• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2004.10a
• /
• pp.433-436
• /
• 2004

In this paper, we introduce a new Fuzzy Polynomial Neural Networks (FPNNS)-like structure whose neuron is based on the Fuzzy Set-based Fuzzy Inference System (FS-FIS) and is different from that of FPNNS based on the Fuzzy relation-based Fuzzy Inference System (FR-FIS) and discuss the ability of the new FPNNS-like structure named Fuzzy Set-based Polynomial Neural Networks (FSPNN). The premise parts of their fuzzy rules are not identical, while the consequent parts of the both Networks (such as FPNN and FSPNN) are identical. This difference results from the angle of a viewpoint of partition of input space of system. In other word, from a point of view of FS-FIS, the input variables are mutually independent under input space of system, while from a viewpoint of FR-FIS they are related each other. The proposed design procedure for networks architecture involves the selection of appropriate nodes with specific local characteristics such as the number of input variables, the order of the polynomial that is constant, linear, quadratic, or modified quadratic functions being viewed as the consequent part of fuzzy rules, and a collection of the specific subset of input variables. On the parameter optimization phase, we adopt Information Granulation (IC) based on HCM clustering algorithm and a standard least square method-based learning. Through the consecutive process of such structural and parametric optimization, an optimized and flexible fuzzy neural network is generated in a dynamic fashion. To evaluate the performance of the genetically optimized FSPNN (gFSPNN), the model is experimented with using the time series dataset of gas furnace process.

• Asian-Australasian Journal of Animal Sciences
• /
• v.21 no.3
• /
• pp.314-319
• /
• 2008

Duck (Anas platyrhynchos) is one of the most important domestic avian species in the world. In the present research, fifteen polymorphic microsatellite markers were used to evaluate the diversity and population structure of 26 Chinese indigenous duck breeds across the country. The Chinese breeds showed high variation with the observed heterozygosity (Ho) ranging from 0.401 (Jinding) to 0.615 (Enshi), and the expected heterozygosity (He) ranging from 0.498 (Jinding) to 0.707 (Jingjiang). In all of the breeds, the values of Ho were significantly lower than those of He, suggesting high selection pressure on these local breeds. AMOVA and Bayesian clustering analysis showed that some breeds had mixed together. The FST value for all breeds was 0.155, indicating medium differentiation of the Chinese indigenous breeds. The FST value also indicated the short domestication history of most of Chinese indigenous ducks and the admixture of these breeds after domestication. Understanding the genetic relationship and structure of these breeds will provide valuable information for further conservation and utilization of the genetic resources in ducks.

• Journal of the Korea Society of Computer and Information
• /
• v.19 no.12
• /
• pp.309-317
• /
• 2014

Recently, crime prediction and prevention are the most important social issues, and global and local governments have tried to prevent crime using various methodologies. One of the methodologies, data mining can be applied at various crime fields such as crime pattern analysis, crime prediction, etc. However, there is few researches to find the relationships between the results of data mining and crime components in terms of criminology. In this study, we introduced environmental criminology, and identified relationships between environment factors related with crime and variables using at data mining. Then, using real burglary data occurred in South Korea, we applied clustering to show relations of results of data mining and crime environment factors. As a result, there were differences in the crime environment caused by each cluster. Finally, we showed the meaning of data mining use at crime prediction and prevention area in terms of criminology.

• Asian-Australasian Journal of Animal Sciences
• /
• v.27 no.10
• /
• pp.1399-1405
• /
• 2014

The effective management of endangered animal genetic resources is one of the most important concerns of modern breeding. Evaluation of genetic diversity and relationship of local breeds is an important factor towards the identification of unique and valuable genetic resources. This study aimed to analyze the genetic diversity and population structure of six Korean native chicken breeds (n = 300), which were compared with three imported breeds in Korea (n = 150). For the analysis of genetic diversity, 30 microsatellite markers from FAO/ISAG recommended diversity panel or previously reported microsatellite markers were used. The number of alleles ranged from 2 to 15 per locus, with a mean of 8.13. The average observed heterozygosity within native breeds varied between 0.46 and 0.59. The overall heterozygote deficiency ($F_{IT}$) in native chicken was $0.234{\pm}0.025$. Over 30.7% of $F_{IT}$ was contributed by within-population deficiency ($F_{IS}$). Bayesian clustering analysis, using the STRUCTURE software suggested 9 clusters. This study may provide the background for future studies to identify the genetic uniqueness of the Korean native chicken breeds.

• Journal of Korea Multimedia Society
• /
• v.5 no.2
• /
• pp.158-166
• /
• 2002

In this paper, we proposed a contour shape description method which use the CFR(contour fluctuation ratio) feature. The CFR is the ratio of the line length to the curve length of a contour segment. The line length means the distance of two end points on a contour segment, and the curve length means the sum of distance of all adjacent two points on a contour segment. We should acquire rotation and scale invariant contour segments because each CFR is computed from contour segments. By using the interleaved contour segment of which length is proportion to the entire contour length and which is generated from all the points on contour, we could acquire rotation and scale invariant contour segments. The CFR can describes the local or global feature of contour shape according to the unit length of contour segment. Therefore we describe the shape of objects with the feature vector which represents the distribution of CFRs, and calculate the similarity by comparing the feature vector of corresponding unit length segments. We implemented the proposed method and experimented with rotated and scaled 165 fish images of fifteen types. The experimental result shows that the proposed method is not only invariant to rotation and scale but also superior to NCCH and TRP method in the clustering power.

