• Journal of Intelligence and Information Systems
• /
• v.22 no.2
• /
• pp.33-56
• /
• 2016

Many researchers have focused on developing bankruptcy prediction models using modeling techniques, such as statistical methods including multiple discriminant analysis (MDA) and logit analysis or artificial intelligence techniques containing artificial neural networks (ANN), decision trees, and support vector machines (SVM), to secure enhanced performance. Most of the bankruptcy prediction models in academic studies have used financial ratios as main input variables. The bankruptcy of firms is associated with firm's financial states and the external economic situation. However, the inclusion of qualitative information, such as the economic atmosphere, has not been actively discussed despite the fact that exploiting only financial ratios has some drawbacks. Accounting information, such as financial ratios, is based on past data, and it is usually determined one year before bankruptcy. Thus, a time lag exists between the point of closing financial statements and the point of credit evaluation. In addition, financial ratios do not contain environmental factors, such as external economic situations. Therefore, using only financial ratios may be insufficient in constructing a bankruptcy prediction model, because they essentially reflect past corporate internal accounting information while neglecting recent information. Thus, qualitative information must be added to the conventional bankruptcy prediction model to supplement accounting information. Due to the lack of an analytic mechanism for obtaining and processing qualitative information from various information sources, previous studies have only used qualitative information. However, recently, big data analytics, such as text mining techniques, have been drawing much attention in academia and industry, with an increasing amount of unstructured text data available on the web. A few previous studies have sought to adopt big data analytics in business prediction modeling. Nevertheless, the use of qualitative information on the web for business prediction modeling is still deemed to be in the primary stage, restricted to limited applications, such as stock prediction and movie revenue prediction applications. Thus, it is necessary to apply big data analytics techniques, such as text mining, to various business prediction problems, including credit risk evaluation. Analytic methods are required for processing qualitative information represented in unstructured text form due to the complexity of managing and processing unstructured text data. This study proposes a bankruptcy prediction model for Korean small- and medium-sized construction firms using both quantitative information, such as financial ratios, and qualitative information acquired from economic news articles. The performance of the proposed method depends on how well information types are transformed from qualitative into quantitative information that is suitable for incorporating into the bankruptcy prediction model. We employ big data analytics techniques, especially text mining, as a mechanism for processing qualitative information. The sentiment index is provided at the industry level by extracting from a large amount of text data to quantify the external economic atmosphere represented in the media. The proposed method involves keyword-based sentiment analysis using a domain-specific sentiment lexicon to extract sentiment from economic news articles. The generated sentiment lexicon is designed to represent sentiment for the construction business by considering the relationship between the occurring term and the actual situation with respect to the economic condition of the industry rather than the inherent semantics of the term. The experimental results proved that incorporating qualitative information based on big data analytics into the traditional bankruptcy prediction model based on accounting information is effective for enhancing the predictive performance. The sentiment variable extracted from economic news articles had an impact on corporate bankruptcy. In particular, a negative sentiment variable improved the accuracy of corporate bankruptcy prediction because the corporate bankruptcy of construction firms is sensitive to poor economic conditions. The bankruptcy prediction model using qualitative information based on big data analytics contributes to the field, in that it reflects not only relatively recent information but also environmental factors, such as external economic conditions.

• Korean Journal of Breeding Science
• /
• v.42 no.3
• /
• pp.262-266
• /
• 2010

'Josaengheugchal', a new blackish purple pigmented glutinous japonica rice cultivar, was developed by the rice breeding team of Department of Functional Crop, NICS, RDA in 2004. This cultivar was derived from a cross between 'Tohoku 149' as black glutinous source and 'Sx 864' as purple colored rice in 1992 and 1993 winter season, and selected by pedigree breeding method until $F_6$ generation. As a result, a promising line, YR15907-6-8-1-5, was advanced and designated as the name of 'Milyang 194' in 2001. The local adaptability test of 'Milyang 194' was carried out at seven locations from 2002 to 2004 and it was named as 'Josaengheugchal'. 'Josaengheugchal' is an early maturing cultivar and has 71 cm culm height. It has higher anthocyanian content compared with 'Heugnambyeo'. It is moderately resistant to leaf blast but susceptible to other disease and insect pests. The yield potential of 'Josaengheugchal' in brown rice was about 4.21 MT/ha at ordinary fertilizer level in local adaptability test. This cultivar would be adaptable to the plain paddy field of middle, Honam, and Yeomgnam in Korea under ordinary and double cropping system.

