• 복식
• /
• 제54권2호
• /
• pp.149-165
• /
• 2004

In this study, the photographic and anthropometric measurements of men in the 20's were made. and pattern making professionals visually evaluated their side photos to classify lateral views. These data were analyzed by being compared with existing research results to select objective standards, and body types were classified according to the selected standard. In addition, body features were defined according to lateral views based on measurement items and indices, and standard lines and determining factors for visual evaluation which determines lateral views were revealed. Back length - front length size smaller than 1.5cm was named as the lean-back type, 1.5∼3.9cm was named as the straight type. and that larger than 3.9cm was named as the bend-forward type. In the straight type, the bisection point of waist depth was located at a similar place to tragion level vertical line. In the lean-back type, the point was at the front of tragion level vertical line. In the bend-forward type, the point was at the back of tragion level vertical line.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제5권3호
• /
• pp.560-574
• /
• 2011

In this paper, we propose a hybrid method of Machine Learning (ML) algorithm and a rule-based algorithm to implement a lightweight Named Entity (NE) extraction system for Korean SMS text. NE extraction from Korean SMS text is a challenging theme due to the resource limitation on a mobile phone, corruptions in input text, need for extension to include personal information stored in a mobile phone, and sparsity of training data. The proposed hybrid method retaining the advantages of statistical ML and rule-based algorithms provides fully-automated procedures for the combination of ML approaches and their correction rules using a threshold-based soft decision function. The proposed method is applied to Korean SMS texts to extract person's names as well as location names which are key information in personal appointment management system. Our proposed system achieved 80.53% in F-measure in this domain, superior to those of the conventional ML approaches.

• 한국언어정보학회:학술대회논문집
• /
• 한국언어정보학회 2007년도 정기학술대회
• /
• pp.303-310
• /
• 2007

Named Entity Recognition (NER) is always limited by its lower recall resulting from the asymmetric data distribution where the NONE class dominates the entity classes. This paper presents an approach that exploits non-local information to improve the NER recall. Several kinds of non-local features encoding entity token occurrence, entity boundary and entity class are explored under Conditional Random Fields (CRFs) framework. Experiments on SIGHAN 2006 MSRA (CityU) corpus indicate that non-local features can effectively enhance the recall of the state-of-the-art NER systems. Incorporating the non-local features into the NER systems using local features alone, our best system achieves a 23.56% (25.26%) relative error reduction on the recall and 17.10% (11.36%) relative error reduction on the F1 score; the improved F1 score 89.38% (90.09%) is significantly superior to the best NER system with F1 of 86.51% (89.03%) participated in the closed track.

• Genomics & Informatics
• /
• 제17권2호
• /
• pp.17.1-17.3
• /
• 2019

Text mining has become an important research method in biology, with its original purpose to extract biological entities, such as genes, proteins and phenotypic traits, to extend knowledge from scientific papers. However, few thorough studies on text mining and application development, for plant molecular biology data, have been performed, especially for rice, resulting in a lack of datasets available to solve named-entity recognition tasks for this species. Since there are rare benchmarks available for rice, we faced various difficulties in exploiting advanced machine learning methods for accurate analysis of the rice literature. To evaluate several approaches to automatically extract information from gene/protein entities, we built a new dataset for rice as a benchmark. This dataset is composed of a set of titles and abstracts, extracted from scientific papers focusing on the rice species, and is downloaded from PubMed. During the 5th Biomedical Linked Annotation Hackathon, a portion of the dataset was uploaded to PubAnnotation for sharing. Our ultimate goal is to offer a shared task of rice gene/protein name recognition through the BioNLP Open Shared Tasks framework using the dataset, to facilitate an open comparison and evaluation of different approaches to the task.

• 한국콘크리트학회:학술대회논문집
• /
• 한국콘크리트학회 1996년도 가을 학술발표회 논문집
• /
• pp.546-550
• /
• 1996

The personal-computer software program named SAMS(Structural Aging Management System) was developed for the concrete structure of NPP(Nuclear Power Plant). SAMS is constituted of three part, detabase system containing various inspection data, operation program for standard input/output of the inspection data, and application program for efficient operation of database system. Using the SAMS, the field engineers can easily acquire the information about the various inspection data, repair and accidental histories of NPP structures. SAMS will contribute to the effcient maintenance of NPP structures.

• 동의생리병리학회지
• /
• 제23권5호
• /
• pp.1063-1072
• /
• 2009

Membranous nephropathy(MN) is the most common cause of adult nephrotic syndrome worldwide. But treatment of MN is not defined. This study was to evaluate the effects of Lonicerae Flos Extract(LFE) on the MN induced by cBSA in mice. Mice were divided into 4 groups. The first group named for 'Normal' was injected with a saline solution. The second group named 'Control' treated with cBSA(10 mg/kg i.p) only. The third group named 'LFE-250', treated with cBSA(10 mg/kg i.p) and LFE(250 mg/kg, p.o). The fourth group named 'LFE-500'treated with cBSA(10 mg/kg i.p) and LFE(500 mg/kg, p.o). After cBSA and LFE treatment for 4 weeks, we measured change of body weight, 24hrs proteinuria, serum albumin, total cholesterol, triglyceride, BUN, creatinine, TNF-$\alpha$, IL-6, IL-$1{\beta}$, IL-10, IFN-$\gamma$, IgA, IgM and IgG levels. The morphologic changes of renal glomeruli were also observed with a light microscope. The levels of 24 hrs proteinuria, total cholesterol, IgG , IgM, IgA, IL-6 were significantly decreased in both LFE groups. The level of triglyceride, IL-$1{\beta}$ was significantly decreased in LFE-500 group. The level of Albumin was significantly increased in LFE-250 group. The level of TNF-$\alpha$, IFN-$\gamma$ were significantly decreased in LFE-250 group. The mRNA expression of IL-$1{\beta}$ in splenocytes was consideraly decreased in LFE-500 group. In histological findings of kidney tissue, thickening of GBM decreased in both LFE groups. This study shows that the LFE might be effective for treatment of MN. More clinical data and studies are to be done for efficient application.

