• Asia pacific journal of information systems
• /
• v.19 no.2
• /
• pp.139-155
• /
• 2009

For the last few decades, many studies have tried to explore and unveil venture companies' success factors and unique features in order to identify the sources of such companies' competitive advantages over their rivals. Such venture companies have shown tendency to give high returns for investors generally making the best use of information technology. For this reason, many venture companies are keen on attracting avid investors' attention. Investors generally make their investment decisions by carefully examining the evaluation criteria of the alternatives. To them, credit rating information provided by international rating agencies, such as Standard and Poor's, Moody's and Fitch is crucial source as to such pivotal concerns as companies stability, growth, and risk status. But these types of information are generated only for the companies issuing corporate bonds, not venture companies. Therefore, this study proposes a method for evaluating venture businesses by presenting our recent empirical results using financial data of Korean venture companies listed on KOSDAQ in Korea exchange. In addition, this paper used multi-class SVM for the prediction of DEA-based efficiency rating for venture businesses, which was derived from our proposed method. Our approach sheds light on ways to locate efficient companies generating high level of profits. Above all, in determining effective ways to evaluate a venture firm's efficiency, it is important to understand the major contributing factors of such efficiency. Therefore, this paper is constructed on the basis of following two ideas to classify which companies are more efficient venture companies: i) making DEA based multi-class rating for sample companies and ii) developing multi-class SVM-based efficiency prediction model for classifying all companies. First, the Data Envelopment Analysis(DEA) is a non-parametric multiple input-output efficiency technique that measures the relative efficiency of decision making units(DMUs) using a linear programming based model. It is non-parametric because it requires no assumption on the shape or parameters of the underlying production function. DEA has been already widely applied for evaluating the relative efficiency of DMUs. Recently, a number of DEA based studies have evaluated the efficiency of various types of companies, such as internet companies and venture companies. It has been also applied to corporate credit ratings. In this study we utilized DEA for sorting venture companies by efficiency based ratings. The Support Vector Machine(SVM), on the other hand, is a popular technique for solving data classification problems. In this paper, we employed SVM to classify the efficiency ratings in IT venture companies according to the results of DEA. The SVM method was first developed by Vapnik (1995). As one of many machine learning techniques, SVM is based on a statistical theory. Thus far, the method has shown good performances especially in generalizing capacity in classification tasks, resulting in numerous applications in many areas of business, SVM is basically the algorithm that finds the maximum margin hyperplane, which is the maximum separation between classes. According to this method, support vectors are the closest to the maximum margin hyperplane. If it is impossible to classify, we can use the kernel function. In the case of nonlinear class boundaries, we can transform the inputs into a high-dimensional feature space, This is the original input space and is mapped into a high-dimensional dot-product space. Many studies applied SVM to the prediction of bankruptcy, the forecast a financial time series, and the problem of estimating credit rating, In this study we employed SVM for developing data mining-based efficiency prediction model. We used the Gaussian radial function as a kernel function of SVM. In multi-class SVM, we adopted one-against-one approach between binary classification method and two all-together methods, proposed by Weston and Watkins(1999) and Crammer and Singer(2000), respectively. In this research, we used corporate information of 154 companies listed on KOSDAQ market in Korea exchange. We obtained companies' financial information of 2005 from the KIS(Korea Information Service, Inc.). Using this data, we made multi-class rating with DEA efficiency and built multi-class prediction model based data mining. Among three manners of multi-classification, the hit ratio of the Weston and Watkins method is the best in the test data set. In multi classification problems as efficiency ratings of venture business, it is very useful for investors to know the class with errors, one class difference, when it is difficult to find out the accurate class in the actual market. So we presented accuracy results within 1-class errors, and the Weston and Watkins method showed 85.7% accuracy in our test samples. We conclude that the DEA based multi-class approach in venture business generates more information than the binary classification problem, notwithstanding its efficiency level. We believe this model can help investors in decision making as it provides a reliably tool to evaluate venture companies in the financial domain. For the future research, we perceive the need to enhance such areas as the variable selection process, the parameter selection of kernel function, the generalization, and the sample size of multi-class.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.32 no.5A
• /
• pp.255-266
• /
• 2012

