• Journal of the Korean Operations Research and Management Science Society
• /
• v.23 no.3
• /
• pp.185-207
• /
• 1998

This research investigates computer generated hybrid second-order model of two numerically based approaches to risk classification : discriminant analysis and neural networks. The hybrid second-order models are derived by rule induction using the ID3 and tested in the several different kinds of data. This new hybrid approach is designed to combine the high prediction accuracy and robustness of DA or NN with perspicuity of ID3. The hybrid model also eliminates the problem of contradictory inputs of ID3. After doing empirical test for the validity of hybrid model using small and medium companies' bankrupt data, hybrid model shows high perspicuity, high prediction accuracy for bankrupt, and simplicity for rules. The hybrid model also shows high performance regardless the type of data such as numeric data, non-numeric data, and combined data.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.31 no.12
• /
• pp.1200-1207
• /
• 2007

An experimental test is presented for photoelastic stress analysis around a crack tip in tensile loaded plate. The hybrid method coupling photoelastsic fringe inputs calculated by finite element method and complex variable formulations involving conformal mappings and analytical continuity is used to calculate full-field stress around the crack tip in uniaxially loaded, finite width tensile plate. In order to accurately compare calculated fringes with experimental ones, both actual and regenerated photoelastic fringe patterns are two times multiplied and sharpened by digital image processing. Regenerated fringes by hybrid method are quite comparable to actual fringes. The experimental results indicate that Mode I stress intensity factor analyzed by the hybrid method are accurate within three percent compared with ones obtained by empirical equation and finite element analysis.

• International Journal of Aeronautical and Space Sciences
• /
• v.16 no.4
• /
• pp.510-519
• /
• 2015

Concerning the issue of high-dimensions, hybrid uncertainties of randomness and intervals including implicit and highly nonlinear limit state function, reliability analysis based on the hybrid uncertainty reliability mode combining with back propagation neural network (HU-BP neural network) is proposed in this paper. Random variables and interval variables are as input layer of the neural network, after the training and approximation of the neural network, the response variables are obtained through the output layer. Reliability index is calculated by solving the optimization model of the most probable point (MPP) searching in the limit state band. Two numerical cases are used to demonstrate the method proposed in this paper, and finally the method is employed to solving an engineering problem of the aerospace friction plate. For this high nonlinear, small failure probability problem with interval variables, this method could achieve a good analysis result.

• Earthquakes and Structures
• /
• v.13 no.3
• /
• pp.289-297
• /
• 2017

This paper presents seismic performance and reliability evaluation on steel-timber hybrid shear wall systems composed of steel moment resisting frames and infill light frame wood shear walls. Based on experimental observations, damage assessment was conducted to determine the appropriate damage-related performance objectives for the hybrid shear wall systems. Incremental time-history dynamic analyses were conducted to establish a database of seismic responses for the hybrid systems with various structural configurations. The associated reliability indices and failure probabilities were calculated by two reliability methods (i.e., fragility analysis and response surface method). Both methods yielded similar estimations of failure probabilities. This study indicated the greatly improved seismic performance of the steel-timber hybrid shear wall systems with stronger infill wood shear walls. From a probabilistic perspective, the presented results give some insights on quantifying the seismic performance of the hybrid system under different seismic hazard levels. The reliability-based approaches also serve as efficient tools to assess the performance-based seismic design methodology and calibration of relative code provisions for the proposed steel-timber hybrid shear wall systems.

• Journal of the Korean Data and Information Science Society
• /
• v.17 no.2
• /
• pp.269-278
• /
• 2006

This paper presents the new hybrid data mining technique using error pattern, modeling of improving classification accuracy. The proposed method improves classification accuracy by combining two different supervised learning methods. The main algorithm generates error pattern modeling between the two supervised learning methods(ex: Neural Networks, Decision Tree, Logistic Regression and so on.) The Proposed modeling method has been applied to the simulation of 10,000 data sets generated by Normal and exponential random distribution. The simulation results show that the performance of proposed method is superior to the existing methods like Logistic regression and Discriminant analysis.

