• Journal of Intelligence and Information Systems
• /
• v.24 no.3
• /
• pp.1-19
• /
• 2018

Large amount of data is now available for research and business sectors to extract knowledge from it. This data can be in the form of unstructured data such as audio, text, and image data and can be analyzed by deep learning methodology. Deep learning is now widely used for various estimation, classification, and prediction problems. Especially, fashion business adopts deep learning techniques for apparel recognition, apparel search and retrieval engine, and automatic product recommendation. The core model of these applications is the image classification using Convolutional Neural Networks (CNN). CNN is made up of neurons which learn parameters such as weights while inputs come through and reach outputs. CNN has layer structure which is best suited for image classification as it is comprised of convolutional layer for generating feature maps, pooling layer for reducing the dimensionality of feature maps, and fully-connected layer for classifying the extracted features. However, most of the classification models have been trained using online product image, which is taken under controlled situation such as apparel image itself or professional model wearing apparel. This image may not be an effective way to train the classification model considering the situation when one might want to classify street fashion image or walking image, which is taken in uncontrolled situation and involves people's movement and unexpected pose. Therefore, we propose to train the model with runway apparel image dataset which captures mobility. This will allow the classification model to be trained with far more variable data and enhance the adaptation with diverse query image. To achieve both convergence and generalization of the model, we apply Transfer Learning on our training network. As Transfer Learning in CNN is composed of pre-training and fine-tuning stages, we divide the training step into two. First, we pre-train our architecture with large-scale dataset, ImageNet dataset, which consists of 1.2 million images with 1000 categories including animals, plants, activities, materials, instrumentations, scenes, and foods. We use GoogLeNet for our main architecture as it has achieved great accuracy with efficiency in ImageNet Large Scale Visual Recognition Challenge (ILSVRC). Second, we fine-tune the network with our own runway image dataset. For the runway image dataset, we could not find any previously and publicly made dataset, so we collect the dataset from Google Image Search attaining 2426 images of 32 major fashion brands including Anna Molinari, Balenciaga, Balmain, Brioni, Burberry, Celine, Chanel, Chloe, Christian Dior, Cividini, Dolce and Gabbana, Emilio Pucci, Ermenegildo, Fendi, Giuliana Teso, Gucci, Issey Miyake, Kenzo, Leonard, Louis Vuitton, Marc Jacobs, Marni, Max Mara, Missoni, Moschino, Ralph Lauren, Roberto Cavalli, Sonia Rykiel, Stella McCartney, Valentino, Versace, and Yve Saint Laurent. We perform 10-folded experiments to consider the random generation of training data, and our proposed model has achieved accuracy of 67.2% on final test. Our research suggests several advantages over previous related studies as to our best knowledge, there haven't been any previous studies which trained the network for apparel image classification based on runway image dataset. We suggest the idea of training model with image capturing all the possible postures, which is denoted as mobility, by using our own runway apparel image dataset. Moreover, by applying Transfer Learning and using checkpoint and parameters provided by Tensorflow Slim, we could save time spent on training the classification model as taking 6 minutes per experiment to train the classifier. This model can be used in many business applications where the query image can be runway image, product image, or street fashion image. To be specific, runway query image can be used for mobile application service during fashion week to facilitate brand search, street style query image can be classified during fashion editorial task to classify and label the brand or style, and website query image can be processed by e-commerce multi-complex service providing item information or recommending similar item.

• Journal of the Korean Institute of Traditional Landscape Architecture
• /
• v.38 no.1
• /
• pp.115-131
• /
• 2020

