• Proceedings of the Korea Water Resources Association Conference
• /
• 2011.05a
• /
• pp.355-355
• /
• 2011

토지피복의 분류는 토지표면의 물리적인 지표면의 상태를 나타내는 자료로 환경, 행정, 수자원, 재해 등 다방면으로 이용되고 있다. 특히 수자원과 관련하여 식생의 증산과 토양의 증발을 통칭하는 증발산과 유출, 토양수분 등과 연관되어 있다. 광범위한 토지피복의 산정에는 경제성 및 주기성 등의 장점으로 인하여 인공위성 영상을 이용하는 기법이 적합하다. 위성영상분류법은 훈련지역의 선정 여부에 따라 감독분류와 무감독 분류로 나누어지며 각각의 알고리즘의 특성에 따라 더욱 세분화된다. 본 연구에서는 Landsat-TM (Thematic Mapper) 영상을 이용하여 감독 분류와 무감독 분류를 각각 적용하여 한강유역의 토지피복을 수역, 시가, 나지 습지, 초지, 산림, 농지의 7가지 부분으로 대분류로 산정하고 비교하였다. 두 경우의 정확도는 각각 91.6%, 90.9%의 비슷한 정확도를 나타내었으며, 세부적으로 우리나라의 대부분의 면적에 분포하는 산림, 농지, 시가, 수역의 정확도가 높게 나타났다. 또한 각 항목별로 정확도를 비교하였을 때 감독분류가 무감독분류에 비해 다소 정확한 것을 확인할 수 있었다. 추후 외부자료를 도입하면 비교적 낮은 정확도를 나타낸 초지, 습지, 나지의 정확도를 보완할 수 있을 것이다.

• 한국공간정보시스템학회:학술대회논문집
• /
• 2007.06a
• /
• pp.156-161
• /
• 2007

도시화에 따른 도시문제발생이라는 결과로 미루어 볼 때, 지속적인 도시 성장을 위한 도시 성장 관리는 필수적이며, 이것을 위해서 도시지역을 추출하는 것은 도시의 성장 추이를 파악할 수 있게 한다는 점에서 매우 의미 있는 일이다. 본 연구에서는 도시 성장 모니터링에 있어서 정규식생지수(NDVI)와 정규시가지화지수(NDBI)를 결합한 방법의 활용성을 규명하는데 목적을 두었다. 이를 위해 토지피복분류에 일반적으로 사용되는 감독 분류기법과 도시지역추출에 이용되는 NDVI와 NDBI를 결합한 방법(식생지수결합법)으로 1988년과 2000년 두 시기의 Landsat TM 영상을 이용하여 도시지역을 추출하고 일치도를 분석하였다. 분석 결과, 1988년 식생지수결합법과 감독분류기법으로 추출한 도시지역의 일치도는 98%, 식생지수결합법 비도시지역으로 추출된 지역이 감독분류기법으로는 도시지역으로 추출될 확률은 37.35%로 나타났고, 같은 경우 2000년은 각각 99.3%와 7.7%로 나타났다. 이를 통해 식생지수결합법을 사용한 도시지역 추출 결과와 감독분류기법을 사용한 도시지역 추출 결과의 일치도가 비교적 높게 나타남을 알 수 있었다. 또, 각 기법을 통한 도시지역 추출 결과와 실제 도시 검사점과의 일치도의 분석을 통해서도 도시지역 추출 결과의 일치도가 비교적 높게 나타났다. 따라서 분류를 통한 도시지역 추출 방법에 비해 식생지수결합법을 이용한 도시지역 추출이 절차상 수월한 점을 감안하면 도시지역 추출에 있어서 식생지수결합법의 효율성을 입증할 수 있었다.

• Journal of KIISE
• /
• v.42 no.6
• /
• pp.817-822
• /
• 2015

Relation extraction is an important information extraction technique that can be widely used in areas such as question-answering and knowledge population. Previous studies on relation extraction have been based on supervised machine learning models that need a large amount of training data manually annotated with relation categories. Recently, to reduce the manual annotation efforts for constructing training data, distant supervision methods have been proposed. However, these methods suffer from a drawback: it is difficult to use these methods for collecting negative training data that are necessary for resolving classification problems. To overcome this drawback, we propose a one-class classification model that can be trained without using negative data. The proposed model determines whether an input data item is included in an inner category by using a similarity measure based on lexical information and syntactic patterns in a vector space. In the experiments conducted in this study, the proposed model showed higher performance (an F1-score of 0.6509 and an accuracy of 0.6833) than a representative one-class classification model, one-class SVM(Support Vector Machine).

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.30 no.4
• /
• pp.397-404
• /
• 2012

Jeju where concentrates on agriculture and tourism, conversion of outdoor culture into cultivation under structure happens actively for the purpose of increasing profit so continuous examination on house cultivation area is very important for this region. This paper is to suggest the effective image classification method using high resolution satellite image to detect the greenhouse. We carried out classification of greenhouse using the supervised classification and rule-based classification method about Formosat-2 images. Connecting result of two classification try to find accuracy improvement for greenhouse detection. Results about each classification method were calculated the accuracy by comparing with the result of visual detection. As a result, mahalanobis distance among the supervised methods was resulted in the highest detection. Also, it could be checked that detection accuracy was improved by tying with result of supervised method and result of rule-based classification. Therefore, it was expected that effective detection of greenhouse would be feasible if henceforward further study is performed in the process of connecting supervised classification and rule-based classification.

