• The KIPS Transactions:PartB
• /
• v.8B no.5
• /
• pp.515-522
• /
• 2001

Feature-based similarity retrieval become an important research issue in image database systems. The features of image data are useful to discrimination of images. In this paper, we propose the highspeed k-Nearest Neighbor search algorithm based on Self-Organizing Maps. Self-Organizing Map(SOM) provides a mapping from high dimensional feature vectors onto a two-dimensional space. A topological feature map preserves the mutual relations (similarity) in feature spaces of input data, and clusters mutually similar feature vectors in a neighboring nodes. Each node of the topological feature map holds a node vector and similar images that is closest to each node vector. We implemented about k-NN search for similar image classification as to (1) access to topological feature map, and (2) apply to pruning strategy of high speed search. We experiment on the performance of our algorithm using color feature vectors extracted from images. Promising results have been obtained in experiments.

• Journal of Families and Better Life
• /
• v.28 no.5
• /
• pp.53-66
• /
• 2010

The purpose of this study is to investigate the influence of family-friendly life environment factors including local community's living environment satisfaction (safety, convenience, comfort, accessibility, exchange of neighbor satisfaction), family support facility satisfaction, family support program satisfaction and nurture and education environment satisfaction, and local community's living information accessibility on the effect of multiple roles of married men and women with children. Data were collected from 380 married men and women with children located Seoul, GyeongGi-Do, ChungCheongBuk-Do, and KyungSangNam-Do. The results show that, first of all, related to general trend of role satisfaction and role strain, the subjects have higher experience of role satisfaction than role strain. Secondly, the variables of social demography, such as monthly income, non-regular full-time working system, white collar occupation, number of children and level of education, and living environment variables, such as satisfaction of living environment stability and satisfaction of neighbor exchange in living environment were significantly related to role strain. Thirdly, social demography variables, such as average monthly earnings, gender (male), non-regular part-time working system, satisfaction of stability in living environment, and satisfaction of convenience in living environment were significantly related to role strain.

• Journal of the Korean Data and Information Science Society
• /
• v.20 no.5
• /
• pp.809-818
• /
• 2009

Collaborative filtering approach predicts the preference of active user about specific items transacted on the e-commerce by using others' preference information. To improve the prediction accuracy through collaborative filtering approach, it must be needed to gain enough preference information of users' for predicting preference. But, a bit much information of users' preference might wrongly affect on prediction accuracy, and also too small information of users' preference might make bad effect on the prediction accuracy. This research suggests the method, which decides suitable numbers of neighbor users for applying collaborative filtering algorithm, improved by existing k nearest neighbors selection methods. The result of this research provides useful methods for improving the prediction accuracy and also refines exploratory data analysis approach for deciding appropriate numbers of nearest neighbors.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.37 no.3B
• /
• pp.158-164
• /
• 2012

Heterogeneous Network and CSG cell are hot issues in the 3GPP LTE/LTE-Advanced system. In this paper, we analyze the system information measurement methods which are essential for handover to CSG cell. Since there have been no sufficient discussion about this problem, we present and analyze five possible solutions. Moreover, we propose a novel solution to reduce system information measurement delay. In the proposed Autonomous Measurement with Parallel Small Gap(AMPSG) method, the UE measures system information of neighbor cells in a parallel manner. As a result, the proposed method shows better delay performance. Therefore, the proposed AMPSG method can reduce handover delay since the UE have to measure the system information of neighbor cells before CSG handover decision.

• The Journal of Korean Association of Computer Education
• /
• v.20 no.2
• /
• pp.47-55
• /
• 2017

The purpose of this study is to investigate the predicting factors on the increase in computer entertainment behavior with the sample from KYPS data. The results of the Decision Tree model revealed that: (1) Neighbor supervision, self-belief, parent attachment, life satisfaction, and peer attachment were significant for the increase in computer entertainment behavior. (2) Neighbor supervision, class participation and leisure satisfaction were significant for male students' increase in computer entertainment behavior. (3) Optimistic disposition, teacher attachment, and peer attachment were significant for female students' increase in computer entertainment behavior. These results suggest that meaningful factors and their divers interactions should be considered in methods and programs for regulating and preventing the increase in computer entertainment behavior.

• Journal of KIISE:Databases
• /
• v.29 no.5
• /
• pp.358-366
• /
• 2002

Feature-based similarity retrieval become an important research issue in image database systems. The features of image data are useful to discrimination of images. In this paper, we propose the high speed k-Nearest Neighbor search algorithm based on Self-Organizing Maps. Self-Organizing Maps(SOM) provides a mapping from high dimensional feature vectors onto a two-dimensional space and generates a topological feature map. A topological feature map preserves the mutual relations (similarities) in feature spaces of input data, and clusters mutually similar feature vectors in a neighboring nodes. Therefore each node of the topological feature map holds a node vector and similar images that is closest to each node vector. We implemented a k-NN search for similar image classification as to (1) access to topological feature map, and (2) apply to pruning strategy of high speed search. We experiment on the performance of our algorithm using color feature vectors extracted from images. Promising results have been obtained in experiments.

