• Journal of Intelligence and Information Systems
• /
• v.23 no.3
• /
• pp.139-153
• /
• 2017

Corporate bankruptcy can cause great losses not only to stakeholders but also to many related sectors in society. Through the economic crises, bankruptcy have increased and bankruptcy prediction models have become more and more important. Therefore, corporate bankruptcy has been regarded as one of the major topics of research in business management. Also, many studies in the industry are in progress and important. Previous studies attempted to utilize various methodologies to improve the bankruptcy prediction accuracy and to resolve the overfitting problem, such as Multivariate Discriminant Analysis (MDA), Generalized Linear Model (GLM). These methods are based on statistics. Recently, researchers have used machine learning methodologies such as Support Vector Machine (SVM), Artificial Neural Network (ANN). Furthermore, fuzzy theory and genetic algorithms were used. Because of this change, many of bankruptcy models are developed. Also, performance has been improved. In general, the company's financial and accounting information will change over time. Likewise, the market situation also changes, so there are many difficulties in predicting bankruptcy only with information at a certain point in time. However, even though traditional research has problems that don't take into account the time effect, dynamic model has not been studied much. When we ignore the time effect, we get the biased results. So the static model may not be suitable for predicting bankruptcy. Thus, using the dynamic model, there is a possibility that bankruptcy prediction model is improved. In this paper, we propose RNN (Recurrent Neural Network) which is one of the deep learning methodologies. The RNN learns time series data and the performance is known to be good. Prior to experiment, we selected non-financial firms listed on the KOSPI, KOSDAQ and KONEX markets from 2010 to 2016 for the estimation of the bankruptcy prediction model and the comparison of forecasting performance. In order to prevent a mistake of predicting bankruptcy by using the financial information already reflected in the deterioration of the financial condition of the company, the financial information was collected with a lag of two years, and the default period was defined from January to December of the year. Then we defined the bankruptcy. The bankruptcy we defined is the abolition of the listing due to sluggish earnings. We confirmed abolition of the list at KIND that is corporate stock information website. Then we selected variables at previous papers. The first set of variables are Z-score variables. These variables have become traditional variables in predicting bankruptcy. The second set of variables are dynamic variable set. Finally we selected 240 normal companies and 226 bankrupt companies at the first variable set. Likewise, we selected 229 normal companies and 226 bankrupt companies at the second variable set. We created a model that reflects dynamic changes in time-series financial data and by comparing the suggested model with the analysis of existing bankruptcy predictive models, we found that the suggested model could help to improve the accuracy of bankruptcy predictions. We used financial data in KIS Value (Financial database) and selected Multivariate Discriminant Analysis (MDA), Generalized Linear Model called logistic regression (GLM), Support Vector Machine (SVM), Artificial Neural Network (ANN) model as benchmark. The result of the experiment proved that RNN's performance was better than comparative model. The accuracy of RNN was high in both sets of variables and the Area Under the Curve (AUC) value was also high. Also when we saw the hit-ratio table, the ratio of RNNs that predicted a poor company to be bankrupt was higher than that of other comparative models. However the limitation of this paper is that an overfitting problem occurs during RNN learning. But we expect to be able to solve the overfitting problem by selecting more learning data and appropriate variables. From these result, it is expected that this research will contribute to the development of a bankruptcy prediction by proposing a new dynamic model.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.30 no.5
• /
• pp.909-928
• /
• 2020

From the early 1970s, the US government began to recognize that penetration testing could not assure the security quality of products. Results of penetration testing such as identified vulnerabilities and faults can be varied depending on the capabilities of the team. In other words none of penetration team can assure that "vulnerabilities are not found" is not equal to "product does not have any vulnerabilities". So the U.S. government realized that in order to improve the security quality of products, the development process itself should be managed systematically and strictly. Therefore, the US government began to publish various standards related to the development methodology and evaluation procurement system embedding "security-by-design" concept from the 1980s. Security-by-design means reducing product's complexity by considering security from the initial phase of development lifecycle such as the product requirements analysis and design phase to achieve trustworthiness of product ultimately. Since then, the security-by-design concept has been spread to the private sector since 2002 in the name of Secure SDLC by Microsoft and IBM, and is currently being used in various fields such as automotive and advanced weapon systems. However, the problem is that it is not easy to implement in the actual field because the standard or guidelines related to Secure SDLC contain only abstract and declarative contents. Therefore, in this paper, we present the new framework in order to specify the level of Secure SDLC desired by enterprises. Our proposed CIA (functional Correctness, safety Integrity, security Assurance)-level-based security-by-design framework combines the evidence-based security approach with the existing Secure SDLC. Using our methodology, first we can quantitatively show gap of Secure SDLC process level between competitor and the company. Second, it is very useful when you want to build Secure SDLC in the actual field because you can easily derive detailed activities and documents to build the desired level of Secure SDLC.