• Journal of KIISE
• /
• v.42 no.7
• /
• pp.939-945
• /
• 2015

From 2009, the market of smart devices has been rapidly increasing. These devices provide various services to users. The cloud messaging service, especially, is applied to many various services, and sends messages asynchronously. In the cloud messaging service, there are two methods for message transmission, message transmission based on an IP address and a publish/subscribe technique. Each technique uses basic messages in order to send messages to mobile devices. In this paper, the hybrid message transmission, based on user-customized analysis to reduce basic messages, is proposed. The hybrid message transmission uses Exponential Moving Average (EMA) and K-means algorithms for user-customized analysis, and determines the message transmission techniques in each timeslot.

• International Journal of Automotive Technology
• /
• v.8 no.6
• /
• pp.791-798
• /
• 2007

The hydraulic hybrid vehicle(HHV) is an application of hydrostatic transmission technology to improve vehicle fuel economy and emissions. A relatively lower energy density of hydraulic accumulator and complicated coordinating operations between two power sources require a special energy management strategy to maximize the fuel saving potential. This paper presents a new type of configuration for parallel HHV to minimize the disadvantages of the hydraulic accumulator, as well as a methodology for developing an energy management strategy tailored specially for PHHV. Based on an analysis of the optimal energy distribution between two power sources over a representative urban driving cycle with a Dynamic Programming(DP) algorithm, a fuzzy-based optimal torque management strategy is designed and developed to control the torque distribution. Simulation results demonstrates that the optimal torque management strategy maximizes the advantages of this hybrid type of configuration, and the high power density characteristics of hydraulic technology effectively improve the robustness of the energy management strategy and fuel economy of the PHHV.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.30 no.4
• /
• pp.27-43
• /
• 2005

This paper presents a new hybrid data mining technique using error pattern modeling to improve classification accuracy when the data type of a target variable is binary. The proposed method increases prediction accuracy by combining two different supervised learning methods. That is, the algorithm extracts a subset of training cases that are predicted inconsistently by both methods, and models error patterns from the cases. Based on the error pattern model, the Predictions of two different methods are merged to generate final prediction. The proposed method has been tested using practical 10 data sets. The analysis results show that the performance of proposed method is superior to the existing methods such as artificial neural networks and decision tree induction.

• Structural Engineering and Mechanics
• /
• v.53 no.5
• /
• pp.1031-1049
• /
• 2015

This paper highlights the role of innovative vibration control system based on two promising properties in a parallel configuration. Hybrid device consists of two main components; recentering wires of shape memory alloy (SMA) and steel pipe section as an energy dissipater element. This approach concentrates damage in the steel pipe and prevents the main structural members from yielding. By regulation of the main adjustable design parameter, an optimum performance of the device is obtained. The effectiveness of the device in passive control of structures is evaluated through nonlinear time history analyses of a five-story steel frame with and without the hybrid device. Comparing the results proves that the hybrid device has a considerable potential to mitigate the residual drift ratio, peak absolute acceleration and peak interstory drift of the structure.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.19 no.3
• /
• pp.274-281
• /
• 2009

The carbon fiber epoxy composite material and aluminum have many advantages over other materials because of their high specific stiffness and good fatigue characteristics. Basically, the propeller shaft of automobile requires bending frequency of higher than 2,700 Nm and high natural frequency of higher than 9,200 rpm occurred by fast revolution. For this reason, natural frequency and torsion torque characteristics of hybrid shaft was studied in variation of its outer-diameter and thickness. Vibration and torque characteristics of hybrid shaft were compared by torsion tester, natural frequency experiments and FE analysis. Designed hybrid shaft satisfied its vibration and torque characteristics when its outer-diameter was 60 mm and thickness was 5 mm. Therefore, hybrid material enables to manufacture one piece structure hybrid propeller shaft rather than current two piece structure.