• 한국노년학
• /
• v.37 no.2
• /
• pp.281-291
• /
• 2017

The present study aimed to investigate the rate of unmet healthcare needs for elderly over the age of 65 years, as well as analyze the relevance between employment status and unmet healthcare needs due to financial reasons. With regard to the study method, a logistic regression analysis was performed to investigate the correlation between employment status and unmet healthcare needs due to financial reasons, targeting 5,528 subjects over the age of 65 years. The results showed that the rate of unmet healthcare needs was 18.9%, in which the rate of unmet healthcare needs due to financial reason was 8.1%. The rate of unmet health needs was higher for temporary workers(ORs=1.75) than for retirement workers. However, the rate of unmet healthcare needs caused by financial reasons was higher among day workers(ORs=1.92). In conclusion, in order to prevent unmet healthcare needs for senior Korean patients, it is necessary to not only improve the income security system for the elderly, but also improve the occupational form and level of income of these economically active citizens, considering the increase in average life expectancy. Moreover, it is also necessary to reinforce health insurance coverage systems for settling medical expenses.

• Journal of Intelligence and Information Systems
• /
• v.25 no.3
• /
• pp.43-62
• /
• 2019

At one time, the anomaly detection sector dominated the method of determining whether there was an abnormality based on the statistics derived from specific data. This methodology was possible because the dimension of the data was simple in the past, so the classical statistical method could work effectively. However, as the characteristics of data have changed complexly in the era of big data, it has become more difficult to accurately analyze and predict the data that occurs throughout the industry in the conventional way. Therefore, SVM and Decision Tree based supervised learning algorithms were used. However, there is peculiarity that supervised learning based model can only accurately predict the test data, when the number of classes is equal to the number of normal classes and most of the data generated in the industry has unbalanced data class. Therefore, the predicted results are not always valid when supervised learning model is applied. In order to overcome these drawbacks, many studies now use the unsupervised learning-based model that is not influenced by class distribution, such as autoencoder or generative adversarial networks. In this paper, we propose a method to detect anomalies using generative adversarial networks. AnoGAN, introduced in the study of Thomas et al (2017), is a classification model that performs abnormal detection of medical images. It was composed of a Convolution Neural Net and was used in the field of detection. On the other hand, sequencing data abnormality detection using generative adversarial network is a lack of research papers compared to image data. Of course, in Li et al (2018), a study by Li et al (LSTM), a type of recurrent neural network, has proposed a model to classify the abnormities of numerical sequence data, but it has not been used for categorical sequence data, as well as feature matching method applied by salans et al.(2016). So it suggests that there are a number of studies to be tried on in the ideal classification of sequence data through a generative adversarial Network. In order to learn the sequence data, the structure of the generative adversarial networks is composed of LSTM, and the 2 stacked-LSTM of the generator is composed of 32-dim hidden unit layers and 64-dim hidden unit layers. The LSTM of the discriminator consists of 64-dim hidden unit layer were used. In the process of deriving abnormal scores from existing paper of Anomaly Detection for Sequence data, entropy values of probability of actual data are used in the process of deriving abnormal scores. but in this paper, as mentioned earlier, abnormal scores have been derived by using feature matching techniques. In addition, the process of optimizing latent variables was designed with LSTM to improve model performance. The modified form of generative adversarial model was more accurate in all experiments than the autoencoder in terms of precision and was approximately 7% higher in accuracy. In terms of Robustness, Generative adversarial networks also performed better than autoencoder. Because generative adversarial networks can learn data distribution from real categorical sequence data, Unaffected by a single normal data. But autoencoder is not. Result of Robustness test showed that he accuracy of the autocoder was 92%, the accuracy of the hostile neural network was 96%, and in terms of sensitivity, the autocoder was 40% and the hostile neural network was 51%. In this paper, experiments have also been conducted to show how much performance changes due to differences in the optimization structure of potential variables. As a result, the level of 1% was improved in terms of sensitivity. These results suggest that it presented a new perspective on optimizing latent variable that were relatively insignificant.

