• Journal of The Korean Society of Agricultural Engineers
• /
• v.57 no.1
• /
• pp.59-67
• /
• 2015

Because reservoirs that supply irrigation water play an important role in water resource management, it is necessary to evaluate the vulnerability of this particular water supply resource. The purpose of this study is to provide water supply risk maps of agricultural reservoirs in South Korea using irrigation vulnerability model and cluster analysis. To quantify water supply risk, irrigation vulnerability indices are estimated to evaluate the performance of the water supply on the agricultural reservoir system using a probability theory and reliability analysis. First, the irrigation vulnerability probabilities of 1,346 reservoirs managed by Korea Rural Community Corporation (KRC) were analyzed using meteorological data on 54 meteorological stations over the past 30 years (1981-2010). Second, using the K-mean method of non-hierarchical cluster analysis and pre-simulation approach, cluster analysis was applied to classify into three groups for characterizing irrigation vulnerability in reservoirs. The morphology index, watershed area, irrigated area, and ratio between watershed and irrigated area are selected as the clustering analysis parameters. It is suggested that the water supply risk map be utilized as a basis for the establishment of risk management measures, and could provide effective information for a reasonable decision making on drought risk mitigation.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.24 no.6
• /
• pp.665-670
• /
• 2014

A SVM is a kind of binary classifier in order to find optimal hyperplane which separates training data into two groups. Due to its remarkable performance, the SVM is applied in various fields such as inductive inference, binary classification or making predictions. Also it is a representative black box model; there are plenty of actively discussed researches about analyzing trained SVM classifier. This paper conducts a study on a method that is automatically detecting the line-shaped echoes, sun strobe echo and radial interference echo, using the SVM algorithm because the line-shaped echoes appear relatively often and disturb weather forecasting process. Using a spatial clustering method and corrected reflectivity data in the weather radar, the training data is made up with mean reflectivity, size, appearance, centroid altitude and so forth. With actual occurrence cases of the line-shaped echoes, the trained SVM classifier is verified, and analyzed its characteristics using the decision tree method.

• Journal of the Korean Geophysical Society
• /
• v.2 no.3
• /
• pp.169-178
• /
• 1999

Low-field anisotropy of magnetic susceptibility (AMS) was measured with 247 samples from 17 sites of Pre-Cambrian anorthositic rocks in the Hadong-Sanchong area, southwestern part of the Ryongnam Block. Tectonic stress-direction is defined by the minimum susceptibility (k3) direction, and flow-direction by the maximum susceptibility (k1) direction. Five sites rendered self-consistent NW-SE site-mean tectonic stress-direction. Even though a general fold test for every site was not possible due to the homoclinal nature of the bedding attitudes, a site with various bedding attitudes shows far better clustering of the k3-direction before the bedding-tilt correction. The in-situ NW-SE tectonic stress-direction is consistent over the study area and compatible with petrographic foliation observed in metamorphic rocks in and arround the study area, suggesting a regional compressive force acted after the emplacement of the anorthositic rocks. On the other hand, flow-directions obtained from six sites varies from site to site. Strong-field IRM experiments show predominance of titanomagnetites over a small amount of hematite in some samples.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.329-331
• /
• 2021

Recently, as various cases of using deep learning in the health-care field are increasing, functions such as electrocardiogram examination and body composition analysis through wearable device can be provided to provide rational decision-making and a process tailored to the individual. In order to utilize deep learning, it it most important to secure refined data, and this data is being made through human intervention or unsupervised learning. In this paper, we propose a model that conducts unsupervised learning by clusters according to gender and age using human body data such as chest and waist circumferences, which are easy to measure, and classifies them with CNN. For data, the 7th human body data provided by Korean Agency for Technology and Standards was used. Through this, it it thought that it can be applied to various application cases such as personalized body shape management service and obesity analysis.

• Journal of Crop Science and Biotechnology
• /
• v.11 no.1
• /
• pp.51-56
• /
• 2008

Azuki bean has never been commercially grown in Thailand, due in part to a lack of suitable varieties. A core collection of 114 azuki bean accessions, originally from different parts of China(northern, central, southern) representing the germplasm of Chinese land races, were evaluated in the experimental field of the Institute of Vegetable Crops, Jiangsu Academy of Agricultural Sciences, China from June to October 2004. The same experiment was repeated at Kamphaeng Saen campus of Kasetsart University, Thailand from February to May 2005. Yield, yield components, and agronomic traits were recorded in all accessions in order to identify certain genotypes for further investigation. The statistical parameters that were used as indicators of phenotypic variation were mean, coefficient of variability(CV), correlation coefficient(r), range, mean difference, and phenotypic clustering of the accessions. The results indicated that the azuki bean varieties planted in Kamphaeng Saen were shorter, earlier in growing duration, and lower in plant height, seed yield per plant, 100-seed weight, and pods per plant as compared to when they were grown in China. This discrepancy was caused largely by the combined effect of temperature, rainfall, and day length. The traits that were rather stable in both locations were branches per plant and seeds per pod. Azuki bean varieties from northern China showed higher response to the changing environments compared with those from central and southern China. Some agronomic traits showed high correlation coefficient between the environments in Thailand and China. The CV of agronomic traits in both locations were ranked in descending order as follows: seed yield per plant, pods per plant, branches per plant, plant height, 100-seed weight, seeds per pod, and growing duration. The CV of seeds per pod and branches per plant were almost the same in both locations. Yield per plant in China correlated well(r=0.75) with pods per plant, but not with the other traits. Based on their response to both environments, the azuki bean accessions can be broadly divided into four groups, viz. northern 1, northern 2, central, and southern. This implied that there was more diversity, but probably less stability among the accessions originating from northern China.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.23 no.4
• /
• pp.354-359
• /
• 2013

