• Journal of Cadastre & Land InformatiX
• /
• v.50 no.1
• /
• pp.75-85
• /
• 2020

This study examines machine learning cross-validation to utilized create ROI for classification of land cover. The study area located in Sejong and one KOMPSAT-3A image was used in this analysis: procedure on October 28, 2019. We used four bands(Red, Green, Blue, Near infra-red) for learning cross validation process. In this study, we used K-fold method in cross validation and used SVM kernel type with cross validation result. In addition, we used 4 kernels of SVM(Linear, Polynomial, RBF, Sigmoid) for supervised classification land cover map using extracted ROI. During the cross validation process, 1,813 data extracted from 3,500 data, and the most of the building, road and grass class data were removed about 60% during cross validation process. Based on this, the supervised SVM linear technique showed the highest classification accuracy of 91.77% compared to other kernel methods. The grass' producer accuracy showed 79.43% and identified a large mis-classification in forests. Depending on the results of the study, extraction ROI using cross validation may be effective in forest, water and agriculture areas, but it is deemed necessary to improve the distinction of built-up, grass and bare-soil area.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.24 no.1
• /
• pp.112-125
• /
• 2021

Marine spatial planning(MSP) designates the marine as nine kinds of use zones for the systematic and rational management of marine spaces. One of them is the fishery protection zone, which is necessary for the sustainable production of fishery products, including the protection and fosterage of fishing activities. This study intends to quantitatively identify the fishing activity space, one of the elements necessary for the designation of fisheries protection zones, by mapping of fishery activities using V-Pass data and deriving the fishery activity concentrated zone. To this end, pre-processing of V-Pass data was performed, such as constructing a dataset that combines static and dynamic information, calculating the speed of fishing vessels, extracting fishing activity points, and removing data in non-fishing activity zone. Finally, using the selected V-Pass point data, a fishery activity map was made by kernel density estimation, and the concentrated space of fishery activity was analyzed. In addition, it was confirmed that there is a difference in the spatial distribution of fishing activities according to the type of fishing vessel and the season. The pre-processing technique of large volume V-Pass data and the mapping method of fishing activities performed through this study are expected to contribute to the study of spatial characteristics evaluation of fishing activities in the future.

• 한국균학회소식:학술대회논문집
• /
• 2009.10a
• /
• pp.3-13
• /
• 2009

90 wild Agaricus strains from China, including 44 Agaricus bisporus strains identified preliminarily by isozyme electrophoresis, were studied by the techniques of SRAP and ISSR. 18 special SRAP bands and 12 special ISSR bands were analyzed, the strains were clustered and a demdrogram was obtained. The results showed that the strains were divided into 2 groups, wild A. bisporus group and the other Agaricus group. It is similar to the result of isozyme electrophoresis. 41 wild A. bisporus strains from Sichuan and Tibet were divided into 4 groups based on their growing places, suggesting the regionally difference of the strains to be quite obvious. Some white wild A. bisporus strains from Xinjiang and Tibet had special patterns, resulting in lower coefficient values with other wild A. bisporus strains. The biological characteristics of three wild A. bisporus strains were analyzed, and the results showed: 1. The wild strains grew slowly on PDA medium with weak appressed mycelia, and grew normally in kernel or fermented cottonseed shell substrate. 2. They grew faster than control strain As2796 under lower temperature of $16^{\circ}C$, and higher temperature of $32^{\circ}C$, with optimum growing temperature of $20-24^{\circ}C$, which was $4^{\circ}C$ lower than that of control strain. 3. In the cultivation with manure compost via twice fermentation, the mycelia grew normally in compost and quite slowly in casing soil, and the fruitbodies occurred less and late with easily opening and low production. 4. The fruitbody was off-white with flat and scaled cap, long stipe and dark gill. The bisporus basidia occupied 70-80% and trisporus basidia 20-30% of the total basidia. 5. Heterokaryotic monospore isolates could fruit in cultivation, and the homokaryotic isolates could cross with those derived from overseas wild A.bisporus strains. 6. The electrophoresis phenotype of isozymes such as esterase etc. belonged to high production type (H type). 7. The RAPD patterns made much difference from those of high production, good quality or hybrid strains, which indicated that the wild strains produce a new kind of RAPD type.

• Korean Journal of Breeding Science
• /
• v.40 no.1
• /
• pp.63-67
• /
• 2008

A new peanut cultivar "Jopyeong" (Arachis hypogaea ssp. hypogaea L.) was developed at the Yeongnam Agricultural Research Institute, NICS, in Milyang in 2006. It was developed from the cross between the very short stem cultivar "CUP brittle" and the high-yielding cultivar "Daekwang". "Jopyeong" which is Virginia plant type has 23 branch number per plant with early maturing and ellipse-shaped large kernel. Each pod has two grains with brown testa and 100 seed weight was 87g in the regional yield trials (RYT). This variety also showed more resistant to late leaf spots compared with check one. Especially it has resistance to lodging owing to short stem and erect plant type. In the regional yield trials "Jopyeong" was out-yielded than check variety by 11% with 8.37 ton/ha for fresh pod and by 4% with 3.95 ton/ha for grain.

