• The Korean Journal of Applied Statistics
• /
• v.31 no.5
• /
• pp.539-554
• /
• 2018

Effective interaction between user and device is considered an important ability of IoT devices. For some applications, it is necessary to recognize human facial expressions in real time and make accurate judgments in order to respond to situations correctly. Therefore, many researches on facial image analysis have been preceded in order to construct a more accurate and faster recognition system. In this study, we constructed an automatic recognition system for facial expressions through two steps - a facial recognition step and a classification step. We compared various models with different sets of data with pixel information, landmark coordinates, Euclidean distances among landmark points, and arctangent angles. We found a fast and efficient prediction model with only 30 principal components of face landmark information. We applied several prediction models, that included linear discriminant analysis (LDA), random forests, support vector machine (SVM), and bagging; consequently, an SVM model gives the best result. The LDA model gives the second best prediction accuracy but it can fit and predict data faster than SVM and other methods. Finally, we compared our method to Microsoft Azure Emotion API and Convolution Neural Network (CNN). Our method gives a very competitive result.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2007.11a
• /
• pp.123-126
• /
• 2007

본 논문은 음성신호를 이용한 감정인식에 관한 연구이다. 감정인식에 관한 연구는 휴먼 인터페이스(Human Interface) 기술의 발전에서 인간과 기계의 상호작용을 위한 것이다. 본 연구에서는 음성신호를 이용하여 감정을 분석하고자 한다. 음성신호의 감정인식을 위해서 음성신호의 특정을 추출하여야한다. 본 논문에서는 개인에 따른 음성신호의 감정인식을 하고자하였다. 그래서 화자인식에 많이 사용되는 음성신호 분석기법인 Perceptual Linear Prediction(PLP) 분석을 이용하여 음성신호의 특정을 추출하였다. 본 연구에서는 PLP 분석을 통하여 개인화된 감정 패턴을 생성하여 간단하면서도 실시간으로 음성신호로부터 감정을 평가 할 수 있는 알고리즘을 만들었다.

• Annual Conference on Human and Language Technology
• /
• 2014.10a
• /
• pp.211-214
• /
• 2014

본 연구에서는 질의를 기반으로 사용자의 감정상태를 예측하는 방법을 제안한다. 제안방법은 자극-감정 규칙베이스 구축, 규칙확률 값 기반 질의 랭킹, 질의 랭킹 기반 사용자 감정예측의 단계로 구성된다. 방법의 적절성을 검증하기 위하여 힘들다와 심심하다에 대한 결과로 사용자평가를 실시하였다. 힘들다의 결과에서는 힘들다 정도에 대한 점수가 높은 질의들을 지속적으로 검색하는 사용자들을 힘들다라고 판단할 수 있다고 분석되었다. 심심하다의 결과에서는 방법 간 유의미한 차이를 보이지 않았으나, 특정 개별질의의 지속적인 패턴을 분석하는 것이 좀 더 높은 점수를 얻은 것으로 평가되었다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2006.10b
• /
• pp.459-463
• /
• 2006

사회가 개인화하고 사용자의 요구가 다양해짐에 따라, 사용자의 감성을 기반으로 하여 서비스를 제공하는 많은 연구와 응용 어플리케이션을 개발되고 있다. 그 중, 시각적인 정보에 대한 인간의 감성은 디자인, 패션, 상품개발과 같은 여러 분야에서 그 중요성이 부각되어 다각적인 측면으로 많은 연구가 진행되고 있다. 그러나, 그러한 연구들이 아직 괄목할 만한 성과를 내지 못하고 있다. 더욱이, 시각 정보로부터 유용한 요소를 추출하고, 감성을 예측하는 자동화된 시스템이 매우 미흡한 실정이다. 그러므로, 본 연구는 칼라와 텍스처를 자동으로 추출하고 그와 관련된 특정 감성에 대해 효율적으로 예측 가능한 직물감성 예측 신경망 시스템을 개발하였다. 또한 칼라와 텍스처와 같은 시각정보와 감성과의 관계를 규명하고자 각 시각 특징을 입력 값으로 하고, 감성 값을 출력 값으로 하는 신경망을 개발하였고 실험을 통해 각 감성에 따라 칼라와 텍스처 요소가 다르게 영향을 미친다는 사실을 증명할 수 있었다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.8
• /
• pp.4090-4102
• /
• 2018

After emerging online communications, text mining and sentiment analysis has been frequently applied into analyzing electronic word-of-mouth. This study aims to develop a domain-specific lexicon of sentiment analysis to predict box office success in Korea film market and validate the feasibility of the lexicon. Natural language processing, a machine learning algorithm, and a lexicon-based sentiment classification method are employed. To create a movie domain sentiment lexicon, 233,631 reviews of 147 movies with popularity ratings is collected by a XML crawling package in R program. We accomplished 81.69% accuracy in sentiment classification by the Korean sentiment dictionary including 706 negative words and 617 positive words. The result showed a stronger positive relationship with box office success and consumers' sentiment as well as a significant positive effect in the linear regression for the predicting model. In addition, it reveals emotion in the user-generated content can be a more accurate clue to predict business success.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2016.01a
• /
• pp.285-286
• /
• 2016

