• 한국경영과학회지
• /
• 제33권3호
• /
• pp.93-105
• /
• 2008

Semi-supervised learning uses a small amount of labeled data to predict labels of unlabeled data as well as to improve clustering performance, whereas unsupervised learning analyzes only unlabeled data for clustering purpose. We propose a new clustering-based semi-supervised learning method by reflecting the initial predicted labels of unlabeled data on the objective function. The initial prediction should be done in terms of a discrete probability distribution through a classification method using labeled data. As a result, clusters are formed and labels of unlabeled data are predicted according to the Information of labeled data in the same cluster. We evaluate and compare the performance of the proposed method in terms of classification errors through numerical experiments with blinded labeled data.

• ETRI Journal
• /
• 제46권1호
• /
• pp.59-70
• /
• 2024

We introduce a high-performance named entity recognition (NER) model for written and spoken language. To overcome challenges related to labeled data scarcity and domain shifts, we use transfer learning to leverage our previously developed KorBERT as the base model. We also adopt a meta-pseudo-label method using a teacher/student framework with labeled and unlabeled data. Our model presents two modifications. First, the student model is updated with an average loss from both human- and pseudo-labeled data. Second, the influence of noisy pseudo-labeled data is mitigated by considering feedback scores and updating the teacher model only when below a threshold (0.0005). We achieve the target NER performance in the spoken language domain and improve that in the written language domain by proposing a straightforward rollback method that reverts to the best model based on scarce human-labeled data. Further improvement is achieved by adjusting the label vector weights in the named entity dictionary.

• Molecules and Cells
• /
• 제22권3호
• /
• pp.254-261
• /
• 2006

DNA microarray is a powerful tool for high-throughput analysis of biological systems. Various computational tools have been created to facilitate the analysis of the large volume of data produced in DNA microarray experiments. Normalization is a critical step for obtaining data that are reliable and usable for subsequent analysis such as identification of differentially expressed genes and clustering. A variety of normalization methods have been proposed over the past few years, but no methods are still perfect. Various assumptions are often taken in the process of normalization. Therefore, the knowledge of underlying assumption and principle of normalization would be helpful for the correct analysis of microarray data. We present a review of normalization techniques from single-labeled platforms such as the Affymetrix GeneChip array to dual-labeled platforms like spotted array focusing on their principles and assumptions.

• 한국정보통신학회논문지
• /
• 제7권5호
• /
• pp.993-1001
• /
• 2003

본 논문에서는 Edge-Labeled Graph에 기반하여 XML 인스턴스들을 관계형 데이터베이스로 저장하는 모델을 제안하고 구현한다. 저장되는 XML 인스턴스들은 Edge-Labeled Graph에 기반 한 Data Graph로 표현하고 이를 이용하여 데이터 경로, 엘리먼트, 속성, 테이블 인덱스 테이블에 정의한 값들을 추출한 후 Mapper를 이용하여 데이터베이스 스키마를 정의하고 추출된 값들을 저장한다. 그리고, 저장 모델은 질의를 지원하기 위해, XPATH를 따르는 질의 언어로 사용되는 XQL을 SQL로 변환하는 변환기 및 저장된 XML 인스턴스를 복원하는 DBtoXML 처리기를 갖도록 한다. 구현 결과, XML 인스턴스들과 제안된 모델 구조간의 저장 관계가 그래프 기반의 경로를 이용한 표현으로 가능했으며, 동시에, 특정 엘리먼트 또는 속성들의 정보들을 쉽게 검색할 수 있는 가능성을 보였다.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제31권8호
• /
• pp.991-998
• /
• 2004

생물 정보학 등 많은 응용 분야에서 데이타 분석을 할 때는 적은 수의 분류표시된 데이터 (labeled data)와 많은 수의 비분류표시된 데이타(unlabeled data)가 있을 수 있다 분류표시된 자료는 사람의 노력이 요구되기 때문에 얻기가 어렵고 비용이 많이 들지만, 비분류표시된 자료는 별 어려움 없이 쉽게 얻을 수 있다. 이때 비분류표시된 자료를 이용하여 자료를 분류하고 분석하는데 널리 이용되고 있는 방법이 co-training 알고리즘이다. 이 방법은 적은 수의 분류표시된 자료에서 두 가지 뷰(view)로 각 분류자를 학습한다. 그리고 각 분류자는 분석하고자 하는 모든 비분류표시된 자료에서 가장 만족할만한 예측자들을 만들어 나간다. 이렇게 훈련 데이타 셋에서 실험을 여러 번 반복적으로 하게 되면 각 뷰에서 새로운 분류자가 학습되어 분류표시된 자료의 수가 증가한다. 본 논문에서는 비분류표시된 데이타를 이용하여 새로운 co-training 방법을 제시한다. 이 방법은 두 가지 분류자와 WebKB 및 BIND XML의 2가지 실험 데이타를 가지고 평가하였다. 실험 결과로서, 이 논문에서 제안한 co-training 방법이 분류표시된 자료의 수가 매우 적을 때 분류정확성을 효과적으로 향상시킬 수 있음을 보였다.