• Journal of the Korean Applied Science and Technology
• /
• v.38 no.1
• /
• pp.318-331
• /
• 2021

This study was conducted on the assumption that bone age would be more effective when it comes to physique and physical fitness assessment for adolescents, and the purpose of this study was to identify the differences in physique and physical fitness for students in their adolescence through bone age and chronological age in order to contribute to the well-balanced physique and physical fitness development in adolescents and the health improvement in students. Total 874 adolescents(483 males, 391 females) aged 11~16 were selected as subjects out of the total population of 1100 adolescents aged 6~16 based on the PAPS(Physical Activity Promotion System) and age standards of the TW3 method; and skeletal maturation, which symbolize the indicators of biological maturation, were evaluated by using the TW3(Tanner-Whitehouse 3) method after hand-wrist radiographs, and birth date was used for chronological age. A stadiometer and InBody 270 (Biospace, Korea) were used to measure 2 components in physique. A total of 7 components in physical fitness, which included muscular strength, muscular endurance, flexibility, power, cardiovascular endurance, balance, agility, were measured as well. A independent samples t-test was conducted for data processing using SPSS 25.0, and the significance level was set at p< .05. The study results are as follows. First, bone age and chronological age used for physique comparison in males aged 11 and 12, height and weight showed significant difference; in males aged 13, weight showed signicant difference. Weight and height in females aged 11, and height in females aged 12 showed significant difference. Second, bone age and chronological age used for physical fitness comparison in males aged 11, muscular strength, power, flexibility, cardiovascular endurance showed significant difference; in males aged 12, muscular strength. power, cardiovascular endurance; in males aged 13, flexibility showed significant difference. Muscular strength, power, flexibility, muscular endurance, cardiovascular endurance in females aged 11, and flexibility in females aged 14 showed significant difference. As a result, this study concluded that in a period of rapid skeletal growth, evaluating physique and physical fitness based on bone age is more accurate than evaluating based on chronological age.

• Journal of Digital Convergence
• /
• v.20 no.4
• /
• pp.147-157
• /
• 2022

This study tried to propose a smart farm technology strategy suitable for the domestic situation, focusing on the differentiation suitable for the domestic situation of ICT technology. In the case of advanced countries in the overseas agricultural industry, it was confirmed that they focused on the development of a specific stage that reflected the geographical characteristics of each country, the characteristics of the agricultural industry, and the characteristics of the people's demand. Confirmed that no enemy development is being performed. Therefore, in response to problems such as a rapid decrease in the domestic rural population, aging population, loss of agricultural price competitiveness, increase in fallow land, and decrease in use rate of arable land, this study aims to develop smart farm ICT technology in the future to create quality agricultural products and have price competitiveness. It was suggested that the smart farm should be promoted by paying attention to the excellent performance, ease of use due to the aging of the labor force, and economic feasibility suitable for a small business scale. First, in terms of economic feasibility, the ICT technology is configured by selecting only the functions necessary for the small farm household (primary) business environment, and the smooth communication system with these is applied to the ICT technology to gradually update the functions required by the actual farmhouse. suggested that it may contribute to the reduction. Second, in terms of performance, it is suggested that the operation accuracy can be increased if attention is paid to improving the communication function of ICT, such as adjusting the difficulty of big data suitable for the aging population in Korea, using a language suitable for them, and setting an algorithm that reflects their prediction tendencies. Third, the level of ease of use. Smart farms based on ICT technology for the development of the Industry6.0 (1.0(Agriculture, Forestry) + 2.0(Agricultural and Water & Water Processing) + 3.0 (Service, Rural Experience, SCM)) perform operations according to specific commands, finally suggested that ease of use can be promoted by presetting and standardizing devices based on big data configuration customized for each regional environment.

