• IEIE Transactions on Smart Processing and Computing
• /
• 제6권1호
• /
• pp.53-59
• /
• 2017

Optical character recognition (OCR) automatically recognizes text in an image. OCR is still a challenging problem in computer vision. A successful solution to OCR has important device applications, such as text-to-speech conversion and automatic document classification. In this work, we analyze character recognition performance using the current state-of-the-art deep-learning structures. One is the AlexNet structure, another is the LeNet structure, and the other one is the SPNet structure. For this, we have built our own dataset that contains digits and upper- and lower-case characters. We experiment in the presence of salt-and-pepper noise or Gaussian noise, and report the performance comparison in terms of recognition error. Experimental results indicate by five-fold cross-validation that the SPNet structure (our approach) outperforms AlexNet and LeNet in recognition error.

• 한국지능시스템학회논문지
• /
• 제11권5호
• /
• pp.441-447
• /
• 2001

In general, Rough Set theory is used for classification, inference, and decision analysis of incomplete data by using approximation space concepts in information system. Information system can include quantitative attribute values which have interval characteristics, or incomplete data such as multiple or unknown(missing) data. These incomplete data cause tole inconsistency in information system and decrease the classification ability in system using Rough Sets. In this paper, we present various types of incomplete data which may occur in information system and propose INcomplete information Processing System(INiPS) which converts incomplete information system into complete information system in using Rough Sets.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제5권4호
• /
• pp.281-285
• /
• 2005

Learning and evolving are two basics for data mining. As compared with classical learning theory based on objective function with minimizing training errors, the recently evolutionary computing has had an efficient approach for constructing optimal model without the minimizing training errors. The global search of evolutionary computing in solution space can settle the local optima problems of learning models. In this research, combining co-evolving algorithm into statistical learning theory, we propose an co-evolutionary computing for statistical learning theory for overcoming local optima problems of statistical learning theory. We apply proposed model to classification and prediction problems of the learning. In the experimental results, we verify the improved performance of our model using the data sets from UCI machine learning repository and KDD Cup 2000.

• 한국안전학회지
• /
• 제32권5호
• /
• pp.88-95
• /
• 2017

As the safety fields are expanding to a variety of industrial fields, safety technology has been developed by convergence between industrial safety fields such as mechanics, ergonomics, electronics, chemistry, construction, and information science. As the technology convergence is facilitating recently advanced safety technology, it is important to explore the trends of safety technology for understanding which industrial technologies have been integrated thus far. For studying the trends of technology, the patent is considered one of the useful sources that has provided the ample information of new technology. The patent has been also used to identify the patterns of technology convergence through various quantitative methods. In this respect, this study aims to identify the convergence patterns and fields of safety technology using association rule mining(ARM)-based patent co-classification(co-class) analysis. The patent co-class data is especially useful for constructing convergence network between technological fields. Through linkages between technological fields, the core and hub classes of convergence network are explored to provide insight into the fields of safety technology. As the representative method for analyzing patent co-class network, the ARM is used to find the likelihood of co-occurrence of patent classes and the ARM network is presented to visualize the convergence network of safety technology. As a result, we find three major convergence fields of safety technology: working safety, medical safety, and vehicle safety.

• 수산해양교육연구
• /
• 제29권3호
• /
• pp.689-701
• /
• 2017

In recent offshore industries, various ambiguous terms have been used without clear definition or classification, causing difficulties in legal, technical, and educational understanding and usage. For an example, the commonly used term of 'Offshore Plant' in Korea is not an universal word technically. There has been no clear technical or legal definition about the 'Offshore Plant' and its classification is also very ambiguous; sometimes it is used to refer offshore oil and gas production platform or it is used to mean offshore renewable power generation plant in some cases. To build a conceptual framework, therefore, this paper suggests a classification of offshore units (1) using internationally agreed terms, (2) agreed with the technical classification used by the ship classification society and (3) being able to include not only the current but also future concepts of offshore units.

• 한국컴퓨터정보학회논문지
• /
• 제22권10호
• /
• pp.121-128
• /
• 2017

In this paper, we propose a multi-label classification method in which multi-label classification estimation techniques are applied to resolving location prediction problem. Most of previous studies related to location prediction have focused on the use of single-label classification by using contextual information such as user's movement paths, demographic information, etc. However, in this paper, we focused on the case where users are free to visit multiple locations, forcing decision-makers to use multi-labeled dataset. By using 2373 contextual dataset which was compiled from college students, we have obtained the best results with classifiers such as bagging, random subspace, and decision tree with the multi-label classification estimation methods like binary relevance(BR), binary pairwise classification (PW).

