• Journal of the Korean Institute of Intelligent Systems
• /
• v.22 no.6
• /
• pp.735-740
• /
• 2012

In this paper, we introduce design methodologies of polynomial radial basis function neural network classifier with the aid of Principal Component Analysis(PCA) and Linear Discriminant Analysis(LDA). By minimizing the information loss of given data, Feature data is obtained through preprocessing of PCA and LDA and then this data is used as input data of RBFNNs. The hidden layer of RBFNNs is built up by Fuzzy C-Mean(FCM) clustering algorithm instead of receptive fields and linear polynomial function is used as connection weights between hidden and output layer. In order to design optimized classifier, the structural and parametric values such as the number of eigenvectors of PCA and LDA, and fuzzification coefficient of FCM algorithm are optimized by Artificial Bee Colony(ABC) optimization algorithm. The proposed classifier is applied to some machine learning datasets and its result is compared with some other classifiers.

• Journal of The Korean Astronomical Society
• /
• v.35 no.3
• /
• pp.111-121
• /
• 2002

We have measured the correlation functions of the optically selected clusters of galaxies in the Abell and the APM catalogs, and of the X-ray clusters in the X-ray-Brightest Abell-type Clusters of galaxies (XBACs) catalog and the Brightest Clusters Sample (BCS). The same analysis method and the same method of characterizing the resulting correlation functions are applied to all observational samples. We have found that the amplitude of the correlation function of the APM clusters is much higher than what has been previously claimed, in particular for richer subsamples. The correlation length of the APM clusters with the richness R $\ge$ 70 (as defined by the APM team) is found to be $r_0 = 25.4_{-3.0}^{+3.1}\;h^{-1}$ Mpc. The amplitude of correlation function is about 2.4 times higher than that of Croft et al. (1997). The correlation lengths of the Abell clusters with the richness class RC $\ge$ 0 and 1 are measured to be $r_0 = 17.4_{-1.1}^{+1.2}$ and $21.0_{-2.8}^{+2.8}\;h^{-1}$ Mpc, respectively, which is consistent with our results for the APM sample at the similar level of richness. The richness dependence of cluster correlations is found to be $r_0= 0.40d_c + 3.2$ where $d_c$ is the mean intercluster separation. This is identical in slope with the Bahcall & West (1992)'s estimate, but is inconsistent with the weak dependence of Croft et al. (1997). The X-ray bright Abell clusters in the XBACs catalog and the X-ray selected clusters in the BCS catalog show strong clustering. The correlation length of the XBACs clusters with $L_x {\ge}0.65{\times} 10^{44}\;h^{-2}erg\;s^{-1}$ is $30.3_{-6.5}^{+8.2}\;h^{-1}$ Mpc, and that of the BCS clusters with $L_x {\ge}0.70{\times} 10^{44}\;h^{-2}erg\;s^{-1}$ is $30.2_{-8.9}^{+9.8}\;h^{-1}$ Mpc. The clustering strength of the X-ray clusters is much weaker than what is expected from the optical clusters.

• Journal of the Korea Society of Computer and Information
• /
• v.22 no.12
• /
• pp.17-25
• /
• 2017

In this paper, we have implemented a low-cost mobile robot supporting the person tracking by detection using RGB-D cameras and ROS(Robot Operating System) framework. The mobile robot was developed based on the Kobuki mobile base equipped with 2's Kinect devices and a high performance controller. One kinect device was used to detect and track the single person among people in the constrained working area by combining point cloud data filtering & clustering, HOG classifier and Kalman Filter-based estimation successively, and the other to perform the SLAM-based navigation supported in ROS framework. In performance evaluation, the person tracking by detection was proved to be robustly executed in real-time, and the navigation function showed the accuracy with the mean distance error being lower than 50mm. The mobile robot implemented has a significance in using the open-source based, general-purpose and low-cost approach.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2009.04a
• /
• pp.1025-1028
• /
• 2009

고속도로의 다양한 주행특성으로는 과속하는 차량, 휴게소나 기타목적의 이용차량, 운전자의 습관이나 피로도등이 있는데 이에 따라 고속도로 주행시간에 차이가 나타난다. 하지만 현재에는 이러한 특성을 고려하지 않고 통행시간 분류가 되고 있어 정확성과 신뢰성을 보장하지 못하고 있는 실정이다. 이에 본 연구에서는 데이터 분포에 따른 해석을 통하여 TCS데이터의 특성을 고려 할 수 있는 Fuzzy c-means 알고리즘과 단순히 임의의 초기값으로 분류하는 K-means와의 비교를 통해서 주행특성을 고려한 클러스터링 기법이 경우에 따라서 더 효과적이고 신뢰성 있는 분류방법이 될 수 있음을 증명하였다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.07a
• /
• pp.187-188
• /
• 2021

본 논문에서는 실시간으로 web-cam을 이용해, 후숙과일의 불량 여부를 판단, 분류하고 불량이 없는 후숙과일의 이미지 분석을 통하여 숙성도 예측하는 시스템을 소개한다. 실시간 다중 객체인식에 탁월한 yolo모델을 활용해, 과일의 불량여부 판단 후 분류하고, 이미지를 획득한 뒤, k-mean clustering 알고리즘을 이용해, 이미지를 segmentation 한다. segmentation된 이미지에 grabcut 알고리즘의 foreground-extraction을 사용해 배경 제거를 한 뒤, cluster의 중심색상값 색상값의 면적%, 전체 면적을 이용해 현재 숙성도를 계산하고 이를 이용해 과일의 후숙 시간 데이터와 비교, 숙성이 완료될 시간을 예측한다. 기존 수작업으로 이루어지고 있는 과일의 분류작업의 인력 감소 및 정확성을 높일 수 있는 알고리즘을 제안한다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.12 no.4
• /
• pp.772-780
• /
• 2008

