• Journal of the Architectural Institute of Korea Planning & Design
• /
• v.34 no.12
• /
• pp.85-94
• /
• 2018

The purpose of this paper was to propose a model that recognizes potential users' emotional response toward design by classifying Electroencephalography(EEG). Studies in neuroscience and psychology have made an effort to recognize subjects' emotional response by analyzing EEG data. And this approach has been adopted in design since it is critical to monitor users' subjective response in the preface of design. Moreover, the building design process cannot be reversed after construction, recognizing clients' affection toward design alternatives plays important role. An experiment was conducted to record subjects' EEG data while they view their most/least liked images of small-house designs selected by them among the eight given images. After the recording, a subjective questionnaire, PANAS, was distributed to the subjects in order to describe their own affection score in quantitative way. Google TensorFlow was used to build and train the model. Dataset for model training and testing consist of feature columns for recorded EEG data and labels for the questionnaire results. After training and testing, the measured accuracy of the model was 0.975 which was higher than the other machine learning based classification methods. The proposed model may suggest one quantitative way of evaluating design alternatives. In addition, this method may support designer while designing the facilities for people like disabled or children who are not able to express their own feelings toward alternatives.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.34-36
• /
• 2022

In the existing text sentiment analysis models, the entire text is usually directly modeled as a whole, and the hierarchical relationship between text contents is less considered. However, in the practice of sentiment analysis, many texts are mixed with multiple emotions. If the semantic modeling of the whole is directly performed, it may increase the difficulty of the sentiment analysis model to judge the sentiment, making the model difficult to apply to the classification of mixed-sentiment sentences. Therefore, this paper proposes a sentiment analysis model BHGCN that considers the text hierarchy. In this model, the output of hidden states of each layer of BERT is used as a node, and a directed connection is made between the upper and lower layers to construct a graph network with a semantic hierarchy. The model not only pays attention to layer-by-layer semantics, but also pays attention to hierarchical relationships. Suitable for handling mixed sentiment classification tasks. The comparative experimental results show that the BHGCN model exhibits obvious competitive advantages.

• 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.

• The KIPS Transactions:PartB
• /
• v.17B no.4
• /
• pp.263-274
• /
• 2010

To provide context-aware music recommendation service, first of all, we need to catch music mood that a user prefers depending on his situation or context. Among various music characteristics, music mood has a close relation with people‘s emotion. Based on this relationship, some researchers have studied on music mood detection, where they manually select a representative segment of music and classify its mood. Although such approaches show good performance on music mood classification, it's difficult to apply them to new music due to the manual intervention. Moreover, it is more difficult to detect music mood because the mood usually varies with time. To cope with these problems, this paper presents an automatic method to classify the music mood. First, a whole music is segmented into several groups that have similar characteristics by structural information. Then, the mood of each segments is detected, where each individual's preference on mood is modelled by regression based on Thayer's two-dimensional mood model. Experimental results show that the proposed method achieves 80% or higher accuracy.

• Journal of The Association for Neo Medicine
• /
• v.1 no.2
• /
• pp.39-55
• /
• 1996

The theory of seven emotions is a unique theory in oriental medicine which describes the mutual relationship between body and mind of human. Although, the term 'Seven emotions' was not clearly indicated in ${\ulcorner}$The Yellow Emperor's Internal Classic(黃帝內經)${\lrcorner}$, it is appeared in ${\ulcorner}$A Treatise on the Three Catagories of Cause of Diseases(三因方)${\lrcorner}$ written by Chen Yan(陳言) in South-Song Dynasty. It seemed that Chen Yan explained seven emotions as the internal etiologic factor according to the classification of seven emotions of ${\ulcorner}$Ye-Gi(禮記)${\lrcorner}$ under the academic influence during Song Dynasy which emphasized more on the standard of right and wrong rather than individual emotion. Meditation or consideration modulates the function of spleen and stomach and the metabolism of blood and body fluid and it also controls the various emotions and maintains the equilibrium of human body. Human emotions are influenced by the changes of nature and deeply related to time and space including social-environmental factors. The function and strength of seven emotions: joy, anger, anxiety, worry, grief, apprehension and fright are determined by the external stimulation as the causes of illness.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.35 no.9
• /
• pp.1099-1111
• /
• 2011

This study identified the types of consumer review information about apparel products based on consumer satisfaction/dissatisfaction with the availability/non-availability of consumer review information for online stores. Data were collected from 318 females aged 20s' to 30s', who had significant experience in reading consumer reviews posted on online stores. Consumer satisfaction/dissatisfaction with availability or non-availability of review information on online stores is different for information in regards to apparel product attributes, product benefits, and store attributes. According to the concept of quality elements suggested by the Kano model, two types of consumer review information were determined: Must-have information (product attribute information about size, fabric, color and design of the apparel product; benefit information about washing & care and comport of the apparel product; store attribute information about responsiveness, disclosure, delivery and after service of the store) and attracting information (attribute information about price comparison; benefit information about coordination with other items, fashionability, price discounts, value for price, reaction from others, emotion experienced during transaction, symbolic features for status, health functionality, and eco-friendly feature; store attribute information about return/refund, damage compensation and reputation/credibility of online store and interactive and dynamic nature of reviews among customers). There were significant differences between the high and low involvement groups in their perceptions of consumer review information.

