• Journal of Intelligence and Information Systems
• /
• v.19 no.2
• /
• pp.55-71
• /
• 2013

The prediction model is the main factor affecting the performance of a knowledge-based system for bankruptcy prediction. Earlier studies on prediction modeling have focused on the building of a single best model using statistical and artificial intelligence techniques. However, since the mid-1980s, integration of multiple techniques (hybrid techniques) and, by extension, combinations of the outputs of several models (ensemble techniques) have, according to the experimental results, generally outperformed individual models. An ensemble is a technique that constructs a set of multiple models, combines their outputs, and produces one final prediction. The way in which the outputs of ensemble members are combined is one of the important issues affecting prediction accuracy. A variety of combination schemes have been proposed in order to improve prediction performance in ensembles. Each combination scheme has advantages and limitations, and can be influenced by domain and circumstance. Accordingly, decisions on the most appropriate combination scheme in a given domain and contingency are very difficult. This paper proposes a confidence-based selection approach as part of an ensemble bankruptcy-prediction scheme that can measure unified confidence, even if ensemble members produce different types of continuous-valued outputs. The present experimental results show that when varying the number of models to combine, according to the creation type of ensemble members, the proposed combination method offers the best performance in the ensemble having the largest number of models, even when compared with the methods most often employed in bankruptcy prediction.

• Journal of Internet of Things and Convergence
• /
• v.10 no.4
• /
• pp.101-108
• /
• 2024

Indoor localization is a critical component for numerous applications, ranging from navigation in large buildings to emergency response. This paper presents an enhanced Pedestrian Dead Reckoning (PDR) scheme using smartphone sensors, integrating neural network-aided motion recognition, Kalman filter-based error correction, and multi-sensor data fusion. The proposed system leverages data from the accelerometer, magnetometer, gyroscope, and barometer to accurately estimate a user's position and orientation. A neural network processes sensor data to classify motion modes and provide real-time adjustments to stride length and heading calculations. The Kalman filter further refines these estimates, reducing cumulative errors and drift. Experimental results, collected using a smartphone across various floors of University, demonstrate the scheme's ability to accurately track vertical movements and changes in heading direction. Comparative analyses show that the proposed CNN-LSTM model outperforms conventional CNN and Deep CNN models in angle prediction. Additionally, the integration of barometric pressure data enables precise floor level detection, enhancing the system's robustness in multi-story environments. Proposed comprehensive approach significantly improves the accuracy and reliability of indoor localization, making it viable for real-world applications.

• Journal of the Korean earth science society
• /
• v.29 no.2
• /
• pp.163-174
• /
• 2008

In this study, we compared textbook knowledge organization with students' mental models to contribute to a more well-designed instruction scheme. The selected science content was the cause of moon phases. We investigated 9 textbooks and 25 third-year middle school students. Patterns and features in participants' mental models were identified through cross inter-rater data analysis by 9 researchers, including in service teachers and experts in science education. According to the results, observing and modeling are the main activities engaged in when dealing with moon phases. The activities consisted of such concepts as: lunar revolution, the sun's parallel rays, the illuminated half of moon, and the relative positions of the sun, moon, and earth. Each concept involved inquiry skills such as: creating and manipulating models, utilizing the relationship between time and space, and communicating. However, the most important skills which are required for authentic scientific inquiry, namely controlling variables and formulating hypotheses, were missing. We categorized students' mental models into three types: scientific models, mixed models, and alternative models. The knowledge structure of each of the models was also discussed in this paper. Consequently, it was found that, typically, students were not given enough opportunities to strengthen the connection among ideas.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.4
• /
• pp.111-116
• /
• 2018

This research examines the drop impact of an external cooling unit package of an air conditioner system. The packaging is composed of a shock-absorbing material, which protects the package contents by absorbing the impact energy and other parts for fixture. Accurate quantification of the impact acceleration experienced by the package contents is necessary to design an effective packaging with minimal volume and sufficient shock absorbing capacity. Explicit time integration was used for the drop impact analyses. A finite element model of the package was constructed, material testing and material model selection were carried out, and sensors for data acquisition were modeled to obtain accurate simulation results. The results were compared with real physical test data. Due to imprecise modeling of the damping, the acceleration and strain values predicted by the simulation were larger than those from physical test. However, the trend of the history data and the peak deceleration value in the direction of impact showed good agreements. Thus, the analysis model and scheme are suitable for the design of an air conditioner cooling unit package.