광고, 게임, 로봇 등 다양한 분야에서 사람의 감정을 이용한 서비스가 늘어나면서 감정 인식에 관한 연구가 활발히 진행되어 왔다. 본 논문에서는 스마트폰의 센서에서 얻어진 사용자 상황정보와 스마트시계의 심박 수 측 정 데이터를 통해 사용자의 감정을 예측하는 모델을 제안한다. 해당 모델을 생성하기 위해서 스마트폰에서 사용 자 상황정보를 수집한다. 스마트시계에서는 기분이 부정적인지 혹은 긍정적인지를 판단하기 위해 심박 수를 측정 한다. 이러한 수집된 정보를 기계 학습 알고리즘을 사용하여 감정 예측 모델을 생성하고, 이 모델을 통해 사용자 의 감정을 예측한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.818-820
• /
• 2022

The keyword 'healing' is essential to the competitive society and culture of Koreans. In addition, as the time at home increases due to COVID-19, the demand for indoor healing services has increased. Therefore, this thesis analyzes the user's facial expression so that people can receive various 'customized' healing services indoors, and based on this, provides lighting, ASMR, video recommendation service, and facial expression recording service.The user's expression was analyzed by applying the ensemble algorithm to the expression prediction results of various CNN models after extracting only the face through object detection from the image taken by the user.

• International Journal of Computer Science & Network Security
• /
• v.22 no.9
• /
• pp.334-342
• /
• 2022

Nowadays, as we can notice on social media, most users choose to use more than one language in their online postings. Thus, social media analytics needs reviewing as code-switching analytics instead of traditional analytics. This paper aims to present evidence comparable to the accuracy of code-switching analytics techniques in analysing the mood state of social media users. We conducted a systematic literature review (SLR) to study the social media analytics that examined the effectiveness of code-switching analytics techniques. One primary question and three sub-questions have been raised for this purpose. The study investigates the computational models used to detect and measures emotional well-being. The study primarily focuses on online postings text, including the extended text analysis, analysing and predicting using past experiences, and classifying the mood upon analysis. We used thirty-two (32) papers for our evidence synthesis and identified four main task classifications that can be used potentially in code-switching analytics. The tasks include determining analytics algorithms, classification techniques, mood classes, and analytics flow. Results showed that CNN-BiLSTM was the machine learning algorithm that affected code-switching analytics accuracy the most with 83.21%. In addition, the analytics accuracy when using the code-mixing emotion corpus could enhance by about 20% compared to when performing with one language. Our meta-analyses showed that code-mixing emotion corpus was effective in improving the mood analytics accuracy level. This SLR result has pointed to two apparent gaps in the research field: i) lack of studies that focus on Malay-English code-mixing analytics and ii) lack of studies investigating various mood classes via the code-mixing approach.

• Science of Emotion and Sensibility
• /
• v.12 no.1
• /
• pp.109-120
• /
• 2009

This study was carried out in order to investigate color sensation and sensibility for yellowish natural dye fabrics and reddish ones and to establish prediction models for color sensibility factors of them by color sensation and the related physical measurements focusing on 40s middle-aged people. Eight fabric stimuli which were dyed with a variety of yellowish or reddish natural dyes was subjectively evaluated in terms of color sensation and sensibility by 40s aged participants. As results, three color sensibility factors including 'Active', 'Characteristic', and 'Relax' were extracted and they were examined in respect of their relationships with color sensation and physical color properties. Color sensibility factor 'Active', the dominant factor for the naturally dyed fabrics was explained by $L^*$ and sensation 'Deep' in its predictive model and a yellowish fabric dyed with 300% solution of armur cork unmordanted was perceived the strongest in the factor. Factor 'Characteristic' was predicted by both $a^*$ and sensation 'Light' and reddish natural dye fabrics tended to be felt more strongly for it. Color sensation 'Strong' was the only predictor for factor 'Relax' in that naturally dyed fabrics with lower values for the sensation seemed to show higher 'Relax' factor and a reddish fabric dyed with safflower 125% was the highest for the color sensibility factor. These results could be utilized to design color-sensible natural dye fabrics for middle-aged people.

• Journal of the Korea Institute of Building Construction
• /
• v.19 no.1
• /
• pp.9-18
• /
• 2019

Concrete, which is the most widely used building material in modern times, has been improved not only in strength but also in structural performance such as increase in toughness and ductility, weight reduction, and improvement in quality of human life. Due to the surge in demand for the building, there is a tendency to be used variously from architectural panel and architecture to interior accessories. In Korea, a light-transmitting concrete, LEFC(Light Emotion Friendly Concrete), that insert plastic rods to stimulate emotional sensation through the combination of light and concrete has developed. In previous research, it was confirmed that the use of a synthetic foam agent rather than an animal foam agent did not cause a fogging phenomenon. In this study, lightweight by applying foaming agent to LEFC and two types of fiber (Nylon Fiber, Polyvinyl Alcohol) were compared to achieve to investigate the fiber to be applied in future. An equation that can predict the loss and adhesion reduction of the concrete section according to the diameter of the rod (5mm, 10mm) and the interval (10mm, 15mm, 20mm) was proposed.