• Journal of Intelligence and Information Systems
• /
• v.28 no.2
• /
• pp.237-262
• /
• 2022

There has been a growing interest in IPOs (Initial Public Offerings) due to the profitable returns that IPO stocks can offer to investors. However, IPOs can be speculative investments that may involve substantial risk as well because shares tend to be volatile, and the supply of IPO shares is often highly limited. Therefore, it is crucially important that IPO investors are well informed of the issuing firms and the market before deciding whether to invest or not. Unlike institutional investors, individual investors are at a disadvantage since there are few opportunities for individuals to obtain information on the IPOs. In this regard, the purpose of this study is to provide individual investors with the information they may consider when making an IPO investment decision. This study presents a model that uses machine learning and text analysis to predict whether an IPO stock price would move up or down after the first 5 trading days. Our sample includes 691 Korean IPOs from June 2009 to December 2020. The input variables for the prediction are three tone variables created from IPO prospectuses and quantitative variables that are either firm-specific, issue-specific, or market-specific. The three prospectus tone variables indicate the percentage of positive, neutral, and negative sentences in a prospectus, respectively. We considered only the sentences in the Risk Factors section of a prospectus for the tone analysis in this study. All sentences were classified into 'positive', 'neutral', and 'negative' via text analysis using TF-IDF (Term Frequency - Inverse Document Frequency). Measuring the tone of each sentence was conducted by machine learning instead of a lexicon-based approach due to the lack of sentiment dictionaries suitable for Korean text analysis in the context of finance. For this reason, the training set was created by randomly selecting 10% of the sentences from each prospectus, and the sentence classification task on the training set was performed after reading each sentence in person. Then, based on the training set, a Support Vector Machine model was utilized to predict the tone of sentences in the test set. Finally, the machine learning model calculated the percentages of positive, neutral, and negative sentences in each prospectus. To predict the price movement of an IPO stock, four different machine learning techniques were applied: Logistic Regression, Random Forest, Support Vector Machine, and Artificial Neural Network. According to the results, models that use quantitative variables using technical analysis and prospectus tone variables together show higher accuracy than models that use only quantitative variables. More specifically, the prediction accuracy was improved by 1.45% points in the Random Forest model, 4.34% points in the Artificial Neural Network model, and 5.07% points in the Support Vector Machine model. After testing the performance of these machine learning techniques, the Artificial Neural Network model using both quantitative variables and prospectus tone variables was the model with the highest prediction accuracy rate, which was 61.59%. The results indicate that the tone of a prospectus is a significant factor in predicting the price movement of an IPO stock. In addition, the McNemar test was used to verify the statistically significant difference between the models. The model using only quantitative variables and the model using both the quantitative variables and the prospectus tone variables were compared, and it was confirmed that the predictive performance improved significantly at a 1% significance level.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.28 no.6
• /
• pp.853-865
• /
• 2022

In this study, from August to October 2019, we conducted a survey of the spatial distribution and dominant species of macrobenthos on the rocky intertidal zones of 38 specified islands distributed along the southern coast of Korea. On the basis of observation made using 50 × 50 cm quadrats, we identified a total of 80 species, among which, Mollusca were the most abundant fauna, with 54 species that accounted for 67.4% of the total, followed by Crustacea with 15 species (18.7%). The recorded numbers of Cnidaria, Porifera, and Echinodermata species ranged from 1 to 6. In terms of the regional patterns of species richness, specified islands in Yeosu were found to be the most species rich, supporting 61 species, whereas islands in Hadong, Namhae, and Chujado were found to have a similar level of species richness, ranging from 42 to 46 species. Islands in Boseong and Goheung were home to the fewest species, with only 29 species being recorded. At the sampling station scale, we noted a considerable difference in faunal richness, ranging from 6 (St. 6) to 33 (St. 20) species. Among the recorded species, Echinolittorina radiata was identified as the dominant species on 15 specified islands, with the next most abundant species being Tetraclita japonica, considered an indicator species of climate change, which was recorded on 11 islands. In terms of frequency, E. radiata, found on 36 islands, was identified as the most frequently occurring species, followed by Reishia clavigera (30 islands), Mytilisepta virgata (29), Nerita japonica (28), Ligia. exotica (27), and Littorina brevicula (26). Of the 80 species identified, 9, 4, and 2 species of Mollusca, Crustacea, and Cnidaria, respectively, are classified as Marine fauna of accepted foreign export, whereas 50 are Red List species, 44 are species of Least Concern, 3 are Data Deficient species, and 1 species was not evaluated. However, during the survey, we found no Near Threatened or Not Applicable species. On the basis of the findings of this survey, it would appear that the abundance and richness of macrobenthic fauna inhabiting the rocky intertidal zones of specified islands along the southern coast of Korea differ according to different habitat conditions, particularly with respect to the duration of exposure and the extent and properties of the substrata. The findings of this study will provide baseline data for future monitoring and management of specified islands in Korea.

