• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2022년도 춘계학술발표대회
• /
• pp.424-427
• /
• 2022

본 연구는 도메인 특성이 강한 HR 평가문장을 BERT PLM 모델을통해 4 가지 class 로 구분하는 문제를 다룬다. 다양한 PLM 모델 적용과 training data 수에 따른 모델 성능 비교를 통해 특정 도메인에 언어모델을 적용하기 위해서 필요한 기준을 확인하였다. 또한 Unlabeled 된 HR 분야 corpus 를 활용하여 BERT 모델을 post-training 한 HR-BERT 가 PLM 분석모델 정확도 향상에 미치는 결과를 탐구한다. 위와 같은 연구를 통해 HR 이 가지고 있는 가장 큰 text data 에 대한 활용 기반을 마련하고, 특수한 도메인 분야에 PLM 을 적용하기 위한 가이드를 제시하고자 한다

• Korean Journal of Radiology
• /
• 제22권11호
• /
• pp.1858-1874
• /
• 2021

Recent advances in the molecular and genetic characterization of central nervous system (CNS) tumors have ushered in a new era of tumor classification, diagnosis, and prognostic assessment. In this emerging and rapidly evolving molecular genetic era, imaging plays a critical role in the preoperative diagnosis and surgical planning, molecular marker prediction, targeted treatment planning, and post-therapy assessment of CNS tumors. This review provides an overview of the current imaging methods relevant to the molecular genetic classification of CNS tumors. Specifically, we focused on 1) the correlates between imaging features and specific molecular genetic markers and 2) the post-therapy imaging used for therapeutic assessment.

• 대한원격탐사학회지
• /
• 제27권3호
• /
• pp.315-328
• /
• 2011

Landsat data incorporated with additional bands-normalized difference vegetation index (NDVI) and band ratios were used to assess the extent and rate of deforestation in the Gunung Mutis Nature Reserve (GMNR), a mountainous tropical forest in Eastern of Indonesia. Hybrid classification was chosen as the classification approach. In this approach, the unsupervised classification-iterative self-organizing data analysis (ISODATA) was used to create signature files and training data set. A statistical separability measurement-transformed divergence (TD) was used to identify the combination of bands that showed the highest distinction between the land cover classes in training data set. Supervised classification-maximum likelihood classification (MLC) was performed using selected bands and the training data set. Post-classification smoothing and accuracy assessment were applied to classified image. Post-classification comparison was used to assess the extent of deforestation, of which the rate of deforestation was calculated by the formula suggested by Food Agriculture Organization (FAO). The results of two periods of deforestation assessment showed that the extent of deforestation during 1989-1999 was 720.72 ha, 0.80% of annual rate of deforestation, and its extent of deforestation during 1999-2009 was 1,059.12 ha, 1.31% of annual rate of deforestation. Such results are important for the GMNR authority to establish strategies, plans and actions for combating deforestation.

• Journal of Advanced Marine Engineering and Technology
• /
• 제39권1호
• /
• pp.58-62
• /
• 2015

대부분의 블로그 사이트에서는 미리 정의된 분류 체계에 따른 내용 기반 분류 환경을 제공하고 있으나, 작성된 포스트의 분류를 수동으로 선택해야하는 번거로움 때문에 대부분의 블로거들은 포스트에 대한 분류를 입력하지 않고 있다. 본 논문에서는 블로그 포스트의 자동 분류를 위해 블로그 사이트에서 분류별 문서를 수집하고 수집된 분류별 문서의 어휘빈도와 문서빈도, 분류별 빈도 등의 다양한 어휘 가중치 조합하여 블로그 포스트의 특성에 적합한 가중치 방식을 찾고자 한다. 실험에서는 본 논문에서 제안한 TF-CTF-IECDF를 어휘 가중치로 사용한 분류 모델이 77.02%의 분류 정확률을 보였다.

• 정보처리학회논문지B
• /
• 제12B권7호
• /
• pp.811-822
• /
• 2005

자동문서분류는 문서의 내용에 기반하여 미리 정의된 항목에 자동으로 할당하는 작업으로서 효율적인 정보관리 및 검색등에 필수적인 작업이다. 기존의 문서분류성능 향상을 위한 연구들은 대부분 분류모델 자체를 개선시키는 데 주력해왔으며 통계적인 방법으로 그 범위가 제한되어왔다. 본 연구에서는 자동문서분류의 성능향상을 위해 데이터마이닝 기법과 결함허용방법을 이용하는 개선된 학습알고리즘과 후처 리 방법에 의한 RTPost 시스템을 제안한다. RTPost 시스템은 학습문서 선택작업 이전에 분류항목 설정의 문제를 다루며, 분류함수의 성능보다는 지정방식의 문제점을 감안하여 학습과 분류 후처리 프로세스를 개선하려는 것이다. 이를 통해 분류결과에 중요한 영향을 미쳐왔던 학습문서의 수와 선택방법, 분류모델의 성능등에 의존하지 않는 안정적인 분류가 가능하였고, 이를 분류오류율이 높은 경계선 인접영역에 위치한 문서들에 적용한 결과 높은 정확율을 얻을 수 있었다. 뿐만 아니라, RTPost 프로세스를 진행하는 동안 능동학습방법의 장점을 수용하여 학습효과는 높이며 비용을 감소시킬 수 있는 자가학습방법(self learning)방법의 효과를 기대할 수 있다.

