• Information Systems Review
• /
• v.24 no.1
• /
• pp.105-123
• /
• 2022

Thanks to the remarkable success of Artificial Intelligence (A.I.) techniques, a new possibility for its application on the real-world problem has begun. One of the prominent applications is the bankruptcy prediction model as it is often used as a basic knowledge base for credit scoring models in the financial industry. As a result, there has been extensive research on how to improve the prediction accuracy of the model. However, despite its impressive performance, it is difficult to implement machine learning (ML)-based models due to its intrinsic trait of obscurity, especially when the field requires or values an explanation about the result obtained by the model. The financial domain is one of the areas where explanation matters to stakeholders such as domain experts and customers. In this paper, we propose a novel approach to incorporate financial domain knowledge into local rule generation to provide explanations for the bankruptcy prediction model at instance level. The result shows the proposed method successfully selects and classifies the extracted rules based on the feasibility and information they convey to the users.

• The KIPS Transactions:PartB
• /
• v.15B no.2
• /
• pp.113-122
• /
• 2008

While there are about 1 million color vision deficiencies in Korea, an assistive technology to digital contents of broadcasting and web for them remains scarce. In this study, we developed a generation method of the ICC profile to correct a graphic digital content adapted to various color perception characteristics of CVD by tuning the correction rules of the ICC profile by themselves. We tested the performance of the ICC profile to apply 10 Ishihara plates to the participants, 1 protanomaly, 1 protanomaly and deuteranomaly and 2 deuteranomaly. We used the color range information to build correction rules. Results of the test show that they passed Ishihara test by 97.5% success rate, compared to 20% success rate without it. The average time for them to spend to tune the customized ICC profile was about 13 minute without any diagnosis of specialist, any special instrument.

• Journal of Intelligence and Information Systems
• /
• v.10 no.2
• /
• pp.79-89
• /
• 2004

Since the amount of E-mail messages has increased , we need a new technique for efficient e-mail classification. E-mail classifications are grouped into two classes: binary classification, multi-classification. The current binary classification methods are mostly spm mail classification methods which are based on rule driven, bayesian, SVM, etc. The current multi- classification methods are based on clustering which groups e-mails by similarity. In this paper, we propose a novel method for e-mail classification. It combines the automatic category generation method based on the vector model and the dynamic category hierarchy construction method. This method can multi-classify e-mail automatically and manage a large amount of e-mail efficiently. In addition, this method increases the search accuracy by dynamic reclassification of e-mails.

• Environmental and Resource Economics Review
• /
• v.23 no.3
• /
• pp.497-513
• /
• 2014

Rate-of-return regulation where a regulator compensates the utilities based upon the cost incurred the regulated companies have the incentive to over-report cost level. However, in case of cost-based competition where a regulator knows the cost of each plant involved and induce the competition among them, one can encounter prisoner's dilemma situation in the short run where the regulated firms under-report cost level. For instance, in case of cost-based pool, a generator may have a strategic behavior to keep its registered variable cost higher than the actual level to maintain its operation rate and generation amounts higher. Eventually, however, such behavior decrease the profitability of a generator and discourage new entry jeopardizing required level of capacity reserves. This is a typical Prisoner's Dilemma situation. The power market operating rule should be revised so that generators' registered variable cost reflect actual level of variable cost.

• Journal of The Korean Association For Science Education
• /
• v.32 no.3
• /
• pp.524-531
• /
• 2012

Categorization is an important human function used to process different stimuli. It is also one of the most important factors affecting measurement of a person's classification ability. Explicit categorization, the representative system by which categorization ability is measured, can verbally describe the categorization rule. The purpose of this study was to develop a prediction model for categorization ability as it relates to the classification process of living organisms using fMRI. Fifty-five participants were divided into two groups: a model generation group, comprised of twenty-seven subjects, and a model verification group, made up of twenty-eight subjects. During prediction model generation, functional connectivity was used to analyze temporal correlations between brain activation regions. A classification ability quotient (CQ) was calculated to identify the verbal categorization ability distribution of each subject. Additionally, the connectivity coefficient (CC) was calculated to quantify the functional connectivity for each subject. Hence, it was possible to generate a prediction model through regression analysis based on participants' CQ and CC values. The resultant categorization ability regression model predictor was statistically significant; however, researchers proceeded to verify its predictive ability power. In order to verify the predictive power of the developed regression model, researchers used the regression model and subjects' CC values to predict CQ values for twenty-eight subjects. Correlation between the predicted CQ values and the observed CQ values was confirmed. Results of this study suggested that explicit categorization ability differs at the brain network level of individuals. Also, the finding suggested that differences in functional connectivity between individuals reflect differences in categorization ability. Last, researchers have provided a new method for predicting an individual's categorization ability by measuring brain activation.

