• Journal of Intelligence and Information Systems
• /
• 제22권2호
• /
• 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.

• The Korean Journal of Rheology
• /
• 제11권2호
• /
• pp.143-152
• /
• 1999

Using a Rheometrics Fluids Spectrometer(RFS II), the steady shear flow and the small-amplitude dynamic viscoelastic properties of three kinds of semi-solid food materials(mayonnaise, tomato ketchup, and wasabi) have been measured over a wide range of shear rates and angular frequencies. The shear rate dependence of steady flow behavior and the angular frequency dependence of dynamic viscoelastic behavior were reported from the experimentally measured data. In addition, some viscoplastic flow models with a yield stress term were employed to make a quantitative evaluation of the steady flow behavior, and the applicability of these models was also examined in detail. Furthermore, the correlations between steady shear flow(nonlinear behavior) and dynamic viscoelastic(linear behavior)properties were discussed using the modified power-law flow equations. Main results obtained from this study can be summarized as follows : (1) Semi-solid food materials are regarded as viscoplastic fluids having a finite magnitude of yield stress, and their flow behavior shows shear-thinning characteristics, exhibiting a decrease in steady flow viscosity with increasing shear rate. (2) The Herschel-Bulkley, Mizrahi-Berk, and Heinz-Casson models are all applicable to describe the steady flow behavior of semi-solid food materials. Among these models, the Heinz-Casson model has the best validity. (3) Semi-solid food materials show a stronger shear-thinning behavior at shear rate region higher than a critical shear rate where a more progressive structure breakdown takes place. (4) Both the storage and loss moduli are increased with increasing angular frequency, but they have a slight dependence on angular frequency. The elastic behavior is dominant to the viscous behavior over a wide range of angular frequencies. (5) All of the steady flow, dynamic, and complex viscosities are well satisfied with the power-law model behavior. The relationships between steady shear flow and dynamic viscoelastic properties can well be described by the modified forms of the power-law flow equations.

• Applied Biological Chemistry
• /
• 제48권1호
• /
• pp.82-88
• /
• 2005

3D QSAR studies for the fungicidal activities against resistive phytophthora blight (RPC; 95CC7303) and sensitive phytophthora blight (Phytopthora capsici) (SPC; 95CC7105) by a series of new 2-alkoxyphenyl-3-phenylthioisoindoline-1-one derivatives (X: A=propynyl & B=2-chloropropenyl) were studied using comparative molecular field analyses (CoMFA) methodology. The CoMFA models were generated from the two different alignment, atom based fit (AF) alignment and field fit (FF) alignment. The atom based alignment exhibited a higher statistical results than that of field fit alignment. The best models, A3 and A7 using combination fields of H-bond field, standard field, LUMO and HOMO molecular orbital field as additional descriptors were selected to improve the statistic of the present CoMFA models. The statistical results of the two models showed the best predictability of the fungicidal activities based on the cross-validated value $q^2\;(r^2_{cv.}=RPC:\;0.625\;&\;SPC:\;0.834)$, non cross-validated value $(r^2_{ncv.}=RPC:\;0.894\;&\;SPC:\;0.915)$ and PRESS value (RPC: 0.105 & SPC: 0.103), respectively. Based on the findings, the predictive ability and fitness of the model for SPC was better than that of the model for RPC. The fugicidal activities exhibited a strong correlation with steric $(66.8{\sim}82.8%)$, electrostatic $(10.3{\sim}4.6%)$ and molecular orbital field (SPC: HOMO, 12.6% and RPC: LUMO, 22.9%) factors of the molecules. The novel selective character for fungicidal activity between two fungi depend on the positive charge of ortho, meta-positions on the N-phenyl ring and size of hydrophilicity of a substituents on the S-phenyl ring.

• The Journal of Engineering Geology
• /
• 제14권4호
• /
• pp.461-468
• /
• 2004

In order to characterize hydraulic property dependant on join roughness in rock mass, this study computed permeability coefficients on each range of joint roughness coefficient (JRC) suggested by Barton(1976). For a quantitative analysis of roughness components spectral analysis using the fast fourier transform was performed to select effective frequencies on each PC range. The results of spectral analyses show that low ranges of the JRC are mainly composed of low frequency domain, while high ranges of the JRC have dominant components at high frequency domain. The inverse Fourier transform made it possible to generate joint models of each JRC range using the effective frequencies of roughness spectrum. The homogenization analysis was applied to calculate permeability coefficient at homogeneous microscale, and then, computes a homogenized permeability coefficient (C-permeability coefficient) at macro scale. Therefore, it is possible to analyze accurate characteristics of permeability reflected with local effect of facture geometry. According to the calculation results, permeability coefficients were distributed between $10^{-3}m/sec\;and\;10^{-4}/sec$. In cases of sheared joint models permeability coefficients were plotted between $10^{-4}m/sec\;and\;10^{-5}/sec$, showing irregular distribution of permeability coefficients on each IRC range. The differences of permeability coefficients for the same aperture models or for the sheared joint models indicate that changes of roughness pattern influence on permeability coefficients. Therefore, the effect of joint roughness should be considered to characterize hydraulic properties in rock joints.

