• 대한원격탐사학회지
• /
• 제27권3호
• /
• pp.315-328
• /
• 2011

Landsat data incorporated with additional bands-normalized difference vegetation index (NDVI) and band ratios were used to assess the extent and rate of deforestation in the Gunung Mutis Nature Reserve (GMNR), a mountainous tropical forest in Eastern of Indonesia. Hybrid classification was chosen as the classification approach. In this approach, the unsupervised classification-iterative self-organizing data analysis (ISODATA) was used to create signature files and training data set. A statistical separability measurement-transformed divergence (TD) was used to identify the combination of bands that showed the highest distinction between the land cover classes in training data set. Supervised classification-maximum likelihood classification (MLC) was performed using selected bands and the training data set. Post-classification smoothing and accuracy assessment were applied to classified image. Post-classification comparison was used to assess the extent of deforestation, of which the rate of deforestation was calculated by the formula suggested by Food Agriculture Organization (FAO). The results of two periods of deforestation assessment showed that the extent of deforestation during 1989-1999 was 720.72 ha, 0.80% of annual rate of deforestation, and its extent of deforestation during 1999-2009 was 1,059.12 ha, 1.31% of annual rate of deforestation. Such results are important for the GMNR authority to establish strategies, plans and actions for combating deforestation.

• Journal of Biosystems Engineering
• /
• 제38권4호
• /
• pp.264-269
• /
• 2013

Purpose: This study was carried out to develop a classification index and grade levels to rate agricultural heaters for energy efficiency classification. Methods: The classification index was developed mainly by taking simplicity of calculation and easy access to relevant data into consideration. The grade levels were developed on the basis of a 5-grade classification system in which graded heaters are to be normally distributed over the grades. The value of each grade level were determined in terms of the classification index values calculated using the published performance data of agricultural heaters tested at the FACT in Korea over the past 12 years. Results: The thermal efficiency of agricultural heaters based on the enthalpy method was proposed as a reasonable classification index. The grade levels were proposed in equation form for three types of agricultural heaters: fossil fuel heaters, wood pellet heaters and wood pellet boilers. A reasonable energy efficiency classification of agricultural heaters could be performed using the proposed classification index and grade levels. Conclusions: It is expected that energy saving programs will be extended to agricultural machines in the near future. The classification index and grade levels to rate agricultural heaters for energy efficiency classification were developed and proposed for such near future to come.

• Journal of Electrical Engineering and Technology
• /
• 제1권2호
• /
• pp.257-262
• /
• 2006

Insulation failure in an electrical utility depends on the continuous stress imposed upon it. Monitoring of the insulation condition is a significant issue for safe operation of the electrical power system. In this paper, comparison of recognition rate variable classification scheme of PD (partial discharge) sources that occur within an electrical utility are studied. To acquire PD data, five defective models are made, that is, air discharge, void discharge and three types of treeinging discharge. Furthermore, these statistical distributions are applied to classify PD sources as the input data for the classification tools. ANFIS shows the highest rate, the value of which is 99% and PCA-LDA and ANFIS are superior to BP in regards to other matters.

• Journal of Information Processing Systems
• /
• 제9권1호
• /
• pp.31-40
• /
• 2013

In this paper, a novel method is proposed to build an ensemble of classifiers by using a feature selection schema. The feature selection schema identifies the best feature sets that affect the arrhythmia classification. Firstly, a number of feature subsets are extracted by applying the feature selection schema to the original dataset. Then classification models are built by using the each feature subset. Finally, we combine the classification models by adopting a voting approach to form a classification ensemble. The voting approach in our method involves both classification error rate and feature selection rate to calculate the score of the each classifier in the ensemble. In our method, the feature selection rate depends on the extracting order of the feature subsets. In the experiment, we applied our method to arrhythmia dataset and generated three top disjointed feature sets. We then built three classifiers based on the top-three feature subsets and formed the classifier ensemble by using the voting approach. Our method can improve the classification accuracy in high dimensional dataset. The performance of each classifier and the performance of their ensemble were higher than the performance of the classifier that was based on whole feature space of the dataset. The classification performance was improved and a more stable classification model could be constructed with the proposed approach.

• 전자공학회논문지CI
• /
• 제48권6호
• /
• pp.35-46
• /
• 2011

본 논문에서는 피셔 선형 분리(FLD, Fisher's Linear Discriminant) 기반의 단계적 분류를 이용한 감성 인식 기법을 제안한다. 제안하는 기법은 2종 이상의 감성에 대한 다중 클래스 분류 문제에 대하여, 이진 분류 모델의 연속적인 결합을 통해 단계적 분류 모델을 구성함으로써 복잡도 높은 특징 공간상의 다수의 감성 클래스에 대한 분류 성능을 향상시킨다. 이를 위하여, 각 계층 단계의 학습에서는 감성 클래스들로 이루어진 두 개의 클래스 그룹에 따라 피셔 선형분리 공간을 구성하며, 구성된 공간상에서 Adaboost 방식을 이용하여 이진 분류 모델을 학습하여 생성한다. 각 계층 단계의 학습 과정은 모든 감성 클래스가 구분이 완료되는 시점까지 반복 수행된다. 본 논문에서는 MIT 생체 신호 프로파일을 이용하여 제안하는 기법을 실험하였다. 실험 결과, 8종의 감성에 대한 분류 실험을 통해 약 72%의 분류 성능을 확인하였고, 특정 3종의 감성에 대한 분류 실험을 통해 약 93% 분류 성능을 확인하였다.

