• Proceedings of the KIEE Conference
• /
• 1992.07a
• /
• pp.172-175
• /
• 1992

This paper proposes the methods to construct the tree-structured database and analyze the distribution system network. In order to cope with an extensive amount of data and the frequent breaker switching operations in distribution systems, the database for system configuration is constructed using binary trees. Once the tree-structured database has been built, the system tracing of distribution network can be rapidly performed. This remarkably enhances the efficiency of data search and easily adapts to system changes due to switching operations. The computation method of fast power flow using tree search strategies is presented. The methods in the paper may be available in the field of distribution system operation.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.23 no.11
• /
• pp.44-51
• /
• 2009

A variety of Urban Rail Transit (URT) systems have been operating and they have different technology bases, causing a lot of difficulties in taking measures against trouble, training, upgrading, interoperability and so on. As such, a standardization project has been carried out to solve the problems by setting up the national standards for URT systems. A common database was built to provide the integrated engineering environment to the community of URT project. This paper discusses the design of the database and how it can be utilized in the successful promotion of the project. The products of the projects are stored into the database with traceability management to be referred to by other new URT projects for reusing and sharing the acquired knowledge through cross organizations.

• Electronics and Telecommunications Trends
• /
• v.38 no.6
• /
• pp.22-30
• /
• 2023

Recently, artificial intelligence has been in the spotlight across various fields. Artificial intelligence uses massive amounts of data to train machine learning models and performs various tasks using the trained models. For model training, large, high-quality data sets are essential, and database systems have provided such data. Driven by advances in artificial intelligence, attempts are being made to improve various components of database systems using artificial intelligence. Replacing traditional complex algorithm-based database components with their artificial-intelligence-based counterparts can lead to substantial savings of resources and computation time, thereby improving the system performance and efficiency. We analyze trends in the application of artificial intelligence to database systems.

• Journal of Welding and Joining
• /
• v.25 no.6
• /
• pp.84-95
• /
• 2007

The International System for Education and Qualification of Welding Personnel has been implemented based on the harmonized European System for education and qualification of welding personnel. This paper gives an overview of the International System focusing on the training guidelines and the quality assurance system developed. Systems for harmonization of Certification of Welding Personnel and for supporting companies using welding to implement ISO 3834 have been developed by EWF and are presently being transferred to IIW in line with the EWF/IIW agreement established in 2000.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.5
• /
• pp.1755-1777
• /
• 2022

The development of wireless communication technology has led to the underutilization of radio spectra. To address this limitation, an intelligent cognitive radio network was developed. Specific emitter identification (SEI) is a key technology in this network. However, in realistic non-cooperative scenarios, the system may detect signal classes beyond those in the training database, and only a few labeled signal samples are available for network training, both of which deteriorate identification performance. To overcome these challenges, a meta-learning-based open-set identification system is proposed for SEI. First, the received signals were pre-processed using bi-spectral analysis and a Radon transform to obtain signal representation vectors, which were then fed into an open-set SEI network. This network consisted of a deep feature extractor and an intrinsic feature memorizer that can detect signals of unknown classes and classify signals of different known classes. The training loss functions and the procedures of the open-set SEI network were then designed for parameter optimization. Considering the few-shot problems of open-set SEI, meta-training loss functions and meta-training procedures that require only a few labeled signal samples were further developed for open-set SEI network training. The experimental results demonstrate that this approach outperforms other state-of-the-art SEI methods in open-set scenarios. In addition, excellent open-set SEI performance was achieved using at least 50 training signal samples, and effective operation in low signal-to-noise ratio (SNR) environments was demonstrated.

