• 대기
• /
• 제20권4호
• /
• pp.415-426
• /
• 2010

A Land cover map over East Asian region (Kongju national university Land Cover map: KLC) is classified by using support vector machine (SVM) and evaluated with ground truth data. The basic input data are the recent three years (2006-2008) of MODIS (MODerate Imaging Spectriradiometer) NDVI (normalized difference vegetation index) data. The spatial resolution and temporal frequency of MODIS NDVI are 1km and 16 days, respectively. To minimize the number of cloud contaminated pixels in the MODIS NDVI data, the maximum value composite is applied to the 16 days data. And correction of cloud contaminated pixels based on the spatiotemporal continuity assumption are applied to the monthly NDVI data. To reduce the dataset and improve the classification quality, 9 phenological data, such as, NDVI maximum, amplitude, average, and others, derived from the corrected monthly NDVI data. The 3 types of land cover maps (International Geosphere Biosphere Programme: IGBP, University of Maryland: UMd, and MODIS) were used to build up a "quasi" ground truth data set, which were composed of pixels where the three land cover maps classified as the same land cover type. The classification results show that the fractions of broadleaf trees and grasslands are greater, but those of the croplands and needleleaf trees are smaller compared to those of the IGBP or UMd. The validation results using in-situ observation database show that the percentages of pixels in agreement with the observations are 80%, 77%, 63%, 57% in MODIS, KLC, IGBP, UMd land cover data, respectively. The significant differences in land cover types among the MODIS, IGBP, UMd and KLC are mainly occurred at the southern China and Manchuria, where most of pixels are contaminated by cloud and snow during summer and winter, respectively. It shows that the quality of raw data is one of the most important factors in land cover classification.

• 시큐리티연구
• /
• 제51호
• /
• pp.39-58
• /
• 2017

이 연구의 목적은 국내에서 지역경찰 현장관리자의 리더십 연구를 활성화하기 위해 한국형 파괴적리더십 척도의 타당성을 검증하는 것이다. 이 연구를 위해 2017년 경남지방경찰청에서 근무하는 경사 이하 경찰관 전체를 모집단으로 하였다. 표집을 위해 비례할당표집을 사용하였고, 할당기준은 근무지, 근무부서, 계급, 성별 등을 설정하였다. 자료수집은 2017년 4월 1일부터 2017년 4월 30일까지 총 1개월에 걸쳐 500명에 응답자를 대상으로 시행하였고, 최종 433부를 분석에 활용하였다. 연구에서는 파괴적리더십의 신뢰도와 타당도는 신뢰도분석, 탐색적 요인분석, 확인적 요인분석 등을 통해 검증하였다. 분석결과, 한국형 지역경찰 현장관리자의 파괴적리더십 척도는 신뢰도의 경우 부하관련 문항은 .948, 조직관련 문항은 .974로 높게 나타났지만, 확인적 요인분석의 모델 적합도는 낮았다. 따라서 추가적인 탐색적 요인분석과 확인적 요인분석을 통해 최종적으로 부하관련 문항은 4문항이 삭제되어 총 6문항으로 재구성하였고, 조직관련 문항은 기존 10문항 모두 적절한 것으로 검증되어, 한국형 지역경찰 파괴적리더십 척도는 2요인 16개 문항으로 재구성하였고, 모델도 통계적으로 적합한 것을 확인하였다. 한국형 지역경찰 현장관리자의 파괴적리더십 척도는 향후 경찰관 대상으로 수행될 리더십 연구의 기초자료로 활용될 수 있을 것이다.