• Journal of the Korean Data and Information Science Society
• /
• 제24권1호
• /
• pp.189-200
• /
• 2013

In this paper, it will be assumed that there are two distinct populations which are multivariate normal with equal covariance matrix. We also assume that the two populations are equally likely and the costs of misclassification are equal. The classification rule depends on the situation whether the training samples include missing values or not. We consider the conditional bootstrap confidence intervals for classification error rate when a block of observation is missing.

• 산업경영시스템학회지
• /
• 제41권2호
• /
• pp.56-64
• /
• 2018

In recent years, imbalanced data is one of the most important and frequent issue for quality control in industrial field. As an example, defect rate has been drastically reduced thanks to highly developed technology and quality management, so that only few defective data can be obtained from production process. Therefore, quality classification should be performed under the condition that one class (defective dataset) is even smaller than the other class (good dataset). However, traditional multi-class classification methods are not appropriate to deal with such an imbalanced dataset, since they classify data from the difference between one class and the others that can hardly be found in imbalanced datasets. Thus, one-class classification that thoroughly learns patterns of target class is more suitable for imbalanced dataset since it only focuses on data in a target class. So far, several one-class classification methods such as one-class support vector machine, neural network and decision tree there have been suggested. One-class support vector machine and neural network can guarantee good classification rate, and decision tree can provide a set of rules that can be clearly interpreted. However, the classifiers obtained from the former two methods consist of complex mathematical functions and cannot be easily understood by users. In case of decision tree, the criterion for rule generation is ambiguous. Therefore, as an alternative, a new one-class classifier using hyper-rectangles was proposed, which performs precise classification compared to other methods and generates rules clearly understood by users as well. In this paper, we suggest an approach for improving the limitations of those previous one-class classification algorithms. Specifically, the suggested approach produces more improved one-class classifier using hyper-rectangles generated by using Gaussian function. The performance of the suggested algorithm is verified by a numerical experiment, which uses several datasets in UCI machine learning repository.

• 한국산업보건학회지
• /
• 제30권3호
• /
• pp.280-291
• /
• 2020

Objectives: Hazard classification is a controversial issue in the new MSDS system in which chemical companies have to prepare and submit MSDS for chemicals that they manufacture or import to the competent authorities according to the amended Occupational Safety and Health Act. The aim of this study is to suggest how to apply and manage harmonized hazard classification criteria and results by investigating current hazard classification systems and trends. Methods: The domestic issues about different hazard classification criteria and results were investigated by reviewing the literature and business outcomes regarding KOSHA. We also checked official and unofficial reports from the UN to understand international discussion about the topic. Chemical hazard classification results from agencies providing chemical information were analyzed to compare a harmonized rate between classifications. Furthermore, a field survey of a few chemical companies was conducted. Results: Under the related competent authorities, an integrated standard proposal was developed to harmonize the domestic hazard classification criteria. Although harmonized chemical information is strongly needed, we recognized the uncertainty and difficulty of harmonized hazard classification from the UN global list project review. In practice the harmonization rate of the classification was generally low between the classification in KOSHA, MoE, and EU CLP. Among hazard classes, health hazards largely led the disharmony. The field survey revealed a change of perception that the main body of chemical information production is manufacturers. Approaches and solutions about hazard classification issues differed depending on business size, types of chemical handling, and other factors. Conclusions: We proposed reasonable ways by time and step to apply hazard classification in the new MSDS system. Chemical manufacturers should make and offer chemical information including responsible hazard classifications. The government should primarily accept these classifications, evaluate them by priority, and support or supervise workplaces in order to communicate reliable chemical information.

• Communications for Statistical Applications and Methods
• /
• 제14권2호
• /
• pp.377-388
• /
• 2007

As one of multi-class classification methods, ECOC (Error Correcting Output Coding) method is known to have low classification error rate. This paper aims at suggesting effective multi-class classification method (1) by comparing various encoding methods and decoding methods in ECOC method and (2) by comparing ECOC method and direct classification method. Both SVM (Support Vector Machine) and logistic regression model were used as binary classifiers in comparison.

• 한국융합학회논문지
• /
• 제5권1호
• /
• pp.35-41
• /
• 2014

An automatic speech recognition system is one of the popular research problems. There are many research groups working in this field for different language including Japanese. Japanese vowel recognition is one of important parts in the Japanese speech recognition system. The vowel classification system with the Mamdani fuzzy inference system was developed in this research. We tested our system on the blind test data set collected from one male native Japanese speaker and four male non-native Japanese speakers. All subjects in the blind test data set were not the same subjects in the training data set. We found out that the classification rate from the training data set is 95.0 %. In the speaker-independent experiments, the classification rate from the native speaker is around 70.0 %, whereas that from the non-native speakers is around 80.5 %.