• Journal of the Korean Geophysical Society
• /
• v.3 no.3
• /
• pp.161-174
• /
• 2000

Bayesian inversion is a stable approach to infer the subsurface structure with the limited data from geophysical explorations. In geophysical inverse process, due to the finite and discrete characteristics of field data and modeling process, some uncertainties are inherent and therefore probabilistic approach to the geophysical inversion is required. Bayesian framework provides theoretical base for the confidency and uncertainty analysis for the inference. However, most of the Bayesian inversion require the integration process of high dimension, so massive calculations like a Monte Carlo integration is demanded to solve it. This method, though, seemed suitable to apply to the geophysical problems which have the characteristics of highly non-linearity, we are faced to meet the promptness and convenience in field process. In this study, by the Gaussian approximation for the observed data and a priori information, fast Bayesian inversion scheme is developed and applied to the model problem with electric well logging and dipole-dipole resistivity data. Each covariance matrices are induced by geostatistical method and optimization technique resulted in maximum a posteriori information. Especially a priori information is evaluated by the cross-validation technique. And the uncertainty analysis was performed to interpret the resistivity structure by simulation of a posteriori covariance matrix.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.1
• /
• pp.634-640
• /
• 2020

The information security management system (ISMS) and the personal information management system (PIMS) have been integrated into a personal information & information security management system (ISMS-P) certification scheme in response to requests to reduce the time and cost to prepare certification schemes. Integration of the certification system has made it possible for the system operator to gain the advantage of easy management of the ISMS-P certification system, and the certification target organization can enjoy the advantage of easy acquisition and maintenance of certification. However, ambiguity in the application criteria of the target organization, and ambiguity in the certification criteria control items require the target organization to operate an excessive management system, and the legal basis to be applied to the certification target organization is ambiguous. In order to improve these problems, this paper uses case studies to identify the types of certification bodies that apply the certification criteria, and to change the control items applied during certification audits based on the types of certification bodies. Institutions that wish to obtain only ISMS certification have proposed three solutions, excluding controls covered by the ISMS-P. This paper suggests ways to operate an efficient certification system, and can be used as a basis for improving problems in the ISMS-P certification system.

• Composites Research
• /
• v.13 no.5
• /
• pp.50-59
• /
• 2000

In this paper, two methods to suppress flutter of the composite panel are examined. First, in the active control method, a controller based on the linear optimal control theory is designed and control input voltage is applied on the actuators and a PZT is used as actuator. Second, a new technique, passive suppression scheme, is suggested for suppression of the nonlinear panel flutter. In the passive suppression scheme, a shunt circuit which consists of inductor-resistor is used to increase damping of the system and as a result the flutter can be attenuated. A passive damping technology, which is believed to be more robust suppression system in practical operation, requires very little or no electrical power and additional apparatuses such as sensor system and controller are not needed. To achieve the great actuating force/damping effect, the optimal shape and location of the actuators are determined by using genetic algorithms. The governing equations are derived by using extended Hamilton's principle. They are based on the nonlinear von Karman strain-displacement relationship for the panel structure and quasi-steady first-order piston theory for the supersonic airflow. The discretized finite element equations are obtained by using 4-node conforming plate element. A modal reduction is performed to the finite element equations in order to suppress the panel flutter effectively and nonlinear-coupled modal equations are obtained. Numerical suppression results, which are based on the reduced nonlinear modal equations, are presented in time domain by using Newmark nonlinear time integration method.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.29 no.1A
• /
• pp.31-43
• /
• 2009