• Journal of the Korean Institute of Landscape Architecture
• /
• 제42권5호
• /
• pp.13-21
• /
• 2014

This study generated regression models to quantify storage and annual uptake of carbon from five native landscape tree species through a direct harvesting method, and established essential information to estimate carbon reduction effects from urban greenspaces. Tree species for the study included the Chionanthus retusus, Prunus armeniaca, Abies holophylla, Cornus officinalis, and Taxus cuspidata, which are usually planted in cities of middle Korea, but for which no information on carbon reduction is available. Ten tree individuals for each species were sampled reflecting various stem diameter sizes at a given interval. The study measured biomass for each part including the roots of sample trees to compute total carbon storage per tree. The annual carbon uptake per tree was quantified by analyzing the radial growth rates of stem samples at breast height or ground level. Regression models were developed using diameter at breast height (dbh) or ground level (dg) as an independent variable to easily estimate storage and annual uptake of carbon per tree for each species. All the regression models showed high fitness with $r^2$ values of 0.92~0.99. Storage and annual uptake of carbon from a tree with dbh of 10 cm were greatest with C. retusus (20.0 kg and 5.9 kg/yr, respectively), followed by P. armeniaca (17.5 kg and 4.5 kg/yr) and A. holophylla (13.2kg and 1.8 kg/yr) in order. A C. officinalis tree and T. cuspidata tree with dg of 10 cm stored 9.3 and 6.3 kg of carbon and annually sequestered 3.2 and 0.6 kg, respectively. The above-mentioned carbon storage equaled the amount of carbon emitted from gasoline consumption of about 23~35 L for C. retusus, P. armeniaca, and A. holophylla, and 11~16 L for C. officinalis and T. cuspidata. A tree with the diameter size of 10 cm annually offset carbon emissions from gasoline use of about 6~10 L for C. retusus, P. armeniaca, and C. officinalis, and 1~3 L for A. holophylla and T. cuspidata. The study breaks new ground to easily quantify biomass and carbon reduction for the tree species by overcoming difficulties in direct cutting and root digging of urban landscape trees.

• Journal of Korea Water Resources Association
• /
• 제54권9호
• /
• pp.731-745
• /
• 2021

In this study, the monthly temperature of the Han River basin was predicted by statistical multiple regression models that use global climate indices and weather data of the target region as predictors. The optimal predictors were selected through teleconnection analysis between the monthly temperature and the preceding patterns of each climate index, and forecast models capable of predicting up to 12 months in advance were constructed by combining the selected predictors and cross-validating the past period. Fore each target month, 1000 optimized models were derived and forecast ranges were presented. As a result of analyzing the predictability of monthly temperature from January 1992 to December 2020, PBIAS was -1.4 to -0.7%, RSR was 0.15 to 0.16, NSE was 0.98, and r was 0.99, indicating a high goodness-of-fit. The probability of each monthly observation being included in the forecast range was about 64.4% on average, and by month, the predictability was relatively high in September, December, February, and January, and low in April, August, and March. The predicted range and median were in good agreement with the observations, except for some periods when temperature was dramatically lower or higher than in normal years. The quantitative temperature forecast information derived from this study will be useful not only for forecasting changes in temperature in the future period (1 to 12 months in advance), but also in predicting changes in the hydro-ecological environment, including evapotranspiration highly correlated with temperature.

• Korean Journal of Remote Sensing
• /
• 제39권2호
• /
• pp.193-205
• /
• 2023

A large amount of floating debris from land-based sources during heavy rainfall has negative social, economic, and environmental impacts, but there is a lack of monitoring systems for floating debris accumulation areas and amounts. With the recent development of artificial intelligence technology, there is a need to quickly and efficiently study large areas of water systems using drone imagery and deep learning-based object detection models. In this study, we acquired various images as well as drone images and trained with You Only Look Once (YOLO)v5s and the recently developed YOLO7 and YOLOv8s to compare the performance of each model to propose an efficient detection technique for land-based floating debris. The qualitative performance evaluation of each model showed that all three models are good at detecting floating debris under normal circumstances, but the YOLOv8s model missed or duplicated objects when the image was overexposed or the water surface was highly reflective of sunlight. The quantitative performance evaluation showed that YOLOv7 had the best performance with a mean Average Precision (intersection over union, IoU 0.5) of 0.940, which was better than YOLOv5s (0.922) and YOLOv8s (0.922). As a result of generating distortion in the color and high-frequency components to compare the performance of models according to data quality, the performance degradation of the YOLOv8s model was the most obvious, and the YOLOv7 model showed the lowest performance degradation. This study confirms that the YOLOv7 model is more robust than the YOLOv5s and YOLOv8s models in detecting land-based floating debris. The deep learning-based floating debris detection technique proposed in this study can identify the spatial distribution of floating debris by category, which can contribute to the planning of future cleanup work.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• 제43권1호
• /
• pp.43-54
• /
• 2023

