• Journal of KIISE:Software and Applications
• /
• v.36 no.12
• /
• pp.1016-1023
• /
• 2009

A license plate recognition system consists of image processing in which characters and features are extracted, and pattern recognition in which extracted characters are classified. Feature extraction plays an important role in not only the level of data reduction but also performance of recognition. Thus, in this paper, we focused on the recognition of numeral characters especially on the feature extraction of numeral characters which has much effect in the result of plate recognition. We suggest a hybrid statistical feature model which assures the best dispersion of input data by reassignment of clustering property of input data. And we verify the effectiveness of suggested model using multi-layer perceptron and learning vector quantization neural networks. The results show that the proposed feature extraction method preserves the information of a license plate well and also is robust and effective for even noisy and external environment.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.15 no.1
• /
• pp.110-115
• /
• 2005

This paper proposes the method to detect contours of a face, eyes and a mouth in a color image for making an avatar automatically. First, we use the HSI color model to exclude the effect of various light condition, and we find skin regions in an input image by using the skin color is defined on HS-plane. And then, we use deformable templates and Genetic Algorithm(GA) to detect contours of a face, eyes and a mouth. Deformable templates consist of B-spline curves and control point vectors. Those can represent various shape of a face, eyes and a mouth. And GA is very useful search procedure based on the mechanics of natural selection and natural genetics. Second, an avatar is created automatically by using contours and Fuzzy C-means clustering(FCM). FCM is used to reduce the number of face color As a result, we could create avatars like handmade caricatures which can represent the user's identity, differing from ones generated by the existing methods.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.17 no.11
• /
• pp.2492-2498
• /
• 2013

In this paper, A lane tracking algoritm is proposed for lane departure warning system. To eliminate perspective effect, input image is converted into Bird's View by inverse perspective mapping. Next, suitable features are extracted for lane detection. Using clustering and lane similarity function with noise suppression features are extracted. Finally, lane model is calculated using RANSAC and lane model is tracked using Kalman Filter. Experimental results show that the proposed algorithm can be processed within 20ms and its detection rate approximately 90% on the highway in a variety of environments.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.34 no.12B
• /
• pp.1349-1358
• /
• 2009

Because of the limitation of supporting power, the current WSN(Wireless Sensor Network) Technologies whose one of the core attributes is low power consumption are the best solution for shipping container networking in stack environment such as on vessel. So it is effective to use the Wireless Sensor Network Technology. In this case, many nodes join in the network through a sink node because there are difficulties to get big money and efforts to set up a lot of sink node. It needs clustering-based proactive protocol to manage many nodes. But it shows low reliability because they have effect on radio frequency in metal obstacle environments(interference, distortion, reflection, and etc) like the intelligent container. In this paper, we proposed an improved Modified LEACH Protocol for stableness radio frequency environment. In the proposed protocol, we tried to join the network and derived stable topology composition after the measuring of link quality. Finally, we verified that the proposed protocol is composing more stable topology than previously protocol in metal obstacle environment.

• Molecular & Cellular Toxicology
• /
• v.2 no.2
• /
• pp.120-125
• /
• 2006

Phenytoin is an anti-epileptic. It works by slowing down impulses in the brain that cause seizures. The recent microarray technology enables us to understand possible mechanisms of genes related to compounds which have toxicity in biological system. We have studied that the effect of a compound related to hepatotoxin in vitro system using a rat whole genome microarray. In this study, we have used a rat liver epithelial cell line WB-F344 and phenytoin as a hepatotoxin. WB-F344 was treated with phenytoin for 1 to 24 hours. Total RNA was isolated at times 1, 6 and 24h following treatment of phenytoin, and hybridized to the microarray containing about 22,000 rat genes. After analysis with clustering methods, we have identified a total of 1,455 differentially expressed genes during the time course. Interestingly, about 1,049 genes exhibited differential expression pattern in response to phenytoin in early time. Therefore, the identification of genes associated with phenytoin in early response may give important insights into various toxicogenomic studies in vitro system.

• Journal of Internet Computing and Services
• /
• v.15 no.1
• /
• pp.125-134
• /
• 2014

As the social media which was simple communication media is activated on account of twitter and facebook, it's usability and importance are growing recently. Although many companies are making full use of its the capacity of information diffusion for marketing, the adverse effects of this capacity are growing. Because social network is formed and communicates based on friendships and relationships, the spreading speed of the spam and mal-ware is very swift. In this paper, we draw parameters affecting malicious data diffusion in social network environment, and compare and analyze the diffusion capacity of each parameters by propagation experiment with XSS Worm and Koobface Worm. In addition, we discuss the structural characteristics of social network environment and then proposed malicious data propagation model based on parameters affecting information diffusion. n this paper, we made up BA and HK models based on SI model, dynamic model, to conduct the experiments, and as a result of the experiments it was proved that parameters which effect on propagation of XSS Worm and Koobface Worm are clustering coefficient and closeness centrality.

