• Proceedings of the KIEE Conference
• /
• 2002.07d
• /
• pp.2614-2616
• /
• 2002

According to the appearance of various virtual websites using multimedia technologies for engineering education, the internet applications in engineering education have drawn much interests. But unidirectional communication, simple text/image based webpages and tedious learning process without motivation etc. have made the lowering of educational efficiency in cyberspace. Thus, to cope with these difficulties this paper presents a web-based educational Flash movies based on ActionScript language for understanding the principles of the computer system architecture. The proposed Flash movies provides the improved learning methods which can enhance the interests of learners. The results of this paper can be widely used to improve the efficiency of cyberlectures in the cyber university. Several sample Flash movies are illustrated to show the validity of the proposed learning method.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.14 no.3
• /
• pp.162-170
• /
• 2014

Appearance-based subspace models such as eigenfaces have been widely recognized as one of the most successful approaches to face recognition and tracking. The success of eigenfaces mainly has its origins in the benefits offered by principal component analysis (PCA), the representational power of the underlying generative process for high-dimensional noisy facial image data. The sparse extension of PCA (SPCA) has recently received significant attention in the research community. SPCA functions by imposing sparseness constraints on the eigenvectors, a technique that has been shown to yield more robust solutions in many applications. However, when SPCA is applied to facial images, the time and space complexity of PCA learning becomes a critical issue (e.g., real-time tracking). In this paper, we propose a very fast and scalable greedy forward selection algorithm for SPCA. Unlike a recent semidefinite program-relaxation method that suffers from complex optimization, our approach can process several thousands of data dimensions in reasonable time with little accuracy loss. The effectiveness of our proposed method was demonstrated on real-world face recognition and tracking datasets.

• Journal of the Semiconductor & Display Technology
• /
• v.19 no.2
• /
• pp.26-30
• /
• 2020

In this paper, we studied the problem if the experiment number occurring in order to identify defect in scaffold. We need to change each of the 5 print factor to predict defect when printing disk type scaffold using FDM 3d printer. So then the number of scaffold print will be more than 100,000 times. This experiment number is difficult to perform in the field. In order to solve this problem, we have produced a prediction model based on machine learning multiple linear regression using print conditions and defect scaffold data for print conditions. The prediction model produced was verified through experiments. The verification confirmed that the error was less than 0.5 %. We have confirmed that satisfied within the target margin of error 5 %.

• Proceedings of the KIEE Conference
• /
• 2001.07d
• /
• pp.2490-2492
• /
• 2001

According to the appearance of various virtual websites using multimedia technologies for engineering education, the internet applications in engineering education have drawn much interests. But unidirectional communication, simple text/image-based webpages and tedious learning process without motivation etc. have made the lowering of educational efficiency in cyberspace. Thus, to cope with these difficulties this paper presents a web-based educational Java applets for understanding the principles or conceptions of digital logic systems. The proposed Java applets provides the improved learning methods which can enhance the interests of learners. The results of this paper can be widely used to improve the efficiency of cyberlectures in the cyber university. Several sample Java applets are illustrated to show the validity of the proposed learning method.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.11
• /
• pp.5496-5521
• /
• 2018

Object detection and tracking is the basic capability of mobile robots to achieve natural human-robot interaction. In this paper, an object tracking system of mobile robot is designed and validated using improved multiple instance learning algorithm. The improved multiple instance learning algorithm which prevents model drift significantly. Secondly, in order to improve the capability of classifiers, an active sample selection strategy is proposed by optimizing a bag Fisher information function instead of the bag likelihood function, which dynamically chooses most discriminative samples for classifier training. Furthermore, we integrate the co-training criterion into algorithm to update the appearance model accurately and avoid error accumulation. Finally, we evaluate our system on challenging sequences and an indoor environment in a laboratory. And the experiment results demonstrate that the proposed methods can stably and robustly track moving object.

• The Journal of Korean Association of Computer Education
• /
• v.6 no.4
• /
• pp.115-123
• /
• 2003

It's difficult to find efforts for individualization other than suggesting simple, branching level learning materials among the developed courseware. The reason is primarily attributed to the facts that the courseware itself is not flexible, a fixed structure which is not reusable, and numerous costs and time should be consumed to develop one. In the same context of the appearance of the object-oriented concept in the method of software development, the concept of 'learning object' has appeared in the development of courses and contents, paving the way toward the possibility of designing versatile courses through the learning object. In the learning object-based course design, however, it still has similar shape and structure to the existing courseware, and the effort to realize the individualized learning by utilizing the learning object is not sufficient, as well. In this study, I suggest a outlined learning object model which can support the individualized learning by expanding the existing learning object, and based on th is model. design a instructional model that can show an individualized learning path, based on the ADDIE model.

