• Journal of the Korean Institute of Intelligent Systems
• /
• v.20 no.5
• /
• pp.672-676
• /
• 2010

This paper presents a learning rule that weights more on data near decision boundary. This learning rule generates better decision boundary by reducing the effect of outliers on the decision boundary. The proposed learning rule is integrated into IAFC neural network. IAFC neural network is stable to maintain previous learning results and is plastic to learn new data. The performance of the proposed fuzzy neural network is compared with performances of LVQ neural network and backpropagation neural network. The results show that the performance of the proposed fuzzy neural network is better than those of LVQ neural network and backpropagation neural network.

• Journal of Institute of Control, Robotics and Systems
• /
• v.21 no.12
• /
• pp.1109-1114
• /
• 2015

This paper presents an improved learning-based visual inspection method for auto parts inspection in severe lighting changes. Automobile sunroof frames are produced automatically by robots in most production lines. In the sunroof frame manufacturing process, there is a quality problem with some parts such as volts are missed. Instead of manual sampling inspection using some mechanical jig instruments, a learning-based machine vision system was proposed in the previous research[1]. But, in applying the actual sunroof frame production process, the inspection accuracy of the proposed vision system is much lowered because of severe illumination changes. In order to overcome this capricious environment, some selective feature vectors and cascade classifiers are used for each auto parts. And we are able to improve the inspection accuracy through the re-learning concept for the misclassified data. The effectiveness of the proposed visual inspection method is verified through sufficient experiments in a real sunroof production line.

• Journal of Fisheries and Marine Sciences Education
• /
• v.25 no.2
• /
• pp.510-525
• /
• 2013

The purpose of this study is to investigate adult learners' experience by studying Humanities & General Education and get to know types and characteristics by classifying their learning experiences. This study uses grounded theory method which is suitable to investigate subjective experiences. In this study, data is collected from 13 adult learners by using Focus Group Interview(FGI) who participate in learning experience of Humanities & General Education of D university in Busan region. The data is categorized by open coding, axial coding and selective coding based on data analysis method of grounded theory and analysis processes. This study provides several outcomes as follows: 113 concepts, 38 subcategories and 16 upper categories are derived through the process of abbreviation and categorization of learning experience of Humanities & General Education. In a process of learning experience, this study shows interrelationship in a frame of paradigm and derives results of a process of abbreviation and categorization casual condition, contextual condition, phenomenon and interaction(help/obstruction factor). Tree types of learning experiences and characteristics are drawn as follows: 1) "Self-realization" is the type who participate in Humanities & General Education with desire of learning and they want to find identity and plan detailed future. 2) "The pursuit of happiness" has less desire on learning than "self-realization" and they are types who participate in Humanities & General Education because of someone else's help and suggestion. 3) "Local community" is the type who participate in Humanities & General Education because they feel necessity of social role and they expect local development based on their interest in local community. Several conclusions and suggestions are provided for further studies.

• International Journal of Contents
• /
• v.14 no.2
• /
• pp.1-6
• /
• 2018

In a wireless mobile communication system, a pilot signal has been considered to be a necessary signal for estimating a changing channel between a base station and a terminal. All mobile communication systems developed so far have a specification for transmitting pilot signals. However, although the pilot signal transmission is easy to estimate the channel,(Ed: unclear wording: it is easy to use the pilot signal transmission to estimate the channel?) it should be minimized because it uses radio resources for data transmission. In this paper, we propose a pilotless channel estimation scheme (PCE) by introducing the clustering method of unsupervised learning used in our deep learning into channel estimation.(Ed: highlight- unclear) The PCE estimates the channel using only the data symbols without using the pilot signal at all. Also, to apply PCE to a real system, we evaluated the performance of PCE based on the resource block (RB), which is a resource allocation unit used in LTE. According to the results of this study, the PCE always provides a better mean square error (MSE) performance than the least square estimator using pilots, although it does not use the pilot signal at all. The MSE performance of the PCE is affected by the number of data symbols used and the frequency selectivity of the channel. In this paper, we provide simulation results considering various effects(Ed: unclear, clarify).

• Journal of Information Technology Applications and Management
• /
• v.22 no.3
• /
• pp.1-18
• /
• 2015

Financial markets are characterized by large numbers of complex and interacting factors which are ill-understood and frequently difficult to measure. Mathematical models developed in finance are precise formulations of theories of how these factors interact to produce the market value of financial asset. While these models are quite good at predicting these market values, because these forces and their interactions are not precisely understood, the model value nevertheless deviates to some extent from the observable market value. In this paper we propose a framework for augmenting the predictive capabilities of mathematical model with a learning component which is primed with an initial set of historical data and then adjusts its behavior after the event of prediction.