• Korean Journal of Social Welfare
• /
• v.59 no.2
• /
• pp.143-169
• /
• 2007

The major purpose of this study was to offer a comprehensive analysis of the changing trends and causes of poverty among urban wage earners' households from 1995 to 2005. In order to do that, this study used the micro data of "Income and Expenditure Survey of Urban Households" by the National Statistical Office(NSO) and GEE(Generalized estimating equation) regression model which is know as an appropriate method for the longitudinal and clustering data. The results show that (1) the numbers of poverty rate and poverty gap in recent years are even getting seriously worse than those in the IMF crisis. (2) Main characteristics of poor are female headed, old aged, low educated households, and having atypical working position. (3) Major determinants of poverty are also related to the variables as mentioned the above. (4) However, poverty reduction effect of public transfer increased preferably in recent years.

• Journal of the Korean Data and Information Science Society
• /
• v.28 no.6
• /
• pp.1257-1260
• /
• 2017

Single-person households recently have been rapidly increasing and one reason may be the increment in elderly single-person. Since the change of living patterns is relevant to the government policy direction, it is important to understand how single-person households are clustered and which factors have influence on them. In this study, we tried to detect spatial clusters of single-person households and low-income elderly single-person households after adjusting for deprivation index. A recently developed fused lasso for Poisson data was used for data analysis and we provided the details on how to use it in R. From these analysis results, we observed the effect of socioeconomic level on the clusters and explained the reason why spatial clusters are shown after adjusting for deprivation index.

• Asian-Australasian Journal of Animal Sciences
• /
• v.33 no.10
• /
• pp.1610-1616
• /
• 2020

Objective: This study was to evaluate the effect of husbandry systems and strains on cecum microbial diversity of Jingyang chickens under the same dietary conditions. Methods: A total of 320 laying hens (body weight, 1.70±0.15 kg; 47 weeks old) were randomly allocated to one of the four treatments: i) Silver-feathered hens in enrichment cages (SEC) with an individual cage (70×60×75 cm), ii) Silver-feathered hens in free range (SFR) with the stocking density of 1.5 chickens per ten square meters, iii) Gold-feathered hens in enrichment cages (GEC), iv) Gold-feathered hens in free range (GFR). The experiment lasted 8 weeks and the cecum fecal samples were collected for 16S rDNA high throughput sequencing at the end of experiment. Results: i) The core microbiota was composed of Bacteroidetes (49% to 60%), Firmicutes (21% to 32%) and Proteobacteria (2% to 4%) at the phylum level. ii) The core bacteria were Bacteroides (26% to 31%), Rikenellaceae (9% to 16%), Parabacteroides (2% to 5%) and Lachnoclostridium (2% to 6%) at the genus level. iii) The indexes of operational taxonomic unit, Shannon, Simpson and observed species were all higher in SFR group than in SEC group while in GEC group than in GFR group, with SFR group showing the greatest diversity of cecum microorganisms among the four groups. iv) The clustering result was consistent with the strain classification, with a similar composition of cecum bacteria in the two strains of laying hens. Conclusion: The core microbiota were not altered by husbandry systems or strains. The free-range system increased the diversity of cecal microbes only for silver feathered hens. However, the cecum microbial composition was similar in two strain treatments under the same dietary conditions.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.8 no.3
• /
• pp.119-128
• /
• 1988

The purpose of this research is to quantify the effects of water content(0.3~1.255%) and temperature ($4{\sim}40^{\circ}C$) on the equilibrium distribution of toxic organic pollutant in unsaturated soil. The priority pollutants, Dichloromethane and 1, 1, 1-Trichloroethane were selected as toxic organic pollutants and the Korean decomposed granite soil as the experimental soil media. Two models were developed on the basis of shapes of soil water distribution in unsaturated soil and compared; complete surface coating(model I) vs. spot clustering (model II). From the experiment, a large decrease in the values of effective partition coefficient ($K_{eff}$) was observed as the water content increased. As the temperature increased, the $K_{eff}$ values decreased, and this effect was magnified at lower water contents. The values of $K_{eff}$ were correlated better with the estimated values using model II. Thus it was experimentally proved that the soil water tends to enclose the soil grain partly at lower water contents.