• 산업공학
• /
• 제18권1호
• /
• pp.10-21
• /
• 2005

With the increasing proliferation of World Wide Web, electronic mail systems have become very widely used communication tools. Researches on e-mail classification have been very important in that e-mail classification system is a major engine for e-mail response management systems which mine unstructured e-mail messages and automatically categorize them. In this research we compare the performance of Naive Bayesian learning and Centroid-Based Classification using the different data set of an on-line shopping mall and a credit card company. We analyze which method performs better under which conditions. We compared classification accuracy of them which depends on structure and size of train set and increasing numbers of class. The experimental results indicate that Naive Bayesian learning performs better, while Centroid-Based Classification is more robust in terms of classification accuracy.

• 한국통신학회논문지
• /
• 제39B권4호
• /
• pp.191-199
• /
• 2014

최근 웹 기반의 다양한 응용과 서비스의 제공으로 인해 HTTP 트래픽의 양이 급격하게 증가하고 있다. 따라서 안정적인 네트워크 관리를 위해서 HTTP 트래픽에 대한 분석이 필수적으로 요구된다. HTTP 트래픽을 다양한 관점에서 분석하기 위해서는 다양한 시그니쳐 기반 분석 방법 중에 페이로드 시그니쳐 기반 분석 방법이 효과적이다. 하지만 트래픽 분류 있어서 페이로드 시그니쳐 기반 방법은 고속 링크의 대용량 트래픽을 실시간으로 처리하는 과정에서 헤더 정보 및 통계 정보 이용 방법론에 비해 상대적으로 높은 부하를 발생시키며 처리 속도가 느린 단점을 갖는다. 따라서 본 논문에서는 HTTP 시그니쳐의 계층 구조에 기반하여 HTTP 트래픽을 다양하게 분류할 수 있는 방법론을 제시한다. 또한 계층 구조의 특징을 반영하여 패턴 매칭의 처리 속도 향상을 위한 방법을 제안한다. 제안하는 방법을 학내망의 실제 트래픽에 적용하여 평가한 결과, Aho-Corasick 알고리즘 보다 더 빠른 처리속도를 보일 수 있었다.

• Smart Structures and Systems
• /
• 제33권1호
• /
• pp.55-64
• /
• 2024

This paper proposes a fusion imaging-based coating-defect classification method for steel structures that uses zero-shot learning. In the proposed method, a halogen lamp generates heat energy on the coating surface of a steel structure, and the resulting heat responses are measured by an infrared (IR) camera, while photos of the coating surface are captured by a charge-coupled device (CCD) camera. The measured heat responses and visual images are then analyzed using zero-shot learning to classify the coating defects, and the estimated coating defects are visualized throughout the inspection surface of the steel structure. In contrast to older approaches to coating-defect classification that relied on visual inspection and were limited to surface defects, and older artificial neural network (ANN)-based methods that required large amounts of data for training and validation, the proposed method accurately classifies both internal and external defects and can classify coating defects for unobserved classes that are not included in the training. Additionally, the proposed model easily learns about additional classifying conditions, making it simple to add classes for problems of interest and field application. Based on the results of validation via field testing, the defect-type classification performance is improved 22.7% of accuracy by fusing visual and thermal imaging compared to using only a visual dataset. Furthermore, the classification accuracy of the proposed method on a test dataset with only trained classes is validated to be 100%. With word-embedding vectors for the labels of untrained classes, the classification accuracy of the proposed method is 86.4%.

• 한국지능시스템학회논문지
• /
• 제12권3호
• /
• pp.202-209
• /
• 2002

본 논문은 제어 시스템에서 규칙기반과 데이터 마이닝에서의 분류규칙의 명료함에 대해 다룬다. 대용량의 데이터로부터 유용한 정보를 얻어내는 데이터 마이닝은 중요한 이슈가 되고 있다. 인공지능에 기반을 둔 데이터 마이닝 분류기법에는 신경망, 의사결정나무 등 여러가지가 있지만 그 결과는 명확하고 이해하기 쉽고 분류규칙이 간단명료해야 한다. 러프집합이론은 불충분하고 비일관적인 데이터로부터 의미있는 지식을 추출하는데 효과적인 기법이고, 다양한 속성들을 효과적으로 사용함으로써 분류와 근사화에 대한 좋은 해법을 제시한다. 본 논문에서는 러프집합이론의 근사화를 이용하여 알갱이 속에 숨겨져 있는 지식들을 찾아내는데 있어 효과적인 접근을 하였으며, 최상위 레벨에 코어를 적용하여 계층적 분류를 함으로써 대량의 데이터를 효율적으로 처리할 수 있도록 하였다. 제안된 분류방법은 정보시스템의 해석을 용이하게 하고 최소의 분류규칙을 만든다.

