• 대한원격탐사학회지
• /
• 제33권5_2호
• /
• pp.689-698
• /
• 2017

이 논문에서는 비접근 지역의 작물 분류를 목적으로 준감독 학습에 인접 화소의 공간 유사성 정보를 결합하는 분류 방법론을 제안하였다. 적은 수의 훈련 자료를 이용한 초기 분류 결과로부터 신뢰성 높은 훈련 자료의 추출을 위해 준감독 학습 기반의 반복 분류를 적용하였으며, 새롭게 훈련 자료 추출시 인접한 화소의 분류 항목을 고려함으로써 불확실성이 낮은 훈련 자료를 추출하고자 하였다. 북한 대홍단에서 수집된 다중시기 Landsat-8 OLI 영상을 이용한 밭작물 구분의 사례 연구를 통해 제안된 분류 방법론의 적용 가능성을 검토하였다. 사례 연구 결과, 초기 분류 결과에서 나타난 작물과 산림의 오분류와 고립된 화소가 제안 분류 방법론에서 완화되었다. 또한 인접 화소의 분류 결과를 고려한 훈련 자료 추출을 통해 이러한 오분류 완화 효과가 더욱 두드러지게 나타났으며, 초기 분류 결과와 기존 준감독 학습에 비해 고립된 화소도 감소되었다. 따라서 비접근 지역으로 인해 훈련 자료의 확보가 어려울 경우 이 연구에서 제안된 방법론이 작물 분류에 유용하게 적용될 수 있을 것으로 기대된다.

• 대한원격탐사학회지
• /
• 제33권6_2호
• /
• pp.1089-1100
• /
• 2017

이 논문에서는 토지피복도 갱신을 목적으로 영상의 객체분할과 훈련 자료 수집에 과거 토지피복도의 정보를 이용하는 방법을 제안하였다. 제안한 방법에서는 영상의 객체분할 시 명확한 토지피복 경계 분할을 위해 과거 토지피복도의 객체 경계를 이용하였다. 또한 적은 수의 초기 훈련 자료를 이용한 초기 분류 결과로부터 유용한 훈련 자료를 추가로 수집하기 위해 과거 토지피복도의 분류 항목 정보를 이용하였다. 충청남도 태안군 일부 지역을 대상으로 환경부 중분류 토지피복도와 WorldView-2 영상을 이용한 토지피복 갱신 사례 연구를 통해 제안된 토지피복도 갱신 방법론의 적용 가능성을 검토하였다. 사례 연구 결과, 초기 분류 결과에서 나타난 시가지와 나지, 논/밭과 초지의 오분류 양상이 제안 방법론을 통해 완화되었다. 또한 과거 토지피복도의 경계를 이용한 객체분할을 통해 객체의 경계를 명확하게 하고 분류 정확도를 향상시켰다. 따라서, 이 연구에서 제안된 방법이 토지피복도 갱신에 유용하게 적용될 수 있을 것으로 기대된다.

• International Journal of Computer Science & Network Security
• /
• 제22권9호
• /
• pp.353-357
• /
• 2022

This article identifies the problems and substantiates the directions for the development of distance learning technologies in the training of personnel. An example of using digital media to create a remote access laboratory is given. The article is devoted to the definition of the main aspects of the organization of distance education. Rapid digitization, economic, political and social changes taking place in Ukraine necessitate the reform of the education system. First of all, it concerns meeting the educational needs of citizens throughout their lives, providing access to educational and professional training for all who have the necessary abilities and adequate training. The most effective solution to the above-mentioned problems is facilitated by distance learning. The article analyzes the essence and methods of distance learning organization, reveals the features of the use of electronic platforms for the organization of this form of education in different countries of the world. The positive characteristics of distance learning are identified, namely: extraterritoriality; savings on transport costs; the interest of modern youth in the use of information tools in everyday life; increase in the number of students; simplicity and accessibility of training; convenient consultation system; democratic relations between the student and the teacher; convenience for organizations in training their employees without interrupting their regular work; low level of payment for distance education compared to traditional education; individual learning pace; new teacher status. Among the negative features of online education, the author refers to the following problems: authentication of users during knowledge verification, calculation of the teacher's methodological load and copyright of educational materials; the high labor intensity of developing high-quality educational content and the high cost of distance learning equipment; the need to provide users with a personal computer and access to the Internet; the need to find and use effective motivation mechanisms for education seekers.

