• 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.

• 대한임베디드공학회논문지
• /
• 제18권6호
• /
• pp.285-292
• /
• 2023

With the wide spread of smart farms and the advancements in IoT technology, it is easy to obtain additional data in addition to crop images. Consequently, deep learning-based crop disease diagnosis research utilizing multimodal data has become important. This study proposes a crop disease diagnosis method using multimodal supervised contrastive learning by expanding upon the multimodal self-supervised learning. RandAugment method was used to augment crop image and time series of environment data. These augmented data passed through encoder and projection head for each modality, yielding low-dimensional features. Subsequently, the proposed multimodal supervised contrastive loss helped features from the same class get closer while pushing apart those from different classes. Following this, the pretrained model was fine-tuned for crop disease diagnosis. The visualization of t-SNE result and comparative assessments of crop disease diagnosis performance substantiate that the proposed method has superior performance than multimodal self-supervised learning.

• 제어로봇시스템학회논문지
• /
• 제21권6호
• /
• pp.565-570
• /
• 2015

Supervised machine learning has become popular in discovering context descriptions from sensor data. However, collecting a large amount of labeled training data in order to guarantee good performance requires a great deal of expense and time. For this reason, semi-supervised learning has recently been developed due to its superior performance despite using only a small number of labeled data. In the existing semi-supervised learning algorithms, unlabeled data are used to build a graph Laplacian in order to represent an intrinsic data geometry. In this paper, we represent the unlabeled data as the spatial-temporal dataset by considering smoothly moving objects over time and space. The developed algorithm is evaluated for position estimation of a smartphone-based robot. In comparison with other state-of-art semi-supervised learning, our algorithm performs more accurate location estimates.

• Journal of Information Technology Applications and Management
• /
• 제15권1호
• /
• pp.225-242
• /
• 2008

PM (Inconsistency Pattern Modeling) is a hybrid supervised learning technique using the inconsistence pattern of input variables in mining data sets. The IPM tries to improve prediction accuracy by combining more than two different supervised learning methods. The previous related studies have shown that the IPM was superior to the single usage of an existing supervised learning methods such as neural networks, decision tree induction, logistic regression and so on, and it was also superior to the existing combined model methods such as Bagging, Boosting, and Stacking. The objectives of this paper is explore the characteristics of the IPM. To understand characteristics of the IPM, three experiments were performed. In these experiments, there are high performance improvements when the prediction inconsistency ratio between two different supervised learning techniques is high and the distance among supervised learning methods on MDS (Multi-Dimensional Scaling) map is long.

• 반도체디스플레이기술학회지
• /
• 제19권4호
• /
• pp.121-125
• /
• 2020

With miniaturization of semiconductor, the manufacturing process become more complex, and undetected small changes in the state of the equipment have unexpectedly changed the process results. Fault detection classification (FDC) system that conducts more active data analysis is feasible to achieve more precise manufacturing process control with advanced machine learning method. However, applying machine learning, especially in supervised learning criteria, requires an arduous data labeling process for the construction of machine learning data. In this paper, we propose a semi-supervised learning to minimize the data labeling work for the data preprocessing. We employed equipment status variable identification (SVID) data and optical emission spectroscopy data (OES) in silicon etch with SF6/O2/Ar gas mixture, and the result shows as high as 95.2% of labeling accuracy with the suggested semi-supervised learning algorithm.

• 한국전자통신학회논문지
• /
• 제14권4호
• /
• pp.701-706
• /
• 2019

최근에는 인공지능의 도래로 인하여 수많은 산업과 일반적인 응용에 적용됨으로써 우리의 생활에 큰 영향을 발휘하고 있다. 이러한 분야에 다양한 기계학습의 방식들이 제공되고 있다. 기계학습의 한 종류인 지도학습은 학습의 과정 중에 특징값과 목표값을 입력으로 가진다. 지도학습에도 다양한 종류가 있으며 이들의 성능은 입력데이터인 빅데이터의 특성과 상태에 좌우된다. 따라서, 본 논문에서는 특정한 빅 데이터 세트에 대한 다수의 지도학습 방식들의 성능을 비교하기 위해 텐서플로우(Tensorflow)와 사이킷런(Scikit-Learn)에서 제공하는 대표적인 지도학습의 방식들을 이용하여 파이썬언어와 주피터 노트북 환경에서 시뮬레이션하고 분석하였다.

• Journal of Multimedia Information System
• /
• 제7권1호
• /
• pp.33-40
• /
• 2020

Machine learning consists of supervised and unsupervised learning among which supervised learning is used for the speech recognition objectives. Supervised learning is the Data mining task of inferring a function from labeled training data. Speech recognition is the current trend that has gained focus over the decades. Most automation technologies use speech and speech recognition for various perspectives. This paper demonstrates an overview of major technological standpoint and gratitude of the elementary development of speech recognition and provides impression method has been developed in every stage of speech recognition using supervised learning. The project will use DNN to recognize speeches using magnitudes with large datasets.

• Journal of the Korean Data and Information Science Society
• /
• 제18권3호
• /
• pp.629-636
• /
• 2007

A kernel type semi-supervised estimate is proposed. The proposed estimate is based on the penalized least squares loss and the principle of Gaussian Random Fields Model. As a result, we can estimate the label of new unlabeled data without re-computation of the algorithm that is different from the existing transductive semi-supervised learning. Also our estimate is viewed as a general form of Gaussian Random Fields Model. We give experimental evidence suggesting that our estimate is able to use unlabeled data effectively and yields good classification.

• 정보과학회 논문지
• /
• 제42권12호
• /
• pp.1561-1567
• /
• 2015

준지도 학습은 기계 학습의 한 분야로서, 레이블된 데이터와 레이블되지 않은 데이터 모두를 사용하여 모델을 학습함으로써 지도 학습에 비해 예측 정확도를 높일 수 있다. 최근 각광받고 있는 그래프 기반 준지도 학습은 입력 데이터를 그래프의 형태로 변환하는 그래프 구축 단계와 이를 사용하여 레이블되지 않은 데이터의 레이블을 예측하는 레이블 추론 단계로 나뉜다. 이 추론은 준지도 학습에서의 평활도 가정을 기본으로 한다. 본 연구에서는 추가로 각 꼭지점 중요도를 결합함으로써 개선된 레이블 추론 알고리즘을 제안한다. 이와 함께 알고리즘의 수렴성을 증명하고, 또한 실험을 통해 알고리즘의 우수성을 검증하였다.

• Journal of Information Processing Systems
• /
• 제17권3호
• /
• pp.453-461
• /
• 2021

Many deep learning approaches have been studied for image classification in computer vision. However, there are not enough data to generate accurate models in medical fields, and many datasets are not annotated. This study presents a new method that can use both unlabeled and labeled data. The proposed method is applied to classify cervix images into normal versus cancerous, and we demonstrate the results. First, we use a patch self-supervised learning for training the global context of the image using an unlabeled image dataset. Second, we generate a classifier model by using the transferred knowledge from self-supervised learning. We also apply attention learning to capture the local features of the image. The combined method provides better performance than state-of-the-art approaches in accuracy and sensitivity.