• Journal of Information Processing Systems
• /
• 제8권4호
• /
• pp.575-588
• /
• 2012

Exploiting unlabeled text data with a relatively small labeled corpus has been an active and challenging research topic in text mining, due to the recent growth of the amount of biomedical literature. Biomedical named-entity recognition is an essential prerequisite task before effective text mining of biomedical literature can begin. This paper proposes an Active Co-Training (ACT) algorithm for biomedical named-entity recognition. ACT is a semi-supervised learning method in which two classifiers based on two different feature sets iteratively learn from informative examples that have been queried from the unlabeled data. We design a new classification problem to measure the informativeness of an example in unlabeled data. In this classification problem, the examples are classified based on a joint view of a feature set to be informative/non-informative to both classifiers. To form the training data for the classification problem, we adopt a query-by-committee method. Therefore, in the ACT, both classifiers are considered to be one committee, which is used on the labeled data to give the informativeness label to each example. The ACT method outperforms the traditional co-training algorithm in terms of f-measure as well as the number of training iterations performed to build a good classification model. The proposed method tends to efficiently exploit a large amount of unlabeled data by selecting a small number of examples having not only useful information but also a comprehensive pattern.

• 한국멀티미디어학회논문지
• /
• 제16권7호
• /
• pp.870-878
• /
• 2013

본 논문에서는 생체인증 시스템의 하나인 지문인식 시스템의 정확도와 효율성을 높이기 위한 새로운 지문 분류 방법을 제안한다. 기존 연구에 따르면 지문은 융선과 골의 방향과 형상에 따라 몇 가지 유형으로 분류할 수 있다. 지문 데이터베이스를 사전에 유형에 따라 분류해 놓고 인식 대상인 지문의 유형을 정확하게 분류할 수 있다면 지문 인식 시간을 크게 줄일 수 있다. 왜냐하면 선택된 부류 안의 지문들만을 상대로 인증 대상인 지문과 비교하면 되기 때문이다. 본 논문은 우선 지문 영상으로부터 실제 지문 정보가 위치하는 관심영역 추출 방법을 제시한다. 다음엔 추출된 관심영역을 대상으로 질감 인식기반의 명암도 동시발생 행렬과 웨이브릿 변환을 통한 특징 추출 방법을 제시하고 기존의 명암도 동시발생 행렬만을 이용한 특징 추출 방법과 다층 퍼셉트론 및 서포트 벡터 머신을 사용해 성능을 비교한다.

• 한국컴퓨터정보학회논문지
• /
• 제19권11호
• /
• pp.43-52
• /
• 2014

본 논문에서는 적외선 영상에서 영상 변위를 이용하여 기동 표적 영역을 탐지하고, SURF(Speeded Up Robust Features) 특징점에 대한 BAS(Beam Angle Statistics)를 이용하여 분류하는 시스템에 대하여 설명한다. 영상 기반 기술 분야에서 대표적인 대응점 정합 알고리즘인 SURF 기법은 SIFT(Scale Invariant Feature Transform) 기법에 비해 정합 속도가 매우 빠르고 비슷한 정합 성능을 보이기 때문에 널리 사용되고 있다. SURF를 이용한 대부분의 객체 인식의 경우 특징점 추출과 정합의 과정을 수행하지만, 제안하는 기법은 표적의 기동 특성을 반영하여 영상의 변위 추정을 통하여 표적의 영역을 탐지하고 SURF 특징점 들의 기하구조를 판단함으로써 표적 분류를 수행한다. 제안하는 기법은 무인 표적 탐지/인지 시스템의 초기모델 구축을 위하여 연구가 진행되었으며, 모의 표적을 이용한 가상 영상과 적외선 실 영상을 이용하여 실험한 결과 약 73~85%의 분류 성능을 확인하였다.

• 한국측량학회지
• /
• 제36권6호
• /
• pp.433-442
• /
• 2018

저수구역은 계획된 홍수위에 의하여 둘러싸인 지역 혹은 댐의 계획된 홍수위 내에 있는 지역으로 정의된다. 본 연구에서는 저수구역 내 농경지를 탐지하기 위하여, 대표적인 기계학습 기법인 RF (Random Forest) 기반의 감독 분류 방법을 적용하였다. 저수구역 내의 농경지를 효과적으로 분류하기 위하여, 질감정보를 정량화하기 위한 대표적인 기법인 GLCM (Gray Level Co-occurrence Matrix)과 NDWI (Normalized Difference Water Index), NDVI (Normalized Difference Vegetation Index)를 추가적인 입력자료로 활용하였다. 특히, 질감정보를 생성하는데 사용된 윈도우 크기가 농경지의 분류 정확도에 미치는 영향을 분석하여, 저수구역 내의 농경지를 효과적으로 분류하기 위한 방법론을 제시하였다. 실험결과, UAV 영상을 이용한 분류결과를 통하여 취득된 다중분광영상과 NDVI, NDWI, GLCM 영상들을 이용하여 저수구역 내의 농경지를 효과적으로 탐지할 수 있음을 확인하였다. 또한, GLCM의 윈도우 크기가 분류정확도를 향상시키기 위한 중요한 변수임을 확인하였다.