• Journal of Intelligence and Information Systems
• /
• v.21 no.3
• /
• pp.79-99
• /
• 2015

The prediction of bankruptcy has been extensively studied in the accounting and finance field. It can have an important impact on lending decisions and the profitability of financial institutions in terms of risk management. Many researchers have focused on constructing a more robust bankruptcy prediction model. Early studies primarily used statistical techniques such as multiple discriminant analysis (MDA) and logit analysis for bankruptcy prediction. However, many studies have demonstrated that artificial intelligence (AI) approaches, such as artificial neural networks (ANN), decision trees, case-based reasoning (CBR), and support vector machine (SVM), have been outperforming statistical techniques since 1990s for business classification problems because statistical methods have some rigid assumptions in their application. In previous studies on corporate bankruptcy, many researchers have focused on developing a bankruptcy prediction model using financial ratios. However, there are few studies that suggest the specific types of bankruptcy. Previous bankruptcy prediction models have generally been interested in predicting whether or not firms will become bankrupt. Most of the studies on bankruptcy types have focused on reviewing the previous literature or performing a case study. Thus, this study develops a model using data mining techniques for predicting the specific types of bankruptcy as well as the occurrence of bankruptcy in Korean small- and medium-sized construction firms in terms of profitability, stability, and activity index. Thus, firms will be able to prevent it from occurring in advance. We propose a hybrid approach using two artificial neural networks (ANNs) for the prediction of bankruptcy types. The first is a back-propagation neural network (BPN) model using supervised learning for bankruptcy prediction and the second is a self-organizing map (SOM) model using unsupervised learning to classify bankruptcy data into several types. Based on the constructed model, we predict the bankruptcy of companies by applying the BPN model to a validation set that was not utilized in the development of the model. This allows for identifying the specific types of bankruptcy by using bankruptcy data predicted by the BPN model. We calculated the average of selected input variables through statistical test for each cluster to interpret characteristics of the derived clusters in the SOM model. Each cluster represents bankruptcy type classified through data of bankruptcy firms, and input variables indicate financial ratios in interpreting the meaning of each cluster. The experimental result shows that each of five bankruptcy types has different characteristics according to financial ratios. Type 1 (severe bankruptcy) has inferior financial statements except for EBITDA (earnings before interest, taxes, depreciation, and amortization) to sales based on the clustering results. Type 2 (lack of stability) has a low quick ratio, low stockholder's equity to total assets, and high total borrowings to total assets. Type 3 (lack of activity) has a slightly low total asset turnover and fixed asset turnover. Type 4 (lack of profitability) has low retained earnings to total assets and EBITDA to sales which represent the indices of profitability. Type 5 (recoverable bankruptcy) includes firms that have a relatively good financial condition as compared to other bankruptcy types even though they are bankrupt. Based on the findings, researchers and practitioners engaged in the credit evaluation field can obtain more useful information about the types of corporate bankruptcy. In this paper, we utilized the financial ratios of firms to classify bankruptcy types. It is important to select the input variables that correctly predict bankruptcy and meaningfully classify the type of bankruptcy. In a further study, we will include non-financial factors such as size, industry, and age of the firms. Thus, we can obtain realistic clustering results for bankruptcy types by combining qualitative factors and reflecting the domain knowledge of experts.

• 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.

• Food Science and Preservation
• /
• v.19 no.6
• /
• pp.799-806
• /
• 2012

This experiment was conducted to establish the optimum conditions for high $CO_2$ gas treatment in combination with a proper gas-permeable packaging film to maintain the quality of fig fruit (Ficus carica L). Among the fig fruits with different high $CO_2$ treatments, the quality change was most effectively controlled during storage in the 70%-$CO_2$-treated fig fruit. Harvested fig fruit was packaged using microperforated oriented polypropylene (MP) film to maintain the optimum gas concentrations in the headspace of packaging for the modified-atmosphere system. MP film had an oxygen transmission rate of about $10,295cm^3/m^2$/day/atm at $25^{\circ}C$. The weight loss, firmness, soluble-solid content (SSC), acidity (pH), skin color (Hunter L, a, b), and decay ratio of the fig fruits were monitored during storage at 5 and $25^{\circ}C$. The results of this study showed that the OPP film, OPP film + 70% $CO_2$, and MP film+70% $CO_2$ were highly effective in reducing the loss rate, firmness and decay occurrence rate of fig fruits that were packaged with them during storage. In the case of using treatments with packages of OPP film and OPP film+70% $CO_2$, however, adverse effects like package bursting or physiological injury of the fig may occur due to the gas pressure or long exposure to $CO_2$. Therefore, the results indicated that MP film containing 70% $CO_2$ can be used as an effective treatment to extend the freshness of fig fruits for storage at a proper low temperature.

