• Journal of Advanced Navigation Technology
• /
• v.15 no.2
• /
• pp.287-297
• /
• 2011

As electronic mails are being widely used for facility and speedness of information communication, as the amount of spam mails which have malice and advertisement increase and cause lots of social and economic problem. A number of approaches have been proposed to alleviate the impact of spam. These approaches can be categorized into pre-acceptance and post-acceptance methods. Post-acceptance methods include bayesian filters, collaborative filtering and e-mail prioritization which are based on words or sentances. But, spammers are changing those characteristics and sending to avoid filtering system. In the case of Korean, the abnormal usages can be much more than other languages because syllable is composed of chosung, jungsung, and jongsung. Existing formal expressions and learning algorithms have the limits to meet with those changes promptly and efficiently. So, we present an methods for recognizing Korean abnormal language(Koral) to improve accuracy and efficiency of filtering system. The method is based on syllabic than word and Smith-waterman algorithm. Through the experiment on filter keyword and e-mail extracted from mail server, we confirmed that Koral is recognized exactly according to similarity level. The required time and space costs are within the permitted limit.

• KIPS Transactions on Software and Data Engineering
• /
• v.6 no.11
• /
• pp.527-536
• /
• 2017

With the recent development of smart grid industry, the necessity for efficient EMS(Energy Management System) has been increased. In particular, in order to reduce electric load and energy cost, sophisticated electric load forecasting and efficient smart grid operation strategy are required. In this paper, for more accurate electric load forecasting, we extend the data collected at demand time into high time resolution and construct an artificial neural network-based forecasting model appropriate for the high time resolution data. Furthermore, to improve the accuracy of electric load forecasting, time series data of sequence form are transformed into continuous data of two-dimensional space to solve that problem that machine learning methods cannot reflect the periodicity of time series data. In addition, to consider external factors such as temperature and humidity in accordance with the time resolution, we estimate their value at the time resolution using linear interpolation method. Finally, we apply the PCA(Principal Component Analysis) algorithm to the feature vector composed of external factors to remove data which have little correlation with the power data. Finally, we perform the evaluation of our model through 5-fold cross-validation. The results show that forecasting based on higher time resolution improve the accuracy and the best error rate of 3.71% was achieved at the 3-min resolution.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.26 no.1
• /
• pp.56-63
• /
• 2016

In this study, we introduce a design of Fuzzy RBFNNs-based digit recognition system using the incremental-PCA in order to recognize the handwritten digits. The Principal Component Analysis (PCA) is a widely-adopted dimensional reduction algorithm, but it needs high computing overhead for feature extraction in case of using high dimensional images or a large amount of training data. To alleviate such problem, the incremental-PCA is proposed for the computationally efficient processing as well as the incremental learning of high dimensional data in the feature extraction stage. The architecture of Fuzzy Radial Basis Function Neural Networks (RBFNN) consists of three functional modules such as condition, conclusion, and inference part. In the condition part, the input space is partitioned with the use of fuzzy clustering realized by means of the Fuzzy C-Means (FCM) algorithm. Also, it is used instead of gaussian function to consider the characteristic of input data. In the conclusion part, connection weights are used as the extended diverse types in polynomial expression such as constant, linear, quadratic and modified quadratic. Experimental results conducted on the benchmarking MNIST handwritten digit database demonstrate the effectiveness and efficiency of the proposed digit recognition system when compared with other studies.

• Journal of Korea Water Resources Association
• /
• v.30 no.4
• /
• pp.347-355
• /
• 1997

In this study, the applicability of genetic algorithms into the parameter estimation of storage function method for flood routing model is investigated. Genetic algorithm is mathematically established theory based on the process of Darwinian natural selection and survival of fittest. It can be represented as a kind of search algorithms for optima point in solution space and make a reach on optimal solutions through performance improvement of assumed model by applying the natural selection of life as mechanical learning province. Flood events recorded in the Daechung dam are selected and used for the parameter estimation and verification of the proposed parameter estimation method by the split sample method. The results are analyzed that the performance of the model are improved including peak discharge and time to peak and shown that the parameter Rsa, and f1 are most sensitive to storage function model. Based on the analysis for estimated parameters and the comparison with the results from experimental equations, the applicability of genetic algorithm is verified and the improvements of those equations will be used for the augmentation of flood control efficiency.