• The Transactions of the Korea Information Processing Society
• /
• v.7 no.4
• /
• pp.1122-1131
• /
• 2000

The efficiency of thesytem depends upon an accurate extraction capability of index terms in the system of information search or in that of automatic index. Therefore, extraction of accurate index terms is of utmost importance. This report presents the generation methods of composition noun for efficient index term extraction by using words of high frequency appearance, so that the right documents can be found during information search. For the sake of presentation of this method, index terms of composition noun shall be extracted by applying the rule of composition and disintegration to the nouns with high frequency of appearance in the documents, such as those with upper 30%∼40% of frequency ratio. In addition, for he purpose of effecting an inspection of validity in relation to a composition of high frequency nouns such as those with upper 30∼40% of frequency ratio as presented in this report, it proposes an adequate frquency ratio during noun composition. Based upon the proposed application, in this short documents with less than 300 syllables, low frequency omissions were noticed, when composed with nouns in the upper 30% of frequency ratio; whereas the documents with more than 30 syllables, when composed with nouns in he upper 40% of frequency ration, had a considerable reduction of low frequency omissions. Thus, total number of index terms has decreased to 57.7% of these existing and an accurate extraction of index terms with an 85.6% adequacy ratio became possible.

• The Journal of the Korea Contents Association
• /
• v.14 no.9
• /
• pp.54-63
• /
• 2014

It is general that the field plant is too large to be monitored by human works. So it is crucial to prepare one automated monitoring system to prevent unexpected accidents in advance. However, most of previous monitoring systems were to be implemented by human programmer independently, so the total developing cost of a set of similar monitoring systems is so high. In order to overcome this disadvantage, we propose a new specification language for meta-description of monitoring system. Also we propose a generation tool for monitoring system with the input meta-description files. Using these meta-description files, we show it is so fast and effective to get a new monitoring system for a specific field plant. In experiment we have shown that our generation system work successfully in newly developing a monitoring system for the water-vessel plant.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.41 no.2
• /
• 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.

• Journal of IKEEE
• /
• v.24 no.1
• /
• pp.52-58
• /
• 2020

This paper describes a hardware implementation of a true random number generator (TRNG) for information security applications. A new approach for TRNG design was proposed by adopting random transition rules in cellular automata and applying different transition rules at every time step. The TRNG circuit was implemented on Spartan-6 FPGA device, and its hardware operation generating random data with 100 MHz clock frequency was verified. For the random data of 2×10⁷ bits extracted from the TRNG circuit implemented in FPGA device, the randomness characteristics of the generated random data was evaluated by the NIST SP 800-22 test suite, and all of the fifteen test items were found to meet the criteria. The TRNG in this paper was implemented with 139 slices of Spartan-6 FPGA device, and it offers 600 Mbps of the true random number generation with 100 MHz clock frequency.

• Journal of KIBIM
• /
• v.5 no.4
• /
• pp.53-62
• /
• 2015

Korea has been at the forefront of green growth initiatives. In 2008, the government declared the new vision toward 'low-carbon society and green growth'. The government subsidies and Feed-in Tariff (FIT) increased domestic usage of solar power by supplying photovoltaic housing and photovoltaic generation systems. Since 2000, solar power industry has been the world's fastest growing source with the annual growth rate of 52.5%. Especially, BIPV(Building Integrated Photovoltaic) systems are capturing a growing portion of the renewable energy market due to several reasons. BIPV consists of photovoltaic cells and modules integrated into the building envelope such as a roof or facades. By avoiding the cost of conventional materials, the incremental cost of photovoltaics is reduced and its life-cycle cost is improved. When it comes to atypical building, numerous problems occur because PV modules are flat, stationary, and have its orientation determined by building surface. However, previous studies mainly focused on improving installations of solar PV technologies on ground and rooftop photovoltaic array and developing prediction model to estimate the amount of produced electricity. Consequently, this paper discusses the problem during a planning and design stage of BIPV systems and suggests the method to select optimal design of the systems by applying the national strategy and economic policies. Furthermore, the paper aims to develop BIM tool based on the engineering knowledge from experts in order for non-specialists to design photovoltaic generation systems easily.