• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.7
• /
• pp.295-302
• /
• 2023

Software requirements written in natural language may have different meanings from the stakeholders' viewpoint. When designing an architecture based on quality attributes, it is necessary to accurately classify quality attribute requirements because the efficient design is possible only when appropriate architectural tactics for each quality attribute are selected. As a result, although many natural language processing models have been studied for the classification of requirements, which is a high-cost task, few topics improve classification performance with the imbalanced quality attribute datasets. In this study, we first show that the classification model can automatically classify the Korean requirement dataset through experiments. Based on these results, we explain that data augmentation through EDA(Easy Data Augmentation) techniques and undersampling strategies can improve the imbalance of quality attribute datasets, and show that they are effective in classifying requirements. The results improved by 5.24%p on F1-score, indicating that handling imbalanced data helps classify Korean requirements of classification models. Furthermore, detailed experiments of EDA illustrate operations that help improve classification performance.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.3 no.1
• /
• pp.5-15
• /
• 2001

For estimating paddy field area with Landsat TM images, two dates, May 31, 1991 (transplanting stage) and August 19, 1991 (heading stage) were selected by the data analysis of digital numbers considering rice cropping calendar. Four different estimating methods (1) rule-based classification method, (2) supervised classification(maximum likelihood), (3) unsupervised classification (ISODATA, No. of class:15), (4) unsupervised classification (ISODATA, No. of class:20) were examined. Paddy field area was estimated to 7291.19 ha by non-classification method. In comparison with topographical map (1:25,000), accuracy far paddy field area was 92%. A new image stacked by 10 layers, Landsat TM band 3,4,5, RVI, and wetness in May 31,1991 and August 19,1991 was made to estimate paddy field area by both supervised and unsupervised classification method. Paddy field was classified to 9100.98 ha by supervised classification. Error matrix showed 97.2% overall accuracy far training samples. Accuracy compared with topographical map was 95%. Unsupervised classifications by ISODATA using principal axis. Paddy field area by two different classification number of criteria were 6663.60 ha and 5704.56 ha and accuracy compared with topographical map was 87% and 82%. Irrespective of the estimating methods, paddy fields were discriminated very well by using two-date Landsat TM images in May 31,1991 (transplanting stage) and August 19,1991 (heading stage). Among estimation methods, rule-based classification method was the easiest to analyze and fast to process.

• Journal of the Korean earth science society
• /
• v.25 no.8
• /
• pp.764-773
• /
• 2004

The soil in wildfire area Sacheon-myeon, Gangneung, Gangweon Province, Korea, were investigated to clarify pattern of the soils. The soils were classified into 5 types on the basis of vegetation, types of organic matter. thickness of soil horizons, and completeness of soil profile. Each type showed different erosion pattern and Landsat ETM image. Coverage of plant leaves, litter, root, ash and other organic matter was an important component that affected soil color and reflectance of Landsat image (digital number). Although the NDVI (Normalized Distribution Vegetation Index) method in the wildfire area did not show much difference in soil types, the applied supervised classification method showed characteristic pattern of Landsat ETM image of soil types. This study showed that the applied supervised Landsat TM image classification in wildfire area is an effective way to estimate the distribution of erosion pattern of soil in wildfire area.

• Journal of Korean Society of Forest Science
• /
• v.104 no.4
• /
• pp.519-526
• /
• 2015

This study was investigated to analyze stand structure in Daegu Dodong T.orientalis Forest for conservation Thuja orientalis forest. Results of cluster analysis, it was classified to Quercus variabilis group(A), Quercus variabilis-Quercus mongolica group(B), Pinus densiflora group(C), Thuja orientalis group(D). Charaters of location environments for D group were analyzed that altitude 99.3 m, slope $59^{\circ}$, rock exposure 68.3%, BHA $21.8m^2/ha$ and North West aspects. The MRPP-test, It classified groups, appropriately. Importance value of D group was T. orientalis 85.42, Q. variabilis 1.28, P.densiflora 1.30, Fraxinus rhynchophylla 3.56 etc. DBH classes of D group were expressed inverted-J-shaped curve. H' was resulted in 0.600~0.834, H'max 1.317~1.466, J' 0.456~0.594, D' 0.405~0.544. Indecator species Analysis were conducted that woody plants were 4 taxa, Herbal plants 9 taxa.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.18 no.3
• /
• pp.113-127
• /
• 2015