• 한국CDE학회논문집
• /
• 제9권2호
• /
• pp.148-157
• /
• 2004

Interactive simulators that simulate mechanical systems are being developed for the purpose of performance evaluation of product design, replacement of physical training, and entertainment game. Use of flight simulator is increasing to reduce risk and cost of physical training, and we need virtual environment which covers large area terrain. We need a method that can reduce development cost and construction time of virtual environment that simulate the real environment. There have been attempts to link GIS or remote sensing field with virtual reality. This paper examines a method that helps to construct virtual environment, and attempts to link geographic information with virtual reality. A construction method of virtual environment based on digital map and satellite image has been studied.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 1999년도 Proceedings of International Symposium on Remote Sensing
• /
• pp.48-53
• /
• 1999

The paper presents an automated method for generating fuzzy rules and fuzzy membership functions for pattern classification from training sets of examples and an application to the land-cover classification. Initially, fuzzy subspaces are created from the partitions formed by the minimum and maximum of individual feature values of each class. The initial membership functions are determined according to the generated fuzzy partitions. The fuzzy subspaces are further iteratively partitioned if the user-specified classification performance has not been archived on the training set. Our classifier was trained and tested on patterns consisting of the DN of each band, (XS1, XS2, XS3), extracted from KITSAT-3 multispectral scene. The result represents that our classification method has higher generalization power.

• Journal of Information Processing Systems
• /
• 제13권2호
• /
• pp.321-339
• /
• 2017

In this work, we are interested in the extraction of areas of interest from satellite images by introducing a MO-TRIBES/OC-SVM approach. The One-Class Support Vector Machine (OC-SVM) is based on the estimation of a support that includes training data. It identifies areas of interest without including other classes from the scene. We propose generating optimal training data using the Multi-Objective TRIBES (MO-TRIBES) to improve the performances of the OC-SVM. The MO-TRIBES is a parameter-free optimization technique that manages the search space in tribes composed of agents. It makes different behavioral and structural adaptations to minimize the false positive and false negative rates of the OC-SVM. We have applied our proposed approach for the extraction of earthquakes and urban areas. The experimental results and comparisons with different state-of-the-art classifiers confirm the efficiency and the robustness of the proposed approach.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2006년도 Proceedings of ISRS 2006 PORSEC Volume II
• /
• pp.812-815
• /
• 2006

Proteins are essential agents for controlling, effecting and modulating cellular functions, and proteins with similar sequences have diverged from a common ancestral gene, and have similar structures and functions. Function prediction of unknown proteins remains one of the most challenging problems in bioinformatics. Recently, various computational approaches have been developed for identification of short sequences that are conserved within a family of closely related protein sequence. Protein function is often correlated with highly conserved motifs. Motif is the smallest unit of protein structure and function, and intends to make core part among protein structural and functional components. Therefore, prediction methods using data mining or machine learning have been developed. In this paper, we describe an approach for protein function prediction of motif-based models using data mining. Our work consists of three phrases. We make training and test data set and construct classifier using a training set. Also, through experiments, we evaluate our classifier with other classifiers in point of the accuracy of resulting classification.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 1999년도 하계종합학술대회 논문집
• /
• pp.496-499
• /
• 1999

This paper describes a medular neural network(MNN) for a vision system which tracks a given object using a sequence of images from a camera unit. The MNN is used to precisely recognize the given robot endeffector and to minize the processing time. Since the robot endeffector can be viewed in many different shapes in 3-D space, a MNN structure, which contains a set of feedforwared neural networks, co be more attractive in recognizing the given object. Each single neural network learns the endeffector with a cluster of training patterns. The training patterns for a neural network share the similar charateristics so that they can be easily trained. The trained MNN is less sensitive to noise and it shows the better performance in recognizing the endeffector. The recognition rate of MNN is enhanced by 14% over the single neural network. A vision system with the MNN can precisely recognize the endeffector and place it at the center of a display for a remote operator.

• 한국측량학회:학술대회논문집
• /
• 한국측량학회 2004년도 추계학술발표회 논문집
• /
• pp.251-256
• /
• 2004

The image classification is one of the most important studies in the remote sensing. In general, the MLC(Maximum Likelihood Classification) classification that in consideration of distribution of training information is the most effective way but it produces a bad result when we apply it to actual hyperspectral image with the same classification technique. The purpose of this research is to reveal that which one is the most effective and suitable way of the classification algorithms iii the hyperspectral image classification. To confirm this matter, we apply the MLC classification algorithm which has distribution information and SAM(Spectral Angle Mapper), SFF(Spectral Feature Fitting) algorithm which use average information of the training class to both multispectral image and hyperspectral image. I conclude this result through quantitative and visual analysis using confusion matrix could confirm that SAM and SFF algorithm using of spectral pattern in vector domain is more effective way in the hyperspectral image classification than MLC which considered distribution.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2002년도 Proceedings of International Symposium on Remote Sensing
• /
• pp.81-81
• /
• 2002

Classification is considered as one of the processes of extracting attributes from satellite imagery and is one of the usual functions in the commercial satellite image processing software. Accuracy of classification plays a key role in deciding the usage of its results. Many tremendous efforts far the higher accuracy have been done in such fields; training area selection, classification algorithm. Our research is one of these effort in different manners. In this research, we conduct classification using multiple satellite image data and evidential approach. We statistically consider the posterior probabilities and certainty in maximum likelihood classification and methodologically Dempster's orthogonal sums. Unfortunately, accuracy for the whole data sets has not assessed yet, but accuracy assessments in training fields and check fields shows accuracy improvement over 10% in overall accuracy and over 0.1 in kappa index.