• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.67 no.1
• /
• pp.114-123
• /
• 2018

This paper concerns a design and learning method of softmax function neural networks based on K-means clustering. The partial discharge data Information is preliminarily processed through simulation using an Epoxy Mica Coupling sensor and an internal Phase Resolved Partial Discharge Analysis algorithm. The obtained information is processed according to the characteristics of the pattern using a Motor Insulation Monitoring System program. At this time, the processed data are total 4 types that void discharge, corona discharge, surface discharge and slot discharge. The partial discharge data with high dimensional input variables are secondarily processed by principal component analysis method and reduced with keeping the characteristics of pattern as low dimensional input variables. And therefore, the pattern classifier processing speed exhibits improved effects. In addition, in the process of extracting the partial discharge data through the MIMS program, the magnitude of amplitude is divided into the maximum value and the average value, and two pattern characteristics are set and compared and analyzed. In the first half of the proposed partial discharge pattern classifier, the input and hidden layers are classified by using the K-means clustering method and the output of the hidden layer is obtained. In the latter part, the cross entropy error function is used for parameter learning between the hidden layer and the output layer. The final output layer is output as a normalized probability value between 0 and 1 using the softmax function. The advantage of using the softmax function is that it allows access and application of multiple class problems and stochastic interpretation. First of all, there is an advantage that one output value affects the remaining output value and its accompanying learning is accelerated. Also, to solve the overfitting problem, L2-normalization is applied. To prove the superiority of the proposed pattern classifier, we compare and analyze the classification rate with conventional radial basis function neural networks.

• School Mathematics
• /
• v.9 no.2
• /
• pp.313-326
• /
• 2007

Recently in algebra curriculum, to recognizes and explains general nile expressing patterns is presented as the one alternative and is emphasized. In the seventh School Mathematic Curriculum regarding 'regularity and function' area, in elementary school curriculum, is guiding pattern activity of various form. But difficulty and problem of students are pointing in study for learning through pattern activity. In this article, emphasizes generalization process through research activity of pictorial/geometric pattern that is introduced much on elementary school mathematic curriculum and investigates various approach and strategy of student's thinking, state of symbolization in generalization process of pictorial/geometric pattern. And discusses generalization of pictorial/geometric pattern, difficulty of symbolization and suggested several proposals for research activity of pictorial/geometric pattern.

• School Mathematics
• /
• v.15 no.1
• /
• pp.15-35
• /
• 2013

The purpose of the research is to categorize math learners into pattern through those tools that distinguish math learning style for middle school students. On the ground of survey for 976 middle school students, the fact that there are 16 different math learning style at the result of cluster analysis is confirmed and the results are compared and analyzed previous research. Also according to the each constituent of math learning style, dissimilarity of distribution about learner of different sexes and grades are analyzed. It's helpful to understanding the whole characteristics of learners regarding math learning to figure out their cognitive and affective learning styles through the tools to distinguish their math learning styles.

• The Journal of Korean Association of Computer Education
• /
• v.6 no.2
• /
• pp.107-120
• /
• 2003

In Web Based Instruction, as evaluation of learning process means individual student's learning activity, it demands data on learning time, pattern, participation, environment in a specific learning contents. The purpose of this paper is to reflect analysis results of individual student's learning status in achievement evaluation using the most suitable web log mining to settle evaluation problem of learning process, an issue in web based instruction. The contents and results of this study are as following. First, conformity item for learning status analysis is determined and web log data preprocessing is executed. Second, on the basis of web log data, I construct student's database and analyze learning status using data mining techniques.

• Journal of Information Technology Applications and Management
• /
• v.26 no.5
• /
• pp.27-39
• /
• 2019

The Internet of Things (IoT) is a new paradigm that is revolutionizing computing. It is intended that all objects around us will be connected to the network, providing "anytime, anywhere" access to information. This study introduces IoT with Kolb's learning style in order to enhance the learning experience especially for inclusive education for primary and secondary schools where delivery of knowledge is not limited to physical, cognitive disabilities, human diversity with respect to ability, language, culture, gender, age and of other forms of human differences. The article also emphasizes the role of learning style as a discovery process that incorporates the characteristics of problem solving and learning. Kolb's Learning Style was chosen as it is widely used in research and in practical information systems applications. A consistent pattern of finding emerges by using a combination of Kolb's learning style and internet of things where specific individual differences, learning approach differences and IoT application differences are taken as a main research framework. Further several suggestions were made by using this combination to IoT architecture and smart environment of internet of things. Based on these suggestions, future research directions are proposed.