• Korean Journal of Soil Science and Fertilizer
• /
• v.44 no.3
• /
• pp.408-414
• /
• 2011

The purpose of this study was to find out optimum cultivated regions for rice organic farming. The organic and conventional rice as control were grown in three different places : secluded hill paddy field for Hapcheon, normal rural paddy field for Sancheong, and suburban paddy field for Jinju from 2005 to 2006. In secluded hill paddy field, the organic material and pesticide to control pest and disease were input twice for organic and conventional rice cultivation. However, in normal rural and suburban paddy field, those were input three times for organic and conventional rice cultivation. The occurrence of sheath blight in organic farming was higher than in conventional farming. Whereas brown planthopper population per 20 plant was significantly high 10.1~19.5 for conventional farming compared with 4.4~10.0 for organic farming. For that reason, the density of the brown planthoppers was higher in organic farming than those in conventional farming. Dominated weeds occurred in organic and conventional paddy field were namely Monochoria vaginalis, Ludwigia prostrata, and Cyperus difformis. The population per 20 plant and dried weight per $m^2$ of weeds were higher in 121 and 50.5 g for organic paddy field. The productivity of rice in different cultivated regions for organic farming was $2.96Mg\;ha^{-1}$ in hill paddy field, $4.03Mg\;ha^{-1}$ in normal rural and suburban paddy field. Toyo-taste value and ratio of perfect grain of milled rice were not different by cultivated regions in both farming system.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.21 no.4
• /
• pp.64-80
• /
• 2018

In Korea, citizens can only know general information about crime. Thus it is difficult to know how much they are exposed to crime. If the police can predict the crime risky area, it will be possible to cope with the crime efficiently even though insufficient police and enforcement resources. However, there is no prediction system in Korea and the related researches are very much poor. From these backgrounds, the final goal of this study is to develop an automated crime prediction system. However, for the first step, we build a big data set which consists of local real crime information and urban physical or non-physical data. Then, we developed a crime prediction model through machine learning method. Finally, we assumed several possible scenarios and calculated the probability of crime and visualized the results in a map so as to increase the people's understanding. Among the factors affecting the crime occurrence revealed in previous and case studies, data was processed in the form of a big data for machine learning: real crime information, weather information (temperature, rainfall, wind speed, humidity, sunshine, insolation, snowfall, cloud cover) and local information (average building coverage, average floor area ratio, average building height, number of buildings, average appraised land value, average area of residential building, average number of ground floor). Among the supervised machine learning algorithms, the decision tree model, the random forest model, and the SVM model, which are known to be powerful and accurate in various fields were utilized to construct crime prevention model. As a result, decision tree model with the lowest RMSE was selected as an optimal prediction model. Based on this model, several scenarios were set for theft and violence cases which are the most frequent in the case city J, and the probability of crime was estimated by $250{\times}250m$ grid. As a result, we could find that the high crime risky area is occurring in three patterns in case city J. The probability of crime was divided into three classes and visualized in map by $250{\times}250m$ grid. Finally, we could develop a crime prediction model using machine learning algorithm and visualized the crime risky areas in a map which can recalculate the model and visualize the result simultaneously as time and urban conditions change.

