• Journal of the Korean Society of Clothing and Textiles
• /
• v.47 no.1
• /
• pp.35-51
• /
• 2023

This study used text mining to extract 2,842 keywords from 7,397 product names and organized them into categories in order to analyze the characteristics of keywords appearing in the product names of jeans after 2020. The item category included denim and Chungbaji [청바지], and Ilja [일자], while the silhouette category included wide and bootcut. In addition, high-waist and banding comprised the making sector, and the materials category consisted of napping, spandex, and soft blue. Denim surpassed the others in frequency, co-occurrence frequency, and centrality, and co-appeared with various other keywords. Also, the co-appearance of item and silhouette was prominent, and there were many keyword combinations that showed characteristics related to (a) high waist; (b) hemline detail; (c) rubber band; and (d) partial tearing. Furthermore, idiom expressions such as 'slim fit' and 'back tearing', which were not highlighted in the co-occurrence frequency, were additionally confirmed through correlation. Therefore, the product name analysis effectively identified the detailed characteristics of the silhouette and the making of jeans preferred by consumers.

• Proceedings of the Korean Society of Plant Pathology Conference
• /
• 2003.10a
• /
• pp.118-118
• /
• 2003

The occurrence of Fusarium wilt in strawberry fields in Korea was assessed from 2001 to 2003. Fusarium wilt was found from June to August in nursery beds, from September to October after planting in production beds, and from January to March during harvest. The symptoms seen were root rots, discolored vascular tissue in the crown and deformation and yellowing of central leaflets. The disease occurred in up to 30％ of plants in 37 of 214 fields surveyed. Fusarium of sporum Schlecht. ex Fr. f. sp. fragariae was frequently isolated from cvs. Dochiodome, Maehyang, Redpearl, Samaberry and Akihime. Factors affecting the occurrence of Fusarium wilt were investigated; infested soils had high salt concentrations, low pH, OM, average P2O5 and exchangeable. Fusarium wilt was more frequent following conventional basal fertilization than after non-nitrogen basal fertilization and more frequent following the use of NH4-N than after NO3-N.

• Parasites, Hosts and Diseases
• /
• v.55 no.2
• /
• pp.225-228
• /
• 2017

The ghost ant Tapinoma melanocephalum is a common household pest worldwide. The present study examined the occurrence of the species in urban homes in Korea. During the period of September 2014 to January 2016, T. melanocephalum workers were collected from 58 homes at 29 different localities using bait traps with 10% sugar solution. The species was widely distributed throughout urban homes at 29 different localities, and the indoor occurrence of T. melanocephalum was highest in Seoul (32.7%) and metropolitan areas of Gyeonggi-do (Province) (29.3%). The indoor incidence rate of T. melanocephalum peaked in September (22.8%), remained moderate from October through April, and peaked again in May (15.7%). In contrast, a low incidence was observed from June to August (7.0%). The present study provides evidence that native ants, such as T. melanocephalum, are potential indoor pests of homes in Korea throughout the year.

• Korean Journal of Remote Sensing
• /
• v.31 no.4
• /
• pp.337-346
• /
• 2015

Water body extraction based on backscatter information is an essential process to analyze floodaffected areas from Synthetic Aperture Radar (SAR) image. Water body in SAR image tends to have low backscatter values due to homogeneous surface of water, while non-water body has higher backscatter values than water body. Non-water body, however, may also have low backscatter values in high resolution SAR image such as Kompsat-5 image, depending on surface characteristic of the ground. The objective of this paper is to present a method to increase backscatter contrast between water body and non-water body and also to remove efficiently misclassified pixels beyond true water body area. We create an entropy image using a Gray Level Co-occurrence Matrix (GLCM) and classify the entropy image into water body and non-water body pixels by thresholding of the entropy image. In order to reduce the effect of threshold value, we also propose Water Body Texture Index (WBTI), which measures simultaneously the occurrence of repeated water body pixel pair and the uniformity of water body in the binary entropy image. The proposed method produced high overall accuracy of 99.00% and Kappa coefficient of 90.38% in water body extraction using Kompsat-5 image. The accuracy analysis indicates that the proposed WBTI method is less affected by the choice of threshold value and successfully maintains high overall accuracy and Kappa coefficient in wide threshold range.

• Journal of the Korea Society of Computer and Information
• /
• v.21 no.11
• /
• pp.17-21
• /
• 2016

Heterogeneity assessment of tumor in oncology is important for diagnosis of cancer and therapy. The aim of this study was performed assess heterogeneity tumor region in PET image using texture analysis. For assessment of heterogeneity tumor in PET image, we inserted sphere phantom in torso phantom. Cu-64 labeled radioisotope was administrated by 156.84 MBq in torso phantom. PET/CT image was acquired by PET/CT scanner (Discovery 710, GE Healthcare, Milwaukee, WI). The texture analysis of PET images was calculated using occurrence probability of gray level co-occurrence matrix. Energy and entropy is one of results of texture analysis. We performed the texture analysis in tumor, liver, and background. Assessment textural features of region-of-interest (ROI) in torso phantom used in-house software. We calculated the textural features of torso phantom in PET image using texture analysis. Calculated entropy in tumor, liver, and background were 5.322, 7.639, and 7.818. The further study will perform assessment of heterogeneity using clinical tumor PET image.

