여 HRC (Heart Rhythm Coherence)을 측정하여 분석하였다. 결론적으로 유아의 주관평가, 영상의 움직임 양, HRC (Heart Rhythm Coherence)수치는 감성인식시스템 피드백 수업 시 긍정적인 유의한 차이를 보였다. 단 주관평가는 감정코칭과 감성인식 시스템 피드백과는 차이가 나지 않았지만 정량적인 데이터 유아의 행동 양에서는 그 양이 증가하는 결과를 확인하였다. 이는 유아의 주관적 반응에 미흡한 정보를 정량적 데이터로 보완 할 수 있으며, 기관에서 정서교육의 효과적 접근으로 감정코칭 교육 프로세스 시스템을 제안하며 아동 정서발달의 정량적 연구 활용이 가능할 것으로 사료 된다.

• 디지털융복합연구
• /
• 제17권1호
• /
• pp.239-247
• /
• 2019

감정을 정확히 예측하는 것은 환자중심의 의료디바이스 개발 및 감성관련 산업에서 매우 중요한 이슈이다. 감정예측에 관한 많은 연구 중 감정 예측에 심박 변동성과 뉴로-퍼지 접근법을 적용한 연구는 없다. 본 연구는 HRV를 이용한 ANFEP(Adaptive Neuro Fuzzy system for Emotion Prediction)을 제안한다. ANFEP의 핵심 기능은 인공 신경망과 퍼지시스템을 통합해 예측 모델을 학습하는 ANFIS(Adaptive Neuro-Fuzzy Inference System)에 기반한다. 제안 모형의 검증을 위해 50명의 실험자를 대상으로 청각자극으로 감정을 유발하고, 심박변이도를 구하여 ANFEP 모형에 입력하였다. STDRR과 RMSSD를 입력으로 하고 입력변수 당 2개의 소속함수로 하는 ANFEP모형이 가장 좋은 결과를 나타났다. 제안한 감정예측 모형을 선형회귀 분석, 서포트 벡터 회귀, 인공신경망, 랜덤 포레스트와 비교한 결과 본 제안모형이 가장 우수한 성능을 보였다. 연구 결과는 보다 적은 입력으로 신뢰성 높은 감정인식이 가능함을 입증했고, 이를 활용해 보다 정확하고 신뢰성 높은 감정인식 시스템 개발에 대한 연구가 필요하다.

• 대한인간공학회지
• /
• 제31권6호
• /
• pp.757-764
• /
• 2012

Objective: The aim of this study is to find the optimal values of sliding factors which influence the mechanical emotion of users when they use sliding type mobile phones. Background: There are various researches that study the emotion of using mobile phones. They focus the correlation between emotion words and design factors and use the commercial products by the subjects in the experiment. However, it has a limit in finding the optimal point of emotional factors because we can search the restricted values in the mass production of the products. Therefore, we will find the optimal points by realizing the full range of the user's mechanical emotion. Method: First, we need to get the detailed factors which can describe the mechanical emotion in sliding up and down the mobile phone. Next, we find the control factors by considering the correlation between the factors of the sliding emotion and the possibility of quantitative design. To find the optimal points on the control factors, we make a sliding evaluation system which can help users feel the sliding mechanical emotion by realizing control factors. Finally, we find the optimal points by doing the experiment the system being used. Results: The critical values of the factors which are the main variables of this study are Open Max Force and Dead point Ratio. The optimal point of the Open Max Force is 200~250g/f, and the Dead point Ratio is 40~50%. Conclusion: In this study we develop the sliding evaluation system to realize the control factors of the sliding type phone and find the optimal values of the critical factors. Application: The results can be used as the criteria for designing sliding type phone.

• 감성과학
• /
• 제10권1호
• /
• pp.1-11
• /
• 2007

노인의 일상생활을 편안하고 즐겁게 지낼 수 있도록 도와주는 동반자 로봇의 기능 중 부정적인 감정/정서상태 개선을 위한 Infotainment Service를 소개한다. 노인의 일상생활 중에서 부정적인 감정/정서상태를 정의하고, 이들의 정서상태를 개선할 수 있는 방법들을 모색한다. 인지행동치료에서의 배경지식을 기반으로 노인의 부정적인 정서상태를 개선할 수 있는 애니메이션 클립들을 제작, 편집하여 검증해 보기로 한다. 또한, 검증된 애니메이션 클립들을 이용하여 바람직한 감정상태로의 전이를 위한 감성 컨텐츠를 제공하는 기능을 도출한다. 구체적으로 일련의 실험적 접근방법을 토대로 제작, 편집한 애니메이션 클립을 이용하여 영화의 감정요소를 분석할 수 있는 도구를 설계하고, 기존의 선호도를 고려한 영화추천 시스템을 확장한 감정요소를 고려한 영화 추천시스템을 제안한다.

• 로봇학회논문지
• /
• 제3권2호
• /
• pp.154-163
• /
• 2008

This paper presents the concept for the development of a pet-type robot with an emotion engine. The pet-type robot named KOBIE (KOala roBot with Intelligent Emotion) is able to interact with a person through touch. KOBIE is equipped with tactile sensors on the body for interaction with a person through recognition of his/her touching behaviors such as "Stroke","Tickle","Hit". We have covered KOBIE with synthetic fur fabric in order to can make him/her feel affection as well. KOBIE is able to also express an emotional status that varies according to the circumstances under which it is presented. The emotion engine of KOBIE's emotion expression system generates an emotional status in an emotion vector space which is associated with a predefined needs and mood models. In order to examine the feasibility of our emotion expression system, we verified a changing emotional status in our emotion vector space by a touching behavior. We specially examined the reaction of children who have interacted with three kind of pet-type robots: KOBIE, PARO, AIBO for roughly 10 minutes to investigate the children's preference for pet-type robots.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2002년도 하계종합학술대회 논문집(4)
• /
• pp.377-380
• /
• 2002

In this paper, speaker and context independent 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 to evaluate the performance of the conventional pattern matching algorithms. The vector quantization based emotion recognition system is proposed for speaker and context independent emotion recognition. Experimental results showed that vector quantization based emotion recognizer using MFCC parameters showed better performance than that using the Pitch and energy Parameters.