• Journal of the Korean Society for Marine Environment & Energy
• /
• v.8 no.4
• /
• pp.227-235
• /
• 2005

This study aimed at suggesting management policy directions for the uninhabited islands of Korea which are national land resources with economic potential for tourism and development and strategic value for boundary delineation of territorial waters and exclusive economic zone as well as their unique ecological status. Review of existing management arrangements related to the uninhabited islands revealed six management issues to be addressed: insufficient data and their low reliability, lack of management policy directions, increase in ecosystem deterioration and perturbation by human activities, lack of policy measures for meeting utilization and development demands, weak management base with insufficient personnel and budget, and legal measures not taking Into account their unique ecological and socioeconomic characteristics. The management policy directions to improve the management of the uninhabited islands of Korea include management directions and strategies, and suggestions for legal improvement. Considering the unique ecological value of the uninhabited islands, management directions suggested are anti-degradation in which current and future demands for their utilization and development do not degrade the ecological potential of the uninhabited islands and integration in which land and sea areas are managed as an integrated management unit. Four strategies proposed to follow the management directions are enhancement of the knowledge base through a comprehensive survey, development and legislation of guidelines for the rational management of utilization and development demands, establishment of the comprehensive island debris collection and disposal system, and enhancement of management capacity. Legal improvement for the effective implementation of the management policy directions should include comprehensive uninhabited islands survey, legal utilization restraints and management guidelines based on classification of the islands, management boundary, and improvement of regulations on designated islands.

• Journal of Intelligence and Information Systems
• /
• v.21 no.1
• /
• pp.1-13
• /
• 2015

As opinion mining in big data applications has been highlighted, a lot of research on unstructured data has made. Lots of social media on the Internet generate unstructured or semi-structured data every second and they are often made by natural or human languages we use in daily life. Many words in human languages have multiple meanings or senses. In this result, it is very difficult for computers to extract useful information from these datasets. Traditional web search engines are usually based on keyword search, resulting in incorrect search results which are far from users' intentions. Even though a lot of progress in enhancing the performance of search engines has made over the last years in order to provide users with appropriate results, there is still so much to improve it. Word sense disambiguation can play a very important role in dealing with natural language processing and is considered as one of the most difficult problems in this area. Major approaches to word sense disambiguation can be classified as knowledge-base, supervised corpus-based, and unsupervised corpus-based approaches. This paper presents a method which automatically generates a corpus for word sense disambiguation by taking advantage of examples in existing dictionaries and avoids expensive sense tagging processes. It experiments the effectiveness of the method based on Naïve Bayes Model, which is one of supervised learning algorithms, by using Korean standard unabridged dictionary and Sejong Corpus. Korean standard unabridged dictionary has approximately 57,000 sentences. Sejong Corpus has about 790,000 sentences tagged with part-of-speech and senses all together. For the experiment of this study, Korean standard unabridged dictionary and Sejong Corpus were experimented as a combination and separate entities using cross validation. Only nouns, target subjects in word sense disambiguation, were selected. 93,522 word senses among 265,655 nouns and 56,914 sentences from related proverbs and examples were additionally combined in the corpus. Sejong Corpus was easily merged with Korean standard unabridged dictionary because Sejong Corpus was tagged based on sense indices defined by Korean standard unabridged dictionary. Sense vectors were formed after the merged corpus was created. Terms used in creating sense vectors were added in the named entity dictionary of Korean morphological analyzer. By using the extended named entity dictionary, term vectors were extracted from the input sentences and then term vectors for the sentences were created. Given the extracted term vector and the sense vector model made during the pre-processing stage, the sense-tagged terms were determined by the vector space model based word sense disambiguation. In addition, this study shows the effectiveness of merged corpus from examples in Korean standard unabridged dictionary and Sejong Corpus. The experiment shows the better results in precision and recall are found with the merged corpus. This study suggests it can practically enhance the performance of internet search engines and help us to understand more accurate meaning of a sentence in natural language processing pertinent to search engines, opinion mining, and text mining. Naïve Bayes classifier used in this study represents a supervised learning algorithm and uses Bayes theorem. Naïve Bayes classifier has an assumption that all senses are independent. Even though the assumption of Naïve Bayes classifier is not realistic and ignores the correlation between attributes, Naïve Bayes classifier is widely used because of its simplicity and in practice it is known to be very effective in many applications such as text classification and medical diagnosis. However, further research need to be carried out to consider all possible combinations and/or partial combinations of all senses in a sentence. Also, the effectiveness of word sense disambiguation may be improved if rhetorical structures or morphological dependencies between words are analyzed through syntactic analysis.

