http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Extraction of Critical Low-Level Image Features for Effective Emotion Analysis
Eui-Hwan Han(한의환),Hyung-Tai Cha(차형태) 제어로봇시스템학회 2019 제어·로봇·시스템학회 논문지 Vol.25 No.4
Sentiment analysis has received considerable critical attention in machine learning, artificial intelligence, human-computer interface, etc. In these fields, many studies have analyzed emotions using images, audio, and bio-signals as features. Among them, those that utilize image features are the most typical for emotion recognition. There are two types of image features: high-level and low-level. Low-level features are more robust than high-level in sentiment analysis. Therefore, in this paper, we investigated the critical features for effective sentiment analysis in low-level image features. For an objective performance evaluation, we utilized the International Affective Picture System dataset for training and testing. We applied the iterative Han and Cha’s feature selection/extraction algorithms and used a multilayer perceptron classification. We also carried out cross-validation by replacing features. Our evaluation items consisted of two elements: accuracy and computational time. According to our results, we were able to find the critical features in sentiment analysis and our method proved more competitive compared with existing algorithms in terms of accuracy and operation time.
복합적 감정,mixed feelings에 대한 감정차원 연구
한의환 ( Eui Hwan Han ),차형태 ( Hyung Tai Cha ) 한국감성과학회 2013 감성과학 Vol.16 No.4
In this paper, we propose new method to reduce variance and express mixed feelings in Russell`s emotional dimension(A Circumplex model). A Circumplex model shows mean and variance of emotions (joy, sad, happy, enjoy et. al.) in PAD(Pleasure, Arousal, Dominace, et. al.) dimension using self-diagnostic method(SAM: Self-Assessment- Manikin). But other researchers consistently insisted that Russell`s model had two problems. First, data(emotional words) gathered by Russell`s method have too big variance. So, it is difficult to separate valid value. Second, Russell`s model can not properly represent mixed feelings because it has structural problem (It has a single Pleasure dimension). In order to solve these problems, we change survey methods, so that we reduce value of variance. And then we conduct survey (which can induce mixed feelings) to prove Positive/Negative (Pleasure) part in emotion and confirm that Russell`s model can be used to express mixed feelings. Using this method, we can obtain high reliability and accuracy of data and Russell`s model can be applied in many other fields such as bio-signal, mixed feelings, realistic broadcasting, et. al.
한의환 ( Eui Hwan Han ),차형태 ( Hyung Tai Cha ) 한국감성과학회 2014 감성과학 Vol.17 No.3
In this paper, we verify the relation between elements (active and inactive) of Russell`s emotional dimension (A Circumplex Model) to propose a new representing method. Russell`s emotional dimension expresses emotional words (happy, joy, sad, nervous, etc.) as a point on the two dimensions (Arousal and Valence). It is most commonly used in many filed such as Science of Emotion & Sensibility, Human-Computer Interaction (HCI), and Psychology etc. But other researchers have insisted that Russell`s emotional dimension have to be modified because of its inherent problems. Such problems included the possibility of mixed feelings, the difference of emotion and sensibility, and the difference of Arousal axis and Valence axis. Therefore, we verify relationship of A Circumplex Model`s elements (active and inactive) and find how to people express their Arousal feelings using survey. We finally propose new method to express emotion in Russell`s emotional dimension. Using this method, we can solve Russell`s problems and compensate other researches.
한의환 ( Eui-hwan Han ),차형태 ( Hyung-tai Cha ) 한국감성과학회 2017 감성과학 Vol.20 No.1
We propose a novel method for modeling emotional dimensions using expansion of Russell`s (1980) emotional dimensions (Circumplex Model). The Circumplex Model represents emotional words in two axes (Arousal, Valence). However, other researchers have insisted that location of word in Russell`s model which is expressed by single point could not represent exact position. Consequently, it is difficult to apply this model in engineering fields (such as Science of Emotion & Sensibility, Human-Computer-Interaction, Ergonomics, etc.). Therefore, we propose a new modeling method which expresses emotional word not as a single point but as a region. We conducted survey to obtain actual data and derived equations using ellipse formula to represent emotional region. Furthermore, we applied ANEW and IAPS which are commonly used in many studies to our emotional model using pattern recognition algorithm. Using our method, we could solve problems with Russell`s model and our model is easily applicable to the field of engineering.
김종현(Jong-Hyun Kim),한의환(Eui-Hwan Han),서보국(Bo-Kug SEO),차형태(Hyung-Tai Cha) 한국방송·미디어공학회 2013 한국방송공학회 학술발표대회 논문집 Vol.2013 No.6
This paper purpose to correct color with histogram equalization, and improve image quality. Fog image is not clear enough to color information. So We need to correct each channel of fog image with histogram equalization. The algorithm offered in this paper is extracting R, G, and B channel, making histogram equalization, and adding or subtraction to brightness of each channel.