• Journal of the Korean Data and Information Science Society
• /
• 제17권2호
• /
• pp.311-324
• /
• 2006

The Support Vector Machine(SVM) is very functional and efficient classification method to any other classification analysis method. However, its optimal extension to more than two classes is not obvious. In this paper several multi-category SVM methods are introduced and compared using simulation and real data sets. Also comparison with traditional multi-category classification and SVM based methods is performed.

• 한국경영과학회:학술대회논문집
• /
• 한국경영과학회 2001년도 추계학술대회 논문집
• /
• pp.265-268
• /
• 2001

As growing the electronic commerce there are significant changes in the products/services catalog into the on-line environment. Advertent of e-catalog business opportunity for their own product/services enlarges the market volume and there are diverse methods for the presentation of its product/services. A method for the presentation of product/services features one uses identification and classification system. This study constructs a classification system and database layout for the product/services classification system as a part of e-catalog system. We consider the specific method for the GDAS-based dataset and UNSPSC classification system in the distribution industry.

• Communications for Statistical Applications and Methods
• /
• 제6권2호
• /
• pp.383-395
• /
• 1999

This study is concerned with the evaluation of predictive ability of classification models with ordered multiple categories. If categories can be ordered or ranked the spread of misclassification should be considered to evaluate the performance of the classification models using loss rate since the apparent error rate can not measure the spread of misclassification. Since loss rate is known to underestimate the true loss rate the bootstrap method were used to estimate the true loss rate. thus this study suggests the method to evaluate the predictive power of the classification models using loss rate and the bootstrap estimate of the true loss rate.

• 한국컴퓨터정보학회:학술대회논문집
• /
• 한국컴퓨터정보학회 2019년도 제59차 동계학술대회논문집 27권1호
• /
• pp.125-126
• /
• 2019

In this paper, we propose an improved kNN classification method. Through improved the mothed and normalizing the data, the purpose of improving the accuracy is achieved. Then we compared the three classification algorithms and the improved algorithm by experimental data.

• 한국측량학회지
• /
• 제36권3호
• /
• pp.135-152
• /
• 2018

The purpose of this study is to propose an optimal fusion method of aerial multi - sensor data to improve the accuracy of land cover classification. Recently, in the fields of environmental impact assessment and land monitoring, high-resolution image data has been acquired for many regions for quantitative land management using aerial multi-sensor, but most of them are used only for the purpose of the project. Hyperspectral sensor data, which is mainly used for land cover classification, has the advantage of high classification accuracy, but it is difficult to classify the accurate land cover state because only the visible and near infrared wavelengths are acquired and of low spatial resolution. Therefore, there is a need for research that can improve the accuracy of land cover classification by fusing hyperspectral sensor data with multispectral sensor and aerial laser sensor data. As a fusion method of aerial multisensor, we proposed a pixel ratio adjustment method, a band accumulation method, and a spectral graph adjustment method. Fusion parameters such as fusion rate, band accumulation, spectral graph expansion ratio were selected according to the fusion method, and the fusion data generation and degree of land cover classification accuracy were calculated by applying incremental changes to the fusion variables. Optimal fusion variables for hyperspectral data, multispectral data and aerial laser data were derived by considering the correlation between land cover classification accuracy and fusion variables.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제37권5호
• /
• pp.378-385
• /
• 2010

이메일 사용의 증가로 수신 메일을 효율적이면서 정확하게 분류할 필요성이 점차 늘고 있다. 현재의 이메일 분류는 SVM, 베이지안 분류자, 규칙 기반 분류자 등을 이용하여 스팸 메일을 필터링하기 위한 이원 분류가 주를 이루고 있다. 그러나 이러한 지도 학습 방법들은 적합한 이메일을 인식하기 위하여서 사용자가 규칙이나 색인어 목록을 작성해야 한다. 비지도 학습 방법으로 군집을 이용한 다원 분류 방법은 메일의 분류 주제를 설정해주어야 한다. 본 논문에서는 비음수 행렬 분해(NMF, Non-negative Matrix Factorization)를 기반으로 한 자동 분류 주제 생성 방법과, 동적 분류 체계(DCH, Dynamic Category Hierarchy) 방법을 이용한 분류 주제 내에 이메일을 재구성하는 방법을 결합한 새로운 이메일 다원 분류 방법을 제안한다. 이 방법은 수신되는 이메일을 자동으로 다원 분류하여 대량의 메일을 효율적으로 관리할 수 있으며, 사용자가 분류 결과를 만족하지 못하면 분류 주제 내의 이메일을 동적으로 재구성하여 분류의 정확률을 높인다.