• 한국기록관리학회지
• /
• 제23권1호
• /
• pp.101-126
• /
• 2023

대학의 사진기록은 대학의 정체성을 확립하고 역사적 증거를 제공하는 매우 가치 있는 기록의 유형 중 하나이나, 텍스트와 달리 의미전달의 취약성을 갖고 있으므로 사진기록의 정보가 포괄적으로 기술되지 않으면 이용자의 검색과 활용이 어렵다. 본 연구에서는 대학기록관 사진 아카이브를 위해 사진기록의 분류체계를 구조화하고, 분류 내의 카테고리 특성을 반영한 메타데이터 셋 개발을 시도하였다. 이를 위해 국내와 미국 대학기록관의 사진기록 분류체계와 메타데이터 요소를 분석하고, 정보구조 모형을 제안하였다. 본 연구에서 제안한 정보구조 모형을 통해 대학기록관 사진기록의 데이터 품질을 향상시킬 수 있으며, 이용자에게는 사진기록에 대한 풍부한 디스커버리를 지원할 수 있다.

• 한국철도학회:학술대회논문집
• /
• 한국철도학회 2003년도 추계학술대회 논문집(II)
• /
• pp.448-453
• /
• 2003

Most urban transit companies recognize the necessity of classification for facility management Classification for urban transit facility is necessary for standardization of maintenance management. The practical application. however. is not easy because of the absence of standardization of classification for urban transit facility and the difficulty in objectification of breakdown structure. This study suggests a proposal of classification for maintenance management in urban transit facility. This study defines standardization of classification as facility, work, maintenance and attribute to manage urban transit facility. And attribute classification consist of material, equipment and document. The suggested classification can be used as a useful maintenance management tool that enables evaluation of urban transit facility by standardization. The results of this study could be used as references for related urban transit companies.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1997년도 한국자동제어학술회의논문집; 한국전력공사 서울연수원; 17-18 Oct. 1997
• /
• pp.365-370
• /
• 1997

In this paper we suggest a development of surface defect inspection algorithms for cold mill strip using tree structure. The defects which exist in a surface of cold mill strip have a scattering or singular distribution. This paper consists of preprocessing, feature extraction and defect classification. By preprocessing, the binarized defect image is achieved. In this procedure, Top-hit transform, adaptive thresholding, thinning and noise rejection are used. Especially, Top-hit transform using local min/max operation diminishes the effect of bad lighting. In feature extraction, geometric, moment, co-occurrence matrix, histogram-ratio features are calculated. The histogram-ratio feature is taken from the gray-level image. For the defect classification, we suggest a tree structure of which nodes are multilayer neural network clasifiers. The proposed algorithm reduced error rate comparing to one stage structure.

• 제어로봇시스템학회논문지
• /
• 제17권5호
• /
• pp.436-443
• /
• 2011

Recognition of structures in urban environments is a fundamental ability for unmanned ground vehicles. In this paper we propose the geometrical featured voxel which has not only 3-D coordinates but also the type of geometrical properties of point cloud. Instead of dealing with a huge amount of point cloud collected by range sensors in urban, the proposed voxel can efficiently represent and save 3-D urban structures without loss of geometrical properties. We also provide an urban structure classification algorithm by using the proposed voxel and machine learning techniques. The proposed method enables to recognize urban environments around unmanned ground vehicles quickly. In order to evaluate an ability of the proposed map representation and the urban structure classification algorithm, our vehicle equipped with the sensor system collected range data and pose data in campus and experimental results have been shown in this paper.

• Journal of Information Processing Systems
• /
• 제17권4호
• /
• pp.787-800
• /
• 2021

Three-dimensional (3D) object classification tasks using point clouds are widely used in 3D modeling, face recognition, and robotic missions. However, processing raw point clouds directly is problematic for a traditional convolutional network due to the irregular data format of point clouds. This paper proposes a pointwise convolution neural network (CNN) structure that can process point cloud data directly without preprocessing. First, a 2D convolutional layer is introduced to percept coordinate information of each point. Then, multiple 2D convolutional layers and a global max pooling layer are applied to extract global features. Finally, based on the extracted features, fully connected layers predict the class labels of objects. We evaluated the proposed pointwise CNN structure on the ModelNet10 dataset. The proposed structure obtained higher accuracy compared to the existing methods. Experiments using the ModelNet10 dataset also prove that the difference in the point number of point clouds does not significantly influence on the proposed pointwise CNN structure.

• 한국도서관정보학회지
• /
• 제33권1호
• /
• pp.1-13
• /
• 2002

이 글에서는 새로이 설계된 국제백진분류법의 주류와 9개 보조표를 포함한 일반적인 개요와 특징에 대해 구체적으로 소개하였다.