• ETRI Journal
• /
• 제44권2호
• /
• pp.232-243
• /
• 2022

Changes in household composition and the residential environment have had a considerable impact on the features of postal delivery regions in recent years, resulting in a large increase in the overall workload of domestic postal delivery services. In this paper, we provide complex analysis results for postal delivery areas using various unsupervised learning approaches. First, we extract highly influential features using several feature-engineering methods. Then, using quantitative and qualitative cluster analyses, we find the distinctive traits and semantics of postal delivery zones. Unsupervised learning approaches are useful for successfully grouping postal service zones, according to our findings. Furthermore, by comparing a postal delivery region to other areas in the same group, workload balancing was achieved.

• The Journal of the Korea Contents Association
• /
• 제8권10호
• /
• pp.198-207
• /
• 2008

The purpose of this study supplies the basic data to plan the optimum mental health service that is reflected needs of the elderly people with mental illness by checking how their demographic-sociological distinctive feature and function level have an effect on their needs of mental health service by being absent situation of a study of the elderly people with mental illness. As results of analysis, the residental type, the disease period, and the decision person of admission-discharge control of demographic-sociological distinctive feature is much effect on needs of programs and also effect commonly on the needs of the health promotion program and the discharge support program. Generally, the function level of the elderly people with mental illness is favorable and the order of function level is the group activity program, the counseling program, and the resource network program.

• Korean Journal of Acupuncture
• /
• 제27권1호
• /
• pp.159-168
• /
• 2010

Objective: ZhangJinYoPian(藏珍要編, ZJYP) is a book witten by Song-WooGe in the late 19th century. While Korea has lost this book to tell us Korea traditional acupuncture treatment in the late 19th century, This book appeared as a manuscript in Japan. There is no reaserch or study carried out for this book. Furthermore, a few people know existence of this book. So I analyzed acupuncture treatment of the ZJYP and sort out the distinctive feature of it. Method: For that, I studied bibliographic information of this book and classified contents of it into three parts - medical thought, needle manipulation and acupoint selection to consider it's caracteristics. Results and Conclusions: 1. The author of ZJYP thought that weakness of good power in the body and strongness of evil power out of the body cause a disease. so Doctor should examine quality of both to care patient's pain. 2. The author of ZJYP thought that needle manipulation is one of the most important thing. Doctors can use needle manipulation to control patient condition. Especially, he suggested cooling and heating manipulation except reinforcement and reduction. 3. He stressed viscera and bowels. he located viscera and bowels theory in front of the book to explain relationship of these. It shows us that ZJYP maintained academic characteristics of acupuncture in Chosun-Korea. 4. While He minimized the number of acupoints used in treatment, he multiplied its combination. He selected one or two acupoints from each meridian pathway. It include Eight Confluent points(八脈交會穴). But these points were used in different ways to control the viscera and bowels, not to care the eight extra meridians.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• 제24권11호
• /
• pp.30-41
• /
• 2010

In this study we propose a new texture feature extraction method based on an estimation of the brightness and structural uniformity of CT images representing the important characteristics for emphysema recognition. The Center-Symmetric Local Binary Pattern (CS-LBP) is first used to combine gray level in order to describe the brightness uniformity characteristics of the CT image. Then the gradient orientation difference is proposed to generate another CS-LBP code combining with gray level to represent the structural uniformity characteristics of the CT image. The usage of the gray level, CS-LBP and gradient orientation differences enables the proposed method to extract rich and distinctive information from the CT images in multiple directions. Experimental results showed that the performance of the proposed method is more stable with respect to sensitivity and specificity when compared with the SGLDM, GLRLM and GLDM. The proposed method outperformed these three conventional methods (SGLDM, GLRLM, and GLDM) 7.85[%], 22.87[%], and 16.67[%] respectively, according to the diagnosis of average accuracy, demonstrated by the Receiver Operating Characteristic (ROC) curves.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권12호
• /
• pp.4456-4475
• /
• 2021

The system for re-identifying persons is used to find and verify the persons crossing through different spots using various cameras. Much research has been done to re-identify the person by utilising features with deep-learned or hand-crafted information. Deep learning techniques segregate and analyse the features of their layers in various forms, and the output is complex feature vectors. This paper proposes a distinctive framework called Integrated Level Feature Pattern (ILFP) framework, which integrates local and global features. A new deep learning architecture named modified XceptionNet (m-XceptionNet) is also proposed in this work, which extracts the global features effectively with lesser complexity. The proposed framework gives better performance in Rank1 metric for Market1501 (96.15%), CUHK03 (82.29%) and the newly created NEC01 (96.66%) datasets than the existing works. The mean Average Precision (mAP) calculated using the proposed framework gives 92%, 85% and 98%, respectively, for the same datasets.