• Fashion & Textile Research Journal
• /
• v.1 no.3
• /
• pp.246-251
• /
• 1999

Headdress which adorns the head has been used not only as a type of dress but also as a vehicle to express the human's mentality and a tool to convey ideas. This study first examines the type of headdress observed in the world folk costumes and investigates their geographical distribution and aims to examine how the types of headdress are inter-related to the peoples' natural environments, way of life and cultural background such as religion and aesthetic, ethical standards. Headdress used as important elements of many peoples' folk costumes can be categorized into scarf-type, hat-type and adornment-type. Veil-type, the one of scarf-types, was developed in Southwestern Asia and Arabic Africa influenced by natural and religious factors. This type is more simplified in Turkey and Eastern Europe and only covers head and neck in the former and only head in the latter while also being called 'headkerchief-type'. Hat-type is observed in many different parts of the world. Adornment-type has been used to symbolized one's noble social status and authority in societies dominated by shamanistic cultural background; it was also used in Far East out of the motivation to fulfil one's aesthetic desire. Headdress though it was originally made from the idential purpose of wearing, has developed into the various types affected by each people's natural environments, emotion and ways of life.

• Journal of Physiology & Pathology in Korean Medicine
• /
• v.20 no.5
• /
• pp.1102-1110
• /
• 2006

Sambyun(三變) is standard classification for nine palace. Through sambyun you can define new meaning of 'self' in three perspective ways. First 'self' could mean desire, emotion and memory which are ontological values. second, 'self' could mean id, ego, and superego which are practical values. Third 'self' could mean unconscious, preconscious and conscious which are epistemological values. Samjae(三才) is method that analyze things base on common features. Sa sang is method that analyze things base on difference. They both are device that searching for reason. If you put one's mind in center to observe the universe creativity of great absolute and symmetry distinction of yingyang produces jeung(情), supreme intelligence(神), and soul(魂魄). With these facts identity of the heaven(天), earth(地) and man(人) which is named samjae(三才) generates symbols of independent sasang(四象). And also, sasang generates relations between five element(五行), six energy(六氣). From ten shen(十神) relation comes seven feelings(七情) of man which creates a category of the eight trigrams(八卦) for divination and unification of nine palace(九宮). All these process are united.

• Journal of Oriental Neuropsychiatry
• /
• v.23 no.3
• /
• pp.33-46
• /
• 2012

Objectives : Emotion is composed by several basic feelings. This basic feeling is called Chiljung in Oriental Medicine. This study examines the positive and negative affects related to Chiljung. Methods : A total of 199 students of Dongshin university oriental medicine were tested by Questionnaire for Sasang Constitution ClassificationII(QSCCII) and Positive Affect and Negative Affect Schedule(PANAS). This study is used 156 students' data, excluding 43 students' data. Of the enrolled 156 students, four groups were classified by QSCCII. The positive and negative properties of Chiljung were determined by PANAS. These data were analyzed by frequency, Pearson's chi-square test, Crosstabulation Analysis with SPSS windows 15.0. Results : 1. Joy(喜) and Anger(怒) has directly-opposed emotional properties. 2. Thought(思) difficult to tell the difference between positive and negative, but it is distinct from Anxiety(憂) and Sorrow(悲) 3. Anxiety(憂) and Sorrow(悲) are superior in negative emotional properties. 4. Fear(恐) and Fright(驚) are superior in negative emotional properties, and Fright(驚) is superior over Fear(恐) in positive emotional properties. Conclusions : This study may serve as the foundation in identifying the psychological traits of Chiljung.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.147-149
• /
• 2021

Recently, the rapid growth of the media market and the expectations of users have been increasing. In this research, tags are extracted through media-derived audio and classified into specific categories using artificial intelligence. This category is a type of emotion including joy, anger, sadness, love, hatred, desire, etc. We use JupyterNotebook to conduct the corresponding study, analyze voice data using the LiBROSA library within JupyterNotebook, and use Neural Network using keras and layer models.