• International Journal of Internet, Broadcasting and Communication
• /
• v.12 no.4
• /
• pp.204-211
• /
• 2020

The era of the 4th industrial revolution is a complex environment in which the cyber world and the physical world are integrated and interacted. In order to successfully implement and be sustainable the 4th industrial revolution of hyper-connectivity, hyper-convergence, and hyper-intelligence, not only the technological aspects that implemented digitalization but also the social aspects must be recognized and dealt with as important. There are socio-technical systems and socio-technical systems theory as concepts that describe systems involving complex interactions between the environmental aspects of human, mechanical and tissue systems. This study confirmed how the Socio-technical System was applied in the research literature for the last 10 years through machine learning-based analysis. Eight clusters were derived by performing co-occurrence keywords network analysis, and 13 research topics were derived and analyzed by performing a structural topic model. This study provides consensus and insight on the social and technological perspectives necessary for the sustainability of the 4th industrial revolution.

• Journal of Korea Multimedia Society
• /
• v.14 no.12
• /
• pp.1544-1548
• /
• 2011

A process of choosing a subset of original features, so called feature selection, is considered as a crucial preprocessing step to image processing applications. There are already large pools of techniques developed for machine learning and data mining fields. In this paper, basically two methods, non-feature selection and feature selection, are investigated to compare their predictive effectiveness of classification. Color co-occurrence feature is used for defining image features. Standard Sequential Forward Selection algorithm are used for feature selection to identify relevant features and redundancy among relevant features. Four color spaces, RGB, YCbCr, HSV, and Gaussian space are considered for computing color co-occurrence features. Gray-level image feature is also considered for the performance comparison reasons. The experimental results are presented.

• Proceedings of the Korean Information Science Society Conference
• /
• 1998.10c
• /
• pp.482-484
• /
• 1998

Abstract : Multimedia data now one of the widely used information in all the fields as the fast developments of computer techniques have been made. Traditional database systems based on textual information have limitations when applied to multimedia information. This is because simple textual descriptions are ambiguous and inadequate for searching multimedia information for multimedia databases and digital libraries. Thus, especially for image data, which is one of the important multimedia information types, which can retrieve and browse image data on the basis of pictorial queries. Therefore, this paper presents an efficient method for describing texture information in image data.

• Annual Conference on Human and Language Technology
• /
• 2007.10a
• /
• pp.122-127
• /
• 2007

최근 대표적인 1인 미디어의 형태인 블로그는 개인 기록의 수단뿐만 아니라 기업의 홍보에까지 널리 사용되는 인터넷 미디어이다. 그러나 누구나 글을 쓸 수 있다는 자유로움 이면에 이를 이용한 덧글 스팸이 성행이 성행하고 있다. 일반적인 스팸 필터의 경우 그 해당 덧글만을 가지고 스팸 필터링을 한다. 그러나 특성상 스팸인 덧글이 정상인 덧글보다 상대적으로 짧기 때문에 일반적인 덧글 자체만의 필터링 방법으로는 높은 정확도를 기대하기 힘든 단점이 있다. 본 논문에서는 정상인 덧글과 본문간의 내용상의 유사도가 있음을 가정해 이런 정보를 역카이제곱 분류기에 동시출현(co-occurrence) 정보로 부여함으로써 스팸 필터의 정확도를 높이고자 했으며, 실제 그러한 정보를 추가함으로 단순한 확률기반 스팸 필터링 방법을 사용하는 것보다 스팸 필터의 전반적인 성능이 상승되었음을 실험 결과를 통해 알 수 있었다.

• Perspectives in Nursing Science
• /
• v.16 no.1
• /
• pp.12-24
• /
• 2019

Purpose: This study examined the suitability of using text network analysis (TNA) methodology for topic analysis of academic papers related to nursing. Methods: TNA background theories, software programs, and research processes have been described in this paper. Additionally, the research methodology that applied TNA to the topic analysis of the academic nursing papers was analyzed. Results: As background theories for the study, we explained information theory, word co-occurrence analysis, graph theory, network theory, and social network analysis. The TNA procedure was described as follows: 1) collection of academic articles, 2) text extraction, 3) preprocessing, 4) generation of word co-occurrence matrices, 5) social network analysis, and 6) interpretation and discussion. Conclusion: TNA using author-keywords has several advantages. It can utilize recognized terms such as MeSH headings or terms chosen by professionals, and it saves time and effort. Additionally, the study emphasizes the necessity of developing a sophisticated research design that explores nursing research trends in a multidimensional method by applying TNA methodology.