Main cable of a suspension bridge is the important member which shows the overall structure integrity at bridge completion. Configuration of main cable is a free hanging state at cable erection completion and is different from that at bridge completion supporting the dead loads such as hanger, girder, and so on. Accordingly, the configuration control under cable erection is considerably significant because the configuration at cable erection completion has direct influence on that at bridge completion. That is performed by sag adjustments at center, side span and tension adjustments at anchor span. The former needs the sag sensitivity which represents the control quantity of strand length corresponding to that of sag. The latter requires the tension sensitivity which shows the change of strand tension according to that of strand temperature. In this study, the fundamental equations of cable were derived with the assumption of either catenary or parabola shape, the differential-related equations using chain rule on horizontal tension were drawn from those and finally the estimation methods of the sag / tension sensitivity were proposed from both those. The nonlinear numerical analysis flow charts of sag sensitivity based on the catenary equations were proposed and the sag sensitivities grounded on the differential-related equations were compared with the results using them for various parameters of sag change. Also, considering the combinations of sag change parameters, the calculation method of the final variation for the cable sag was suggested. For the real suspension bridge under construction with PPWS method, the sag/tension sensitivity were estimated considering the construction conditions like the change of PPWS length, PPWS temperature, bridge span, etc.. We hope that this study will be a systematic guideline for the configuration control under main cable erection and improved highly by field verification in the real bridge site.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.20 no.4
• /
• pp.401-412
• /
• 2008

Simulations of three-dimensional numerical wave tank are performed to investigate wave force acting on a large cylindrical structure and consequent wave deformation, which are induced by bore after breaking waves. The numerical model is based on the three-dimensional Navier-Stokes equations with a finite-difference method combined with a volume of fluid(VOF) method, which is capable of tracking the complex free surface, including wave breaking. In order to promote wave breaking of the incident wave, the approach slope was built seaward of the structure with a constant slope and a large cylindrical structure was installed on a flat bed. The incident waves were broken on the approach slope or flat bed by its wave height. In the present study, all waves acting on the large cylindrical structure were limited to breaking bore after wave breaking. The effects of the position of the structure and the incident wave height on the wave force and wave transformations were mainly investigated with the concern of wave breaking. Further, the relations between the variation of wave energy by wave propagation after wave breaking and wave force acting on the structure were discussed to give the understanding of the full-linear wave-structure interactions in three-dimensional wave fields.

• Journal of the Korean Geotechnical Society
• /
• v.32 no.4
• /
• pp.5-14
• /
• 2016

Numerical simulation of dynamic soil-pile-structure interaction embedded in a dry sand was carried out. 3D model of the dynamic centrifuge model tests was formulated in a time domain to consider nonlinear behavior of soil using the finite difference method program, FLAC3D. As a modeling methodology, Mohr-Coulomb criteria was adopted as soil constitutive model. Soil nonlinearity was considered by adopting the hysteretic damping model, and an interface model which can simulate separation and slip between soil and pile was adopted. Simplified continuum modeling (Kim et al., 2012) was used as boundary condition to reduce analysis time. Calibration process for numerical modeling results and test results was performed through the parametric study. Verification process was then performed by comparing numerical modeling results with another test results. Based on the calibration and validation procedure, it is identified that proposed modeling method can properly simulate dynamic behavior of soil-pile system in dry condition.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.18 no.10
• /
• pp.75-80
• /
• 2017

In this paper, we describe the effect of the regularization method and the network with identity mapping on the performance of the activation functions in deep convolutional neural networks. The activation functions act as nonlinear transformation. In early convolutional neural networks, a sigmoid function was used. To overcome the problem of the existing activation functions such as gradient vanishing, various activation functions were developed such as ReLU, Leaky ReLU, parametric ReLU, and ELU. To solve the overfitting problem, regularization methods such as dropout and batch normalization were developed on the sidelines of the activation functions. Additionally, data augmentation is usually applied to deep learning to avoid overfitting. The activation functions mentioned above have different characteristics, but the new regularization method and the network with identity mapping were validated only using ReLU. Therefore, we have experimentally shown the effect of the regularization method and the network with identity mapping on the performance of the activation functions. Through this analysis, we have presented the tendency of the performance of activation functions according to regularization and identity mapping. These results will reduce the number of training trials to find the best activation function.

• Geophysics and Geophysical Exploration
• /
• v.9 no.3
• /
• pp.241-249
• /
• 2006

Due to the long tectonic history and the very complex geologic formations in Korea, the anisotropic characteristics of subsurface material may often change very greatly and locally. The algorithms commonly used, however, may not give sufficiently precise computational results of traveltime data particularly for the complex and strong anisotropic model, since they are based on the two-dimensional (2D) earth and/or weak anisotropy assumptions. This study is intended to develope a three-dimensional (3D) modeling algorithm to precisely calculate the first arrival time in the complex anisotropic media. Considering the complex geology of Korea, we assume 3D TTI (tilted transversely isotropy) medium having the arbitrary symmetry axis. The algorithm includes the 2D non-linear interpolation scheme to calculate the traveltimes inside the grid and the 3D traveltime mapping to fill the 3D model with first arrival times. The weak anisotropy assumption, moreover, can be overcome through devising a numerical approach of the steepest descent method in the calculation of minimum traveltime, instead of using approximate solution. The performance of the algorithm developed in this study is demonstrated by the comparison of the analytic and numerical solutions for the homogeneous anisotropic earth as well as through the numerical experiment for the two layer model whose anisotropic properties are greatly different each other. We expect that the developed modeling algorithm can be used in the development of processing and inversion schemes of seismic data acquired in strongly anisotropic environment, such as migration, velocity analysis, cross-well tomography and so on.