• 산업경영시스템학회지
• /
• 제46권4호
• /
• pp.312-320
• /
• 2023

Recently, there has been an increasing attempt to replace defect detection inspections in the manufacturing industry using deep learning techniques. However, obtaining substantial high-quality labeled data to enhance the performance of deep learning models entails economic and temporal constraints. As a solution for this problem, semi-supervised learning, using a limited amount of labeled data, has been gaining traction. This study assesses the effectiveness of semi-supervised learning in the defect detection process of manufacturing using the MixMatch algorithm. The MixMatch algorithm incorporates three dominant paradigms in the semi-supervised field: Consistency regularization, Entropy minimization, and Generic regularization. The performance of semi-supervised learning based on the MixMatch algorithm was compared with that of supervised learning using defect image data from the metal casting process. For the experiments, the ratio of labeled data was adjusted to 5%, 10%, 25%, and 50% of the total data. At a labeled data ratio of 5%, semi-supervised learning achieved a classification accuracy of 90.19%, outperforming supervised learning by approximately 22%p. At a 10% ratio, it surpassed supervised learning by around 8%p, achieving a 92.89% accuracy. These results demonstrate that semi-supervised learning can achieve significant outcomes even with a very limited amount of labeled data, suggesting its invaluable application in real-world research and industrial settings where labeled data is limited.

• International Journal of Internet, Broadcasting and Communication
• /
• 제16권1호
• /
• pp.280-286
• /
• 2024

In this paper, layered UNet with warmup and dropout tricks was used to segment teeth instantly by using data labeled for each individual tooth and increase performance of the result. The layered UNet proposed before showed very good performance in tooth segmentation without distinguishing tooth number. To do instance segmentation of teeth, we labeled teeth CBCT data according to tooth numbering system which is devised by FDI World Dental Federation notation. Colors for labeled teeth are like AI-Hub teeth dataset. Simulation results show that layered UNet does also segment very well for each tooth distinguishing tooth number by color. Layered UNet model using warmup trick was the best with IoU values of 0.80 and 0.77 for training, validation data. To increase the performance of instance segmentation of teeth, we need more labeled data later. The results of this paper can be used to develop medical software that requires tooth recognition, such as orthodontic treatment, wisdom tooth extraction, and implant surgery.

• 인터넷정보학회논문지
• /
• 제4권6호
• /
• pp.33-42
• /
• 2003

본 논문에서는 Edge-Labeled Graph에 기반하여 XML 인스턴스들을 관계형 데이터베이스내에 저장하는 모델을 제안하고 구현한다. 저장 모델은 저장되는 XMI 인스턴스들을 Edge-Labeled Graph에 기반하여 데이터 그래프로 표현하며, 표현한 데이터 그래프상의 정보를 저장하기 위해 데이터베이스 스키마로 제시된 데이터 경로, 요소, 속성, 테이블 인덱스 테이블의 구조에 따라 정의된 값들을 추출하고 Mapper 모듈을 이용하여 저장하며 질의를 지원하기 위해, XPATH를 따르는 질의 언어인 XQL을 SQL로 변환하는 모듈, 또한 저장된 XML 인스턴스를 복원하는 DBtoXML 모듈을 갖도록 하였다. 구현 결과, XML 인스턴스들과 제안한 저장 모델 구조로의 저장 관계가 그래프 기반의 경로를 이용한 표현으로 가능했으며, 동시에, 특정 요소 또는 속성들의 정보들을 쉽게 검색할 수 있는 가능성을 보였다.

• 대한간호학회지
• /
• 제27권3호
• /
• pp.588-600
• /
• 1997

Postpartum depression is one of the most serious problems in maternal health because it affects not only the mother but also her family. Postpartum depression disturbs the maternal-infant interaction and attachment. However, most postpartum depression patients ignore this problem and do not seek treatment. Many clinicians and researchers realiza there is a need to develop a postpartum depression scale. Thus, this study has been designed to development of a postpartum depression scale. Data were collected through a survey over a period of three months. Subjects who participated in the study were 167 Korean mothers in their postpartum period. The author used a convenience sampling method. The analysis of the data was done with SPSS PC/sup ＋/ for descriptive statistics, item analysis and factor analysis. Initially 62 items were generated from the interview data of eight postpartum depression patients and from a literature review. This preliminary scale was analyzed for reliability and validity. The results of this analysis are as follows. 1. Initially 62 items were analyzed through the Index of Content Validity(CVI) and 48 items were selected. 2. Seven factors were extracted through the principal component analysis, and these contributed 61% of the variance in the total score. Finally 46 items in the scale loaded .41∼ .84 on one of seven factors. 3. Each factor was labeled. Factor 1 was labeled 'emotional phenomena-emotional upset' and included 13 items, factor 2 was labeled' cognitive phenomena-self concept disturbance' and included seven items, factor 3 was labeled 'relationship to baby-negative feeling' and included six items, factor 4 was labeled 'relationship to baby- overload' and included eight items, factor 5 was labeled 'negative maternal identity' and included five items, factor 6 was labeled 'biophysiological phenomena-disturbance of physical functioning' and included four items, and factor 7 was labeled' interpersonal relationship phenomena-blamed others' and included three items. 4. Cronbach Coefficient Alpha for internal consistency was .95 for the total 46 items. Finally, the author suggests that this scale could be adequately applied in assessing the postpartum depression of mothers during the postpartum period. The results of this study can contribute to designing an appropriate postpartum depression prevention strategy.

• 대한임베디드공학회논문지
• /
• 제17권3호
• /
• pp.129-138
• /
• 2022

Collecting and labeling sufficient training data, which is essential to deep learning-based visual inspection, is difficult for manufacturers to perform because it is very expensive. This paper presents a steel plate surface defect detection system with industrial-grade detection performance by training a small amount of steel plate surface images consisting of labeled and non-labeled data. To overcome the problem of lack of training data, we propose two data augmentation techniques: program-based augmentation, which generates defect images in a geometric way, and generative model-based augmentation, which learns the distribution of labeled data. We also propose a 4-step semi-supervised learning using pseudo labels and consistency training with fixed-size augmentation in order to utilize unlabeled data for training. The proposed technique obtained about 99% defect detection performance for four defect types by using 100 real images including labeled and unlabeled data.