• Journal of Korean Society of Disaster and Security
• /
• v.14 no.2
• /
• pp.61-75
• /
• 2021

Recently, as the occurrence frequency of sudden floods due to climate change increased and the aging of the existing spillway, it is necessary to establish a plan to utilize an auxiliary spillway to minimize the flood damage of downstream rivers. Most studies have been conducted on the review of flow characteristics according to the operation of auxiliary spillway through the hydraulic experiments and numerical modeling. However, the studies on examination of flood damage in the downstream rivers and the stability of the revetment according to the operation of the auxiliary spillway were relatively insufficient in the literature. In this study, the stability of the revetment on the downstream river according to the outflow conditions of the existing and auxiliary spillway was examined by using 3D numerical model, FLOW-3D. The velocity, water surface elevation and shear stress results of FLOW-3D were compared with the permissible velocity and shear stress of design criteria. It was assumed the sluice gate was fully opened. As a result of numerical simulations of various auxiliary spillway operations during flood season, the single operation of the auxiliary spillway showed the reduction effect of maximum velocity and the water surface elevation compared with the single operation of the existing spillway. The stability of the revetment on downstream was satisfied under the condition of outflow less than 45% of the design flood discharge. However, the potential overtopping damage was confirmed in the case of exceeding the 45% of the design flood discharge. Therefore, the simultaneous operation with the existing spillway was important to ensure the stability on design flood discharge condition. As a result of examining the allocation ratio and the total allowable outflow, the reduction effect of maximum velocity was confirmed on the condition, where the amount of outflow on auxiliary spillway was more than that on existing spillway. It is because the flow of downstream rivers was concentrated in the center due to the outflow of existing spillway. The permissible velocity and shear stress were satisfied under the condition of less than 77% of the design flood discharge with simultaneous operation. It was found that the flood damage of downstream rivers can be minimized by setting the amount allocated to the auxiliary spillway to be larger than the amount allocated to the existing spillway for the total outflow with simultaneous operation condition. However, this study only reviewed the flow characteristics around the revetment according to the outflow of spillway under the full opening of the sluice gate condition. Therefore, the various sluice opening conditions and outflow scenarios will be asked to derive more efficient utilization of the auxiliary spillway in th future.

• Journal of Mushroom
• /
• v.19 no.1
• /
• pp.23-32
• /
• 2021

This study investigated the anti-hyperlipidemic and anti-obesity effects of Sparassis latifolia (S. latifolia) fruiting body powder in rats fed with a high fat and cholesterol diet (HFD). Rats were fed a normal control diet (ND), an HFD, an HFD supplemented with 5% fruiting body powder of S. latifolia (HFD+SL), or an HFD supplemented with 0.03% simvastatin (HFD+SS), for 6 weeks. The HFD group demonstrated considerable increase in body weight gain, the food efficiency ratio (FER), and plasma cholesterol and triglyceride levels, compared to the ND group. In contrast, the HFD+SL and HFD+SS groups showed significantly reduced body weight gain, food intake, and plasma cholesterol and triglyceride levels compared to the HFD group. In particular, the HFD+SL and HFD+SS diets significantly suppressed the occurrence of non-alcoholic fat deposits in the liver. Taken together, these results suggest that dietary supplementation of the fruiting body powder of S. latifolia in an HFD could lower the risks of hyperlipidemia, atherogenesis, and obesity and may be used as a functional food to manage cardiovascular disease and fecal lipid and cholesterol levels.

• Journal of fish pathology
• /
• v.35 no.1
• /
• pp.1-25
• /
• 2022

The aquaculture industry has developed rapidly over the last three decades and is an important industry that supplies over 15% of humans' animal protein intake; therefore, there is a need to increase production to meet the continuous demand. The fish cage farms on the southern coast (Kyengsangnam-do and Jeollanam-do) of Korea are critical resources in aquaculture because they account for approximately 90% of the national total fish cage farms by water area ratio. However, the current aquaculture environment is being gradually affected by climate change, which is a global issue, and its effects are expected to intensify in the future. Therefore, it is urgently imperative to accurately evaluate the effects of climate change on South Korean aquaculture industries and to develop social and national strategies to minimize damage to the fishing industry. The damage to fish farmed in cage farms on the southern coast is increasing annually and the leading causes are high and low water temperature and red tides, which are directly or indirectly related to climate change. At present, global warming can provide opportunities for aquaculture industrialization of fish or other novel species, with economic implications. However, despite such opportunities, the influx of new species can also cause problems such as ecological disturbances, increase in the reproduction frequency of microalgae such as red tide, increase in disease incidence, and occurrence and periods of high water temperatures in summer. The scale of farmed fish mortality is increasing due to the complex effects of these factors. Increased damages due to fish mortality not only have severe economic impacts on the aquaculture industry, but the social costs of responding to the damage and follow-up measures also increase. various active responses can reduce the mortality damage in fish farms such as improving the management skills in aquaculture, improved species breeding, efficient food management, disease prevention, proactive responses, and system-wide improvements. This review article analyzes the large-scale mortality cases occurring in fish cage farms on the southern coast of Korea and proposes measures to mitigate mortality and enhance responses to such scenarios.