• Journal of Internet Computing and Services
• /
• v.23 no.4
• /
• pp.21-33
• /
• 2022

Recently, the recommender system has been widely used in various fields such as movies, music, online shopping, and social media, and in the meantime, the recommender model has been developed from correlation analysis through the Apriori model, which can be said to be the first-generation model in the recommender system field. In 2005, many models have been proposed, including deep learning-based models, which are receiving a lot of attention within the recommender model. The recommender model can be classified into a collaborative filtering method, a content-based method, and a hybrid method that uses these two methods integrally. However, these basic methods are gradually losing their status as methodologies in the field as they fail to adapt to internal and external changing factors such as the rapidly changing user-item interaction and the development of big data. On the other hand, the importance of deep learning methodologies in recommender systems is increasing because of its advantages such as nonlinear transformation, representation learning, sequence modeling, and flexibility. In this paper, among deep learning methodologies, RNN, CNN, and GAN-based models suitable for sequential modeling that can accurately and flexibly analyze user-item interactions are classified, compared, and analyzed.

• The Korean Journal of Rheology
• /
• v.11 no.1
• /
• pp.18-27
• /
• 1999

Predicting the deformation behaviors of sheets in thermoforming processes has been a daunting challenge due to the strong nonlinearities arising from very large deformations, mold-polymer contact condition and hyperelasticity constitutive equations. Nonlinear numerical analysis is always required to face this challenge especially for realistic processing conditions. In this study a 3-D algorithm and the membrane approximation are developed for thermoforming processes. The constitutive equation is expressed in terms of the 2nd Piola-Kirchhoff stress tensor and the Cauchy-Green deformation tensor. The 2-term Mooney-Rivlin model is used for the material model equation. The algorithm is established by the finite element formulation employing the total Lagrangian coordinate. The deformation behavior and the stress distribution results of 3-D algorithm with various point boundary conditions are compared to those of the membrane approximation algorithm. Also, the slip boundary condition and the no-slip boundary condition are applied for the systems that have molds. Finally, the effect of sheet temperatures on the final thickness distribution is investigated for the ABS material.

• Geophysics and Geophysical Exploration
• /
• v.7 no.2
• /
• pp.109-116
• /
• 2004

Petroleum reservoir characterization is a process for quantitatively describing various reservoir properties in spatial variability using all the available field data. Porosity and permeability are the two fundamental reservoir properties which relate to the amount of fluid contained in a reservoir and its ability to flow. These properties have a significant impact on petroleum fields operations and reservoir management. In un-cored intervals and well of heterogeneous formation, porosity and permeability estimation from conventional well logs has a difficult and complex problem to solve by conventional statistical methods. This paper suggests an intelligent technique using fuzzy logic and neural network to determine reservoir properties from well logs. Fuzzy curve analysis based on fuzzy logics is used for selecting the best related well logs with core porosity and permeability data. Neural network is used as a nonlinear regression method to develop transformation between the selected well logs and core analysis data. The intelligent technique is demonstrated with an application to the well data in offshore Korea. The results show that this technique can make more accurate and reliable properties estimation compared with previously used methods. The intelligent technique can be utilized a powerful tool for reservoir characterization from well logs in oil and natural gas development projects.

• Journal of Korea Water Resources Association
• /
• v.49 no.1
• /
• pp.61-72
• /
• 2016

In Korea, the aquifers at the coastal areas are mostly shallow alluvial unconfined aquifers. To simulate the flow and dispersion in unconfined aquifer, a FDM model has been developed to solve the nonlinear Boussinesq equation. Related analysis and verification have been executed. The iteration method is used to solve the nonlinearity, and the model shows 3-D shape because it is a 2-D y model that consider the undulation of water table and bottom. For the verification of the model, the output of flow module is compared to the 1-D analytic solution of Lee (1989) which have the drawdown or uplift boundary condition, and the two results show almost the same value. and the mass balance of dispersion module shows about 10% error. The developed model can be used for the analysis and design of the flow and dispersion in the unconfined aquifers. The model has been applied to the estuary area of Ssangcheon watershed, and the parameters have been deduced as a result : hydraulic conductivity is 90 m/day, and longitudinal dispersivity is 15 m. And the analysis with these parameters shows that the wells are situated in the influence circle of each others except for No. 7 well. Groundwater discharge to sea is $3700m^3/day$. And the chlorine ion ($cl^-$) concentration at the pumping wells increase at least 1000 mg/L if groundwater dam is not exist, so the groundwater dam plays an important role for the prevention of sea water intrusion.