Through literature research and field investigation, this paper attempts to study the distribution, morphology and the typification of the visual and perceptual stone inscription in Wuyi-Gugok of China. The results are as follows: First, there are 350 stone inscriptions in total from the 1^st Gok to 9^th Gok in Wuyi-Gugok. Second, according to the analysis of the stone inscription distribution, 74(21.2%) stone inscriptions in the 5^th Gok, 67(19.2%) in the 6^th Gok, 65(18.6%) in the 1^st Gok, 60(17.2%) in the 2^nd Gok and 53(15.2%) in the 4^th Gok are confirmed. The above five Goks contain 319(91.1%) stone inscriptions, so they have rich cultural landscape. Third, according to the survey, the number of the stone inscriptions existed in the Sugwangseok of the 1^st Gok are 41(22.6%), in the Homagan of Cheonyubong of the 6^th Gok are 29(8.3%), in the Jesiam of the 4^th Gok are 23(6.6%), in the Nyeongam of the 2^nd Gok are 22(6.3%), in the Hyangseongam of the 6^th Gok are 21(6%), in the Unwa of the 5^th Gok are 19(5.4%), in the Bokhoam of the 5^th Gok are 18(5.1%), in the Eunbyeongbong of the 5^th Gok are 17(4.9%), in the Daejangbong of the 4^th Gok are 14(4%), in the Daewangbong of the 1^st Gok and the Geumgokam of the 4^th Gok are 12(3.4%). Thus, a total of 228 (65.1%) stone inscriptions are concentrated in these 11 sites, which represent the popularity and cultural value of these rocks. Fourth, the stone inscription of Wuyi-Gugok, praising the landform and topographical geological landscape of Mount Wuyi, mainly describe the scenic name of each Gok related to Zhu Xi's Gugok culture, appreciate Zhu Xi's tracks and the stone inscription in the sacred land of Neo-Confucianism culture, and also record the Confucian edification of mencius thoughts, Muigun(武夷君) and the myths and legends related to the site names of Wuyi mountain, which can remind people of the worldview of the celestial paradise where the gods live and the fairyland of the land of peach blossoms. In addition, it indicates that the historical and cultural landscape, which is full of colorful history and myths and legends, including allusions related to Confucian, buddhist and Taoist celebrities and the ancestor ancient things related to traditional culture of China is very diverse. Fifth, the results of the classification, based on the content of the stone inscription in Wuyi-Gugok, are classified as the scenery name inscription, the praise scene inscription, the recording travel inscription, the recording event inscription, the philosophy inscription, the expressing emotion inscription, the religion inscription, the inscription for auspiciousness, the slogan and expressing ambition inscription and the official document notice inscription, among which there are 102(29.1%) praise scene inscriptions, 93(26.6%) scenery name inscriptions and 61(17.4%) recording travel inscriptions. The stone inscriptions of Wuyi-Gugok have the characteristics of the special emphasis on scenery names, landscape praise and commemorative tours. Sixth, the analysis of the intertext between the 「Figure of Wuyi-Gugok」 and Wuyi-Gugok rock letters, in the study found that the method of propagation between media was mostly the method of propagation of quotations and maintained intermedia through extension, repetition, extension, and compression.

• Journal of Intelligence and Information Systems
• /
• v.26 no.2
• /
• pp.57-78
• /
• 2020

With the development of the Internet, consumers have had an opportunity to check product information easily through E-Commerce. Product reviews used in the process of purchasing goods are based on user experience, allowing consumers to engage as producers of information as well as refer to information. This can be a way to increase the efficiency of purchasing decisions from the perspective of consumers, and from the seller's point of view, it can help develop products and strengthen their competitiveness. However, it takes a lot of time and effort to understand the overall assessment and assessment dimensions of the products that I think are important in reading the vast amount of product reviews offered by E-Commerce for the products consumers want to compare. This is because product reviews are unstructured information and it is difficult to read sentiment of reviews and assessment dimension immediately. For example, consumers who want to purchase a laptop would like to check the assessment of comparative products at each dimension, such as performance, weight, delivery, speed, and design. Therefore, in this paper, we would like to propose a method to automatically generate multi-dimensional product assessment scores in product reviews that we would like to compare. The methods presented in this study consist largely of two phases. One is the pre-preparation phase and the second is the individual product scoring phase. In the pre-preparation phase, a dimensioned classification model and a sentiment analysis model are created based on a review of the large category product group review. By combining word embedding and association analysis, the dimensioned classification model complements the limitation that word embedding methods for finding relevance between dimensions and words in existing studies see only the distance of words in sentences. Sentiment analysis models generate CNN models by organizing learning data tagged with positives and negatives on a phrase unit for accurate polarity detection. Through this, the individual product scoring phase applies the models pre-prepared for the phrase unit review. Multi-dimensional assessment scores can be obtained by aggregating them by assessment dimension according to the proportion of reviews organized like this, which are grouped among those that are judged to describe a specific dimension for each phrase. In the experiment of this paper, approximately 260,000 reviews of the large category product group are collected to form a dimensioned classification model and a sentiment analysis model. In addition, reviews of the laptops of S and L companies selling at E-Commerce are collected and used as experimental data, respectively. The dimensioned classification model classified individual product reviews broken down into phrases into six assessment dimensions and combined the existing word embedding method with an association analysis indicating frequency between words and dimensions. As a result of combining word embedding and association analysis, the accuracy of the model increased by 13.7%. The sentiment analysis models could be seen to closely analyze the assessment when they were taught in a phrase unit rather than in sentences. As a result, it was confirmed that the accuracy was 29.4% higher than the sentence-based model. Through this study, both sellers and consumers can expect efficient decision making in purchasing and product development, given that they can make multi-dimensional comparisons of products. In addition, text reviews, which are unstructured data, were transformed into objective values such as frequency and morpheme, and they were analysed together using word embedding and association analysis to improve the objectivity aspects of more precise multi-dimensional analysis and research. This will be an attractive analysis model in terms of not only enabling more effective service deployment during the evolving E-Commerce market and fierce competition, but also satisfying both customers.

