• 대한원격탐사학회지
• /
• 제15권1호
• /
• pp.39-50
• /
• 1999

위성에서 관측된 다 대역 위성영상 데이터를 이용목적에 따라 분류하기 위해서는 복잡한 처리과정과 많은 시간을 필요로 하며, 감독분류시 훈련 데이터의 선택과 고려되는 다양한 특징 값들은 분류 정확도를 좌우할 만큼 민감한 특성을 나타내고 있다. 따라서 본 논문에서는 훈련데이터의 선택과 다양한 특징 값들 중 실제 영상분류에 기여도가 높은 특징을 추출하기 위하여 퍼지 기반의 $\gamma$모델을 이용한 분류네트웍을 구성하였다. 훈련집합 선택시 분류하고자 하는 지역의 밝기 분포도, 텍스쳐 특징 그리고 NDVI(Normalized Difference Vegetation Index)를 분류에 사용될 특징으로 선택하였고, 분류네트웍 출력 값의 오류가 최소화 되도록 Gradient Desoent 방법을 이용하여 각 노드의 $\gamma$파라미터를 훈련시키는 과정을 채택하였다. 이러한 훈련을 통하여 얻어진 파라미터를 이용하면 각 노드의 연결특성을 알 수 있으며, 다양한 입력 노드의 특징들 중 영상분류에 기여도가 적은 특징들을 추출하여 제거할 수 있다.

• 반도체디스플레이기술학회지
• /
• 제19권4호
• /
• pp.121-125
• /
• 2020

With miniaturization of semiconductor, the manufacturing process become more complex, and undetected small changes in the state of the equipment have unexpectedly changed the process results. Fault detection classification (FDC) system that conducts more active data analysis is feasible to achieve more precise manufacturing process control with advanced machine learning method. However, applying machine learning, especially in supervised learning criteria, requires an arduous data labeling process for the construction of machine learning data. In this paper, we propose a semi-supervised learning to minimize the data labeling work for the data preprocessing. We employed equipment status variable identification (SVID) data and optical emission spectroscopy data (OES) in silicon etch with SF6/O2/Ar gas mixture, and the result shows as high as 95.2% of labeling accuracy with the suggested semi-supervised learning algorithm.

• 한국초등과학교육학회지:초등과학교육
• /
• 제34권1호
• /
• pp.142-152
• /
• 2015

The purpose of this study was to identify the differences in eye movement pattern shown in shown in classification process between the scientifically gifted and general students in elementary schools. The subjects for the research consisted of 16 gifted students in special education center for the gifted at Seoul National University of Education and 22 general students at G elementary schools. The tasks consisted of four hierarchical biology classification tasks and one non-hierarchical tasks. SMI's Eye Tracker (iView $X^{TM}$ RED) was used to collect eye movement data while the Begaze software analyzed the task performing process and eye movements. The findings of this study were twofold. First, there was a significant difference in students' fixation duration by students' academic achievement level. Gifted students spent little time on scanning details and found the features successfully. Second, the process of the classification is different by students' academic achievement. General students spent more time to gaze the salient features not relevant features. They had a difficulty to find the element to classify.

• 정보관리학회지
• /
• 제34권4호
• /
• pp.33-57
• /
• 2017

본 연구는 새로운 분석법으로 떠오르는 처방적 분석 기법을 소개하고, 이를 분류 기반의 시스템에 효율적으로 적용하는 방안을 제시하는 것을 목적으로 한다. 처방적 분석 기법은 분석의 결과를 제시함과 동시에 최적화된 결과가 나오기까지의 과정 및 다른 선택지까지 제공한다. 새로운 개념의 분석 기법을 도입함으로써 문헌 분류를 기반으로 하는 응용 시스템을 더욱 쉽게 최적화하고 효율적으로 운영하는 방안을 제시하였다. 최적화의 과정을 시뮬레이션하기 위해, 대용량의 학술문헌을 수집하고 기준 분류 체계에 따라 자동 분류를 실시하였다. 처방적 분석 개념을 적용하는 과정에서 대용량의 문헌 분류를 위한 동적 자동 분류 기법과 학문 분야의 지적 구조 분석 기법을 동시에 활용하였다. 실험의 결과로 효과적으로 서비스 분류 체계를 수정하고 재적용할 수 있는 몇 가지 최적화 시나리오를 효율적으로 도출할 수 있음을 보여 주었다.