• Korean Journal of Social Welfare
• /
• v.68 no.3
• /
• pp.73-103
• /
• 2016

In this study, it investigates the life of normal adolescents who have parents with intellectual disability and their difficulties which suggested social welfare meanings of this study. In order to conduct wide and in-depth analysis on cases by utilizing the characteristics of qualitative case studies, it describes and analyzes the intellectual disability parents' normal children in detail from the viewpoint of an insider through in-depth interviews, various sources and diverse data collecting methods. As for the subject of this study, both parents should be persons with intellectual disability and their child shall be non-disabled and at least a high school student or older. Through the intentional sampling, five late adolescents who were in high school, all males participated in the study. The data collection process had been conducted from January 2014 to May, which is commonly utilized for qualitative case studies, and comparative analysis between cases were practiced for analysis. For credibility of the research results, it obtained severity at each stage by meeting the standard. The analysis results were largely divided into "growth story of non-disabled adolescents" and "life of non-disabled adolescents". Nine upper categories analyzed the common features in each case. The nine categories were "no one tells me to study", "advance while learning the sense of academic achievement", "hide into my own space", "having to grown up early", "different parents but same love", "relatives raised me", "have a friend who accepts me as I am", "being pressed by poverty", and "standing on a knife edge of being hurt and taking heart". Based on the in-depth research on normal teens that have intellectually disabled parents, theoretically speaking, this study expanded the prospect of study on intellectually disabled to their normal, intellectual teenage children. As for practical significance, understanding their parents' intellectual disability, parenting technique training, case management from the community level is suggested. Rregular real condition research of the families, allowance system for economic support et al. is suggested in policy aspect.

• Journal of The Korean Association For Science Education
• /
• v.30 no.1
• /
• pp.170-180
• /
• 2010

Among the various fields of Earth Science, especially in Astronomy, we often deal with the change of space-time in an abstract way. Thus, making use of 'Concept Sketches'-simplified sketches that represent the main features, principles, processes and interrelationships of the learning content by using some concise explanations, signs and terms could help the students efficiently learn the phenomena of Astronomy. This study's aim was to check its effects and analyze the results of the lessons that included concept sketches and a discussion about the field of Earth Science in high school. The control group took traditional lessons, while the experimental group did a small-group discussion that used the concept sketches. After the lesson, some students were chosen to answer a questionnaire and go through an in-depth interview. The result of the data shows that the small-group discussion lesson that used the concept sketches helped both the high-ranking and low-ranking students to build concepts and was able to attract students' attention. Moreover, the students produced long-term memories of the content learned through the class discussion, which allowed them to exchange their own thoughts and opinions with other students. Most of all, drawing pictures, a familiar activity, appealed to the students, so they took part in the class eagerly.

• Journal of The Korean Association For Science Education
• /
• v.34 no.6
• /
• pp.549-558
• /
• 2014

Integrated concepts that are broad enough to embrace facts, principles, laws, and concepts of multiple disciplines could become the core of integrated education. Integrated concept-centered education enables effective and practical learning. In this study, the Delphi Method was implemented targeting experts in science (physics, life science, chemistry, and earth science) and humanities (history, geology, economics, ethics, and politics) to find out the integrated concept that can be used to design the concept-centered integrated education in the Republic of Korea. 124 experts participated in this survey. Delphi survey was conducted for three rounds. In the first round, an open questionnaire was given to experts to collect feasible integrated concepts in each major field. Then, in the second round experts were asked to select integrated concepts that could be used practically in the field of their major. In the third round, the integrated concept with selection frequency over medium value were given. They were asked to evaluate the applicability of integrated concepts by using the Likert-scale questionnaire. Through this process, content validity was analyzed. As a result, five integrated concepts (change, interaction, space-time, energy, and equilibrium) were selected for the inter-science integration. And thirteen integrated concepts (conflict, community, relationship, structure, power, diversity, culture, change, society, interaction, freedom, justice, and equality) were chosen for the inter-humanities integration. Finally, for the science-humanities integration, seven integrated concepts (structure, diversity, change, interaction, cycle, system, and environment) were determined.

