• 대한원격탐사학회지
• /
• 제22권3호
• /
• pp.211-219
• /
• 2006

A random forests classifier is applied to multi-sensor data fusion for supervised land-cover classification in order to account for the importance of variable. The random forests approach is a non-parametric ensemble classifier based on CART-like trees. The distinguished feature is that the importance of variable can be estimated by randomly permuting the variable of interest in all the out-of-bag samples for each classifier. Two different multi-sensor data sets for supervised classification were used to illustrate the applicability of random forests: one with optical and polarimetric SAR data and the other with multi-temporal Radarsat-l and ENVISAT ASAR data sets. From the experimental results, the random forests approach could extract important variables or bands for land-cover discrimination and showed reasonably good performance in terms of classification accuracy.

• Asian Journal of Innovation and Policy
• /
• 제8권1호
• /
• pp.73-96
• /
• 2019

This study suggests a new approach for identifying core robot tech-nologies based on technological cross-impact. Specifically, the approach applies data mining techniques and multi-criteria decision-making methods to the co-classification information of registered patents on the robots. First, a cross-impact matrix is constructed with the confidence values by applying association rule mining (ARM) to the co-classification information of patents. Analytic network process (ANP) is applied to the co-classification frequency matrix for deriving weights of each robot technology. Then, a technique for order performance by similarity to ideal solution (TOPSIS) is employed to the derived cross-impact matrix and weights for identifying core robot technologies from the overall cross-impact perspective. It is expected that the proposed approach could help robot technology managers to formulate strategy and policy for technology planning of robot area.

• International Journal of Safety
• /
• 제1권1호
• /
• pp.28-35
• /
• 2002

Kullback Discrimination Information (KDI) is one of the pattern recognition methods. KDI defined as a measure of the mutual dissimilarity computed between two time series was studied for detection and classification of bearing flaking on outer-race and inner-races. To model the damages, the bearings in normal condition, outer-race flaking condition and inner-races flaking condition were provided. The vibration sensor was attached by the bearing housing. This produced the total 25 pieces of data each condition, and we chose the standard data and measure of distance between standard and tested data. It is difficult to detect the flaking because similar pulses come out when balls pass the defection point. The detection and classification method for inner and outer races are defected by KDI and nearest neighbor classification rule is proposed and its high performance is also shown.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2022년도 춘계학술대회
• /
• pp.367-369
• /
• 2022

본 논문에서는 훈련된 모델이 분류에 실패한 이미지들에 대한 정확한 결과를 확인하기 위해 다중 클래스의 이미지 분류를 구현하면서 각각의 클래스에 맞게 레이블 매핑을 하여 예측 결과를 확인했다. Kaggle의 Intel Image Classification 데이터셋을 사용하여 CNN 모델을 구축하고 훈련을 진행하였으며, 테스트 데이터셋의 이미지들을 레이블 매핑을 통해 다중 클래스의 이미지들이 매핑된 레이블 값과 모델이 분류한 값을 비교하였다.

• Journal of Gastric Cancer
• /
• 제11권2호
• /
• pp.78-85
• /
• 2011

Since January of 2010, the seventh edition of UICC tumor node metastasis (TNM) Classification, which has recently been revised, has been applied to almost all cases of malignant tumors. Compared to previous editions, the merits and demerits of the current revisions were analyzed. Many revisions have been made for criteria for the classification of lymph nodes. In particular, all the cases in whom the number of lymph nodes is more than 7 were classified as N3 without being differentiated. Therefore, the coverage of the N3 was broad. Owing to this, there was no consistency in predicting the prognosis of the N3 group. By determining the positive cases to a distant metastasis as TNM stage IV, the discrepancy in the TNM stage IV compared to the sixth edition was resolved. In regard to the classification system for an esophagogastric (EG) junction carcinoma, it was declared that cases of an invasion to the EG junction should follow the classification system for esophageal cancer. A review of clinical cases reported from Asian patients suggests that it would be more appropriate to follow the previous editions of the classification system for gastric cancer. In addition, in the classification of the TNM stages in the overall cases, the discrepancy in the prognosis between the different stages and the consistency in the prognosis between the same TNM stages were achieved to a lesser extent as compared to that previously. Accordingly, further revisions are needed to develop a purposive classification method where the prognosis can be predicted specifically to each variable and the mode of the overall classification can be simplified.