• Proceedings of the Korean Society of Surveying, Geodesy, Photogrammetry, and Cartography Conference
• /
• 2004.11a
• /
• pp.167-171
• /
• 2004

최근 들어 위성영상은 자료 처리 방식에 따라 지구표면이나 또는 지하면에 대한 다양한 정보(물리적인 정보, 화학적인 정보)를 얻을 수 있고 실제 지구를 가상으로 구현하는 데 활용될 수 있기 때문에 여러 산업에서 활용하고 있다. 또한 분류는 영상에 포함된 여러 가지 대상물을 구별하기 위해서 화소와 비교적 성질이 같은 화소 그룹별 특징에 대응되는 레벨을 지정하는 기술이 요구되며, 최소거리 분류법, 평행사변형법, 마하나로비스거리법(Mahanalobis Distance Method), 최대우도법(Maximum Likelihood Method)등 비교하여 분류를 수행

• Journal of the Korean Association of Geographic Information Studies
• /
• v.4 no.4
• /
• pp.1-7
• /
• 2001

Remotely sensed data is the most fundamental data in acquiring the GIS informations, and may be analyzed to extract useful thematic information. Multi-spectral classification is one of the most often used methods of information extraction. The actual multi-spectral classification may be performed using either supervised or unsupervised approaches. This paper analyze the effect of assigning clever initial values to image classes on the performance of parallelepiped classification algorithm, which is one of the supervised classification algorithms. First, we investigate the effect on serial computing model, then expand it on MIMD(Multiple Instruction Multiple Data) parallel computing model. On serial computing model, the performance of the parallel pipe algorithm improved 2.4 times at most and, on MIMD parallel computing model the performance improved about 2.5 times as clever initial values are assigned to image class. Through computer simulation we find that initial values of image class greatly affect the performance of parallelepiped classification algorithms, and it can be improved greatly when classes on both serial computing model and MIMD parallel computation model.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.20 no.1
• /
• pp.21-31
• /
• 2002

This study applied each Neural Networks theory and Fuzzy Set theory to improve accuracy in remotely sensed images. Remotely sensed data have been used to map land cover. The accuracy is dependent on a range of factors related to the data set and methods used. Thus, the accuracy of maps derived from conventional supervised image classification techniques is a function of factors related to the training, allocation, and testing stages of the classification. Conventional image classification techniques assume that all the pixels within the image are pure. That is, that they represent an area of homogeneous cover of a single land-cover class. But, this assumption is often untenable with pixels of mixed land-cover composition abundant in an image. Mixed pixels are a major problem in land-cover mapping applications. For each pixel, the strengths of class membership derived in the classification may be related to its land-cover composition. Fuzzy classification techniques are the concept of a pixel having a degree of membership to all classes is fundamental to fuzzy-sets-based techniques. A major problem with the fuzzy-sets and probabilistic methods is that they are slow and computational demanding. For analyzing large data sets and rapid processing, alterative techniques are required. One particularly attractive approach is the use of artificial neural networks. These are non-parametric techniques which have been shown to generally be capable of classifying data as or more accurately than conventional classifiers. An artificial neural networks, once trained, may classify data extremely rapidly as the classification process may be reduced to the solution of a large number of extremely simple calculations which may be performed in parallel.

• 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.

• Korean Journal of Forensic Psychology
• /
• v.12 no.1
• /
• pp.15-33
• /
• 2021

In this study, we analyzed the difference in survival rates of those subject to electronic supervision of sex crimes based on the tracking of the period of recidivism and whether they were recidivism, and wanted to confirm the ability of the criminal record to predict recidivism. The criteria for recidivism were defined as cases where a conviction was confirmed due to a criminal case that occurred during the execution of electronic monitoring, and the date of recidivism was the date of occurrence of a case that was confirmed guilty. A total of 122 re-offenders were used in the analysis, and all of them were charged with electronic supervision for committing sex crimes. Studies have confirmed that the subjects commit the most recidivism within three years. In addition, in this study, the difference in survival rate between groups was analyzed after classifying mixed and sex recidivism cases. The number of members was 88 for the mixed recidivism group and 34 for the sex recidivism group. The analysis confirmed that both groups had the most recidivism within three years. There was a slight difference between the survival rate of the mixed recidivism group and the survival rate of the sex recidivism group. So the Log Rank Test and the Generalized Wilcoxon Test were conducted, but no statistically significant differences were identified(Wilcoxon statistic = 2.326, df = 1, p = .13, Log Rank = 1.345, df = 1, p = .25). Next, a Cox Regression analysis was performed to confirm the ability of the criminal record to predict recidivism. As a result, the number of criminal records(sex offense, violent crime) have been confirmed to be a good predictor of recidivism(X²=27.33, df=1, p< .001). As a result, the recidivism rate is gradually decreasing due to the implementation of the electronic monitoring. However, the duration of recidivism required by sex offenders in high-risk groups was found to be rather short. Currently, security measures against felons are being strengthened, so it is necessary to select high-risk groups. Therefore, based on the related studies, the characteristics of high-risk groups and the results of recidivism studies will be used as a basis for disposal within the criminal justice system, which will play a major role in granting objectivity.

• The KIPS Transactions:PartD
• /
• v.19D no.2
• /
• pp.147-150
• /
• 2012

While LDA is a supervised dimension reduction method which finds projective directions to maximize separability between classes, the performance of LDA is severely degraded when the number of labeled data is small. Recently semi-supervised dimension reduction methods have been proposed which utilize abundant unlabeled data and overcome the shortage of labeled data. However, matrix computation usually used in statistical dimension reduction methods becomes hindrance to make the utilization of a large number of unlabeled data difficult, and moreover too much information from unlabeled data may not so helpful compared to the increase of its processing time. In order to solve these problems, we propose an ensemble approach for semi-supervised dimension reduction. Extensive experimental results in text classification demonstrates the effectiveness of the proposed method.