• 생물환경조절학회지
• /
• 제31권4호
• /
• pp.270-278
• /
• 2022

본 연구는 무대재배 복숭아 '미황'을 대상으로 성숙기간 중 RGB 영상을 취득한 후 다양한 품질 지표를 측정하고 이를 딥러닝 기술에 적용하여 복숭아 과실 숙도 분류의 가능성을 탐색하고자 실시하였다. 취득 영상 730개의 데이터를 training과 validation에 사용하였고, 170개는 최종테스트 이미지로 사용하였다. 본 연구에서는 딥러닝을 활용한 성숙도 자동 분류를 위하여 조사된 품질 지표 중 경도, Hue 값, a^*값을 최종 선발하여 이미지를 수동으로 미성숙(immature), 성숙(mature), 과숙(over mature)으로 분류하였다. 이미지 자동 분류는 CNN(Convolutional Neural Networks, 컨볼루션 신경망) 모델 중에서 이미지 분류 및 탐지에서 우수한 성능을 보이고 있는 VGG16, GoogLeNet의 InceptionV3 두종류의 모델을 사용하여 복숭아 품질 지표 값의 분류 이미지별 성능을 측정하였다. 딥러닝을 통한 성숙도 이미지 분석 결과, VGG16과 InceptionV3 모델에서 Hue_left 특성이 각각 87.1%, 83.6%의 성능(F1 기준)을 나타냈고, 그에 비해 Firmness 특성이 각각 72.2%, 76.9%를 나타냈고, Loss율이 각각 54.3%, 62.1%로 Firmness를 기준으로 한 성숙도 분류는 적용성이 낮음을 확인하였다. 추후에 더 많은 종류의 이미지와 다양한 품질 지표를 가지고 학습이 진행된다면 이전 연구보다 향상된 정확도와 세밀한 성숙도 판별이 가능할 것으로 판단되었다.

• 한국근적외분광분석학회:학술대회논문집
• /
• 한국근적외분광분석학회 2001년도 NIR-2001
• /
• pp.1154-1154
• /
• 2001

Near infra-red (NIR) spectroscopy has been used for the non-invasive assessment of intact fruit for eating quality attributes such as total soluble solids (TSS) content. However, little information is available in the literature with respect to the robustness of such calibration models validated against independent populations (however, see Peiris et al. 1998 and Guthrie et al. 1998). Many studies report ‘prediction’ statistics in which the calibration and prediction sets are subsets of the same population (e. g. a three year calibration validated against a set from the same population, Peiris et al. 1998; calibration and validation subsets of the same initial population, Guthrie and Walsh 1997 and McGlone and Kawano 1998). In this study, a calibration was developed across 84 melon fruit (R$^2$= 0.86$^{\circ}$Brix, SECV = 0.38$^{\circ}$Brix), which predicted well on fruit excluded from the calibration set but taken from the same population (n = 24, SEP = 0.38$^{\circ}$Brix with 0.1$^{\circ}$Brix bias), relative to an independent group (same variety and farm but different harvest date) (n = 24, SEP= 0.66$^{\circ}$ Brix with 0.1$^{\circ}$Brix bias). Prediction on a different variety, different growing district and time was worse (n = 24, SEP = 1.2$^{\circ}$Brix with 0.9$^{\circ}$Brix bias). Using an ‘in-line’ unit based on a silicon diode array spectrometer, as described in Walsh et al. (2000), we collected spectra from fruit populations covering different varieties, growing districts and time. The calibration procedure was optimized in terms of spectral window, derivative function and scatter correction. Performance of a calibration across new populations of fruit (different varieties, growing districts and harvest date) is reported. Various calibration sample selection techniques (primarily based on Mahalanobis distances), were trialled to structure the calibration population to improve robustness of prediction on independent sets. Optimization of calibration population structure (using the ISI protocols of neighbourhood and global distances) resulted in the elimination of over 50% of the initial data set. The use of the ISI Local Calibration routine was also investigated.