• Economic and Environmental Geology
• /
• v.55 no.1
• /
• pp.63-76
• /
• 2022

Dacitic tuffs, 97 to 118 m thick, were recovered from the lower part of the subsurface Seongdongri Formation, Janggi Basin, which was drilled to assess the potential for underground storage of carbon dioxide. The tuffs are divided into four depositional units(Unit 1 to 4) based on internal structures and particle componentry. Unit 1 and Units 3/4 are ignimbrites that accumulated in subaerial and subaqueous settings, respectively, whereas Unit 2 is braided-stream deposits that accumulated during a volcanic quiescence, and no dacitic tuff is observed. A series of analysis shows that mordenite and clinoptilolite mainly fill the vesicles of glass shards, suggesting their formation by replacement and dissolution of volcanic glass and precipitation from interstitial water during burial and diagenesis. Glass-replaced clinoptilolite has higher Si/Al ratios and Na contents than the vesicle-filling clinoptilolite in Units 3. However, the composition of clinoptilolite becomes identical in Unit 4, irrespective of the occurrence and location. This suggests that the Si/Al ratio and pH in the interstitial water increased with time because of the replacement and leaching of volcanic glass, and that the composition of interstitial water was different between the eastern and western parts of the basin during the formation of the clinoptilolite in Units 1 and 3. It is also inferred that the formation of the two zeolite minerals was sequential according to the depositional units, i.e., the clinoptilolite formed after the growth of mordenite. To summarize, during a volcanic quiescence after the deposition of Unit 1, pH was higher in the western part of the basin because of eastward tilting of the basin floor, and the zeolite ceased to grow because of the closure of the pore space as a result of the growth of smectite. On the other hand, clinoptilolite could grow in the eastern part of the basin in an open system affected by groundwater, where braided stream was developed. Afterwards, Units 3 and 4 were submerged under water because of the basin subsidence, and the alkali content of the interstitial water increased gradually, eventually becoming identical in the eastern and western parts of the basin. This study thus shows that volcanic deposits of similar composition can have variable distribution of zeolite mineral depending on the drainage and depositional environment of basins.

• Economic and Environmental Geology
• /
• v.55 no.5
• /
• pp.477-495
• /
• 2022

This study examined the sustainability of CO₂-rich water by analyzing the water level and water quality change pattern with the amount of its use in Angseong area, Chungju. The origin and supply of CO₂ component were discussed in consideration of ⁸⁷Sr/⁸⁶Sr ratio, occurrence of CO₂-rich fluid inclusions in nearby W-Mo deposits and other surrounding geological characteristics. According to the data from 1986 to 2017, the depth of the water level of CO₂-rich water was significantly lowered in the late period (2009-2015) than in the early period (1986-1992) of the development of hot spa wells, and the optimal yields for pumping tests also showed a tendency to gradual decrease. Concentrations of CO₂ component also decreased continuously in the later stages compared to the early stages of development, but it has been stable since 2012. It is inferred that the geological environment related to forming W-Mo quartz vein deposits (0.5×1.5×several km) around the study area are largely involved in the origin and supply of CO₂ component, and the supply of CO₂ component is not infinitely supplied from deep current magma activity. Rather, since it is finitely supplied from a restricted subsurface region formed in the past geological period, it is necessary to efficiently control its use in order to maintain the sustainability of CO₂-rich water in the study area.