• 한국초등과학교육학회지:초등과학교육
• /
• 제27권1호
• /
• pp.9-22
• /
• 2008

The purpose of this study was to investigate the type of classification criterion and the characteristic of classification strategy that appear in pre-service elementary teachers' classification activity. The 4 tasks were developed for classification activity; button as a real things that attribute is prominent, shell as a real things that attribute is less prominent, snow flake as a picture cards that attribute is prominent, and galaxy as a picture cards that attribute is less prominent. The 5 college students who major in elementary education were selected. Data were collected by interview with participants, participants' classification recording paper, investigator's observation of participants' action observation, and videotaped that record participants' subject classification process. Result proved in this study is as following. First, pre-service elementary teachers used 4 qualitative classification criterion of feature, random field, image and secondary property, and used 2 dimension classification criterion of space and quantity. They used single quality classification criterion or combining dimension classification criterion in classification activity. Second, pre-service elementary teachers have classification strategy that apply each various classification criterion, and also classification strategy are different according to subject, but discussed that "anchor" and "priming effect" are important for effective classification. Result of this study is expected to contribute classification research and classification teaching program development.

• IEIE Transactions on Smart Processing and Computing
• /
• 제4권4호
• /
• pp.202-208
• /
• 2015

In this study, we propose a new inference algorithm for a multiclass Gaussian process classification model using a variational EM framework and the Laplace approximation (LA) technique. This is performed in two steps, called expectation and maximization. First, in the expectation step (E-step), using Bayes' theorem and the LA technique, we derive the approximate posterior distribution of the latent function, indicating the possibility that each observation belongs to a certain class in the Gaussian process classification model. In the maximization step, we compute the maximum likelihood estimators for hyper-parameters of a covariance matrix necessary to define the prior distribution of the latent function by using the posterior distribution derived in the E-step. These steps iteratively repeat until a convergence condition is satisfied. Moreover, we conducted the experiments by using synthetic data and Iris data in order to verify the performance of the proposed algorithm. Experimental results reveal that the proposed algorithm shows good performance on these datasets.

• 한국멀티미디어학회논문지
• /
• 제22권5호
• /
• pp.558-572
• /
• 2019

Anthropomorphism is the attribution of human traits, emotions, or intentions to non-human entities. Anthropomorphic animal face masking is the process by which human characteristics are plotted on the animal kind. In this research, we are proposing a compact system which finds the resemblance between a human face and animal face using Deep Convolutional Neural Network (DCNN) and later applies morphism between them. The whole process is done by firstly finding which animal most resembles the particular human face through a DCNN based animal face classification. And secondly, doing triangulation based morphing between the particular human face and the most resembled animal face. Compared to the conventional manual Control Point Selection system using an animator, we are proposing a Viola-Jones algorithm based Control Point selection process which detects facial features for the human face and takes the Control Points automatically. To initiate our approach, we built our own dataset containing ten thousand animal faces and a fourteen layer DCNN. The simulation results firstly demonstrate that the accuracy of our proposed DCNN architecture outperforms the related methods for the animal face classification. Secondly, the proposed morphing method manages to complete the morphing process with less deformation and without any human assistance.