• 한국운동역학회지
• /
• 제30권1호
• /
• pp.111-119
• /
• 2020

Objective: The purpose of this study is to apply exercise learning effect to various subjects through training effect and information accumulation based on verification of the effect on dumbbell curl exercises applied with virtual reality. Method: To analyze the effect on the dumbbell curl exercise in the virtual environment, a total of 20 persons with 10 males and 10 females who does not have orthopedics diseases were selected. The dumbbell weight of the subjects was set to a weight of 70% strength of 1RM. At this time, the virtual environment situation was set to four types; presence/absence of virtual environment, preferred colors, and unfavorable colors to perform dumbbell curl exercise. The anaysis of muscle activity was conducted by adhering four surface electrodes (Biceps Brachii, Triceps Brachii, Brachioradialis Muscle, Extensor Carpi Radialis Longus Muscle) on the right upper limbs. Independent sample t-test using SPSS (24.0) program was carried out to analyze average values and standard deviations for each variable depending on the presence/absence of virtual environments and changes in color (preferred colors, unfavorable colors) and the level of significance was set to a=.05. Results: In the eccentric contraction, males showed high muscle activity in the Biceps Brachii under virtual reality. On the other hand, females had high muscle activity in the Biceps Brachii in the absence of virtual reality. Also, in case of a change of colors in the virtual environment, females had the high muscle activity in the unfavorable color in the eccentric contraction. Conclusion: During the dumbbell curl exercise, results of different exercises present depending on gender. When males put VR on and performs a basic dumbbell curl exercise, the effect of Biceps presents Brachii for them while exercising in unfavorable colors. However, since it is the basic research data of muscle exercise using virtual reality, it is necessary to verify whether or not it is effective for myopachynsis through long-term training rather than unity.

• Wind and Structures
• /
• 제26권2호
• /
• pp.75-87
• /
• 2018

A large number of low-rise buildings experienced serious roof covering failures under strong wind while few suffered structural damage. Clay and concrete tiles are two main kinds of roof covering. For the tile roof system, few researches were carried out based on Finite Element (FE) analysis due to the difficulty in the simulation of the interface between the tiles and the roof sheathing (the bonding materials, foam or mortar). In this paper, the FE analysis of a single clay or concrete tile with foam-set or mortar-set were built with the interface simulated by the equivalent nonlinear springs based on the mechanical uplift and displacement tests, and they were expanded into the whole roof. A detailed wind tunnel test was carried out at Tongji University to acquire the wind loads on these two kinds of roof tiles, and then the test data were fed into the FE analysis. For the purpose of validation and calibration, the results of FE analysis were compared with the full-scale performance ofthe tile roofs under simulated strong wind impact through one-of-a-kind Wall of Wind (WoW) apparatus at Florida International University. The results are consistent with the WoW test that the roof of concrete tiles with mortar-set provided the highest resistance, and the material defects or improper construction practices are the key factors to induce the roof tiles' failure. Meanwhile, the staggered setting of concrete tiles would help develop an interlocking mechanism between the tiles and increase their resistance.

• 한국축산시설환경학회지
• /
• 제20권3호
• /
• pp.117-124
• /
• 2014

The objectives were to assess the use of near-infrared reflectance spectroscopy (NIRS) as a tool for estimating nutrient compositions of corn kernel, and to apply an NIRS-based indium gallium arsenide array detector to the system for collecting spectra and analyzing calibration equations using equipments designed for field application. Partial Least Squares Regression (PLSR) was employed to develop calibration equations based on representative data sets. The kennard-stone algorithm was applied to induce a calibration set and a validation set. As a result, the method for structuring a calibration set significantly affected prediction accuracy. The prediction of chemical composition of corn kernel resulted in the following (kennard-stone algorithm: relative) moisture ($R^2=0.82$, RMSEP=0.183), crude protein ($R^2=0.80$, RMSEP=0.142), crude fat ($R^2=0.84$, RMSEP=0.098), crude fiber ($R^2=0.74$, RMSEP=0.098), and crude ash ($R^2=0.81$, RMSEP=0.048). Result of this experiment showed the potential of NIRS to predict the chemical composition of corn kernel.