• Journal of Intelligence and Information Systems
• /
• v.25 no.4
• /
• pp.105-122
• /
• 2019

Dimensionality reduction is one of the methods to handle big data in text mining. For dimensionality reduction, we should consider the density of data, which has a significant influence on the performance of sentence classification. It requires lots of computations for data of higher dimensions. Eventually, it can cause lots of computational cost and overfitting in the model. Thus, the dimension reduction process is necessary to improve the performance of the model. Diverse methods have been proposed from only lessening the noise of data like misspelling or informal text to including semantic and syntactic information. On top of it, the expression and selection of the text features have impacts on the performance of the classifier for sentence classification, which is one of the fields of Natural Language Processing. The common goal of dimension reduction is to find latent space that is representative of raw data from observation space. Existing methods utilize various algorithms for dimensionality reduction, such as feature extraction and feature selection. In addition to these algorithms, word embeddings, learning low-dimensional vector space representations of words, that can capture semantic and syntactic information from data are also utilized. For improving performance, recent studies have suggested methods that the word dictionary is modified according to the positive and negative score of pre-defined words. The basic idea of this study is that similar words have similar vector representations. Once the feature selection algorithm selects the words that are not important, we thought the words that are similar to the selected words also have no impacts on sentence classification. This study proposes two ways to achieve more accurate classification that conduct selective word elimination under specific regulations and construct word embedding based on Word2Vec embedding. To select words having low importance from the text, we use information gain algorithm to measure the importance and cosine similarity to search for similar words. First, we eliminate words that have comparatively low information gain values from the raw text and form word embedding. Second, we select words additionally that are similar to the words that have a low level of information gain values and make word embedding. In the end, these filtered text and word embedding apply to the deep learning models; Convolutional Neural Network and Attention-Based Bidirectional LSTM. This study uses customer reviews on Kindle in Amazon.com, IMDB, and Yelp as datasets, and classify each data using the deep learning models. The reviews got more than five helpful votes, and the ratio of helpful votes was over 70% classified as helpful reviews. Also, Yelp only shows the number of helpful votes. We extracted 100,000 reviews which got more than five helpful votes using a random sampling method among 750,000 reviews. The minimal preprocessing was executed to each dataset, such as removing numbers and special characters from text data. To evaluate the proposed methods, we compared the performances of Word2Vec and GloVe word embeddings, which used all the words. We showed that one of the proposed methods is better than the embeddings with all the words. By removing unimportant words, we can get better performance. However, if we removed too many words, it showed that the performance was lowered. For future research, it is required to consider diverse ways of preprocessing and the in-depth analysis for the co-occurrence of words to measure similarity values among words. Also, we only applied the proposed method with Word2Vec. Other embedding methods such as GloVe, fastText, ELMo can be applied with the proposed methods, and it is possible to identify the possible combinations between word embedding methods and elimination methods.

• Journal of the Korean Institute of Traditional Landscape Architecture
• /
• v.34 no.2
• /
• pp.16-26
• /
• 2016

In this paper, we collected information on Palgyeong of the Gangneung area that were scattered around several literatures, and analyzed and interpreted regional distribution, elements of scenery and inherent meanings from various angles. we shed light on the origin and the meaning of Palgyeong, which have been passed down in the Gangneung area. Palgyeong of the Gangneung area have been accumulated and expanded for a long period of time, since Goryeo up to the modern times, and it does not simply reflect the beauty of natural scenery, but also reflect historical facts and sentiments rooted in this region. In addition, given the comprehensive veiw of Palgyeong of the Gangneung area and in consideration of its type and distribution of the eight sceneries the most common format is similar to Sosang(瀟湘類似型). What are repeatedly appearing among them include 'smoke from cooking supper' and 'catching fish', showing the living conditions of local residents of Gangneung at the time, which refers to the fact that Palgyeong consisted of village units. Palgyeong in the Gangneung area are distributed in diverse ranges between the city and Nujung. Most of Palgyeong are clustered in the east of Gangneung city and in the region tangent to Gangdong-myeon and Gujeong-myeon. When we consider the situation where most of Palgyeong in the Gangneung area are distributed in this region, it suggests that the region occupies the heart of scenery of Gangneung. Palgyeong of the Gangneung area consists of 60% natural factors, 36% humanity factors, and 4% other factors, where the natural factors hold the beauty of nature itself and the humanities and other factors hold the legends and history contained in the targets. The sceneries expressed by Palgyeong cannot be individually separated. Namedaecheon, Jukdobong, Sumseokcheon, Sumdulmaeul, Gunseongang, Pungho and Kyungpoho were connected to Nujung and Hongjamam, and they eventually became a panorama. Hansongjung, Hwanseondeung, Hansongsa, Pungho and Gunseongang are related to Hwarang of Silla and have become representative historical sceneries of the Gangneung area. Judging from the fact that currently non-existing sceneries such as Kyeonjodo, Hansongjung and Gulsansa remained in Palgyeong and been passed, Palgyeong have positioned imaginary spaces of the Gangneung people beyond simply expressing sceneries. In conclusion, Palgyeong in the Gangneung area are aesthetical objects and while at the same time, they are historical and cultural space, and furthermore, we can see that they still remain as imaginary spaces.