• 한국문헌정보학회지
• /
• 제33권1호
• /
• pp.87-111
• /
• 1999

본고는 분류용 MARC 포맷에 대해 기능과 필요성, 개발현황에 대해 살펴보고, KORMARC 분류용포맷의 개발필요성을 제시하였다. 아울러 MARC포맷의 3요소로 일컬어지는 구조와, 내용표지법, 레코드의 내용을 이미 개발된 USMARC 포맷을 중심으로 분석하였다. 레코드의 구조와 내용표지법은 서지용 및 전거용포맷과 대부분 동일하다. 데이터필드는 기본적으로 기능별블록으로 구분되어 있다. 고정길이필드의 레코드의 내용에는 기호의 유형, 유효성, 표준 및 임의규정, 합성기호표시 등 분류기호에 관련된 요소들이 추가되어 있다. 가변길이필드의 내용은 번호와 코드 분류기호와 용어 참조 및 표목지시, 주기, 색인어, 기호합성, 전자상의 소재 및 접근 필드 등으로 구성되어 있다. 각 필드의 데이터들은 가능한 한 관련포맷과 조기성을 유지할 수 있도록 배려하고 있다.

• 한국과학교육학회지
• /
• 제11권2호
• /
• pp.133-142
• /
• 1991

The purpose of this study is to develop a data base system for the information on research and development of science education. As the first step of this study and development, a classification system for the research and development materials was devised after discussing the process of science education and the research and development of science education. The classification system has nine main categories : 1. area, 2. subject, 3. behavior, 4. skill, 5. support, 6. type, 7. materials, 8. language, and 9. the others, each of which has one or two levels of subcategory. This classification system was revised and supplemented through the theoretical analysis by speci.diSts and the practical classification of master's theses and doctoral dissertations from the Department of Science Education, Seoul National University. But it still needs more revision and enlargement through the continuous application and analysis.

• 대한수학회보
• /
• 제55권5호
• /
• pp.1371-1387
• /
• 2018

The classification of the self-dual codes over Galois rings GR(p, 2) and $GR(p^2,2)$ of length 4 is completed for all primes p up to equivalence in terms of automorphism group. We obtain all inequivalent classes and the number of each classes of self-dual codes for all primes.

• 디지털융복합연구
• /
• 제19권12호
• /
• pp.347-352
• /
• 2021

본 논문은 다중 에이전트 강화학습 방식을 사용하여 입력 데이터로부터 분류에 효과적인 특징 집합을 찾아내는 방식을 제안한다. 기계 학습 분야에 있어서 분류에 적합한 특징들을 찾아내는 것은 매우 중요하다. 데이터에는 수많은 특징들이 존재할 수 있으며, 여러 특징들 중 일부는 분류나 예측에 효과적일 수 있지만 다른 특징들은 잡음 역할을 함으로써 올바른 결과를 생성하는 데에 오히려 악영향을 줄 수 있다. 기계 학습 문제에서 분류나 예측 정확도를 높이기 위한 특징 선택은 매우 중요한 문제 중 하나이다. 이러한 문제를 해결하기 위해 강화학습을 통한 특징 선택 방법을 제시한다. 각각의 특징들은 하나의 에이전트를 가지게 되며, 이 에이전트들은 특징을 선택할 것인지 말 것인지에 대한 여부를 결정한다. 에이전트들에 의해 선택된 특징들과 선택되지 않은 특징들에 대해서 각각 보상을 구한 뒤, 보상에 대한 비교를 통해 에이전트의 Q-value 값을 업데이트 한다. 두 하위 집합에 대한 보상 비교는 에이전트로 하여금 자신의 행동이 옳은지에 대한 판단을 내릴 수 있도록 도와준다. 이러한 과정들을 에피소드 수만큼 반복한 뒤, 최종적으로 특징들을 선별한다. 이 방법을 통해 Wisconsin Breast Cancer, Spambase, Musk, Colon Cancer 데이터 세트에 적용한 결과, 각각 0.0385, 0.0904, 0.1252, 0.2055의 정확도 향상을 보여주었으며, 최종적으로 0.9789, 0.9311, 0.9691, 0.9474의 분류 정확도를 보여주었다. 이는 우리가 제안한 방법이 분류에 효과적인 특징들을 잘 선별하고 분류에 대한 정확도를 높일 수 있음을 보여준다.

• 한국통계학회:학술대회논문집
• /
• 한국통계학회 2005년도 추계 학술발표회 논문집
• /
• pp.193-197
• /
• 2005

Classification tree is one of the most suitable base learners for ensemble. For past decade, it was found that bagging gives the most accurate prediction when used with unpruned tree and boosting with stump. Researchers have tried to understand the relationship between the size of trees and the accuracy of ensemble. With experiment, it is found that large trees make boosting overfit the dataset and stumps help avoid it. It means that the accuracy of each classifier needs to be sacrificed for better weighting at each iteration. Hence, split effect in boosting can be explained with the trade-off between the accuracy of each classifier and better weighting on the misclassified points. In bagging, combining larger trees give more accurate prediction because bagging does not have such trade-off, thus it is advisable to make each classifier as accurate as possible.