• (The) Research of the performance art and culture
• /
• no.25
• /
• pp.253-289
• /
• 2012

Dasiraegi is a traditional funeral rite performance of Jindo located in the South Jeolla Province of South Korea. With its unique stylistic structure including various dances, songs and witty dialogues, and a storyline depicting the birth of a new life in the wake of death, embodying the Buddhism belief that life and death is interconnected; it attracted great interest from performance organizers and performers who were desperately seeking new contents that can be put on stage as a performance. It is needless to say previous research on Dasiraegi had been most valuable in its recreation as it analyzed the performance from a wide range of perspectives. Despite its contributions, the previous researches were mainly academic focusing on: the symbolic meanings of the performance, basic introduction to the components of the performance such as script, lyrics, witty dialogue, appearance (costume and make-up), stage properties, rhythm, dance and etc., lacking accurate representation of the most crucial element of the performance which is sori (song). For this reason, the study analyzes the music of Dasiraegi and presents its musical characteristics along with its scores to provide practical support for performers who are active in the field. Out of all the numbers in Dasiraegi, this study analyzed all of Geosa-nori and Sadang-nori, the funeral dirge (mourning chant) sung as the performers come on stage and Gasangjae-nori, because among the five proceedings of the funeral rite they were the most commonly performed. There are a plethora of performance recordings to choose from, however, this study chose Jindo Dasiraegi, an album released by E&E Media. The album offers high quality recordings of performances, but more importantly, it is easy to obtain and utilize for performers who want to learn the Dasiraegi based on the script provided in this study. The musical analysis discovered a number of interesting findings. Firstly, most of the songs in Dasiraegi use a typical Yukjabaegi-tori which applies the Mi scale frequently containing cut-off (breaking) sounds. Although, Southern Kyoung-tori which applies the Sol scale was used, it was only in limited parts and was musically incomplete. Secondly, there was no musical affinity between Ssitgim-gut and Dasiraegi albeit both are for funeral rites. The fundamental difference in character and function of Ssitgim-gut and Dasiraegi may be the reason behind this lack of affinity, as Ssitgim-gut is sung to guide the deceased to heaven by comforting him/her, whereas, Dasiaregi is sung to reinvigorate the lives of the living. Lastly, traces of musical grammar found in Pansori are present in the earlier part of Dasiraegi. This may be attributed to the master artist (Designee of Important Intangible Cultural Heritage), who was instrumental in the restoration and hand-down of Dasiaregi, and his experience in a Changgeuk company. The performer's experience with Changgeuk may have induced the alterations in Dasiraegi, causing it to deviate from its original form. On the other hand, it expanded the performative bais by enhancing the performance aspect of Dasiraegi allowing it to be utilized as contents for Performing Arts. It would be meaningful to see this study utilized to benefit future performance artists, taking Dasiraegi as their inspiration, which overcomes the loss of death and invigorates the vibrancy of life.

• Sijohaknonchong
• /
• v.22
• /
• pp.85-113
• /
• 2005

This paper's target is two music books, 100 man's Gagok songs and 88 woman's Gagok songs compiled by Kim Kee-soo. The next is an interpretation on 9 subject classifications. 1. There is a similiarity in subject between $\lceil$kyobonyukdaesijo's collection$\rfloor$ and man's Gagok song. 2. There is a wide difference in man and woman's love subject between man's Gagok songs and woman's Gagok songs. 3. The subject changes as Gagok progreasses. 4. There are many nameless writers in the prograss of Nong$\cdot$Na k$\cdot$Peon. 5. Taepeongga, whose theme is to enjoy pleasure, forms the last beauty. Sijo poem's subjects, which belongs to the noble class, shows the mode of scholar's elegant life at that time.