• Journal of Korean Home Economics Education Association
• /
• v.20 no.4
• /
• pp.59-75
• /
• 2008

This study is designed to support the development and the teaching of revised curriculum of 2007 "Technology & Home Economics" by investigating the actual condition and the necessity of education for elderly housing education. Questionnaire survey was conducted with 488 high school students in Gyeongnam in 2008. The data analyzed by descriptive statistics, t-test, One-way ANOVA, Duncan's multiple range test by using SPSS 14 program. The results showed that most of the students were dissatisfied with their middle school education of elderly housing due to the lack of interesting and practical contents. Thus, various teaching-learning methods where student can experience and experiment is needed. Also, the students demanded more of factors of elderly housing, spacing plan, elderly welfare service and less of three-generation housing and senior housing in their elderly housing education. The needs of education contents differed among students depending on variables such as sex, graduated middle school, household income, dwelling space and length of residential years. Therefore, revised 2007 curriculum of "Technology & Home Economics" should include required contents in related chapters. Because there are significant differences among textbooks about elderly housing, further attention needs to be paid to the new textbooks in order to include education contents evenly. At the same time, teachers should organize their teaching contents considering the divergence of variables. The effect of elderly housing education will be maximized if the revised curriculum consists of more experimental activities such as elderly simulation in the local community.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.21 no.6
• /
• pp.749-754
• /
• 2011

In this study, we propose the design of optimized pRBFNNs-based face recognition system using two-dimensional Image and ASM algorithm. usually the existing 2 dimensional face recognition methods have the effects of the scale change of the image, position variation or the backgrounds of an image. In this paper, the face region information obtained from the detected face region is used for the compensation of these defects. In this paper, we use a CCD camera to obtain a picture frame directly. By using histogram equalization method, we can partially enhance the distorted image influenced by natural as well as artificial illumination. AdaBoost algorithm is used for the detection of face image between face and non-face image area. We can butt up personal profile by extracting the both face contour and shape using ASM(Active Shape Model) and then reduce dimension of image data using PCA. The proposed pRBFNNs consists of three functional modules such as the condition part, the conclusion part, and the inference part. In the condition part of fuzzy rules, input space is partitioned with Fuzzy C-Means clustering. In the conclusion part of rules, the connection weight of RBFNNs is represented as three kinds of polynomials such as constant, linear, and quadratic. The essential design parameters (including learning rate, momentum coefficient and fuzzification coefficient) of the networks are optimized by means of Differential Evolution. The proposed pRBFNNs are applied to real-time face image database and then demonstrated from viewpoint of the output performance and recognition rate.

• Journal of the Korean Institute of Traditional Landscape Architecture
• /
• v.31 no.4
• /
• pp.123-128
• /
• 2013

This study was performed with an aim to examine the inner thoughts of Muso Soseki through his works. In this study, we reviewed currently existing Mus$\bar{o}$ Soseki. Works in which his idea or intention behind his works are to be understood in terms of landscaping science or religious perspective. Targeting his best representative works of temple gardens such as Jochou-ji, Eiho-ji, Zuisen-ji, Tenryu-ji, it was sought his view of gardening and technique of garden making. Those temples, selected as target of this study, have significance as a places to have started his learning till matured of his thought into his gardening works. What we need to concentrate and think about regarding the works of Muso is the fact that we are to be impressed upon just looking at his works. The study result indicates that Muso not only symbolized his various mastered ideas & philosophies into spatial configuration into the garden based on Zen Buddhism idea, but also accomplished the Sabi-gardening beauty. Through his writing "Mongjoongmundap(夢中問答)" that is created using his core thoughts, his works can be understood better. This study has significance in that the idea. It could be understood that Muso's work is rooted in the basic idea of three ideas. The first of it is Zen philosophy being indicated in his configuration of gardening such as Zen meditation Stone, cave, chamdo etc. The second of it is shown as the merciful heart of Sangguboje(上求普提), Hahwajoongsaeng(下化衆生), being indicated in his configuration of gardening such as the pond And finally, there appears the Tao idea. Taoist thought has become of where the background space.