• 한국멀티미디어학회논문지
• /
• 제16권7호
• /
• pp.795-801
• /
• 2013

서포트 벡터 머신은 뛰어난 일반화 성능에 힘입어 다양한 분야에서 의사 결정 나무나 인공 신경망에 비해 더 좋은 분류 성능을 보이고 있기 때문에 최근 널리 사용되고 있다. 서포트 벡터 머신은 기본적으로 이진 분류 문제를 위하여 설계되었기 때문에 서포트 벡터 머신을 다중 클래스 문제에 적용하기 위한 방법으로 다중 이진 분류기의 출력 결과를 이용하는 출력 코딩 방법이 주로 사용되고 있다. 그러나 출력 코딩 기반 서포트 벡터 머신에 사용된 기존 특징 선택 기법은 각 분류기의 정확도 향상을 위한 특징이 아니라 전체 분류 정확도 향상을 위한 특징을 선택하고 있다. 본 논문에서는 출력 코딩 기반 서포트 벡터 머신의 각 이진 분류기의 분류 정확도를 최대화하는 특징을 각각 선택하여 사용함으로써, 전체 분류 정확도를 향상시키는 특징 선택 기법을 제안한다. 실험 결과는 제안 기법이 기존 특징 선택 기법에 비하여 통계적으로 유의미한 분류 정확도 향상이 있었음을 보여주었다.

• 정보처리학회논문지B
• /
• 제11B권2호
• /
• pp.159-168
• /
• 2004

본 논문에서는 위성영상의 분류에 대한 성능 개선을 위하여 ISODATA 클러스터링, 퍼지 C-Means 알고리즘, 베이시안 최대우도 분류기법을 통합한 하이브리드 분류기법을 제안하였다. 본 연구에서는 분석자에 의하여 분류항목별 학습 데이터를 선정한 후 이를 ISODATA 클러스터링을 이용하여 각각의 분류항목별로 분광특징에 따라 학습 데이터를 세분화하여 새로운 학습 데이터를 선정하였다. 새롭게 선정된 학습 데이터를 이용하여 퍼지 C-Means 알고리즘을 이용하여 분류를 수행하고 그 결과를 베이시안 최대우도 분류기의 사전확률로 적용하여 분류를 수행하였다. 그 결과 분석자가 선정한 분류항목별 훈련데이터의 분광적인 특징에 관계없이 분류를 수행할 수 있었으며 위성영상의 분류의 성능을 개선할 수 있었다. 제안된 기법은 Landsat TM 위성영상을 이용하여 그 적용성을 시험하였다.

• Current Optics and Photonics
• /
• 제5권3호
• /
• pp.270-277
• /
• 2021

The adaptive sparse representation (ASR) can effectively combine the structure information of a sample dictionary and the sparsity of coding coefficients. This algorithm can effectively consider the correlation between training samples and convert between sparse representation-based classifier (SRC) and collaborative representation classification (CRC) under different training samples. Unlike SRC and CRC which use fixed norm constraints, ASR can adaptively adjust the constraints based on the correlation between different training samples, seeking a balance between l₁ and l₂ norm, greatly strengthening the robustness and adaptability of the classification algorithm. The correlation coefficients (CC) can better identify the pixels with strong correlation. Therefore, this article proposes a hyperspectral image classification method called correlation coefficients and adaptive sparse representation (CCASR), based on ASR and CC. This method is divided into three steps. In the first step, we determine the pixel to be measured and calculate the CC value between the pixel to be tested and various training samples. Then we represent the pixel using ASR and calculate the reconstruction error corresponding to each category. Finally, the target pixels are classified according to the reconstruction error and the CC value. In this article, a new hyperspectral image classification method is proposed by fusing CC and ASR. The method in this paper is verified through two sets of experimental data. In the hyperspectral image (Indian Pines), the overall accuracy of CCASR has reached 0.9596. In the hyperspectral images taken by HIS-300, the classification results show that the classification accuracy of the proposed method achieves 0.9354, which is better than other commonly used methods.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제8권3호
• /
• pp.838-856
• /
• 2014

Enhanced network speed and the appearance of various applications have recently resulted in the rapid increase of Internet users and the explosive growth of network traffic. Under this circumstance, Internet users are eager to receive reliable and Quality of Service (QoS)-guaranteed services. To provide reliable network services, network managers need to perform control measures involving dropping or blocking each traffic type. To manage a traffic type, it is necessary to rapidly measure and correctly analyze Internet traffic as well as classify network traffic according to applications. Such traffic classification result provides basic information for ensuring service-specific QoS. Several traffic classification methodologies have been introduced; however, there has been no favorable method in achieving optimal performance in terms of accuracy, completeness, and applicability in a real network environment. In this paper, we propose a method to classify Internet traffic as the first step to provide stable network services. We integrate the existing methodologies to compensate their weaknesses and to improve the overall accuracy and completeness of the classification. We prioritize the existing methodologies, which complement each other, in our integrated classification system.