• Science of Emotion and Sensibility
• /
• v.13 no.1
• /
• pp.47-60
• /
• 2010

Most of the researches about classification usually have used kNN(k-Nearest Neighbor), SVM(Support Vector Machine), which are known as learn-based model, and Bayesian classifier, NNA(Neural Network Algorithm), which are known as statistics-based methods. However, there are some limitations of space and time when classifying so many web pages in recent internet. Moreover, most studies of classification are using uni-gram feature representation which is not good to represent real meaning of words. In case of Korean web page classification, there are some problems because of korean words property that the words have multiple meanings(polysemy). For these reasons, LSA(Latent Semantic Analysis) is proposed to classify well in these environment(large data set and words' polysemy). LSA uses SVD(Singular Value Decomposition) which decomposes the original term-document matrix to three different matrices and reduces their dimension. From this SVD's work, it is possible to create new low-level semantic space for representing vectors, which can make classification efficient and analyze latent meaning of words or document(or web pages). Although LSA is good at classification, it has some drawbacks in classification. As SVD reduces dimensions of matrix and creates new semantic space, it doesn't consider which dimensions discriminate vectors well but it does consider which dimensions represent vectors well. It is a reason why LSA doesn't improve performance of classification as expectation. In this paper, we propose new LSA which selects optimal dimensions to discriminate and represent vectors well as minimizing drawbacks and improving performance. This method that we propose shows better and more stable performance than other LSAs' in low-dimension space. In addition, we derive more improvement in classification as creating and selecting features by reducing stopwords and weighting specific values to them statistically.

• Korean journal of communication and information
• /
• v.84
• /
• pp.99-123
• /
• 2017

We analyzed the movie (2016/ directed by J-yong E), which is entangled in politics of gender, age, class, or sexuality, naming as "spaces of Others", using the concepts of heterotopia of Foucault. Foucault addressed three types of spaces: the realistic space where we currently live, the unrealistic and non-existent utopia, and heterotopia, which functions antithetically to reality. Thus, Foucault's heterotopia can be considered to indicate "heterogeneous spaces" in reality. The Bacchus Lady revolves a 65-year old prostitute So-Young, sells her body to old men at the parks in downtown of Seoul. Old prostitute on streets are often referred as "Bacchus Ladies", because suggest the popular energy drink a bottle of Bacchus while selling sex. The movie represents some minorities such as transgender, Tina and madam of the club, G-spot, migrant women like Camila and Aindu, and a amputee, Dohoon. Through these people's bodies, the problems such as imperials, nations, ethnics, gender, age, class are entangled in the movie. The politics of these points work and construct heterotopias in four spaces of Others. First, the spaces which ageing and death are intersected. Second, the spaces of So-Young for prostitutes, Third, the spaces of So-Young's mothering: she adopted her baby to American when he was a infant, so she have felt guilty. Fourth, the spaces for So-young's quasi-family with Minho, a Kopian boy who was abandoned by Korean father, Dohoon, who is a poor amputee, and Tina, who is a transgender singer. Fifth, the spaces of speech of So-Young as the subaltern: the subaltern does not have the language to express its own experiences. In order to listen to the words of subaltern, we must do the task of measuring the silence. This cinematic representation of So-young as the subaltern makes her speak about her situation. Finally, the spaces constructed by the movie can be connected 'heterotopia of crisis', 'heterotopia of deviation' and 'heterotopia of fantasy'. The spaces of the movie represents lives of Others, nevertheless, So-Young's Otherness through spaces of heterotopia was transformed to an absolute Other by patriarchal traits of cinematic narrative.