• The KIPS Transactions:PartB
• /
• v.13B no.6 s.109
• /
• pp.591-600
• /
• 2006

This paper describes the development and implementation of a algorithm to decompose word images from image regions mixed text/graphics in document images using statistical analyses. To decompose word images from image regions, the character components need to be separated from graphic components. For this process, we propose a method to separate them with an analysis of box-plot using a statistics of structural components. An accuracy of this method is not sensitive to the changes of images because the criterion of separation is defined by the statistics of components. And then the character regions are determined by analyzing a local crowdedness of the separated character components. finally, we devide the character regions into text lines and word images using projection profile analysis, gap clustering, special symbol detection, etc. The proposed system could reduce the influence resulted from the changes of images because it uses the criterion based on the statistics of image regions. Also, we made an experiment with the proposed method in document image processing system for keyword spotting and showed the necessity of studying for the proposed method.

• Journal of Information Management
• /
• v.42 no.4
• /
• pp.75-94
• /
• 2011

The purpose of this study is to analyze the domain on the field of Electrical Engineering in Korea by the author bibliographic coupling analysis. The data set contains a total of 2,157 articles from two core journals with 23,411 citation data from 2005 to 2009 published in two prestigious journals. In order to achieve the purpose of this study, MDS analysis, clustering analysis and network analysis were used to examine core subject areas. In addition, the centrality analysis in the weighted networks was used to explore the key authors in this field such as the top global centrality authors and the top local centrality authors. The findings of this study can be utilized to guide the current research trend and author network for collection development and information services in the field of Electrical Engineering.

• The Bulletin of The Korean Astronomical Society
• /
• v.36 no.2
• /
• pp.129.1-129.1
• /
• 2011

We have applied an advanced multi-aperture indexing photometry and sophisticated de-trending method to existing Taiwanese-American Occultation Survey (TAOS) data sets. TAOS, a wide-field ($3^{\circ}{\times}3^{\circ}$) and rapid photometry (5Hz) survey, is designed to detect small objects in the Kuiper Belt. Since TAOS has fast and multiple exposures per zipper mode image, point spread function (PSF) varies in a given image. Selecting appropriate aperture among various size apertures allows us to reflect these variations in each light curve. The survey data turned out to contain various trends such as telescope vibration, CCD noise, and unstable local weather. We select multiple sets of stars using a hierarchical clustering algorithm in such a way that the light curves in each cluster show strong correlations between them. We then determine a primary trend (PT) per cluster using a weighted sum of the normalized light curves, and we use the constructed PTs to remove trends in individual light curves. After removing the trend, we can get each synthetic light curve of star that has much higher signal-to-noise ratio. We compare the efficiency of the synthetic light curves with the efficiency of light curves made by previous existing photometry pipelines. Our photometric method is able to restore subtle brightness variation that tends to be missed in conventional aperture photometric methods, and can be applied to other wide-field surveys suffering from PSF variations and trends. We are developing an analysis package for the next generation TAOS survey (TAOS II) based on the current experiments.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.33 no.4B
• /
• pp.174-183
• /
• 2008

In this paper we design and implement a sensor network management framework(SNMF) for ubiquitous sensor networks(USNs). The SNMF employs the policy-based management approach for the autonomous and energy-efficient management of USNs. Moreover, a new light-weight policy distribution protocol called TinyCOPS-PR is designed and USN PIB for low-level policy is also defined. This allows the high-level policies defined by an administrator to translate into the specific low-level policies. The low-level policies are executed on sensor nodes so it can fulfill the proper management actions. The sensor nodes that receive some policies from an administrator perform local management actions according to those policies. SNMF can therefore realize small energy consumption and bring long network lifetime. It can also manage USNs automatically with a minimum of human interference.

• Journal of Korean Society for Geospatial Information Science
• /
• v.22 no.1
• /
• pp.63-70
• /
• 2014

This study is to analyze impact of geography and timing on the real transactions prices of apartment complexes in Seoul using data provided by the Ministry of Land, Infrastructure and Transport. The average real transactions and location data of apartment complex was combined into the GIS data. First, the pattern of apartment real transaction price change by period and by area was analyzed by kriging, the one of the spatial interpolation technique. Second, to analyze the pattern of apartment market price change by administrative district(administrative 'Dong' unit), the average of market price per unit area was calculated and converted to Moran I value, which was used to analyze the clustering level of the real transaction price. Through the analysis, spatial-temporal distribution pattern can be found and the type of change can be forecasted. Therefore, this study can be referred as of the base data research for the housing or local policies. Also, the regional unbalanced apartment price can be presented by analyzing the vertical pattern of the change in the time series and the horizontal pattern of the change based on GIS.