• Journal of KIISE:Computer Systems and Theory
• /
• v.30 no.5_6
• /
• pp.307-318
• /
• 2003

In this paper, we design and construct a TMO object group that provides the guaranteed real-time services in the distributed object computing environments, and verify execution power of its model for the correct distributed real-time services. The TMO object group we suggested is based on TINA's object group concept. This model consists of TMO objects having real-time properties and some components that support the object management service and the real-time scheduling service in the TMO object group. Also TMO objects can be duplicated or non-duplicated on distributed systems. Our model can execute the guaranteed distributed real-time service on COTS middlewares without restricting the specially ORB or the of operating system. For achieving goals of our model. we defined the concepts of the TMO object and the structure of the TMO object group. Also we designed and implemented the functions and interactions of components in the object group. The TMO object group includes the Dynamic Binder object and the Scheduler object for supporting the object management service and the real-time scheduling service, respectively The Dynamic Binder object supports the dynamic binding service that selects the appropriate one out of the duplicated TMO objects for the clients'request. And the Scheduler object supports the real-time scheduling service that determines the priority of tasks executed by an arbitrary TMO object for the clients'service requests. And then, in order to verify the executions of our model, we implemented the Dynamic Binder object and the Scheduler object adopting the binding priority algorithm for the dynamic binding service and the EDF algorithm for the real-time scheduling service from extending the existing known algorithms. Finally, from the numerical analyzed results we are shown, we verified whether our TMO object group model could support dynamic binding service for duplicated or non-duplicated TMO objects, also real-time scheduling service for an arbitrary TMO object requested from clients.

• Korean Journal of Heritage: History & Science
• /
• v.53 no.2
• /
• pp.156-179
• /
• 2020

The Preservation Decree (1933) is the basic law relevant to the conservation of cultural property of colonial Chosun, and invoked clauses from the Old History Preservation Act (1897), the Historic Scenic Sites Natural Monument Preservation Act (1919), and the National Treasure Preservation Act (1929), which were all forms of Japanese Modern Cultural Heritage Law, and actually used the corresponding legal text of those laws. Thus, the fact that the Preservation Decree transplanted or imitated the Japanese Modern Cultural Heritage Law in the composition of the constitution can be proved to some extent. The main features and characteristics of the Preservation Decree are summarized below. First, in terms of preservation of cultural property, the Preservation Decree strengthened and expanded preservation beyond the existing conservation rules. In the conservation rules, the categories of cultural properties were limited to historic sites and relics, while the Preservation Decree classifies cultural properties into four categories: treasures, historic sites, scenic spots, and natural monuments. In addition, the Preservation Decree is considered to have advanced cultural property preservation law by establishing the standard for conserving cultural property, expanding the scope of cultural property, introducing explicit provisions on the restriction of ownership and the designation system for cultural property, and defining the basis for supporting the natural treasury. Second, the Preservation Decree admittedly had limitations as a colonial cultural property law. Article 1 of the Preservation Decree sets the standard of "Historic Enhancement or Example of Art" as a criteria for designating treasures. With the perspective of Japanese imperialism, this acted as a criterion for catering to cultural assets based on the governor's assimilation policy, revealing its limitations as a standard for preserving cultural assets. In addition, the Japanese imperialists asserted that the cultural property law served to reduce cultural property robbery, but the robbery and exporting of cultural assets by such means as grave robbery, trafficking, and exportation to Japan did not cease even after the Preservation Decree came into effect. This is because governors and officials who had to obey and protect the law become parties to looting and extraction of property, or the plunder and release of cultural property by the Japanese continued with their acknowledgement,. This indicates that cultural property legislation at that time did not function properly, as the governor allowed or condoned such exporting and plundering. In this way, the cultural property laws of the Japanese colonial period constituted discriminative colonial legislation which was selected and applied from the perspective of the Japanese government-general in the designation and preservation of cultural property, and the cultural property policy of Japan focused on the use of cultural assets as a means of realizing their assimilation policy. Therefore, this suggests that the cultural property legislation during the Japanese colonial period was used as a mechanism to solidify the cultural colonial rules of Chosun and to realize the assimilation policy of the Japanese government-general.