• Asian-Australasian Journal of Animal Sciences
• /
• v.31 no.12
• /
• pp.1871-1880
• /
• 2018

Objective: Recently, there has been an increasing interest in conservation of native genetic resources of chicken on a worldwide basis. Most of the native chicken breeds are threatened by extinction or crossing with ecotypes. Methods: Six Saudi native chicken breeds including black naked neck, brown frizzled, black, black barred, brown and gray were used in the current study. The aim of the current study was to evaluate genetic diversity, relationship and population structure of Saudi native chicken breeds based on 20 microsatellite markers. Results: A total of 172 alleles were detected in Saudi native chicken breeds across all 20 microsatellite loci. The mean number of alleles per breed ranged from 4.35 in gray breed to 5.45 in normally feathered black with an average of 8.6 alleles. All breeds were characterized by a high degree of genetic diversity, with the lowest heterozygosity found in the brown breed (72%) and the greatest in the frizzled and black barred populations (78%). Higher estimate of expected heterozygosity (0.68) was found in both black breeds (normal and naked neck) compared to the other chicken populations. All studied breeds showed no inbreeding within breed (negative inbreeding coefficient [$F_{IS}$]). The phylogenetic relationships of chickens were examined using neighbor-joining trees constructed at the level of breeds and individual samples. The neighbor-joining tree constructed at breed level revealed three main clusters, with naked neck and gray breeds in one cluster, and brown and frizzled in the second cluster leaving black barred in a separate one. Conclusion: It could be concluded that the genetic information derived from the current study can be used as a guide for genetic improvement and conservation in further breeding programs. Our findings indicate that the Saudi native chicken populations have a rich genetic diversity and show a high polymorphism.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.5
• /
• pp.21-28
• /
• 2022

All health problems that occur in the circulatory system are refer to cardiovascular illness, such as heart and vascular diseases. Deaths from cardiovascular disorders are recorded one third of in total deaths in 2019 worldwide, and the number of deaths continues to rise. Therefore, if it is possible to predict diseases that has high mortality rate with patient's data and AI system, they would enable them to be detected and be treated in advance. In this study, models are produced to predict heart disease, which is one of the cardiovascular diseases, and compare the performance of models with Accuracy, Precision, and Recall, with description of the way of improving the performance of the Decision Tree(Decision Tree, KNN (K-Nearest Neighbor), SVM (Support Vector Machine), and DNN (Deep Neural Network) are used in this study.). Experiments were conducted using scikit-learn, Keras, and TensorFlow libraries using Python as Jupyter Notebook in macOS Big Sur. As a result of comparing the performance of the models, the Decision Tree demonstrates the highest performance, thus, it is recommended to use the Decision Tree in this study.

• Journal of Life Science
• /
• v.22 no.1
• /
• pp.62-73
• /
• 2012

This study was carried out to investigate the genetic relationship of Flammulina velutipes with other species. The ribosomal DNA cluster containing 4 rRNA genes from F. velutipes 4154 were sequenced. The length of the rDNA cluster sequence was estimated at 7,403 bp long and consisted of 1,806 bp of SSU rDNA, 245 bp of ITS 1 region, 159 bp of 5.8S rDNA, 308 bp of ITS 2 region, 3,402 bp of LSU rDNA, 1,400 bp of IGS 1 region, and 83 bp of 5S rDNA. The F. velutipes 4154 genes were contained in the rDNA cluster of F. velutipes in the order of SSU rDNA - ITS 1 - 5.8S rDNA - ITS 2 - LSU rDNA - IGS 1 - 5S rDNA. The phylogenetic relationships of 20 strains of Tricholomataceae and Physalacriaceae were analyzed by conducting distance analysis using the Neighbor-joining (NJ) method. The 20 strains used in this study were divided into three groups and the strains of the genus Flammulina were related very closely to strains of Physalacria bambusae.

• Journal of Convergence for Information Technology
• /
• v.10 no.7
• /
• pp.1-6
• /
• 2020

A new resource management algorithm is proposed for 5G networks which have a coordinated network architecture. By sharing the contol information among multiple neighbor cells and managing in centralized structure, the propsed algorithm fully utilizes the benefits of network coordination to increase fairness and throughput at the same time. This optimization of network performance is achieved while operating within a tolerable amount of signaling overhead and computational complexity. Simulation results confirm that the proposed scheme improve the network capacity up to 40% for cell edge users and provide network-wise fairness as much as 23% in terms of the well-knwon Jain's Fainess Index.