• Korean Journal of Remote Sensing
• /
• v.36 no.6_2
• /
• pp.1591-1604
• /
• 2020

This study is a study on classifying land cover by applying high-resolution satellite images to deep learning algorithms and verifying the performance of algorithms for each spatial object. For this, the Fully Convolutional Network-based algorithm was selected, and a dataset was constructed using Kompasat-3 satellite images, land cover maps, and forest maps. By applying the constructed data set to the algorithm, each optimal hyperparameter was calculated. Final classification was performed after hyperparameter optimization, and the overall accuracy of DeeplabV3+ was calculated the highest at 81.7%. However, when looking at the accuracy of each category, SegNet showed the best performance in roads and buildings, and U-Net showed the highest accuracy in hardwood trees and discussion items. In the case of Deeplab V3+, it performed better than the other two models in fields, facility cultivation, and grassland. Through the results, the limitations of applying one algorithm for land cover classification were confirmed, and if an appropriate algorithm for each spatial object is applied in the future, it is expected that high quality land cover classification results can be produced.

• The Transactions of the Korea Information Processing Society
• /
• v.5 no.4
• /
• pp.1048-1056
• /
• 1998

In this paper, a fractal image coding based on discrete wavelet transform is proposed to improve PSNR at low bit rates and reduce computational complexity of encoding process. The proposed method takes the absolute value of discrete wavelet transform coefficients, and then constructs significant coefficients trees, which indicate the positions and signs of the significant coefficients. This method improves PSNR and reduces computational complexity of mapping contracted domain pool onto range block, by matching only the significant coefficients of range block to coefficients of contracted domain block. Also, this paper proposes a classification scheme which minimizes the number of contracted domain blocks compared with range block. This scheme significantly reduces the number of range and contracted domain block comparison.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2007.11a
• /
• pp.886-890
• /
• 2007

Machine fault prognosis techniques have been considered profoundly in the recent time due to their profit for reducing unexpected faults or unscheduled maintenance. With those techniques, the working conditions of components, the trending of fault propagation, and the time-to-failure are forecasted precisely before they reach the failure thresholds. In this work, we propose an approach of Least Square Regression Tree (LSRT), which is an extension of the Classification and Regression Tree (CART), in association with one-step-ahead prediction of time-series forecasting technique to predict the future conditions of machines. In this technique, the number of available observations is firstly determined by using Cao's method and LSRT is employed as prognosis system in the next step. The proposed approach is evaluated by real data of low methane compressor. Furthermore, the comparison between the predicted results of CART and LSRT are carried out to prove the accuracy. The predicted results show that LSRT offers a potential for machine condition prognosis.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.13 no.1
• /
• pp.85-94
• /
• 1995

Remote Sensing plays an Important role when we gather and extract many informations about development of the land, circumstances of urbans, land use, surveying resource and marine, geological survey, classification of trees, and condition of trees. For geometric collection to improve the accuracy of positioning with data in the processing of projection treatment by remote sensing. Authors have compared two methods by maps and GPS. Thereafter authors study exact transmation of coordinates in the projection of satellite. Authors have tried to gain improvability of difficulties and problems in the real topography, and Authors consider the coordinates system about global superposition by satellite image.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.21 no.5
• /
• pp.618-623
• /
• 2011

This paper proposes a novel method to discriminate meaningful tables from decorative one using a composite kernel for handling structural information of tables. In this paper, structural information of a table is extracted with two types of parse trees: context tree and table tree. A context tree contains structural information around a table, while a table tree presents structural information within a table. A composite kernel is proposed to efficiently handle these two types of trees based on a parse tree kernel. The support vector machines with the proposed kernel dised kuish meaningful tables from the decorative ones with rich structural information.

• Korean Journal of Plant Resources
• /
• v.25 no.1
• /
• pp.72-79
• /
• 2012

Vaccinium oldhami Miq. is a Korean native tree, which is deciduous and shrub tree with broad leaf. It grows 1~4m in height generally. Ecologically, this tree grows well in shady place even in barren soil. Also, the tree has resistance to cold and dry, which tend to form a little community. This research investigates quantitative morphological characteristics of leaf and fruit among the V. oldhami in South Korea and then considers its relationship on the basis of raw data among the 10 populations. This study will give us invaluable information about growing conditions, reasonable management and breeding by selection of V. oldhami in South Korea. The main results obtained from this study are summarized as follows; Leaf size of Mudeung population was larger than other populations. Naebyeon population was smaller in size of the leaf than other populations. Anmyeondo population was larger in fruit characteristics compared with other populations and Deogyu population was the smallest among populations. According to cluster analysis based on the leaf and fruit morphological characteristics, the natural V. oldhami populations were classified into four groups such as the first group of Kumo population, the second group of Mudeung population, the third group of Anmyundo, Daedun, Doolyun population and the fourth group of the other five populations.