• Asian Pacific Journal of Cancer Prevention
• /
• 제17권12호
• /
• pp.5217-5221
• /
• 2016

Objective: A study of primary cancer morbidity among children and subsequent calculation of average annual incidence were carried out for boys and girls, and young men and women in Kazakhstan. Methods: The investigated population lived in three areas of the Aral Sea region: designated catastrophe (Aral, Kazalt, Shalkar regions), crisis (Zhalagash, Karmakshy, Shiely regions), pre-crisis (Irgiz, Arys, Ulytau regions). Zhanaarka region of Karaganda oblast was applied as a control. Parameters were retrospective analyzed for the 10 years from 2004 to 2013. Result: The results indicate that indices of children cancer morbidity were slightly higher in the Aral Sea region than in the control district, but they were comparable with similar data from studies in other regions. In all areas of the Aral Sea region, except for Ulytau, primary cancer morbidity exceeded the control level by 1.3-2.7 times (4.7%000). Hematological malignancies, including solid tumors - tumors of musculoskeletal system and skin, digestive system, brain and central nervous system predominated. Stress levels in zones of the Aral Sea region were slightly higher in the crisis zone than in the catastrophe zone that can be explained by the phenomenon of wave-like dynamics of disease growth risk. Gender differences in characteristics of malignancy formation were not more pronounced in the studied region. Conclusion: Indices of children cancer are slightly higher in the Aral Sea region than in the control area of Kazakhstan, but they are comparable to results for other regions.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제2권4호
• /
• pp.291-302
• /
• 2013

사이니지란 공공장소에서 불특정 다수의 이용자에게 특정 정보를 제공해 주는 미디어 기기이다. 최근에 상황인지 기술이 적용되면서 사이니지는 개인별 맞춤형 정보서비스를 제공할 수 있게 됨에 따라 단순한 광고 플랫폼에서 새로운 차원의 미디어 기기로 진화하고 있다. 본 연구의 목적은 사이니지에 대한 이용자들의 인식과 태도를 파악하고, 그것들을 유형별로 분류하여 사이니지 인식에 대한 기준을 제시하는 것이다. 본 연구에서는 사이니지에 대한 이용자의 인식과 태도를 파악하기 위해 관련 전문가와 실무자 인터뷰를 실시한 후, Q방법론을 활용하여 사이니지에 대한 이용자 인식과 태도를 유형별로 분류하였다. 본 연구 결과, 제1유형을 '스마트미디어 사이니지 인지형', 제2유형을 '수동형미디어 사이니지 인지형', 제3유형을 '양방향미디어 사이니지 인지형'이라고 각각 분류하여 분석하였다. 본 연구 결과는 향후 사이니지 관련 학술연구와 R&D에 유용한 가이드라인이 될 것이다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권7호
• /
• pp.1759-1772
• /
• 2023

Chinese named entity recognition (NER) is a challenging work that seeks to find, recognize and classify various types of information elements in unstructured text. Due to the Chinese text has no natural boundary like the spaces in the English text, Chinese named entity identification is much more difficult. At present, most deep learning based NER models are developed using a bidirectional long short-term memory network (BiLSTM), yet the performance still has some space to improve. To further improve their performance in Chinese NER tasks, we propose a new NER model, IDCNN-BiLSTM-Highway, which is a combination of the BiLSTM, the iterated dilated convolutional neural network (IDCNN) and the highway network. In our model, IDCNN is used to achieve multiscale context aggregation from a long sequence of words. Highway network is used to effectively connect different layers of networks, allowing information to pass through network layers smoothly without attenuation. Finally, the global optimum tag result is obtained by introducing conditional random field (CRF). The experimental results show that compared with other popular deep learning-based NER models, our model shows superior performance on two Chinese NER data sets: Resume and Yidu-S4k, The F1-scores are 94.98 and 77.59, respectively.

• 대한토목학회논문집
• /
• 제38권4호
• /
• pp.621-625
• /
• 2018

본 연구는 딥러닝을 활용하여 교량 점검보고서에서 손상 및 손상 인자를 자동으로 식별하는 방법을 제안한다. 교량 점검보고서에는 점검 결과 발견된 손상 및 원인 분석 결과가 기록되어 있다. 그러나 점검보고서의 양이 방대하여 인력으로 보고서로부터 정보를 수집하는 데 한계가 있다. 따라서 본 연구에서는 딥러닝 기반 개체명 인식 방법을 활용하여 교량 점검보고서 텍스트로부터 손상 및 손상 인자에 해당하는 단어들을 식별할 수 있는 모델을 제안한다. 모델 구현의 주요 방법론으로는 개체명 인식(Named Entity Recognition), 워드 임베딩(Word Embedding), 딥러닝의 일종인 순환신경망(Recurrent Neural Network)을 활용하였다. 실험 결과 제안된 모델은 1)훈련 데이터에 포함된 손상 및 손상 인자 단어들을 잘 식별할 수 있고, 2)단어 주변 맥락에 따라 특정 단어가 손상에 해당하는지 손상 인자에 해당하는지 잘 판별할 수 있을 뿐만 아니라, 3)훈련 데이터에 포함되지 않은 새로운 종류의 손상 단어도 잘 인식할 수 있는 것으로 확인되었다.