• Earthquakes and Structures
• /
• 제23권5호
• /
• pp.403-417
• /
• 2022

Reinforced concrete (RC) structures with low-strength RC columns are rampant in several countries, especially those constructed during the early 1960s and 1970s. The weakness of these structures due to overloading or some natural disasters such as earthquakes and building age effects are some of the main reasons to collapse, particularly with the scarcity of data on the impact of aspect ratio and corner radius on the confinement effectiveness. Hence, it is crucial to investigate if these columns (with different aspect ratios) can be made safe by strengthening them with carbon fiber-reinforced polymers (CFRP) sheets. Therefore, experimental and numerical studies of CFRP-strengthened low-strength reinforced concrete short rectangular, square, and circular columns were studied. In this investigation, a total of 6 columns divided into three sets were evaluated. The first set had two circular cross-sectional columns, the second set had two square cross-section columns, and the third set has two rectangular cross-section columns. Furthermore, FEM validation has been conducted for some of the experimental results obtained from the literature. The experimental results revealed that the confinement equations for RC columns as per both CSA and ACI codes could give incorrect results for low-strength concrete. The control specimen (unstrengthened ones) displayed that both ACI and CSA equations overestimate the ultimate strength of low-strength RC columns by order of extent. For strengthened columns with CFRP, the code equations of CSA and ACI code overestimate the maximum strength by around 6 to 13% and 23 to 29%, respectively, depending on the cross-section of the column (i.e., square, rectangular, or circular). Results of finite element models (FEMs) showed that increasing the layer number of new commonly CFRP type (B) from one to 3 for circular columns can increase the column's ultimate loads by around eight times compared to unjacketed columns. However, in the case of strengthened square and rectangular columns with CFRP, the increase of the ultimate loads of columns can reach up to six times and two times, respectively.

• Korean Journal of Radiology
• /
• 제23권12호
• /
• pp.1281-1289
• /
• 2022

Objective: Radiomic modeling using multiple regions of interest in MRI of the brain to diagnose juvenile myoclonic epilepsy (JME) has not yet been investigated. This study aimed to develop and validate radiomics prediction models to distinguish patients with JME from healthy controls (HCs), and to evaluate the feasibility of a radiomics approach using MRI for diagnosing JME. Materials and Methods: A total of 97 JME patients (25.6 ± 8.5 years; female, 45.5%) and 32 HCs (28.9 ± 11.4 years; female, 50.0%) were randomly split (7:3 ratio) into a training (n = 90) and a test set (n = 39) group. Radiomic features were extracted from 22 regions of interest in the brain using the T1-weighted MRI based on clinical evidence. Predictive models were trained using seven modeling methods, including a light gradient boosting machine, support vector classifier, random forest, logistic regression, extreme gradient boosting, gradient boosting machine, and decision tree, with radiomics features in the training set. The performance of the models was validated and compared to the test set. The model with the highest area under the receiver operating curve (AUROC) was chosen, and important features in the model were identified. Results: The seven tested radiomics models, including light gradient boosting machine, support vector classifier, random forest, logistic regression, extreme gradient boosting, gradient boosting machine, and decision tree, showed AUROC values of 0.817, 0.807, 0.783, 0.779, 0.767, 0.762, and 0.672, respectively. The light gradient boosting machine with the highest AUROC, albeit without statistically significant differences from the other models in pairwise comparisons, had accuracy, precision, recall, and F1 scores of 0.795, 0.818, 0.931, and 0.871, respectively. Radiomic features, including the putamen and ventral diencephalon, were ranked as the most important for suggesting JME. Conclusion: Radiomic models using MRI were able to differentiate JME from HCs.

• Journal of the Korean Data and Information Science Society
• /
• 제20권6호
• /
• pp.1093-1101
• /
• 2009

분위수 회귀모형은 확률변수들 사이에 확률적인 관계구조를 포함한 함수 모형을 좀 더 완벽하게 추정하도록 제공한다. 본 논문에서는 함수 추정에 로버스트하다고 알려져 있는 서포트벡터기계 기법과 이중벌칙커널기계를 이용하여 분위수 회귀모형을 추정하고자 한다. 이중벌칙커널기계는 고차원의 입력변수에 대한 분위수 회귀가 요구될 때 분위수 회귀모형을 잘 추정한다고 알려져 있다. 또한 본 논문에서는 광범위한 형태의 분위수 회귀모형 추정을 위해서 정규분포보다 비대칭 라플라스 분포를 이용한다. 본 논문에서 제안한 모형은 분위수 회귀모형 추정을 위해서 서포트벡터기계 기법에 이중벌칙커널기계를 이용하여 각각의 평균과 분산을 동시에 추정한다. 평균과 분산함수 추정을 위해 사용된 커널함수의 모수들은 최적의 값을 찾기 위해 일반화근사 교차타당성을 이용한다.