• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1998.06a
• /
• pp.404-409
• /
• 1998

In this paper, we propose a learning algorithm of fuzzy neural networks with trapezoidal fuzzy weights. This fuzzy neural networks can use fuzzy numbers as well as real numbers, and represent linguistic information better than standard neural networks. We construct trapezodal fuzzy weights by the composition of two triangles, and devise a learning algorithm using the two triangular membership functions, The results of computer simulations on numerical data show that the fuzzy neural networks have high fitting ability for target output.

• Journal of Institute of Control, Robotics and Systems
• /
• v.10 no.11
• /
• pp.1107-1111
• /
• 2004

As an information technology is developed, more intelligent system considering emotional factor for implementing the personality is required. In this paper, Reactive Learning Inference System considering emotional factor is proposed. Emotional Facter(E) is defined for a criterion for representing the personal preference. This system is designed to have functions of Reactive filtering by Emotional factor, Incremental learning, perception & inference and knowledge retrieval. This system is applied to the area for analysis of customer's tastes and its performance is analyzed and compared.

• Korean Journal of Cognitive Science
• /
• v.1 no.1
• /
• pp.103-127
• /
• 1989

Learning systems by using examples have been developed which include ALEX, LP, and LEX.Specially Silver's LP systems suggerts the method to use a seyuence of operators, which was applied to the worked example, to sove a symbolic equation.This paper presents the new learning system, called LRD, in which generalization and discrimination steps are suggerted to solv all the problems similar to the worked example.The system LRD is illustrated by the problem of finding the ranges of transcendentral functions and compared to LP and LEX by the problems discussed in them.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1996.10a
• /
• pp.243-248
• /
• 1996

In this paper, a general neural-network-based connectionist model, called Fuzzy Neural Network(FNN), is proposed for the realization of a fuzzy logic control system. The proposed FNN is a feedforward multi-layered network which integrates the basic elements and functions of a traditional fuzzy logic controller into a connectionist structure which has distributed learning abilities. Such FNN can be constructed from training examples by learning rule, and the connectionist structure can be trained to develop fuzzy logic rules and find optimal input/output membership functions. Computer simulation examples will be presented to illustrate the performance and applicability of the proposed FNN, and their associated learning algorithms.

• The Transactions of the Korea Information Processing Society
• /
• v.7 no.3
• /
• pp.1025-1031
• /
• 2000

Pre-existing pattern recognition techniques, in the case of character recognition, have limited on the application field. But CAI character learning system and writer's recognition system are very important parts. The application field of pre-existing system can be expanded in the content that the learning of characters and the recognition of writers in the proposed paper. In order to achieve these goals, the development contents are the following: Firstly, pre-processing method by understanding the image structure is proposed, secondly, recognition of characters are accomplished b the histogram distribution characteristics. Finally, similarity measure functions are defined from standard character pattern for matching of the input character pattern. Also the effectiveness of this system is demonstrated by experimenting the standard primitive image.

• Journal of Information Processing Systems
• /
• v.15 no.2
• /
• pp.422-432
• /
• 2019

A hybrid kernel function of support vector machine is proposed to improve the classification performance of power quality disturbances. The kernel function mathematical model of support vector machine directly affects the classification performance. Different types of kernel functions have different generalization ability and learning ability. The single kernel function cannot have better ability both in learning and generalization. To overcome this problem, we propose a hybrid kernel function that is composed of two single kernel functions to improve both the ability in generation and learning. In simulations, we respectively used the single and multiple power quality disturbances to test classification performance of support vector machine algorithm with the proposed hybrid kernel function. Compared with other support vector machine algorithms, the improved support vector machine algorithm has better performance for the classification of power quality signals with single and multiple disturbances.

• Management & Information Systems Review
• /
• v.5
• /
• pp.249-285
• /
• 2000

This paper discusses management education by utilizing the cyber education learning system in a web-based. New learning system tools offer great promise for a new contents of management learning. The cyber education learning system a shift from face-to-face lecturing to interactive learning. The situation changes profoundly when information technology becomes develope and education paradigm is shift. By exploiting the digital media. educations, and students, managers can shift to a new, more effect cyber education learning system. The following shift from classic educations to cyber educations learning system: from instruction to construction, from teacher-centered to learner-centered, from school to lifelong, from one-size-fits-all to customized, from teacher as transmitter to teacher as facilitator. Cyber education learning system has an important role to play in management education. Web-based technology is regarded as a general solution to cyber education learning. This study discussed many factors of implementation in cyber education systems and provide utilizing the learning system at main, detail functions. Lastly, management implications of these cyber education utilize are discussed in more detail.

• International Journal of Contents
• /
• v.9 no.3
• /
• pp.35-41
• /
• 2013

This paper aims at investigating what Regional University E-Learning Centers (RUECs) has done in promoting e-learning in university education in Korea. First, the e-learning situation in university education in Korea is introduced. Secondly, the background of establishment of RUECs and its functions are explained in detail. Thirdly, a case of RUECs is suggested by using the CNU-University E-Learning Center. In particular, the performance of e-learning is evaluated based on the student satisfaction data, and a paired-t test is implemented to see if there was any difference between 'before' and 'after' e-learning. Lastly, some suggestions are made to promote the e-learning in university education.

• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.195-206
• /
• 2022

Crack detection is essential for inspection of existing structures and crack segmentation based on deep learning is a significant solution. However, datasets are usually one of the key issues. When building a new dataset for deep learning, laborious and time-consuming annotation of a large number of crack images is an obstacle. The aim of this study is to develop an approach that can automatically select a small portion of the most informative crack images from a large pool in order to annotate them, not to label all crack images. An active learning method with difficulty learning mechanism for crack segmentation tasks is proposed. Experiments are carried out on a crack image dataset of a steel box girder, which contains 500 images of 320×320 size for training, 100 for validation, and 190 for testing. In active learning experiments, the 500 images for training are acted as unlabeled image. The acquisition function in our method is compared with traditional acquisition functions, i.e., Query-By-Committee (QBC), Entropy, and Core-set. Further, comparisons are made on four common segmentation networks: U-Net, DeepLabV3, Feature Pyramid Network (FPN), and PSPNet. The results show that when training occurs with 200 (40%) of the most informative crack images that are selected by our method, the four segmentation networks can achieve 92%-95% of the obtained performance when training takes place with 500 (100%) crack images. The acquisition function in our method shows more accurate measurements of informativeness for unlabeled crack images compared to the four traditional acquisition functions at most active learning stages. Our method can select the most informative images for annotation from many unlabeled crack images automatically and accurately. Additionally, the dataset built after selecting 40% of all crack images can support crack segmentation networks that perform more than 92% when all the images are used.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.33B no.3
• /
• pp.186-192
• /
• 1996

A modified learning rule is introduced for the implementation of feedforward artificial neural networks with on-chip learning circuitry using standard analog CMOS technology. Learning rule, is modified form the EBP (error back propagation) rule which is one of the well-known learning rules for the feedforward rtificial neural nets(FANNs). The employed MEBP ( modified EBP) rule is well - suited for the hardware implementation of FANNs with on-chip learning rule. As a ynapse circuit, a four-quadrant vector-product linear multiplier is employed, whose input/output signals are given with voltage units. Two $2{\times}2{\times}1$ FANNs are implemented with the learning circuitry. The implemented FANN circuits have been simulatied with learning test patterns using the PSPICE circuit simulator and their results show correct learning functions.