Recently, there has been a growing interest in UAS(Unmanned Aerial System), and it is required to develop techniques to effectively detect water body from the recorded images in order to implement flood monitoring using UAS. This study used a UAS with RGB and NIR+RG bands to achieve images, and applied supervised classification method to evaluate the accuracy of water body detection. Firstly, the result for accuracy in water body image classification by RGB images showed high Kappa coefficients of 0.791 and 0.783 for the artificial neural network and minimum distance method respectively, and the maximum likelihood method showed the lowest, 0.561. Moreover, in the evaluation of accuracy in water body image classification by NIR+RG images, the magalanobis and minimum distance method showed high values of 0.869 and 0.830 respectively, and in the artificial neural network method, it was very low as 0.779. Especially, RGB band revealed errors to classify trees or grasslands of Songsan amusement park as water body, but NIR+RG presented noticeable improvement in this matter. Therefore, it was concluded that images with NIR+RG band, compared those with RGB band, are more effective for detection of water body when the mahalanobis and minimum distance method were applied.

• The KIPS Transactions:PartB
• /
• v.16B no.2
• /
• pp.131-140
• /
• 2009

This paper presents a new algorithm to the segmentation of the FISH images. First, for segmentation of the cell nuclei from background, a threshold is estimated by using the gaussian mixture model and maximizing the likelihood function of gray value of cell images. After nuclei segmentation, overlapped nuclei and isolated nuclei need to be classified for exact nuclei analysis. For nuclei classification, this paper extracted the morphological features of the nuclei such as compactness, smoothness and moments from training data. Three probability density functions are generated from these features and they are applied to the proposed Bayesian networks as evidences. After nuclei classification, segmenting of overlapped nuclei into isolated nuclei is necessary. This paper first performs intensity gradient transform and watershed algorithm to segment overlapped nuclei. Then proposed stepwise merging strategy is applied to merge several fragments in major nucleus. The experimental results using FISH images show that our system can indeed improve segmentation performance compared to previous researches, since we performed nuclei classification before separating overlapped nuclei.

• Proceedings of the Korean Information Science Society Conference
• /
• 2007.10b
• /
• pp.285-290
• /
• 2007

본 논문에서 구현하고자 하는 유비쿼터스 컴퓨팅 응용에 필요한 위치 인식 시스템의 주 요소는 블루투스 프로토콜 스택(BlueZ)에서 제공하는 RSSI(Received Signal Strength Indicator) 값을 측정하는 블루투스 AP, 측정된 RSSI 값을 위치 인식 서버에 전달하기 위한 무선 AP 공유기 그리고, 받은 데이터로 위치 값을 측정하는 위치 인식 서버 및 Context Broker(고 수준의 상황 정보를 추론하는 서버 역할)로 이루어져있다. 전체적인 동작 시스템은 위치 값을 측정하고자 하는 이동 매제(마스터)를 중심으로 최대 여덟 개까지 네트워크가 가능한 블루투스 AP(슬레이브)장치로 구성된 피코넷(Piconet) 영역에서 삼각측량 필요에 적절한 세 개의 블루투스 AP를 RSSI값을 이용하여 분류 한 후 이동 매체의 위치를 측정한다. 그 결과로 나온 데이터는 피코넷 영역에서 가장 가까운 무선 AP 공유기를 거쳐서 위치 값을 측정하는 위치 인식 서버에 전달한 후, 그 결과 값으로 Context Broker에서 상황 정보를 추론해서 Community Manager에서 유비쿼터스 컴퓨팅 응용에 맞게 서비스를 구현한다. 또한, 위와 같은 시스템 내부 구조 된 데이터처리는 리눅스 운영체제 내에서 디바이스 드라이버와 사용자 프로그램으로 구현된다.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2018.05a
• /
• pp.15-15
• /
• 2018

