• Journal of Korea Multimedia Society
• /
• v.21 no.12
• /
• pp.1425-1430
• /
• 2018

In this paper, we propose a CNN based deep learning algorithm for semantic segmentation of images. In order to improve the accuracy of semantic segmentation, we combined pixel level object classification and image level object classification. The image level object classification is used to accurately detect the characteristics of an image, and the pixel level object classification is used to indicate which object area is included in each pixel. The proposed network structure consists of three parts in total. A part for extracting the features of the image, a part for outputting the final result in the resolution size of the original image, and a part for performing the image level object classification. Loss functions exist for image level and pixel level classification, respectively. Image-level object classification uses KL-Divergence and pixel level object classification uses cross-entropy. In addition, it combines the layer of the resolution of the network extracting the features and the network of the resolution to secure the position information of the lost feature and the information of the boundary of the object due to the pooling operation.

• Journal of the Korean Society for information Management
• /
• v.40 no.4
• /
• pp.147-165
• /
• 2023

New technologies representing the Fourth Industrial Revolution are already being realized in library services. There is not, however, active research on measures to increase work efficiency by introducing a new technology in the work of "classification" that is part of the traditional librarian jobs they should continue in the future. The Dewey Decimal Classification (DDC) has not issued a print version since 2018. This study analyzes cases of WebDewey, Classification Web, and UDC Online. The functions required for the development of the Korean Decimal Classification (KDC) web version were derived, and the final functions suitable for the development of the KDC web version were proposed through AHP analysis.

• The Journal of Information Systems
• /
• v.6 no.1
• /
• pp.181-221
• /
• 1997

In order to provide effective information services in a province, we should first select vendors who enable to meet end-users' needs and develop information services for the sake of end-users. Cases, policies, technological and legislative issues in information services have been researched well. But no research has been done on potential information services in the future and their classification. In this study, based on literature survey, future information services are gathered, described, and classified with respect to the needs of end-users, and finally a framework for the classification of information services is developed. This framework can be used as a criterion to select, with a priority, information services to be provided in province through the information super highway. The framework will contribute to accomplishing the effective use of information resources in the province, and eventually balancing the level of information utilization between provinces.

• Journal of Information Processing Systems
• /
• v.9 no.1
• /
• 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.

• Journal of the Korean Society for information Management
• /
• v.33 no.2
• /
• pp.33-59
• /
• 2016

This study examined the factors affecting the performance of automatic classification for the domestic conference papers based on machine learning techniques. In particular, In view of the classification performance that assigning automatically the class labels to the papers in Proceedings of the Conference of Korean Society for Information Management using Rocchio algorithm, I investigated the characteristics of the key factors (classifier formation methods, training set size, weighting schemes, label assigning methods) through the diversified experiments. Consequently, It is more effective that apply proper parameters (${\beta}$, ${\lambda}$) and training set size (more than 5 years) according to the classification environments and properties of the document set. and If the performance is equivalent, I discovered that the use of the more simple methods (single weighting schemes) is very efficient. Also, because the classification of domestic papers is corresponding with multi-label classification which assigning more than one label to an article, it is necessary to develop the optimum classification model based on the characteristics of the key factors in consideration of this environment.

• Journal of the Korean Society for Library and Information Science
• /
• v.55 no.2
• /
• pp.25-50
• /
• 2021

General-purpose classification scheme encompasses all subject areas, While the whole classification scheme is constructed by library studies experts, structure and preparation of each specific subject area's classification should be referenced to that specific subject. In order for the whole system to be practical and useful classification scheme, not just a simple collection of each subject area's scheme, it is necessary to set the rule for properly distributing the amount of classification items, and the collections assigned to these items. The rule to set the distribution of items based on the amount of document collections is called 'literary warrant'. This study examines actual status of assignment of each classification items to information resources, as a result of application of Korean Decimal Classification, and then suggests a way to improve these practices.

• IEIE Transactions on Smart Processing and Computing
• /
• v.3 no.5
• /
• pp.319-324
• /
• 2014

Web applications make life more convenient. Many web applications have several kinds of user input (e.g. personal information, a user's comment of commercial goods, etc.) for the activities. On the other hand, there are a range of vulnerabilities in the input functions of Web applications. Malicious actions can be attempted using the free accessibility of many web applications. Attacks by the exploitation of these input vulnerabilities can be achieved by injecting malicious web code; it enables one to perform a variety of illegal actions, such as SQL Injection Attacks (SQLIAs) and Cross Site Scripting (XSS). These actions come down to theft, replacing personal information, or phishing. The existing solutions use a parser for the code, are limited to fixed and very small patterns, and are difficult to adapt to variations. A machine learning method can give leverage to cover a far broader range of malicious web code and is easy to adapt to variations and changes. Therefore, this paper suggests the adaptable classification of malicious web code by machine learning approaches for detecting the exploitation user inputs. The approach usually identifies the "looks-like malicious" code for real malicious code. More detailed classification using sequence information is also introduced. The precision for the "looks-like malicious code" is 99% and for the precise classification with sequence is 90%.

• Journal of Information Management
• /
• v.41 no.3
• /
• pp.1-26
• /
• 2010

The purpose of this study is to compare and analyze the print form of UDC(Universal Decimal Classification) standard edition which was published by British Standards Institution in 2005 to Korean edition which was published by Korea Scientific & Technological Information Center in 1973, and to suggest the appropriate revision directions of future Korean edition. This study suggests that the future Korean edition should be revised based on the Master Reference File and should be a print edition which is composed of systematic tables and alphabetical index from the standard edition. In addition, the future Korean edition needs to strengthen international universality and to extend synthetic method using its auxiliary tables.

• Journal of the Korean BIBLIA Society for library and Information Science
• /
• v.10 no.1
• /
• pp.243-268
• /
• 1999

The purpose of this study is to develop the classification scheme in subject-based directory search engine for educational research information on the web. Five classification systems. Yahoo Korea, Argus Clearinghouse, DDC, ERIC thesaurus and KEDI thesaurus were measured in terms of coverage of subject fields, system logic, accuracy of terminology and efficiency of searching. For the design of Classification Scheme, this study considered the content of subject areas, features of information resources and efficiency based on users. Finally, the Classification Scheme was established in terms of 16 main divisions and 47 sub-divisions in educational research information.

• Journal of Information Processing Systems
• /
• v.11 no.3
• /
• pp.421-437
• /
• 2015

This paper aims to present a supervised classification algorithm based on data fusion for the segmentation of the textured images. The feature extraction method we used is based on discrete wavelet transform (DWT). In the segmentation stage, the estimated feature vector of each pixel is sent to the support vector machine (SVM) classifier for initial labeling. To obtain a more accurate segmentation result, two strategies based on information fusion were used. We first integrated decision-level fusion strategies by combining decisions made by the SVM classifier within a sliding window. In the second strategy, the fuzzy set theory and rules based on probability theory were used to combine the scores obtained by SVM over a sliding window. Finally, the performance of the proposed segmentation algorithm was demonstrated on a variety of synthetic and real images and showed that the proposed data fusion method improved the classification accuracy compared to applying a SVM classifier. The results revealed that the overall accuracies of SVM classification of textured images is 88%, while our fusion methodology obtained an accuracy of up to 96%, depending on the size of the data base.