• Journal of Fisheries and Marine Sciences Education
• /
• v.21 no.4
• /
• pp.523-542
• /
• 2009

The purpose of this study was to figure out the procedure of learning Korean for international students. A research question was set up as follows: What is the procedure of leaning Korean for international students in Korean universities? To achieve the research purpose, this study implemented a method of semi-constructed interviews. Nineteen international students participated in the interview. The collected data for this study included transcripts from each interview. The transcripts of 60 minutes of interviews with all the participants was audio-taped recorded. This study investigated the research question based on the grounded theory. The analysis of open coding, axial-coding, and selective coding was used in the study. Results indicated that international students learned Korean in a daily basis, and then they adapted to academic Korean in their majored fields. Both personality and mother tongue influenced Korean language learning positively and negatively. International students' improvement of Korean was related in studying with Korean mass media such as TV soap dramas, talk shows, and songs. International students think that TOPIK(Test Of Proficiency In Korean) is not much related with their Korean language fluency. In conclusion, the researchers suggested to give more emphasis on academic training courses for Korean language and to improve the TOPIK in general academic Korean.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.19 no.12
• /
• pp.2779-2784
• /
• 2015

The prediction of the accurate traffic information can provide an optimal route from the place of departure to a destination, therefore, this makes it possible to obtain a saving of time and money. To predict traffic information, we use a Bayesian network method based on probability model in this paper. Existing researches predicting the traffic information based on a Bayesian network generally used to study the data for all time. In this paper, however, only data corresponding to same time and day of the week to predict selectively will be used for learning. In fact, the experiment was carried out for 14 links zone in Seoul, also, the accuracy of the prediction results of the two different methods should be tested with MAPE (Mean Absolute Percentage Error) which is commonly used. In view of MAPE, experimental results show that the proposed method may calculate traffic prediction value with a higher accuracy than the method used to learn the data for all time zones.

• Journal of the Korean Geographical Society
• /
• v.49 no.6
• /
• pp.970-984
• /
• 2014

This study aims to inquire into experience of geography teachers participating in a teacher learning community based on the grounded theory methodology. Participation observation was conducted on one of geography teacher learning communities. The total of 11 research participants were selected to conduct in-depth interviews. The data collected were analyzed by the coding method proposed by Strauss and Corbin(1990, 1998). In open coding, 125 concepts, 43 sub-categories and 17 categories were drawn and in axial coding by paradigm model, phenomenon, conditions, action/interaction and consequences turned out. In selective coding, the participants were classified into four types and the condition/consequence matrix was developed. As a result of the analysis, first, participation, obstacles and continuous participation factors of geography teachers in the teacher learning community could be understood from multi-dimensional aspects. Second, principles of the collaborative teacher learning and the factors promoting collaborative teacher learning were established. Third, the professional development of geography teachers through teacher learning community could be understood.

• Journal of the Korean Society for Library and Information Science
• /
• v.41 no.4
• /
• pp.251-271
• /
• 2007

The purpose of this study is to investigate grade differences in the effect of reading methods - "oral reading" "silent reading", "intensive reading", "extensive reading" "thorough reading", "selective reading" - influences on the self-directed learning ability. The data were collected by using 12 classes of 2nd, 4th, 6th-grade, 286 children of an elementary school. The influences according to reading methods on the self-directed learning ability were surveyed through the self-directed learning ability test and through questionnaire. Out of reading methods, "intensive reading" had significant influence on the self-directed learning ability Out of reading methods of 4th and 6th-grade children, "intensive reading" had the most influence on the self-directed learning ability. However. out of reading methods of 2nd-grade children "thorough reading" had most influence on the self-directed learning ability.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.24 no.8
• /
• pp.55-61
• /
• 2010

In this paper, we proposed selective extraction method of frequency information and PCA-ELM based diagnosis system for three-phase induction motors. As the first step for diagnosis procedure, DFT is performed to transform the acquired current signal into frequency domain. And then, frequency components are selected according to discriminate order calculated by variance As the next step, feature extraction is performed by principal component analysis (PCA). Finally, we used the classifier based on Extreme Learning Machine (ELM) with fast learning procedure. To show the effectiveness, the proposed diagnostic system has been intensively tested with the various data acquired under different electrical and mechanical faults with varying load.