• IEIE Transactions on Smart Processing and Computing
• /
• v.6 no.1
• /
• pp.10-17
• /
• 2017

We propose classification algorithms for human and dog movement. The proposed algorithms use micro-Doppler signals obtained from humans and dogs moving in four different directions. A two-stage classifier based on a support vector machine (SVM) is proposed, which uses a radial-based function (RBF) kernel and $16^{th}$-order linear predictive code (LPC) coefficients as feature vectors. With the proposed algorithms, we obtain the best classification results when a first-level SVM classifies the type of movement, and then, a second-level SVM classifies the moving object. We obtain the correct classification probability 95.54% of the time, on average. Next, to deal with the difficult classification problem of human and dog running, we propose a two-layer convolutional neural network (CNN). The proposed CNN is composed of six ($6{\times}6$) convolution filters at the first and second layers, with ($5{\times}5$) max pooling for the first layer and ($2{\times}2$) max pooling for the second layer. The proposed CNN-based classifier adopts an auto regressive spectrogram as the feature image obtained from the $16^{th}$-order LPC vectors for a specific time duration. The proposed CNN exhibits 100% classification accuracy and outperforms the SVM-based classifier. These results show that the proposed classifiers can be used for human and dog classification systems and also for classification problems using data obtained from an ultra-wideband (UWB) sensor.

• The Transactions of the Korean Institute of Electrical Engineers A
• /
• v.49 no.10
• /
• pp.516-523
• /
• 2000

In this paper, intelligent methods using digital protective relay in power supervisory control system is developed in order to protect power systems by means of timely fault detection and diagnosis during operation for induction motor which has various load environments and capacities in power systems. The spectrum pattern of input currents was used to monitor to state of induction motors, and by clustering the spectrum pattern of input currents, the newly occurrence of spectrums pattern caused by faults were detected. For diagnosis of the fault detected, the fuzzy fault tree was derived, and the fuzzy relation equation representing the relation between an induction motor fault and each fault type, was solved. The solution of the fuzzy relation equation shows the possibility of each fault's occurring. The results obtained are summarized as follows: 1) The test result on the basis of KEMC1120 and IEC60255, show that the operation time error of the digital motor protective relay is improved within ${\pm}5%$. 2) Using clustering algorithm by unsupervisory learning, an on-line fault detection method, not affected by the characteristics of loads and rates, was implemented, and the degree of dependency by experts during fault detection was reduced. 3) With the fuzzy fault tree, fault diagnosis process became systematic and expandable to the whole system, and the diagnosis for sub-systems can be made as an object-oriented module.

• Journal of Institute of Control, Robotics and Systems
• /
• v.20 no.7
• /
• pp.760-766
• /
• 2014

This paper represents a portable robot for use in the welding process of the double hulls in shipbuilding yards. It has 5 degrees of freedom and 3kg of payload. Its body weight is 17.3 [kg] so that human workers can carry it by hand to the work place. Its body is mainly made of magnesium and aluminum alloys. Since the robot is placed about 25m apart from its controller, EtherCAT is adopted for reliable connection between the robot and controller through a single light cable. RTX real-time kernel and KPA EtherCAT master are used to control the robot on a Windows XP environment. The performance of the developed robot is satisfactory to the requirement in welding tasks of U-type cells in shipbuilding yards.

• The Journal of the Korea Contents Association
• /
• v.10 no.4
• /
• pp.84-90
• /
• 2010

DBMS is used for a range of applications from data warehousing through on-line transaction processing. As a result of this demand, DBMS has continued to grow in terms of its size. This growth invokes the most important issue of manually tuning the performance of DBMS. The DBMS tuning should be adaptive to the type of the workload put upon it. But, identifying workloads in mixed database applications might be quite difficult. Therefore, a method is necessary for identifying workloads in the mixed database environment. In this paper, we propose a SVM workload classifier to automatically identify a DBMS workload. Database workloads are collected in TPC-C and TPC-W benchmark while changing the resource parameters. Parameters for SVM workload classifier, C and kernel parameter, were chosen experimentally. The experiments revealed that the accuracy of the proposed SVM workload classifier is about 9% higher than that of Decision tree, Naive Bayes, Multilayer perceptron and K-NN classifier.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.30 no.2
• /
• pp.127-135
• /
• 2017

The computing environment has changed rapidly to enable large-scale finite element models to be analyzed at the PC or workstation level, such as multi-core CPU, optimal math kernel library implementing BLAS and LAPACK, and popularization of direct sparse solvers. In this paper, the design considerations on a parallel finite element code for shared memory based multi-core CPU system are proposed; (1) the use of optimized numerical libraries, (2) the use of latest direct sparse solvers, (3) parallelism using OpenMP for computing element stiffness matrices, and (4) assembly techniques using triplets, which is a type of sparse matrix storage. In addition, the parallelization effect is examined on the time-consuming works through a large scale finite element model.

• KIPS Transactions on Software and Data Engineering
• /
• v.9 no.5
• /
• pp.153-160
• /
• 2020

Energy Consumption Predictions for Industries has a prominent role to play in the energy management and control system as dynamic and seasonal changes are occurring in energy demand and supply. This paper introduces and explores the steel industry's predictive models of energy consumption. The data used includes lagging and leading reactive power lagging and leading current variable, emission of carbon dioxide (tCO2) and load type. Four statistical models are trained and tested in the test set: (a) Linear Regression (LR), (b) Radial Kernel Support Vector Machine (SVM RBF), (c) Gradient Boosting Machine (GBM), and (d) Random Forest (RF). Root Mean Squared Error (RMSE), Mean Absolute Error (MAE) and Mean Absolute Percentage Error (MAPE) are used for calculating regression model predictive performance. When using all the predictors, the best model RF can provide RMSE value 7.33 in the test set.