• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.1
• /
• pp.364-380
• /
• 2016

The most popular approach in object classification is based on the bag of visual-words model, which has several fundamental problems that restricting the performance of this method, such as low time efficiency, the synonym and polysemy of visual words, and the lack of spatial information between visual words. In view of this, an object classification based on weakly supervised E2LSH and saliency map weighting is proposed. Firstly, E2LSH (Exact Euclidean Locality Sensitive Hashing) is employed to generate a group of weakly randomized visual dictionary by clustering SIFT features of the training dataset, and the selecting process of hash functions is effectively supervised inspired by the random forest ideas to reduce the randomcity of E2LSH. Secondly, graph-based visual saliency (GBVS) algorithm is applied to detect the saliency map of different images and weight the visual words according to the saliency prior. Finally, saliency map weighted visual language model is carried out to accomplish object classification. Experimental results datasets of Pascal 2007 and Caltech-256 indicate that the distinguishability of objects is effectively improved and our method is superior to the state-of-the-art object classification methods.

• Asia pacific journal of information systems
• /
• v.14 no.2
• /
• pp.115-130
• /
• 2004

This paper proposes how to build an expert profile database in KMS, which provides the information of expertise that each expert possesses in the organization. To manage tacit knowledge in a knowledge management system, recent researches in this field have shown that it is more applicable in many ways to provide expert search mechanisms in KMS to pinpoint experts in the organizations with searched expertise so that users can contact them for help. In this paper, we develop a framework to automate expert classification using a text categorization technique called Vector Space Model, through which an expert database composed of all the compiled profile information is built. This approach minimizes the maintenance cost of manual expert profiling while eliminating the possibility of incorrectness and obsolescence resulted from subjective manual processing. Also, we define the structure of expertise so that we can implement the expert classification framework to build an expert database in KMS. The developed prototype system, "Knowledge Portal for Researchers in Science and Technology," is introduced to show the applicability of the proposed framework.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.12
• /
• pp.6080-6096
• /
• 2019

Text classification is one of the fundamental techniques in natural language processing. Numerous studies are based on text classification, such as news subject classification, question answering system classification, and movie review classification. Traditional text classification methods are used to extract features and then classify them. However, traditional methods are too complex to operate, and their accuracy is not sufficiently high. Recently, convolutional neural network (CNN) based one-hot method has been proposed in text classification to solve this problem. In this paper, we propose an improved method using CNN based skip-gram method for Chinese text classification and it conducts in Sogou news corpus. Experimental results indicate that CNN with the skip-gram model performs more efficiently than CNN-based one-hot method.

• Journal of the Society of Disaster Information
• /
• v.12 no.1
• /
• pp.19-31
• /
• 2016

The purpose of this study was to establish the initial computerized management database which can be applied to a universal project management computer system for managing universal project management and operation. Database construction model presented in this paper suggested the model of organization, activity and operation of bridge construction(two abutment-three-span) based on the organization information classification system of the facility classification, functional component classification, work classification, resource classification. Database model established in this study are considered to be able to take advantage of a very systematic and scientific management for future universal project management and operations.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.14 no.10
• /
• pp.2365-2370
• /
• 2010

The method of cancer classification based on microarray could contribute to being accurate cancer classification by finding differently expressing gene pattern statistically according to a cancer type. Therefore, the process to select a closely related informative gene with a particular cancer classification to classify cancer using present microarray technology with effect is essential. In this paper, the system can detect marker genes to likely express the most differentially explaining the effects of cancer using ovarian cancer microarray data. And it compare and analyze a performance of classification of the proposed system with it of established microarray system using multi-perceptron neural network layer. Microarray data set including marker gene that are selected using ANOVA method represent the highest classification accuracy of 98.61%, which show that it improve classification performance than established microarray system.