• Journal of KIISE:Software and Applications
• /
• 제31권4호
• /
• pp.420-438
• /
• 2004

Artificially or naturally contained texts in the natural images have significant and detailed information about the scenes. If we develop a method that can extract and recognize those texts in real-time, the method can be applied to many important applications. In this paper, we suggest a new method that extracts the text areas in the natural images using the low-level image features of color continuity. gray-level variation and color valiance and that verifies the extracted candidate regions by using the high-level text feature such as stroke. And the two level features are combined hierarchically. The color continuity is used since most of the characters in the same text lesion have the same color, and the gray-level variation is used since the text strokes are distinctive in their gray-values to the background. Also, the color variance is used since the text strokes are distinctive in their gray-values to the background, and this value is more sensitive than the gray-level variations. The text level stroke features are extracted using a multi-resolution wavelet transforms on the local image areas and the feature vectors are input to a SVM(Support Vector Machine) classifier for the verification. We have tested the proposed method using various kinds of the natural images and have confirmed that the extraction rates are very high even in complex background images.

• Journal of Korean Medical classics
• /
• 제29권1호
• /
• pp.125-137
• /
• 2016

Objectives : Introduction to Medicine(醫學入門, Yixuerumen) is one of the basic clinical texts in Korean medical history. This study is designed to prove clinical value of Introduction to Medicine for practitioners in their early stage of clinical practice. Methods : Introduction to Medicine is closely reviewed in various aspects in order to examine broad outlines of specificity as well as its distinctive constructional feature. Results : Since Introduction to Medicine showed peculiar intention of developing practitioner's clinical ability, it has been a preferential choice for Korean medicine practitioners to enhance their qualification at the early stage of one's career in Korean history. It is still valid for modern practitioners because composite medical texts are needed in order to systematize one's fragmental knowledge acquired from institutional education. Conclusions : Introduction to Medicine shows a large potential as a clinical textbook in the course of maximizing one's clinical ability with its aid. Through understanding multilateral aspects of clinical guidelines and directions engraved in Introduction to Medicine, learners will be able to derive full capacity from the text.

• Journal of Korean Medical classics
• /
• 제22권2호
• /
• pp.35-69
• /
• 2009

Yang Shangseon(楊上善)'s "Hwangjenaegyeongtaeso(黃帝內經太素)" was the first commentary book of "Hwangjenaegyeong(黃帝內經)", its importance often mentioned in level with Wang Bing (王冰)'s "Somun(素問)" "Yeongchu(靈樞)". The distinctive feature of Yang Sangseon(楊上善)'s commentary is that it is easy to comprehend in accordance with an organized classification, and that the explanations are simple and clear. Despite strict application of the Eumyang(陰陽, Yinyang) theory and Five phases[五行] theory throughout the text, should there be sentences which fall out of consistency with the basic theories, he added his own substantial commentary. His medical theory gives attention to the Meridian system[經絡], lays emphasis on developing the soul[神], and has a unique opinion about the Opening closing and pivot[開闔樞] theory along with the Myeongmun(命門). To explain the methods for preserving health[養生], he adopted the Nojang philosophy(老莊思想); to enrich the vitality he adopted the Buddhist philosophy(佛敎思想); and to analyze physiologic and pathogenic factors, he adopted the Confucian philosophy(儒家思想).

• Proceedings of the Korea Contents Association Conference
• /
• 한국콘텐츠학회 2007년도 추계 종합학술대회 논문집
• /
• pp.501-505
• /
• 2007

Recently KISTI has developed the KnowlegeMatrix which is a stand-alone type bibliographic data analysis software. In this paper, we try to benchmark test on the performance level of KnowledgeMatrix with well-known S/Ws such as VantagePoint and BibTechMon. We compare distinctive functions and usability of each S/Ws on comparative categories including Data, Matrix, Analysis, Visualization and Preprocessing. Test results show that all S/Ws have differentiated specific feature, but there is some performance gaps. KnowledgeMatrix overally shows better performance than others.

• Journal of Chest Surgery
• /
• 제14권2호
• /
• pp.127-130
• /
• 1981

A 39-year-old male was admitted to Dept. of Thoracic Cardiovasc. Surgery, Korea University Hospital with the chief complaints of progressively enlarged mass on right upper lung which revealed on routine chest P-A since 4 Years ago. Chest PA and tomography revealed well circumscribed huge mass of 7cm. in diameter without invasion on bronchus. so, right upper lobectomy was performed under impression of lung cancer. Postoperative pathologic examination revealed pulmonary blastoma. Pulmonary blastoma is accepted as a distinctive neoplasm recently. One case of typical pulmonary blastoma is reported, and the previous literature is reviewed. There are no specific clinical or radiologic feature of pulmonary blastoma. The presentation is can be that of any other pulmonary tumor although a peripheral situation is usual and a large size is often attained before detection. Pulmonary blastoma is a mixed tumor with malignant epithelial and connective tissue components with a distinctive resemblance to fetal lung. The treatment of choice is surgical excision but the overall prognosis is poor. There is no evidence of recurrence or metastasis on follow-up study during 6 months period after right upper lobectomy.