• Journal of the Korean Institute of Traditional Landscape Architecture
• /
• v.30 no.3
• /
• pp.42-56
• /
• 2012

This study was carried out to investigate the construction characteristics and the landscaping design skill for Wiyiam at Ongnyucheon(玉流川) in the rear garden of Changdeok Palace focusing on constructing technique, space composition and transformational process of the site. The results of this study were summarized as follows; First, Wiyiam of Ongnyucheon was constructed as garden ornament which was modified the huge bedrock into the shape of the mountain. The waterfall of Wiyiam was originally made of torrent which water flowed into the bottom, but it was reconstructed to take the effect of Inak(離落: the method to drop water from high place) by carving rock into square shape at the era of King Gojong(高宗). Second, main characteristics of Wiyiam appeared in Donggwoldo was the hill built up with a square pond and ground at the back of Wiyiam and the profound scenery of mountains and stream from the view of Wiyiam. Also, pavilions such as Soyojeong(逍遙亭), Cheongujeong and Taegeukjeong(太極亭) built in Ongnyucheon seemed to be constructed as the spots to appreciate the view and waterfall sound of Wiyiam. Also the spots were not bounded by the function of creating special water systems such as Cheongujeong pond and Taegeukjeong pond and showed the outstanding landscape design skill to make people feel unusual interest from each spot. On the other hand, this study considered that the evening scenery of Wiyiam, beautiful sound of falling water, unusual water system with beautiful plant materials were landscaped for the function of the psychological peace and stability to the appreciators. Lastly, the extreme change of space composition in Ongnyucheon was assumed as a strategy to improve the existing poor drain environment by confirming that the mountain stream and wall of Soyojeong were removed and drainage in both side of Soyojeong was installed in the 21th year of King Gojong's reign(1884).

• Journal of the Korean Institute of Traditional Landscape Architecture
• /
• v.28 no.2
• /
• pp.127-136
• /
• 2010

This study is aimed at reviewed and analyzed in order to suggest the improved plans related to natural monuments. The summary of this study is as followings; First, Replacing the current term 'cultural properties', which denotes the meaning of 'goods', we need to devise an new categorization that separates such properties into cultural heritage and natural heritage under the national heritage framework. Second, the designation criteria for natural monuments should be divided into the individual realm for animals and plants respectively, since they are not divided in the current Act. Third, the guidelines for naming of natural monuments should be established with the following new categories in accordance with the clear standards. Fourth, such imbalances require us to give priority to the relatively neglected types and areas. Fifth, as the big and old trees account for more than a half of the designated plants, it is necessary to search out new resources(wet plant communities, seashores, sand dune plant communities, etc.) such as geological resources, mineral springs, hot springs, and fossils that are in danger of completely being exploited and exhausted. While most of the designated animals are protected nationally, the existing designation system is required to protect habitats and breeding places for the systematic and efficient conservation. Sixth, as long as we need to preserve those historical and cultural resources for the future generations from national and global perspectives, we should enhance their values by designating them as natural monuments even though they are protected by other regulations such as the natural environment area. Seventh, as a result of the survey, we found that more budgets and experts in the local governments, more empowered organizations, more active public participation should be provided for the better Natural Monument management in Korea. Eighth, the Lap of Natural Heritage in the National Research Institute of Cultural Heritage needs to be developed to the Natural Heritage Institute to conduct the diverse activities such as researches, restoration, exhibition and education programs in a systematic and efficient way. Ninth and the last, major damages to natural monuments can be generally categorized into the artificial one and natural one, respectively. The artificial damages include toxics, soil covering, excessive humidity, fire, construction and management works, unlawful damages, fishing, oil spillage, etc, and the natural ones include lightning, storms(typhoons), heavy snowfalls, damage by insects and diseases, lack of prey, etc. This study will become meaningful in that it proposes specific measures for the improvement of the institutions, designation, and management of natural monuments on the basis of the comprehensive analysis on natural monuments. We wish to leave the other subjects related with this study to the future researches.