• Imaging Science in Dentistry
• /
• 제53권1호
• /
• pp.69-75
• /
• 2023

Purpose: Maxillofacial trauma predominantly affects young adults between 20 and 40 years of age. Although radioprotection is a legal requirement, the significant potential of dose reduction in computed tomography (CT) is still underused in the clinical routine. The objective of this study was to evaluate whether maxillofacial fractures can be reliably detected and classified using ultra-low-dose CT. Materials and Methods: CT images of 123 clinical cases with maxillofacial fractures were classified by two readers using the AOCOIAC software and compared with the corresponding results from post-treatment images. In group 1, consisting of 97 patients with isolated facial trauma, pre-treatment CT images at different dose levels (volumetric computed tomography dose index: ultra-low dose, 2.6 mGy; low dose, <10 mGy; and regular dose, <20 mGy) were compared with post-treatment cone-beam computed tomography (CBCT). In group 2, consisting of 31 patients with complex midface fractures, pre-treatment shock room CT images were compared with post-treatment CT at different dose levels or CBCT. All images were presented in random order and classified by 2 readers blinded to the clinical results. All cases with an unequal classification were re-evaluated. Results: In both groups, ultra-low-dose CT had no clinically relevant effect on fracture classification. Fourteen cases in group 2 showed minor differences in the classification code, which were no longer obvious after comparing the images directly to each other. Conclusion: Ultra-low-dose CT images allowed the correct diagnosis and classification of maxillofacial fractures. These results might lead to a substantial reconsideration of current reference dose levels.

• 대한임베디드공학회논문지
• /
• 제16권1호
• /
• pp.17-27
• /
• 2021

In this paper, we develop a galaxy image classification method based on hand-crafted features and machine learning techniques. Additionally, we provide an empirical analysis to reveal which combination of the techniques is effective for galaxy image classification. To achieve this, we developed a framework which consists of four modules such as preprocessing, feature extraction, feature post-processing, and classification. Finally, we found that the best technique for galaxy image classification is a method to use a median filter, ORB vector features and a voting classifier based on RBF SVM, random forest and logistic regression. The final method is efficient so we believe that it is applicable to embedded environments.

• The Journal of Korean Physical Therapy
• /
• 제26권5호
• /
• pp.315-323
• /
• 2014

Purpose: This study was conducted in order to investigate the effect of motor ability on mastery motivation in children with cerebral palsy. Methods: Sixty children with cerebral palsy (5~12 years) and their parents participated in the study. Data on general characteristics and disability condition, Gross Motor Functional Classification System, Manual Ability Classification System, and The Dimensions of Mastery questionnaire were collected for this study. Independent t-test, and ANOVA were used for analysis of the effect of The Dimensions of Mastery questionnaire according to general and disability condition, Gross Motor Functional Classification System, and Manual Ability Classification System. Linear regression analysis was performed to determine the effects of Gross Motor Functional Classification System and Manual Ability Classification System on The Dimensions of Mastery questionnaire. SPSS win. 22.0 was used and Tukey was used for post hoc analysis, level of statistical significance was less than 0.05. Results: The Dimensions of Mastery questionnaire score showed statistically significant difference according to gender, region, type, disability rating, Gross Motor Functional Classification System, and Manual Ability Classification System (p<0.05). Gross Motor Functional Classification System and Manual Ability Classification System were the effect factor on The Dimensions of Mastery questionnaire significantly (p<0.05). Conclusion: These results suggest that motor ability of children with cerebral palsy was an important factor having an effect on The Dimensions of Mastery questionnaire.

• 반도체디스플레이기술학회지
• /
• 제8권3호
• /
• pp.39-44
• /
• 2009

Local Binary Pattern (LBP) is becoming a popular tool for various machine vision applications such as face recognition, classification and background subtraction. In this paper, we propose a new extension of LBP, called the Diagonal LBP (DLBP), to handle the image-based gender classification problem arise in interactive display systems. Instead of comparing neighbor pixels with the center pixel, DLBP generates codes by comparing a neighbor pixel with the diagonal pixel (the neighbor pixel in the opposite side). It can reduce by half the code length of LBP and consequently, can improve the computation complexity. The Support Vector Machine is utilized as the gender classifier, and the texture profile based on DLBP is adopted as the feature vector. Experimental results revealed that our approach based on the diagonal LPB is very efficient and can be utilized in various real-time pattern classification applications.

• 한국컴퓨터정보학회논문지
• /
• 제23권5호
• /
• pp.1-7
• /
• 2018

Reference string recognition is to extract individual reference strings from a reference section of an academic article, which consists of a sequence of reference lines. This task has been attacked by heuristic-based, clustering-based, classification-based approaches, exploiting lexical and layout characteristics of reference lines. Most classification-based methods have used sequence labeling to assign labels to either a sequence of tokens within reference lines, or a sequence of reference lines. Unlike the previous token-level sequence labeling approach, this study attempts to assign different labels to the beginning, intermediate and terminating tokens of a reference string. After that, post-processing is applied to identify reference strings by predicting their beginning and/or terminating tokens. Experimental evaluation using English and German reference string recognition datasets shows that the proposed method obtains above 94% in the macro-averaged F1.