• Journal of the Korean Society for Library and Information Science
• /
• v.14
• /
• pp.3-18
• /
• 1987

The factors which can help the library users trace the specific subject that she or he needs are most important, when they are not sure of what they need exactly in front of a classified catalogue. This study is about what the factors are and how the factors affect the inference of users' reasoning structure. Since the classified catalogues are reflected by the classification structure, naturally the logic in the classification system becomes the focus of the study. This study concludes the classification system which enables the library users to use their reasoning capabilities, viz. the classification system which can help the users trace the specific subject even as they are not sure of the exact subject they need has following factors in the system. 1. It should have the validity based on the facts in the components of the classification system. 2. It should be logically arranged when the components of the classification system are placed in due sequence. 3. The notation of the system should be based on mnemonics. The reason is that the indispensable factors in the formation of inference of human reasoning structure are: 1. the premises which are based on the facts and 2. the logical relationship between the premises and conclusions which are induced from the premises.

• Archives of design research
• /
• v.17 no.4
• /
• pp.79-88
• /
• 2004

This study is aimed to grasp the organization of Internet information resources and to infer the characteristics of resource search engines so that criteria may be established to classify and evaluate Internet information resources. In addition, the author has compared and analyzed interior design classification systems of directory sites of each subject that provide classification system based on the Internet, foreign sites to be used to search for information, and domestic information-specialized sites in order to set up models of interior design classification systems of directories of each Web subject. The systems have been analyzed against such four measures as comprehensiveness of the subject scope, logicality of classification systems, preciseness of subject terms, and effectiveness of searches. Information of interior designs is mixed with that of related fields, and so its information search and classification are not organized systematically. The author has analyzed such a problem so as to present models of search engine classification systems for interior design information classification after considering both academic and practical aspects.

• IE interfaces
• /
• v.24 no.3
• /
• pp.248-257
• /
• 2011

The amount of Meta-data to be managed increases with development of information technology. However, when trying to integrate and share product information of heterogeneous systems within or between companies, sharing of information is impossible if product information classification systems are different. Due to the situation mentioned above, engineers judge the product information classification system and maps corresponding Meta-data for document-based sharing. Judging exponentially increasing amount of data by engineers and sharing product information using documents create great amount of time delay and errors in data handling. Therefore, construction of a system for integrated management and interoperability between product information based on semantic information similar to engineer's judgment is required. This paper proposes a methodology and necessity of a system for interoperability of product information based on semantic web, and also designs a system to integrate heterogeneous systems with different product information using rule based reasoning. This paper also suggests a system base for interoperability and integration of product information between heterogeneous systems by integrating the product information classification system semantically.

• Journal of the Korean Society for information Management
• /
• v.22 no.4 s.58
• /
• pp.5-22
• /
• 2005

As the development of advertising industry and media the research about an advertisement get accomplished. As the result information resources called on the advertising materials are on an Increasing trend. However, it looks into the classification system In advertising field of KDC, the problems are as the follows : (1) the classification items are too incomplete, (2) the main class is badly arranged. The reason have no regard for the correlation with a science. So, it gives rise to confusion to the librarian and user. The purpose of the study is to present the improvement plan on the classification system in advertising field of KDC. In order to build the improvement plan, the four steps are utilized. The first step Is to investigate the characteristic of sciences on advertising and a type. The second one is to survey the current status of the library classification as KDC, NDC, DDC, and LCC. The third one is to analyse the classification system of library and web site on the advertising. The forth one is to grasp the problems on the classification system In advertising field of KDC.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.10
• /
• pp.4092-4107
• /
• 2015

We propose a background subtraction method for moving cameras based on trajectory classification, image segmentation and label inference. In the trajectory classification process, PCA-based outlier detection strategy is used to remove the outliers in the foreground trajectories. Combining optical flow trajectory with watershed algorithm, we propose a trajectory-controlled watershed segmentation algorithm which effectively improves the edge-preserving performance and prevents the over-smooth problem. Finally, label inference based on Markov Random field is conducted for labeling the unlabeled pixels. Experimental results on the motionseg database demonstrate the promising performance of the proposed approach compared with other competing methods.