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.

Surveillance plays a crucial role in safeguards. Reviewing surveillance data requires a significant number of inspection manpower. As the number of surveillance cameras increases, the demand for such manpower is expected to grow even more. Recently, in the field of security, there has been a development of deep learning models that automatically detect abnormal events from video images, and their usage is expanding. In this study, we used an AutoEncoder-based semi-supervised learning model, which can detect unexpected abnormal events, to detect anomalies in the UCSDped2 dataset and in simulating safeguards-related event videos taken at Dry Mockup facility of KAERI. To improve the model performance, we transformed the video images into two parts: the appearance part, which are sequences of video image frames, and the motion part, which are the pixel value differences of consecutive video frames. In addition, we added memory module to the bottle neck of the AutoEncoder model, and skip connection to enhance the model performance. To evaluate the model performance, we proposed a new evaluation index, which is adequate to the video images of safeguards surveillance in addition to the widely used AUC (Area Under the ROC Curve).

Recently, many studies have been conducted to improve quality by applying machine learning models to semiconductor manufacturing process data. However, in the semiconductor manufacturing process, the ratio of good products is much higher than that of defective products, so the problem of data imbalance is serious in terms of machine learning. In addition, since the number of features of data used in machine learning is very large, it is very important to perform machine learning by extracting only important features from among them to increase accuracy and utilization. This study proposes an anomaly detection methodology that can learn excellently despite data imbalance and high-dimensional characteristics of semiconductor process data. The anomaly detection methodology applies the LIME algorithm after applying the SMOTE method and the RFECV method. The proposed methodology analyzes the classification result of the anomaly classification model, detects the cause of the anomaly, and derives a semiconductor process requiring action. The proposed methodology confirmed applicability and feasibility through application of cases.

A mid-story isolation system was proposed for seismic response reduction of high-rise buildings and presented good control performance. Control performance of a mid-story isolation system was enhanced by introducing semi-active control devices into isolation systems. Seismic response reduction capacity of a semi-active mid-story isolation system mainly depends on effect of control algorithm. AI(Artificial Intelligence)-based control algorithm was developed for control of a semi-active mid-story isolation system in this study. For this research, an practical structure of Shiodome Sumitomo building in Japan which has a mid-story isolation system was used as an example structure. An MR (magnetorheological) damper was used to make a semi-active mid-story isolation system in example model. In numerical simulation, seismic response prediction model was generated by one of supervised learning model, i.e. an RNN (Recurrent Neural Network). Deep Q-network (DQN) out of reinforcement learning algorithms was employed to develop control algorithm The numerical simulation results presented that the DQN algorithm can effectively control a semi-active mid-story isolation system resulting in successful reduction of seismic responses.

감성어휘는 텍스트로 감성을 표현하거나, 반대로 텍스트로부터 감성을 인식하기 위한 특징으로써 감성분류 연 구에 필수요소이다. 본 연구는 감성어휘의 집합인 감성사전을 자동으로 구축하는 그래프 기반 준지도 학습 방법 을 제안한다. 특히 감성어휘가 사용되어지는 분야에 따라 그 감성이 변하는 중의성 문제를 고려하여 분야 별 감 성사전을 구축하고자 한다. 제안하는 방법은 어휘와 어휘들 간의 밀접도를 토대로 그래프를 구성하고, 사전에 학 습 된 일부 소량의 감성어휘들의 감성을 구성된 그래프 전체에 전파하는 방식으로 모든 어휘의 감성을 추론한다. 감성어휘는 대표적으로 감성단어와 감성구문이 있으며, 본 연구에서는 이들 각각에 대한 그래프를 구성하고 감성을 추론하여 전체 감성사전을 구축하였다. 제안하는 방법의 성능을 검증하기 위해 영화평 분야의 감성사전을 구축하고, 이를 이용한 영화평 감성분류 실험을 수행하였다. 그 결과 기존 범용 감성사전의 어휘들을 이용한 감 성분류보다 더 높은 분류 성능을 확인하였다.