• Journal of Radiopharmaceuticals and Molecular Probes
• /
• v.9 no.1
• /
• pp.9-16
• /
• 2023

Liposomes as drug delivery system have proved useful carrier for various disease, including cancer. In addition, perfluorocarbon cored microbubbles are utilized in conjunction with high-intensity focused-ultrasound (HIFU) to enable simultaneous diagnosis and treatment. However, microbubbles generally exhibit lower drug loading efficiency, so the need for the development of a novel liposome-based drug delivery material that can efficiently load and deliver drugs to targeted areas via HIFU. This study aims to develop a liposome-based drug delivery material by introducing a substance that can burst liposomes using ultrasound energy and confirm the ability to target tumors using PET imaging. Liposomes (Lipo-DOX, Lipo-DOX-Au, Lipo-DOX-Au-RGD) were synthesized with gold nanoparticles using an avidin-biotin bond, and doxorubicin was mounted inside by pH gradient method. The size distribution was measured by DLS, and encapsulation efficiency of doxorubicin was analyzed by UV-vis spectrometer. The target specificity and cytotoxicity of liposomes were assessed in vitro by glioblastoma U87mg cells to HIFU treatment and analyzed using CCK-8 assay, and fluorescence microscopy at 6-hour intervals for up to 24 hours. For the in vivo study, U87mg model mouse were injected intravenously with 1.48 MBq of ⁶⁴Cu-labeled Lipo-DOX-Au and Lipo-DOX-Au-RGD, and PET images were taken at 0, 2, 4, 8, and 24 hours. As a result, the size of liposomes was 108.3 ± 5.0 nm at Lipo-DOX-Au and 94.1 ± 12.2 nm at Lipo-DOX-Au-RGD, and it was observed that doxorubicin was mounted inside the liposome up to 52%. After 6 hours of HIFU treatment, the viability of U87mg cells treated with Lipo-DOX-Au decreased by around 20% compared to Lipo-DOX, and Lipo-DOX-Au-RGD had a higher uptake rate than Lipo-DOX. In vivo study using PET images, it was confirmed that ⁶⁴Cu-Lipo-DOX-Au-RGD was taken up into the tumor immediately after injection and maintained for up to 4 hours. In this study, drugs released from liposomes-gold nanoparticles via ultrasound and RGD targeting were confirmed by non-invasive imaging. In cell-level experiments, HIFU treatment of gold nanoparticle-coupled liposomes significantly decreased tumor survival, while RGD-liposomes exhibited high tumor targeting and rapid release in vivo imaging. It is expected that the combination of these models with ultrasound is served as an effective drug delivery material with therapeutic outcomes.

• Informatization Policy
• /
• v.30 no.2
• /
• pp.22-45
• /
• 2023

In research on the use of AI-based voice assistant services, problems related to the user's trust and privacy protection arising from the experience of service use are constantly being raised. The purpose of this study was to investigate empirically the effects of individual trust in AI and online privacy concerns on the continued use of AI-based voice assistants, specifically the impact of their interaction. In this study, question items were constructed based on previous studies, with an online survey conducted among 405 respondents. The effect of the user's trust in AI and privacy concerns on the adoption and continuous use intention of AI-based voice assistant services was analyzed using the Heckman selection model. As the main findings of the study, first, AI-based voice assistant service usage behavior was positively influenced by factors that promote technology acceptance, such as perceived usefulness, perceived ease of use, and social influence. Second, trust in AI had no statistically significant effect on AI-based voice assistant service usage behavior but had a positive effect on continuous use intention. Third, the privacy concern level was confirmed to have the effect of suppressing continuous use intention through interaction with trust in AI. These research results suggest the need to strengthen user experience through user opinion collection and action to improve trust in technology and alleviate users' concerns about privacy as governance for realizing digital government. When introducing artificial intelligence-based policy services, it is necessary to disclose transparently the scope of application of artificial intelligence technology through a public deliberation process, and the development of a system that can track and evaluate privacy issues ex-post and an algorithm that considers privacy protection is required.