• Proceedings of the KIEE Conference
• /
• 2003.11b
• /
• pp.167-170
• /
• 2003

본 논문에서는 패턴 인식의 전형적인 경우인 보이기 기반 물체 인식(Appearance based object recognition)을 수행하기 위하여, 일반적인 퍼지 분류 모델과, 서포트 벡터 머신을 하이브리드(hybrid) 하게 연결한 서포트 벡터 기반 퍼지 분류 시스템이라는 새로운 방법을 제안하고 이에 대하여 연구한다. 일반적인 분류(classification)문제의 경우 두 클래스로 구분하는데 최적의 성능을 가지고 있는 서포트 벡터 머신이 다중클래스(Multiclass)의 경우 발생 하는 계산량의 증가 문제를 해 결하기 위하여 다중 클래스 분류(Multiclass classification)에 장점을 가진 퍼지 분류 시스템을 도입, 서포트 벡터 머신에 연결함으로써 단점을 보완하는 시스템을 제안한다. 즉 서포트 벡터 머신을 통해 퍼지 시스템의 구조를 러닝(learning)하는데 사용하여 최종 적으로는 퍼지 분류 시스템(Fuzzy Classifier)이 나오도록 하는 것이다. 이 시스템의 성능을 확인하고자 여러 가지 물체들에 대한 이미지를 가지고 있는 COIL(Columbia Object Image Library) 데이터 베이스를 사용하여 보이기 기반 물체 인식(Appearance based Object Recognition)을 수행 하였으며 이를 순수한 서포트 벡터 머신만을 이용하여 물체 인식을 수행한 경우와 정확도 및 인식 시간에 대하여 비교하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.2
• /
• pp.871-891
• /
• 2019

Visual tracking is a challenging task that needs learning an effective model to handle the changes of target appearance caused by factors such as pose variation, illumination change, occlusion and motion blur. In this paper, a novel tracking algorithm based on weighted local sub-space reconstruction error is presented. First, accounting for the appearance changes in the tracking process, a generative weight calculation method based on structural reconstruction error is proposed. Furthermore, a template update scheme of occlusion-aware is introduced, in which we reconstruct a new template instead of simply exploiting the best observation for template update. The effectiveness and feasibility of the proposed algorithm are verified by comparing it with some state-of-the-art algorithms quantitatively and qualitatively.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2019.06a
• /
• pp.150-152
• /
• 2019

본 논문에서는 기존의 연구를 극복하여 단일 영상이 아닌 단안 비디오로부터 5D 라이트필드 영상을 합성하는 딥러닝 프레임워크를 제안한다. 현재 일반적으로 사용 가능한 Lytro Illum 카메라 등은 초당 3프레임의 비디오만을 취득할 수 있기 때문에 학습용 데이터로 사용하기에 어려움이 있다. 이러한 문제점을 해결하기 위해 본 논문에서는 가상 환경 데이터를 구성하며 이를 위해 UnrealCV를 활용하여 사실적 그래픽 렌더링에 의한 데이터를 취득하고 이를 학습에 사용한다. 제안하는 딥러닝 프레임워크는 두 개의 입력 단안 비디오에서 $5{\times}5$의 각 SAI(sub-aperture image)를 갖는 라이트필드 비디오를 합성한다. 제안하는 네트워크는 luminance 영상으로 변환된 입력 영상으로부터 appearance flow를 추측하는 플로우 추측 네트워크(flow estimation network), appearance flow로부터 얻어진 두 개의 라이트필드 비디오 프레임 간의 optical flow를 추측하는 광학 플로우 추측 네트워크(optical flow estimation network)로 구성되어있다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.2
• /
• pp.742-762
• /
• 2015

In this study, we propose a distance metric learning approach called discriminant metric learning (DML) for face verification, which addresses a binary-class problem for classifying whether or not two input images are of the same subject. The critical issue for solving this problem is determining the method to be used for measuring the distance between two images. Among various methods, the large margin nearest neighbor (LMNN) method is a state-of-the-art algorithm. However, to compensate the LMNN's entangled data distribution due to high levels of appearance variations in unconstrained environments, DML's goal is to penalize violations of the negative pair distance relationship, i.e., the images with different labels, while being integrated with LMNN to model the distance relation between positive pairs, i.e., the images with the same label. The likelihoods of the input images, estimated using DML and LMNN metrics, are then weighted and combined for further analysis. Additionally, rather than using the k-nearest neighbor (k-NN) classification mechanism, we propose a verification mechanism that measures the correlation of the class label distribution of neighbors to reduce the false negative rate of positive pairs. From the experimental results, we see that DML can modify the relation of negative pairs in the original LMNN space and compensate for LMNN's performance on faces with large variances, such as pose and expression.