• 대한원격탐사학회지
• /
• 제16권4호
• /
• pp.367-373
• /
• 2000

Natural and artificial land features are very dynamic, changing somewhat repidly in our lifetime. It is important that such changes are inventoried accurately so that the physical and human processes at work can be more fully understood. Change detection is a technique used to determine the change between two or more time periods of a particular object of study. Change detection is an important process in monitoring and managing natural resources and urban development because it provides quantitative analysis of the spatial distribution in the population of interest. The purpose of this research is to detect environmental changes surrounding an area of Mountain Moscow, Idaho using Landsat Thematic Maper (TM) images of (July 8, 1990 and July 20, 1991). For accurate classification, the Image enhancement process was performed for improving the image quality of each image. A SPOT image (Aug. 14, 1992) was used for image merging in this research. Supervised classification was performed using the maximum likelihood method. Accuracy assessments were done for each classification. Two images were compared on a pixel-by-pixel basis using the post-classification comparison method that is used for detecting the changes of the study area in this research. The 'from-to' change class information can be detected by post classification comparison using this method and we could find which class change to another.

• Nuclear Engineering and Technology
• /
• 제54권4호
• /
• pp.1336-1342
• /
• 2022

Risk-informed safety classification of structures, systems and components (SSCs) is very important for ensuring the safety and economic efficiency of nuclear power plants (NPPs). However, previous methods for safety classification of SSCs do not take the plant operating modes or the operational process of SSCs into consideration, thus cannot concentrate on the safety and economic efficiency accurately. In this contribution, a new method for safety classification of SSCs based on the categorization of plant operating modes is proposed, which considers the NPPs operating history to improve the economic efficiencies while maintaining the safety. According to the time duration of plant configurations in plant operating modes, average importances of SSCs are accessed for an NPP considering the operational process, and then safety classification of SSCs is performed for plant operating modes. The correctness and effectiveness of the proposed method is demonstrated by application in an NPP's safety classification of SSCs.

• 한국문헌정보학회지
• /
• 제23권
• /
• pp.207-261
• /
• 1992

The purpose of this study is (1) to design and test a database which can be automatically classified, and (2) to generate automatic classification number by processing the keywords in titles using the code combination method of Colon Classification(CC) as well as an automatic recognition of subjects in order to develop an automatic classification system (Auto BC System) based on CC which can be applied to any research library. To conduct this study, 1,510 words in the fields of agricultrue and medicine were selected, analized in terms of [P], [M], [E], [S], [T] employed in CC, and included in a database for classification. For the above-mentioned subject fields, the principle of an automatic classification was specified in order to generate automatic classification codes as well as to perform an automatic subject recognition of the titles included. Whenever necessary, editing, deleting, appending and reindexing of a database can be made in this automatic classification system. Appendix 1 shows the result of the automatic classification of books in the fields of agriculture and medicine. The results of the study are summarized below. 1. The classification number for the title of a book can be automatically generated by using the facet principles of Colon Classification. 2. The automatic subject recognition of a book is achieved by designing a database making use of a globe-principle, and by specifying the subject field for each word. 3. The automatic subject-recognition of input data is achieved by measuring the number of searched words by each subject field. 4. The combination of classification numbers is achieved by flowcharting of classification formular of each subject field. 5. The efficient control of classification numbers is achieved by designing control codes on the database for classification. 6. The automatic classification by means of Auto BC has been proved to be successful in the research library concentrating on a Single field. The general library may have some problem in employing this system. The automatic classification through Auto BC has the following advantages: 1. Speed of the classification process can be improve. 2. The revision or updating of classification schemes can be facilitated. 3. Multiple concepts can be expressed in a single classification code. 4. The consistency of classification can be achieved with the classification formular rather than the classifier's subjective judgement. 5. A user's retrieving process can be made after combining the classification numbers through keywords relating to the material to be searched. 6. The materials can be classified by a librarian without subject backgrounds. 7. The large body of materials can be quickly classified by means of a machine processing. 8. This automatic classification is expected to make a good contribution to design of the total system for library operations. 9. The information flow among libraries can be promoted owing to the use of the same program for the automatic classification.