• Journal of the Korean Society for information Management
• /
• v.15 no.3
• /
• pp.45-71
• /
• 1998

There is increasing importance of a system to reorganize explosive expansion of internet information resources efficiently; therefore, an increasing concern about classification system as an instrument for facilitating an access to a specific subject and improving efficiency in information retrieval. Comparing the hierarchical structure and access methodology of internet-based classification system with those of library classification such as Dewey Decimal Classification through their structural aspects and retrival process, this paper proposes the proper classification system in internet environment.

• International Journal of Contents
• /
• v.13 no.2
• /
• pp.66-74
• /
• 2017

Patent classification is becoming more critical as patent filings have been increasing over the years. Despite comprehensive studies in the area, there remain several issues in classifying patents on IPC hierarchical levels. Not only structural complexity but also shortage of patents in the lower level of the hierarchy causes the decline in classification performance. Therefore, we propose a new method of classification based on different criteria that are categories defined by the domain's experts mentioned in trend analysis reports, i.e. Patent Landscape Report (PLR). Several experiments were conducted with the purpose of identifying type of features and weighting methods that lead to the best classification performance using Support Vector Machine (SVM). Two types of features (noun and noun phrases) and five different weighting schemes (TF-idf, TF-rf, TF-icf, TF-icf-based, and TF-idcef-based) were experimented on.

• International Journal of Computer Science & Network Security
• /
• v.21 no.6
• /
• pp.169-180
• /
• 2021

Since machine learning was invented, there have been many different machine learning-based algorithms, from shallow learning to deep learning models, that provide solutions to the classification tasks. But then it poses a problem in choosing a suitable classification algorithm that can improve the classification/detection efficiency for a certain network context. With that comes whether an algorithm provides good performance, why it works in some problems and not in others. In this paper, we present a data-centric analysis to provide a way for selecting a suitable classification algorithm. This data-centric approach is a new viewpoint in exploring relationships between classification performance and facts and figures of data sets.

• Journal of the Korean Society of Safety
• /
• v.20 no.2 s.70
• /
• pp.127-132
• /
• 2005

The purpose of this study is to compare representative posture classification schemes of OWAS, RULA and REBA in terms of correctness for postural load. The comparison was based on the evaluation results by the three methods for 224 working postures sampled from steel, electronics, automotive, and chemical industries. The results showed that OWAS and REBA generally underestimated postural stress than RULA irrespective of industry type, work performed and whether or not leg posture is balanced. While about $71\%\;and\;73\%$ of the 224 posture were evaluated with the action category/level 1 or 2 by OWAS and REBA respectively, about $60\%$ of the postures were classified into the action level of 3 or 4 by RULA. The coincidence rate of postural stress category between OWAS and RULA was just $33.5\%$, while the rate between RULA and REBA was $46.0\%$. It is concluded from the findings of this study and the previous research that compared to OWAS and REBA, RULA more precisely evaluates postural stress.

• Journal of Korea Society of Industrial Information Systems
• /
• v.12 no.4
• /
• pp.41-54
• /
• 2007

To make most out of Order Review/Release(ORR) models, they are to be analyzed and classified according to their prospective users' requirements. To this end, we discuss ORR functions and so-called "ORR paradox", and propose an ORR model classification scheme named "COMPACT(COMplexity-imPACT) Matrix". Under the scheme, the complexity and impact levels of each ORR model are rated one after another in order to position it across the matrix. We explore the process and present the results, insisting that a DSS should suggest ORR models to its users on the complexity-impact basis.

• Journal of Information Processing Systems
• /
• v.17 no.1
• /
• pp.178-190
• /
• 2021

Alzheimer's disease (AD) is an insidious and degenerative neurological disease. It is a new topic for AD patients to use magnetic resonance imaging (MRI) and computer technology and is gradually explored at present. Preprocessing and correlation analysis on MRI data are firstly made in this paper. Then kernel principal component analysis (KPCA) is used to extract features of brain gray matter images. Finally supervised classification schemes such as AdaBoost algorithm and support vector machine algorithm are used to classify the above features. Experimental results by means of AD program Alzheimer's Disease Neuroimaging Initiative (ADNI) database which contains brain structural MRI (sMRI) of 116 AD patients, 116 patients with mild cognitive impairment, and 117 normal controls show that the proposed method can effectively assist the diagnosis and analysis of AD. Compared with principal component analysis (PCA) method, all classification results on KPCA are improved by 2%-6% among which the best result can reach 84%. It indicates that KPCA algorithm for feature extraction is more abundant and complete than PCA.

• The Journal of Society for e-Business Studies
• /
• v.12 no.2
• /
• pp.111-132
• /
• 2007

Developing and managing Web applications are more complex than ever because of their growing functionalities, advancing Web technologies, increasing demands for integration with legacy applications, and changing content and structure. All these factors call for a more inclusive and comprehensive Web application design method. In response, we propose a context-based Web application design methodology that is based on several classification schemes including a Webpage classification, which is useful for identifying the information delivery mechanism and its relevant Web technology; a link classification, which reflects the semantics of various associations between pages; and a software component classification, which is helpful for pinpointing the roles of various components in the course of design. The proposed methodology also incorporates a unique Web application model comprised of a set of information clusters called compendia, each of which consists of a theme, its contextual pages, links, and components. This view is useful for modular design as well as for management of ever-changing content and structure of a Web application. The proposed methodology brings together all the three classification schemes and the Web application model to arrive at a set of both semantically cohesive and syntactically loose-coupled design artifacts.

• Journal of Electrical Engineering and Technology
• /
• v.1 no.2
• /
• 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 Korea Multimedia Society
• /
• v.21 no.3
• /
• pp.391-399
• /
• 2018

In this paper, we construct and compare various guitar chord classification systems using perceptron neural network and convolutional neural network without pre-processing other than Fourier transform to identify the optimal chord classification system. Conventional guitar chord classification schemes use, for better feature extraction, computationally demanding pre-processing techniques such as stochastic analysis employing a hidden markov model or an acoustic data filtering and hence are burdensome for real-time chord classifications. For this reason, we construct various perceptron neural networks and convolutional neural networks that use only Fourier tranform for data pre-processing and compare them with dataset obtained by playing an electric guitar. According to our comparison, convolutional neural networks provide optimal performance considering both chord classification acurracy and fast processing time. In particular, convolutional neural networks exhibit robust performance even when only small fraction of low frequency components of the data are used.

• Journal of Electrical Engineering and Technology
• /
• v.12 no.6
• /
• pp.2089-2098
• /
• 2017

Microgrid is a convenient, reliable, and eco-friendly approach for the integration of Distributed Generation (DG) sources into the utility power systems. To date, AC microgrids have been the most common architecture, but DC microgrids are gaining an increasing interest owing to the provision of numerous benefits in comparison with AC ones. These benefits encompass higher reliability, power quality and transmission capacity, non-complex control as well as direct connection to some DG sources, loads and Energy Storage Systems (ESSs). In this paper, main challenges and available approaches for the protection of AC and DC microgrids are discussed. After description, analysis and classification of the existing schemes, some research directions including coordination between AC and DC protective devices as well as development of combined control and protection schemes for the realization of future hybrid AC/DC microgrids are pointed out.