In this paper, we suggested the method for implementation of unsupervised nonlinear classification using Binary Harmony Search (BHS) algorithm, which is known as a optimization algorithm. Various algorithms have been suggested for classification of feature vectors from the process of machine learning for pattern recognition or EEG signal analysis processing. Supervised learning based support vector machine or fuzzy c-mean (FCM) based on unsupervised learning have been used for classification in the field. However, conventional methods were hard to apply nonlinear dataset classification or required prior information for supervised learning. We solved this problems with proposed classification method using heuristic approach which took the minimal Euclidean distance between vectors, then we assumed them as same class and the others were another class. For the comparison, we used FCM, self-organizing map (SOM) based on artificial neural network (ANN). KEEL machine learning datset was used for simulation. We concluded that proposed method was superior than other algorithms.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.8
• /
• pp.2043-2050
• /
• 2014

As most the scanning systems developed until now provide radiation scan plane images of the inspected objects, there has been a limitation in judging exactly the shape of the objects inside a logistics container exactly with only 2-D radiation image information. As a radiation image is just the density information of the scanned object, the direct application of general stereo image processing techniques is inefficient. So we propose that a new volume-based 3-D reconstruction algorithm. Experimental results show the proposed new volume based reconstruction technique can provide more efficient visualization for X-ray inspection. For validation of the proposed shape reconstruction algorithm using volume, 15 samples were scanned and reconstructed to restore the shape using an X-ray stereo inspection system. Reconstruction results of the objects show a high degree of accuracy compared to the width (2.56%), height (6.15%) and depth (7.12%) of the measured value for a real object respectively. In addition, using a K-Mean clustering algorithm a detection efficiency of 97% is achieved. The results of the reconstructed shape information using the volume based shape reconstruction algorithm provide the depth information of the inspected object with stereo X-ray inspection. Depth information used as an identifier for an automated search is possible and additional studies will proceed to retrieve an X-ray inspection system that can greatly improve the efficiency of an inspection.

• Journal of Digital Contents Society
• /
• v.14 no.4
• /
• pp.419-428
• /
• 2013

Real-time accessibility and agility are required in u-commerce under ubiquitous computing environment. Most of the existing recommendation techniques adopt the method of evaluation based on personal profile, which has been identified with difficulties in accurately analyzing the customers' level of interest and tendencies, as well as the problems of cost, consequently leaving customers unsatisfied. Researches have been conducted to improve the accuracy of information such as the level of interest and tendencies of the customers. However, the problem lies not in the preconstructed database, but in generating new and diverse profiles that are used for the evaluation of the existing data. Also it is difficult to use the unique recommendation method with hierarchy of each customer who has various characteristics in the existing recommendation techniques. Accordingly, this dissertation used the implicit method without onerous question and answer to the users based on the data from purchasing, unlike the other evaluation techniques. We applied FRAT technique which can analyze the tendency of the various personalization and the exact customer.

• Journal of Navigation and Port Research
• /
• v.27 no.5
• /
• pp.563-568
• /
• 2003

Currently, the adoption of FTZ( Free Trade Zone) has been recognized as one of the most important strategies for becoming hub port in the world. For this reason, various policies for successful implementation and adoption of FTZ have been presented, and u special law related this FTZ was actually built in 1999. In the mean time, a port logistics industry is deeply related to the successful implementation of FTZ. However, although many research about FTZ have been conducted, there have been little previous studies about port logistics firms and FTZ. Thus, the aim of this study is to investigate a market structure of firms related to Port Logistics effectively and to analyze the perception of these firms about FTZ in Busan.

• Journal of Korea Multimedia Society
• /
• v.16 no.12
• /
• pp.1376-1384
• /
• 2013

In this paper, we propose an automaticdetection method of foreign bodies through template matching in industrial CT volume data. Our method is composed of three main steps. First,Indown-sampling data, the product region is separated from background after noise reduction and initial foreign-body candidates are extracted using mean and standard deviation of the product region. Then foreign-body candidates are extracted using K-means clustering. Second, the foreign body with different intensity of product region is detected using template matching. At this time, the template matching is performed by evaluating SSD orjoint entropy according to the size of detected foreign-body candidates. Third, to improve thedetection rate of foreign body in original volume data, final foreign bodiesare detected using percolation method. For the performance evaluation of our method, industrial CT volume data and simulation data are used. Then visual inspection and accuracy assessment are performed and processing time is measured. For accuracy assessment, density-based detection method is used as comparative method and Dice's coefficient is measured.