• The Journal of Information Technology and Database
• /
• v.2 no.2
• /
• pp.71-85
• /
• 1995

Many research results conducted by neural network researchers have claimed that the classification accuracy of neural networks is superior to, or at least equal to that of conventional methods. However, in series of neural network classifications, it was found that the classification accuracy strongly depends on the characteristics of training data set. Even though there are many research reports that the classification accuracy of neural networks can be different, depending on the composition and architecture of the networks, training algorithm, and test data set, very few research addressed the problem of classification accuracy when the basic assumption of data monotonicity is violated, In this research, development project of automated credit evaluation system is described. The finding was that arrangement of training data is critical to successful implementation of neural training to maintain monotonicity of the data set, for enhancing classification accuracy of neural networks.

• The Journal of Information Technology and Database
• /
• v.8 no.1
• /
• pp.95-104
• /
• 2001

In the text classification domain, labeling the training documents is an expensive process because it requires human expertise and is a tedious, time-consuming task. Therefore, it is important to reduce the manual labeling of training documents while improving the text classifier. Selective sampling, a form of active learning, reduces the number of training documents that needs to be labeled by examining the unlabeled documents and selecting the most informative ones for manual labeling. We apply this methodology to Naive Bayes, a text classifier renowned as a successful method in text classification. One of the most important issues in selective sampling is to determine the criterion when selecting the training documents from the large pool of unlabeled documents. In this paper, we propose two measures that would determine this criterion : the Mean Absolute Deviation (MAD) and the entropy measure. The experimental results, using Renters 21578 corpus, show that this proposed learning method improves Naive Bayes text classifier more than the existing ones.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.34 no.3C
• /
• pp.257-267
• /
• 2009

This paper presents a training method for neural networks and the employment of MSE (mean scare error) values as the basis of a decision regarding the identity claim of a speaker in a recurrent neural networks based speaker verification system. Recurrent neural networks (RNNs) are employed to capture temporally dynamic characteristics of speech signal. In the process of supervised learning for RNNs, target outputs are automatically generated and the generated target outputs are made to represent the temporal variation of input speech sounds. To increase the capability of discriminating between the true speaker and an impostor, a discriminative training method for RNNs is presented. This paper shows the use and the effectiveness of the MSE value, which is obtained from the Euclidean distance between the target outputs and the outputs of networks for test speech sounds of a speaker, as the basis of speaker verification. In terms of equal error rates, results of experiments, which have been performed using the Korean speech database, show that the proposed speaker verification system exhibits better performance than a conventional hidden Markov model based speaker verification system.

• The Journal of Information Systems
• /
• v.1
• /
• pp.149-178
• /
• 1992

The field of Artificial Intelligence (AI) is growing, and many firms are investing in expert system, one of AI's subfields. An expert system is defined as a computer program designed to replicate some aspect of the decision making of one or more experts and to be used by nonexperts. The kernel of an expert system is the knowledge base, which consists of the facts and rules that represent the expert's knowledge. Firms need expert systems for training employees to provide competitive advantage. This paper describes the model of an instructional expert training system which interfaces to external programs, such as an ASCII file, a work-sheet program, and a database program. A model for such an expert training system, and its prototype have been developed to demonstrate its functionality. A modular knowledge base has been developed and implemented in support of this study. The modularized knowledge base offers the user an easy and quick maintenance of facts and rules, which are frequently required to change in future.

• Journal of the Korea Computer Graphics Society
• /
• v.26 no.3
• /
• pp.111-121
• /
• 2020

Realistic training contents utilizing intensive immersion of virtual reality are being used in various fields such as industry, education, and medical care. High-risk, high-cost education training, in particular, is difficult to conduct in reality, but it can be applied with the latest virtual reality technology that enhances educational effectiveness by efficiently and safely experiencing it in an environment similar to reality. This study introduces a management system that systematically manages realistic virtual training contents and visualizes training results in schematic pictures based on defined evaluation elements. The management system can store the information generated from the content in the database and manage the training records of each trainee in a practical way. In addition, a content-based scenario can be created in multiple scenarios by setting training goals, number of participants, and methods for applying evaluation elements. This paper describes the management system's production method and the results based on the virtual reality training content as an application example.