• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.11
• /
• pp.2037-2042
• /
• 2017

The manufacturing facility is generally operated by a pre-set program under the existing factory automation system. On the other hand, the manufacturing facility must decide how to operate autonomously in Industry 4.0. Determining the operation mode of the production facility itself means, for example, that it detects the abnormality such as the deterioration of the facility at the shop-floor, prediction of the occurrence of the problem, detection of the defect of the product, In this paper, we propose a manufacturing process modeling using a queue for detection of manufacturing process abnormalities at the shop-floor, and detect abnormalities in the modeling using SVM, one of the machine learning techniques. The queue was used for M / D / 1 and the conveyor belt manufacturing system was modeled based on ${\mu}$, ${\lambda}$, and ${\rho}$. SVM was used to detect anomalous signs through changes in ${\rho}$.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.1
• /
• pp.471-476
• /
• 2024

With the spread of various smart devices and computing devices, big data generation is occurring widely. Machine learning is an algorithm that performs reasoning by learning data patterns. Among the various machine learning algorithms, the algorithm that attracts attention is deep learning based on neural networks. Deep learning is achieving rapid performance improvement with the release of various applications. Recently, among deep learning algorithms, attempts to analyze data using graph structures are increasing. In this study, we present a graph generation method for transferring to a deep learning network. This paper proposes a method of generalizing node properties and edge weights in the graph generation process and converting them into a structure for deep learning input by presenting a matricization We present a method of applying a linear transformation matrix that can preserve attribute and weight information in the graph generation process. Finally, we present a deep learning input structure of a general graph and present an approach for performance analysis.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2020.11a
• /
• pp.148-150
• /
• 2020

최근 VVC(Versatile Video Coding) 표준 완료 이후 JVET(Joint Video Experts Team)은 인공신경망 기반의 비디오 부호화를 위한 AhG(Ad-hoc Group) 구성하고 인공지능을 이용한 비디오 압축 기술들을 검증하고 있으며, MPEG(Moving Picture Experts Group)에서는 DNNVC(Deep Neural Network based Video Coding) 활동을 통해 딥러닝 기반의 차세대 비디오 부호화 표준 기술을 탐색하고 있다. 본 논문은 VVC 에 채택된 신경망 기반의 기술인 MIP(Matrix Weighted Intra Prediction)를 참조하여, MIP 모델의 학습에서 손실함수가 예측 성능에 미치는 영향을 분석한다. 즉, 예측의 왜곡(MSE)만을 고려한 경우와 예측오차의 부호화 비용도 함께 반영한 손실함수를 비교한다. 실험을 위해 HEVC(High Efficiency Video Coding) 화면내 예측 대비 평균적인 PSNR 향상 정도를 나타내는 성능 지표(��PSNR)를 정의한다. 실험결과 예측오차의 부호화 특성을 반영하는 손실함수를 이용한 학습이 MSE 만 고려한 학습 대비 ��PSNR 기준 평균 0.4dB 향상됨을 보였다.

• Journal of KIISE:Software and Applications
• /
• v.36 no.10
• /
• pp.851-860
• /
• 2009

Recently, among the computational methods of protein-protein interaction prediction, vast amounts of domain based methods originated from domain-domain relation consideration have been developed. However, it is true that multi domains collaboration is avowedly ignored because of computational complexity. In this paper, we implemented a protein interaction prediction system based the Interaction Significance matrix, which quantified an influence of domain combination pair on a protein interaction. Unlike conventional domain combination methods, IS matrix contains weighted domain combinations and domain combination pair power, which mean possibilities of domain collaboration and being the main body on a protein interaction. About 63% of sensitivity and 94% of specificity were measured when we use interaction data from DIP, IntAct and Pfam-A as a domain database. In addition, prediction accuracy gradually increased by growth of learning set size, The prediction software and learning data are currently available on the web site.

• Journal of KIISE:Software and Applications
• /
• v.37 no.5
• /
• pp.378-385
• /
• 2010

The explosive increase in the use of email has made to need email classification efficiently and accurately. Current work on the email classification method have mainly been focused on a binary classification that filters out spam-mails. This methods are based on Support Vector Machines, Bayesian classifiers, rule-based classifiers. Such supervised methods, in the sense that the user is required to manually describe the rules and keyword list that is used to recognize the relevant email. Other unsupervised method using clustering techniques for the multi-category classification is created a category labels from a set of incoming messages. In this paper, we propose a new automatic email multi-category classification method using NMF for automatic category label construction method and dynamic category hierarchy method for the reorganization of email messages in the category labels. The proposed method in this paper, a large number of emails are managed efficiently by classifying multi-category email automatically, email messages in their category are reorganized for enhancing accuracy whenever users want to classify all their email messages.