Due to climate change, drought and flood occurrences have been increasing. Accurate projections of watershed discharges are imperative to effectively manage natural disasters caused by climate change. However, climate change and hydrological model uncertainty can lead to imprecise analysis. To address this issues, we used two lumped models, IHACRES and GR4J, to compare and analyze the changes in discharges under climate stress scenarios. The Hapcheon and Seomjingang dam basins were the study site, and the Nash-Sutcliffe efficiency (NSE) and the Kling-Gupta efficiency (KGE) were used for parameter optimizations. Twenty years of discharge, precipitation, and temperature (1995-2014) data were used and divided into training and testing data sets with a 70/30 split. The accuracies of the modeled results were relatively high during the training and testing periods (NSE>0.74, KGE>0.75), indicating that both models could reproduce the previously observed discharges. To explore the impacts of climate change on modeled discharges, we developed climate stress scenarios by changing precipitation from -50 % to +50 % by 1 % and temperature from 0 ℃ to 8 ℃ by 0.1 ℃ based on two decades of weather data, which resulted in 8,181 climate stress scenarios. We analyzed the yearly maximum, abundant, and ordinary discharges projected by the two lumped models. We found that the trends of the maximum and abundant discharges modeled by IHACRES and GR4J became pronounced as changes in precipitation and temperature increased. The opposite was true for the case of ordinary water levels. Our study demonstrated that the quantitative evaluations of the model uncertainty were important to reduce the impacts of climate change on water resources.

• Investigative Magnetic Resonance Imaging
• /
• 제10권2호
• /
• pp.98-107
• /
• 2006

Magnetization Transfer (MT) imaging generates contrast dependent on the phenomenon of magnetization exchange between free water proton and restricted proton in macromolecules. In biological materials in knee, MT or cross-relaxation is commonly modeled using two spin pools identified by their different T2 relaxation times. Two models for cross-relaxation emphasize the role of proton chemical exchange between protons of water and exchangeable protons on macromolecules, as well as through dipole-dipole interaction between the water and macromolecule protons. The most essential tool in medical image manipulation is the ability to adjust the contrast and intensity. Thus, it is desirable to adjust the contrast and intensity of an image interactively in the real time. The proton density (PD) and T2-weighted SE MR images allow the depiction of knee structures and can demonstrate defects and gross morphologic changes. The PD- and T2-weighted images also show the cartilage internal pathology due to the more intermediate signal of the knee joint in these sequences. Suppression of fat extends the dynamic range of tissue contrast, removes chemical shift artifacts, and decreases motion-related ghost artifacts. Like fat saturation, phase sensitive methods are also based on the difference in precession frequencies of water and fat. In this study, phase sensitive methods look at the phase difference that is accumulated in time as a result of Larmor frequency differences rather than using this difference directly. Although how MT work was given with clinical evidence that leads to quantitative model for MT in tissues, the mathematical formalism used to describe the MT effect applies to explaining to evaluate knee disorder, such as anterior cruciate ligament (ACL) tear and meniscal tear. Calculation of the effect of the effect of the MT saturation is given in the magnetization transfer ratio (MTR) which is a quantitative measure of the relative decrease in signal intensity due to the MT pulse.

• KDI Journal of Economic Policy
• /
• 제30권2호
• /
• pp.225-270
• /
• 2008

We analyze macroeconomic consequences of pay-as-you-go (PAYGO) public pension system with a simple overlapping generations model. Contrary to large body of existing literatures offering quantitative results based on simulation study, we take another route by adopting a highly simplified framework in search of qualitatively tractable analytical results. The main contribution of our results lies in providing a sound theoretical foundation that can be utilized in interpreting various quantitative results offered by simulation studies of large scale general equilibrium models. We present a simple overlapping generations model with a defined benefit(DB) PAYGO public pension system as a benchmark case and derive an analytical equilibrium solution utilizing graphical illustration. We also discuss the modifications of the benchmark model required to encompass a defined contribution(DC) public pension system into the basic framework. Comparative statics analysis provides three important implications; First, introduction and expansion of the PAYGO public pension, DB or DC, result in lower level of capital accumulation and higher expected rate of return on the risky asset. Second, it is shown that the progress of population aging is accompanied by lower capital stock due to decrease in both demand and supply of risky asset. Moreover, risk premium for risky asset increases(decreases) as the speed of population aging accelerates(decelerates) so that the possibility of so-called "the great meltdown" of asset market cannot be excluded although the odds are not high. Third, it is most likely that the switch from DB PAYGO to DC PAYGO would result in lower capital stock and higher expected return on the risky asset mainly due to the fact that the young generation regards DC PAYGO pension as another risky asset competing against the risky asset traded in the market. This theoretical prediction coincides with one of the firmly established propositions in empirical literature that the currently dominant form of public pension system has the tendency to crowd out private capital accumulation.