In this study, the numerical method is presented, which can consider the various train types and can solve the equations of motion for a vehicle-bridge interaction analysis by non-iteration procedure through formulating the coupled equations of motion. The coupled equations of motion for the vehicle-bridge interaction are solved by the Newmark ${\beta}$ of a direct integration method, and by composing the effective stiffness matrix and the effective force vector according to a analysis step, those can be solved with the same manner of the solving procedure of equilibrium equations in static analysis. Also, the effective stiffness matrix is reconstructed by the Skyline method for increasing the analysis effectiveness. The Cholesky's matrix decomposition scheme is applied to the analysis procedure for minimizing the numerical errors that can be generated in directly calculating the inverse matrix. The equations of motion for the conventional trains are derived, and the numerical models of the conventional trains are idealized by a set of linear springs and dashpots with 16 degrees of freedom. The bridge models are simplified by the 3 dimensional space frame element which is based on the Euler-Bernoulli theory. The rail irregularities of vertical and lateral directions are generated by the PSD functions of the Federal Railroad Administration (FRA). The results of the vehicle-bridge interaction analysis are verified by the experimental results for the railway plate girder bridges of a span length with 12 m, 18 m, and the experimental and analytical data are applied to the low pass filtering scheme, and the basis frequency of the filtering is a 2 times of the 1st fundamental frequency of a bridge bending.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.26 no.5
• /
• pp.939-951
• /
• 2002

We propose a new multiscale Galerkin method based on interpolation wavelets for two-dimensional Poisson's and plane elasticity problems. The major contributions of the present work are: 1) full multiresolution numerical analysis is carried out, 2) general boundaries are handled by a fictitious domain method without using a penalty term or the Lagrange multiplier, 3) no special integration rule is necessary unlike in the (bi-)orthogonal wavelet-based methods, and 4) an efficient adaptive scheme is easy to incorporate. Several benchmark-type problems are considered to show the effectiveness and the potentials of the present approach. is 1-2m/s and impact deformation of the electrode depends on the strain rate at that velocity, the dynamic behavior of the sinter-forged Cu-Cr is a key to investigate the impact characteristics of the electrodes. The dynamic response of the material at the high strain rate is obtained from the split Hopkinson pressure bar test using disc-type specimens. Experimental results from both quasi-static and dynamic compressive tests are Interpolated to construct the Johnson-Cook model as the constitutive relation that should be applied to simulation of the dynamic behavior of the electrodes. The impact characteristics of a vacuum interrupter are investigated with computer simulations by changing the value of five parameters such as the initial velocity of a movable electrode, the added mass of a movable electrode, the wipe spring constant, initial offset of a wipe spring and the virtual fixed spring constant.

• Plant Biotechnology Reports
• /
• v.5 no.2
• /
• pp.147-156
• /
• 2011

Efficient Agrobacterium-mediated genetic transformation of Scoparia dulcis L. was developed using Agrobacterium tumefaciens strain LBA4404 harboring the binary vector pCAMBIA1301 with ${\beta}$-glucuronidase (GUS) (uidA) and hygromycin phosphotransferase (hpt) genes. Two-day precultured leaf segments of in vitro shoot culture were found to be suitable for cocultivation with the Agrobacterium strain, and acetosyringone was able to promote the transformation process. After selection on shoot organogenesis medium with appropriate concentrations of hygromycin and carbenicillin, adventitious shoots were developed on elongation medium by twice subculturing under the same selection scheme. The elongated hygromycin-resistant shoots were subsequently rooted on the MS medium supplemented with $1mg\;l^{-1}$ indole-3-butyric acid and $15mg\;l^{-1}$ hygromycin. Successful transformation was confirmed by PCR analysis using uidA- and hpt-specific primers and monitored by histochemical assay for ${\beta}$-GUS activity during shoot organogenesis. Integration of hpt gene into the genome of transgenic plants was also verified by Southern blot analysis. High transformation efficiency at a rate of 54.6% with an average of $3.9{\pm}0.39$ transgenic plantlets per explant was achieved in the present transformation system. It took only 2-3 months from seed germination to positive transformants transplanted to soil. Therefore, an efficient and fast genetic transformation system was developed for S. dulcis using an Agrobacterium-mediated approach and plant regeneration via shoot organogenesis, which provides a useful platform for future genetic engineering studies in this medicinally important plant.