강우에 의해 발생되는 토양침식의 정도를 나타내는 강우침식인자의 산정공식은 미국에서 경험적인 방법으로 유도된 식이지만, 전 세계적으로 널리 활용되고 있다. 강우침식인자는 토양침식을 유발하는 호우사상의 지속기간 중에 발생한 총 강우에너지와 30분 최대 강우강도 값을 곱하여 호우사상별로 산정하게 되며, 이 값의 연간 총합이 연강우침식인자가 된다. 최근 강우침식인자에 대한 관심이 국내외적으로 고조되면서 많은 연구 산물이 학계에 보고되고 있다. 본 연구의 목적은 동일 기간, 동일 지점일지라도 연구자에 따라 강우침식인자 값이 달라지는 원인과 그 불확실성을 규명하기 위한 것이다. 이를 위하여 본 연구는 강우침식인자와 관련된 국내외 문헌연구를 토대로 연구방법에 따라 결과값이 달라지는 현상을 분석하고 이에 대한 대안을 제시하고자 한다. 연구결과, 강우침식인자 산정의 불확실성의 가장 큰 인자는 연구자가 사용하는 데이터로서, 5분 단위 이하의 강우자료를 사용하는 것과, 그 이상의 자료를 사용하는 것으로 구분할 수 있었다. 두 번째 중요한 인자는 유효 호우사상의 분류기준을 어떻게 적용하느냐에 있었다. 세 번째는 강우 에너지를 계산할 때 어떤 강우운동에너지식을 적용하는지에 따라 결과값이 달라지는 것을 알 수 있었다. 네 번째는 연구자가 어떤 프로그램을 이용하여 산정했느냐에 따라 차이가 발생할 수 있음을 알 수 있었다. 다섯 번째 지역단위 강우침식인자 산정시 어떤 공간분포 기법을 적용하느냐에 따라 결과값의 차이가 발생함을 알 수 있었다. 이를 바탕으로 본 연구에서는 국내에서 강우침식인자 산정시 연구자들이 적용할 수 있는 표준 계산 절차에 대해서 제안하였다.

• Journal of Intelligence and Information Systems
• /
• v.7 no.1
• /
• pp.17-25
• /
• 2001

Tree model is the most popular classification algorithm in data mining due to easy interpretation of the result. In CART(Breiman et al., 1984) and C4.5(Quinlan, 1993) which are representative of tree algorithms, the split fur classification proceeds to attain the homogeneous terminal nodes with respect to the composition of levels in target variable. But, fur instance, in the chum prediction modeling fur CRM(Customer Relationship management), the rate of churn is generally very low although we are interested in mining the churners. Thus it is difficult to get accurate prediction modes using tree model based on the traditional split rule, such as mini or deviance. Buja and Lee(1999) introduced a new split rule, one-sided purity for classifying minor interesting group. In this paper, we compared one-sided purity with traditional split rule, deviance analyzing churning vs. non-churning data of ISP company. Also reviewing the result of tree model based on one-sided purity with some simulated data, we discussed problems and researchable topics.

• Korean Journal of Fisheries and Aquatic Sciences
• /
• v.16 no.4
• /
• pp.368-378
• /
• 1983

The community structure of intertidal benthic marine algae were studied seasonally at Odongdo, southern coast of Korea, from June 1982 to May 1983. Algal coverage in $50{\times}50\;cm$ quadrat were recorded for each species by line transect method. The vertical zonation investigated by line transects is recognized into three groups : Upper, middle, and lower zones. The representative species are Gelidium divaricatum, Enteromorpha linza, Porphyra yezoensis, Scytosiphon lomentaria, Blidingia nana, Ectocarpus confervoides in the upper, Ulva pertusa, Chondria crassicaulis in the middle, and Sargassum sagamianum, S. thunbergii, Undaria pinnatifida, Gelidium amansii and various other red algae in the lower zone. The number of algal species and coverage were generally highest in April and lowest in August. Species which appear dominant at least once a year were all of the spring type and the others were autumn type. According to the cluster analysis by similarity index community coefficient(SICC) among 5 transects, the algal communities are divided into two groups, i. e. open-sea group and inland-sea group.