• The Journal of Information Systems
• /
• v.30 no.4
• /
• pp.21-42
• /
• 2021

Purpose In order for companies to continue to grow, they should properly manage human resources, which are the core of corporate competitiveness. Employee turnover means the loss of talent in the workforce. When an employee voluntarily leaves his or her company, it will lose hiring and training cost and lead to the withdrawal of key personnel and new costs to train a new employee. From an employee's viewpoint, moving to another company is also risky because it can be time consuming and costly. Therefore, in order to reduce the social and economic costs caused by employee turnover, it is necessary to accurately predict employee turnover intention, identify the factors affecting employee turnover, and manage them appropriately in the company. Design/methodology/approach Prior studies have mainly used logistic regression and decision trees, which have explanatory power but poor predictive accuracy. In order to develop a more accurate prediction model, XGBoost is proposed as the classification technique. Then, to compensate for the lack of explainability, SHAP, one of the XAI techniques, is applied. As a result, the prediction accuracy of the proposed model is improved compared to the conventional methods such as LOGIT and Decision Trees. By applying SHAP to the proposed model, the factors affecting the overall employee turnover intention as well as a specific sample's turnover intention are identified. Findings Experimental results show that the prediction accuracy of XGBoost is superior to that of logistic regression and decision trees. Using SHAP, we find that jobseeking, annuity, eng_test, comm_temp, seti_dev, seti_money, equl_ablt, and sati_safe significantly affect overall employee turnover intention. In addition, it is confirmed that the factors affecting an individual's turnover intention are more diverse. Our research findings imply that companies should adopt a personalized approach for each employee in order to effectively prevent his or her turnover.

• Korean Journal of Plant Resources
• /
• v.35 no.2
• /
• pp.192-200
• /
• 2022

Nitrogen is the most essential macronutrient for the growth of fruit trees and is important factor determining the fruit yield. In order to produce high-quality fruits, it is necessary to supply the appropriate nitrogen fertilizer at the right time. For this, it is a prerequisite to accurately diagnose the nitrogen status of fruit trees. The fastest and most accurate way to determine the nitrogen deficiency of fruit trees is to measure the nitrogen concentration in leaves. However, it is not easy for citrus growers to measure nitrogen concentration through leaf analysis. In this study, several machine learning models were developed to classify the nitrogen deficiency based on the concentration measurement of mineral nutrients in the leaves of tangor Shiranuhi (Citrus unshiu × C. sinensis). The data analyzed from the leaves were increased to about 1,000 training dataset through the bootstrapping method and used to train the models. As a result of testing each model, gradient boosting model showed the best classification performance with an accuracy of 0.971.

• Journal of the Korea Convergence Society
• /
• v.13 no.2
• /
• pp.249-255
• /
• 2022

This study proposed an analysis framework for real-time prediction of CNC processing defects using machine learning-based models that are recently attracting attention as processing defect prediction methods, and applied it to CNC machines. Analysis shows that the XGBoost, CatBoost, and LightGBM models have the same best accuracy, precision, recall, F1 score, and AUC, of which the LightGBM model took the shortest execution time. This short run time has practical advantages such as reducing actual system deployment costs, reducing the probability of CNC machine damage due to rapid prediction of defects, and increasing overall CNC machine utilization, confirming that the LightGBM model is the most effective machine learning model for CNC machines with only basic sensors installed. In addition, it was confirmed that classification performance was maximized when an ensemble model consisting of LightGBM, ExtraTrees, k-Nearest Neighbors, and logistic regression models was applied in situations where there are no restrictions on execution time and computing power.

• Korean Journal of Environment and Ecology
• /
• v.34 no.3
• /
• pp.235-248
• /
• 2020

The purpose of this study was to quantitatively analyze and investigate changes in the structural characteristics of the warm-temperate evergreen broad-leaved forest community in Mt. Cheomchalsan on Jindo Island. The Mt. Cheomchalsan has high conservation value because the representative warm temperate species such as Quercus acuta and Castanopsis sieboldii are distributed there. The community classification with TWINSPAN and DCA identified 4 communities: C. sieboldii community (I), C. sieboldii-Q. Salicina community (II), Q. acuta-C.sieboldii community (III), and deciduous broad-leaved trees-evergreen broad-leaved trees community (IV). According to the results of the mean importance percentage (MIP) analysis, C. sieboldii, Q. salicina, and Q. acuta were dominant species in the canopy layer, Camellia japonica, Ligustrum japonicum, and Cinnamomum yabunikkei were dominant in the understory layer, and Trachelospermum asiaticum, C. japonica, and C. sieboldii were dominant in the shrub layer. The comparison of the results of the diameter of breast height (DBH) analysis with the past data showed that the ratio of large-sized trees in the C. sieboldii and Q. acuta, which dominated the canopy layer, increased. However, there was no difference in the distribution of C. japonica and L. japonicum in the understory layer. In the future, it is necessary to generate a precision inhabiting vegetation map around the Natural Reserve to understand the actual habitation of evergreen broad-leaved trees and rezone the protective districts of evergreen broad-leaved trees forest with the watershed concept to preserve the evergreen broad-leaved forests of Mt. Cheomchalsan in Jindo.