K-means is one of the simplest unsupervised learning algorithms that solve the clustering problem. However K-means suffers the basic shortcoming: the number of clusters k has to be known in advance. In this paper, we propose extensions of X-means, which can estimate the number of clusters using Bayesian information criterion(BIC). We introduce two different versions of algorithm: modified X-means(MX-means) and generalized X-means(GX-means), which employ one full covariance matrix for one cluster and so can estimate the number of clusters efficiently without severe over-fitting which X-means suffers due to its spherical cluster assumption. The algorithms start with one cluster and try to split a cluster iteratively to maximize the BIC score. The former uses K-means algorithm to find a set of optimal clusters with current k, which makes it simple and fast. However it generates wrongly estimated centers when the clusters are overlapped. The latter uses EM algorithm to estimate the parameters and generates more stable clusters even when the clusters are overlapped. Experiments with synthetic data show that the purposed methods can provide a robust estimate of the number of clusters and cluster parameters compared to other existing top-down algorithms.

• The Journal of the Korea Contents Association
• /
• v.8 no.3
• /
• pp.252-263
• /
• 2008

This study was conducted to derive the optimal regionalization of the precipitation data which can be classified on the basis of climatologically and geographically homogeneous regions all over the regions except Cheju and Ulreung islands in Korea. A total of 65 rain gauges were used to regional analysis of precipitation. Annual maximum series for the consecutive durations of 1, 3, 6, 12, 24, 36, 48 and 72hr were used for various statistical analyses. K-means clustering mettled is used to identify homogeneous regions all over the regions. Five homogeneous regions for the precipitation were classified by the K-means clustering. Using the L-moment ratios and Kolmogorov-Smirnov test, the underlying regional probability distribution was identified to be the generalized extreme value (GEV) distribution among applied distributions. The regional and at-site parameters of the generalized extreme value distribution were estimated by the linear combination of the probability weighted moments, L-moment. The regional and at-site analysis for the design rainfall were tested by Monte Carlo simulation. Relative root-mean-square error (RRMSE), relative bias (RBIAS) and relative reduction (RR) in RRMSE were computed and compared with those resulting from at-site Monte Carlo simulation. All show that the regional analysis procedure can substantially reduce the RRMSE, RBIAS and RR in RRMSE in the prediction of design rainfall. Consequently, optimal design rainfalls following the regions and consecutive durations were derived by the regional frequency analysis.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.49 no.3
• /
• pp.82-89
• /
• 2012

This paper presents the intelligent tracking algorithm for maneuvering target using the positional error compensation of the maneuvering target. The difference between measured point and predict point is separated into acceleration and noise. Fuzzy c-mean clustering and predicted impact point are used to get the optimal acceleration value. The membership function is determined for acceleration and noise which are divided by fuzzy c-means clustering and the characteristics of the maneuvering target is figured out. Divided acceleration and noise are used in the tracking algorithm to compensate computational error. The filtering process in a series of the algorithm which estimates the target value recognize the nonlinear maneuvering target as linear one because the filter recognize only remained noise by extracting acceleration from the positional error. After filtering process, we get the estimates target by compensating extracted acceleration. The proposed system improves the adaptiveness and the robustness by adjusting the parameters in the membership function of fuzzy system. To maximize the effectiveness of the proposed system, we construct the multiple model structure. Procedures of the proposed algorithm can be implemented as an on-line system. Finally, some examples are provided to show the effectiveness of the proposed algorithm.

• Asian-Australasian Journal of Animal Sciences
• /
• v.25 no.2
• /
• pp.177-182
• /
• 2012

To investigate the genetic diversity of seven Chinese indigenous meat goat breeds (Tibet goat, Guizhou white goat, Shannan white goat, Yichang white goat, Matou goat, Changjiangsanjiaozhou white goat and Anhui white goat), explain their genetic relationship and assess their integrity and degree of admixture, 302 individuals from these breeds and 42 Boer goats introduced from Africa as reference samples were genotyped for 11 microsatellite markers. Results indicated that the genetic diversity of Chinese indigenous meat goats was rich. The mean heterozygosity and the mean allelic richness (AR) for the 8 goat breeds varied from 0.697 to 0.738 and 6.21 to 7.35, respectively. Structure analysis showed that Tibet goat breed was genetically distinct and was the first to separate and the other Chinese goats were then divided into two sub-clusters: Shannan white goat and Yichang white goat in one cluster; and Guizhou white goat, Matou goat, Changjiangsanjiaozhou white goat and Anhui white goat in the other cluster. This grouping pattern was further supported by clustering analysis and Principal component analysis. These results may provide a scientific basis for the characteristization, conservation and utilization of Chinese meat goats.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.26 no.4
• /
• pp.301-307
• /
• 2016

This paper proposes a lyric search method to consider the characteristics of the user query. According to the fact that queries for the lyric search are derived from highlight parts of the music, this paper uses the hierarchical agglomerative clustering to find the highlight and proposes a Gaussian weighting to consider the neighbor of the highlight as well as highlight. By setting the mean of a Gaussian weighting at the highlight, this weighting function has higher weights near the highlight and the lower weights far from the highlight. Then, this paper constructs a index of lyrics with the gaussian weighting. According to the experimental results on a data set obtained from 5 real users, the proposed method is proved to be effective.