• Journal of KIISE:Software and Applications
• /
• v.31 no.10
• /
• pp.1332-1344
• /
• 2004

Upon development of information super-highway and multimedia-related technoiogies in recent years, more efficient technologies to transmit, store and retrieve the multimedia data are required. Among such technologies, firstly, it is common that the semantic-based image retrieval is annotated separately in order to give certain meanings to the image data and the low-level property information that include information about color, texture, and shape Despite the fact that the semantic-based information retrieval has been made by utilizing such vocabulary dictionary as the key words that given, however it brings about a problem that has not yet freed from the limit of the existing keyword-based text information retrieval. The second problem is that it reveals a decreased retrieval performance in the content-based image retrieval system, and is difficult to separate the object from the image that has complex background, and also is difficult to extract an area due to excessive division of those regions. Further, it is difficult to separate the objects from the image that possesses multiple objects in complex scene. To solve the problems, in this paper, I established a content-based retrieval system that can be processed in 5 different steps. The most critical process of those 5 steps is that among RGB images, the one that has the largest and the smallest background are to be extracted. Particularly. I propose the method that extracts the subject as well as the background by using an Image, which has the largest background. Also, to solve the second problem, I propose the method in which multiple objects are separated using RGB channel selection techniques having optimized the excessive division of area by utilizing Watermerge's threshold value with the object separation using the method of RGB channels separation. The tests proved that the methods proposed by me were superior to the existing methods in terms of retrieval performances insomuch as to replace those methods that developed for the purpose of retrieving those complex objects that used to be difficult to retrieve up until now.

• Journal of the Korean association of regional geographers
• /
• v.6 no.3
• /
• pp.101-115
• /
• 2000

This study aims to make a research on the secondary school education of geography and the system of teacher training in Belgium, focused on the case of Francophone Community. What has been made clear by this research can be summed up as follows. The first two years of the secondary school offer two hours of 'environment education', per week, which can be categorized into the learning of living geography, in that at this stage students learn how to observe the geographic phenomena in their daily life and pigeonhole them. The two years of the second stage of the secondary school offer one hour of 'world geography' which actually is focused on the district of Europe and Russia. The two years of the third stage of the secondary school offer an advanced course of geography which aims to teach systematically the physical geography and the human geography. A remarkable change in geographic education in Belgium is that in the wake of the Revision Act of the secondary school education, textbooks were replaced by other teaching manuals adapted to the regional condition by the teachers. This may result in a wide gap of achievements in geography according to the conditions of educational establishments. Another notable change is that the stress of geographic education tends to be placed on the ability of acquiring practical geographic knowledge rather than the geographic information itself. And it is also another marked tendency that most learning activities in geography class are conducted on the basis of student-centered and the method of investigation. Teachers of the lower secondary schools in Belgium are trained in the School of Education as multi-major teachers, such as a teacher for biology-chemistry-geography or a teacher for history-sociology-geography. Teachers of the higher secondary school education are trained in the Department of Teacher Education in universities as solo-major teachers in that they are required to know more deeply to teach an advanced course of geography in the higher secondary schools. To improve the teacher education many folds of policies are adopted. One is that many in-service teachers are officially put into services of guiding and teaching teacher training. Another is that faculty members in charge of teacher training course are trying to level up the qualifications of teachers by rigorous disciplining.

• The Korean Society of Law and Medicine
• /
• v.17 no.2
• /
• pp.85-124
• /
• 2016

The Human gene testing act (GenDG) in Germany starts from the characteristic features of gene testing, i.e. dualisting structure consisted of anlaysis on the one side and the interpretation on the other side. The linguistic distincion of 'testing', 'anlaysis' and 'judgment' in the act is a fine example. Another important basis of the regulation is the ideological purpose of the law, that is information autonomy. The normative texts as such and the founding principle are the basis of the classification of testing types. Especially in the case of gene testing for medical purpose is classified into testing for diagnostic purpose and predictive purpose. However, those two types are not always clearly differentiated because the predictive value of testing is common in both types. In the legal regulation of gene testing it is therefore important to manage the uncertainty and subjectivity which are inherent in the gene-analysis and the judgment. In GenDG the system ensuring the quality of analysis is set up and GEKO(Commity for gene tisting) based on the section 23 of GenDG concretes the criterium of validity through guidelines. It is also very important in the case of gene testing for medical purpose to set up the system for ensurement of procedural rationality of the interpretation. The interpretation of the results of analysis has a wide spectrum because of the consistent development of technology on the one side and different understandings of different subjects who performs gene testings. Therefore the process should include the communication process for patients in oder that he or she could understand the meaning of gene testing and make plans of life. In GenDG the process of genetic counselling and GEKO concretes the regulation very precisely. The regulation as such in GenDG seems to be very suggestive to Korean legal polic concerning the gene testing.