• The Research Journal of the Costume Culture
• /
• v.29 no.3
• /
• pp.346-360
• /
• 2021

Universities have recently introduced problem-based learning (PBL) to various subjects to enhance problem-solving skills (including self-directed learning and small-group learning) required in industry. The PBL module was applied to the personal production process in a draping class. A study was based on a questionnaire after conducting two PBL modules with a group of students. Each PBL module included 'design analysis', 'presentation of flat sketch and draping plan', 'discussion of the plan', 'evaluation of the draping result and correcting the problem', and 'final evaluation of the completed project'. Results showed that satisfaction with the PBL method and its activities was higher than satisfaction with existing teaching methods. In particular, among the various components, the 'design analysis' and 'the presentation step of flat sketch and draping plan' stages were more helpful to students compared to small-group discussion. Moreover, the effects of PBL were observed through student reflection essays, in which students suggested that PBL was very effective in enhancing problem-solving through self-directed and small-group learning. Despite the overall satisfaction with PBL, students expressed some minor difficulties associated with awkwardness with a novel learning method, lack of diverse perspectives among each group, and poor communication skills. Therefore, the study shows that PBL is highly likely to be useful to students when they are solving pattern drafting problems and making samples through self-directed learning and small-group learning.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.20 no.42
• /
• pp.161-169
• /
• 1997

A variety of learning methods are used for neural networks. Among them, the backpropagation algorithm is most widely used in such image processing, speech recognition, and pattern recognition. Despite its popularity for these application, its main problem is associated with the running time, namely, too much time is spent for the learning. This paper suggests a method which maximize the convergence speed of the learning. Such reduction in e learning time of the backpropagation algorithm is possible through an adaptive adjusting of the slope of the activation function depending on total errors, which is named as the variable slope algorithm. Moreover experimental results using this variable slope algorithm is compared against conventional backpropagation algorithm and other variations; which shows an improvement in the performance over pervious algorithms.

• Proceedings of the Korean Institute Of Construction Engineering and Management
• /
• autumn
• /
• pp.610-613
• /
• 2003

Ensuring technical ability is essential in the construction industry to increase competitiveness in the global market. A new paradigm is coming up in academic education system to cultivate the competent engineers. The major objective of this research is to suggest a positive learning pattern In order to overcome the limitations of the passive learning style. A case study, technical upgrading with a tower crane, us explained in terms of active learning process, results, and evaluation of students' performance.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.23 no.2
• /
• pp.139-146
• /
• 2020

The camouflage pattern was difficult to distinguish from the surrounding background, so it was difficult to classify the object and the background image when the color image is used as the training data of deep-learning. In this paper, we proposed a red-green color blindness image transformation method using the principle that people of red-green blindness distinguish green color better than ordinary people. Experimental results show that the camouflage soldier's recognition performance improved by proposed a deep learning model of the ensemble technique using the imitated red-green-blind image data and the original color image data.

• Journal of Multimedia Information System
• /
• v.3 no.4
• /
• pp.155-160
• /
• 2016

The Pulse Coupled Neural Network (PCNN) is a kind of neural network models that consists of spiking neurons and local connections. The PCNN was originally proposed as a model that can reproduce the synchronous phenomena of the neurons in the cat visual cortex. Recently, the PCNN has been applied to the various image processing applications, e.g., image segmentation, edge detection, pattern recognition, and so on. The method for the image matching using the PCNN had been proposed as one of the valuable applications of the PCNN. In this method, the Genetic Algorithm is applied to the PCNN parameter learning for the image matching. In this study, we propose the method of the similar image rating using the PCNN. In our method, the Genetic Algorithm based method is applied to the parameter learning of the PCNN. We show the performance of our method by simulations. From the simulation results, we evaluate the efficiency and the general versatility of our parameter learning method.