• Korean Journal of Mathematics
• /
• v.21 no.4
• /
• pp.503-521
• /
• 2013

For over 20 years, the issue of using an adequate CAS tool in teaching and learning of linear algebra has been raised constantly. And a variety of CAS tools were introduced in many linear algebra textbooks. In Korea, however, because of some realistic problems, they have not been introduced in the class and the theoretical aspect of linear algebra has been focused on in teaching and learning of it. In this paper, we suggest Sage as an alternative for CAS tools overcoming the problems mentioned above. And, we introduce full contents for linear algebra and matrix calculator that Sage was used to develop. Taking advantage of them, almost all the concepts of linear algebra can be easily covered and the size of matrices can be expanded without difficulty.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.8
• /
• pp.39-48
• /
• 2023

This study was conducted to provide a solution to the problem of sizing errors occurring in online purchases due to discrepancies and non-standardization in clothing sizes. This paper discusses an implementation approach for a machine learning-based recommender system capable of providing personalized sizes to online consumers. We trained multiple validated collaborative filtering algorithms including Non-Negative Matrix Factorization (NMF), Singular Value Decomposition (SVD), k-Nearest Neighbors (KNN), and Co-Clustering using purchasing data derived from online commerce and compared their performance. As a result of the study, we were able to confirm that the NMF algorithm showed superior performance compared to other algorithms. Despite the characteristic of purchase data that includes multiple buyers using the same account, the proposed model demonstrated sufficient accuracy. The findings of this study are expected to contribute to reducing the return rate due to sizing errors and improving the customer experience on e-commerce platforms.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.16 no.1
• /
• pp.41-49
• /
• 2023

A convolutional neural network (CNN) is a representative algorithm for implementing artificial neural networks. CNNs have improved on the issues of rapid increase in calculation amount and low object classification rates, which are associated with a conventional multi-layered fully-connected neural network (FNN). However, because of the rapid development of IT devices, the maximum resolution of images captured by current smartphone and tablet cameras has reached 108 million pixels (MP). Specifically, a traditional CNN algorithm requires a significant cost and time to learn and process simple, high-resolution images. Therefore, this study proposes an improved CNN algorithm for implementing an object classification learning model for simple, high-resolution images. The proposed method alters the adjacency matrix value of the pooling layer's max pooling operation for the CNN algorithm to reduce the high-resolution image learning model's creation time. This study implemented a learning model capable of processing 4, 8, and 12 MP high-resolution images for each altered matrix value. The performance evaluation result showed that the creation time of the learning model implemented with the proposed algorithm decreased by 36.26% for 12 MP images. Compared to the conventional model, the proposed learning model's object recognition accuracy and loss rate were less than 1%, which is within the acceptable error range. Practical verification is necessary through future studies by implementing a learning model with more varied image types and a larger amount of image data than those used in this study.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.6
• /
• pp.682-689
• /
• 2019

In part-based image representation, the partial shapes of an object are represented as basis vectors, and an image is decomposed as a linear combination of basis vectors where the coefficients of those basis vectors represent the partial (or local) feature of an object. In this paper, a face recognition for occluded faces is proposed in which face images are represented using non-negative matrix factorization(NMF), one of part-based representation techniques, and recognized using an artificial neural network technique. Standard NMF, projected gradient NMF and orthogonal NMF were used in part-based representation of face images, and their performances were compared. Learning vector quantizer were used in the recognizer where Euclidean distance was used as the distance measure. Experimental results show that proposed recognition is more robust than the conventional face recognition for the occluded faces.

• KIPS Transactions on Computer and Communication Systems
• /
• v.11 no.4
• /
• pp.105-112
• /
• 2022

Recently, many studies using reinforcement learning-based autoscaling have been performed to make autoscaling policies that are adaptive to changes in the environment and meet specific purposes. However, training the reinforcement learning-based Horizontal Pod Autoscaler(HPA) policy in a real environment requires a lot of money and time. And it is not practical to retrain the reinforcement learning-based HPA policy from scratch every time in a real environment. In this paper, we implement a reinforcement learning-based HPA in Kubernetes, and propose a transfer leanring technique using a queuing model-based simulation to accelerate the training of a reinforcement learning-based HPA policy. Pre-training using simulation enabled training the policy through simulation experience without consuming time and resources in the real environment, and by using the transfer learning technique, the cost was reduced by about 42.6% compared to the case without transfer learning technique.