Abstract: Ubiquitous data mining (UDM) is a methodology for creating new knowledge by building an integrated financial database in a ubiquitous computing environment, extracting useful rules by using diverse rule-extraction-based data mining techniques, and combining these rules. In this study, we built six credit rating forecasting models using traditional statistical methods (i.e., logistic regression and Bayesian networks), multilayer perceptron (i.e., MLP), classification tree algorithms (i.e., C5.0), neural network rule extraction algorithms (i.e., NeuroRule), and UDM in order to predict personal credit ratings. To verifythe feasibility and effectiveness of UDM, credit ratings and credit loan data provided by A Financial Group in Korea were used in this study. Empirical results indicated that UDM outperforms other single traditional classifiers such as logistic regression, neural networks, frequency matrix, C5.0, and NeuroRule. UDM always outperforms other single classifiers in credit ratin

• Publication Date: 04-Aug-2013
• DOI: 10.15224/978-981-07-7227-7-09
• Views: 0
• Downloads: 0

Abstract: Magnetic levitation has shown its potential in many engineering fields with promising future applications. This paper deals with the asymptotic tracking problem of desired reference position trajectories in an active mechanical suspension system using magnetic levitation foundations. A differential flatness-based output feedback controller is proposed for accomplishing this control objective using only position measurements. The electromagnetic circuit dynamics is considered for design of the control voltage to regulate the position of the mechanical system in accordance with the specified motion planning. A robust observer is also presented for real-time estimation of the unavailable signals of acceleration and velocity. The electric current is algebraically reconstructed through the estimated signals. The efficient performance of the proposed observer-control scheme is verified by computer simulation.

• Publication Date: 14-Jul-2013
• DOI: 10.15224/978-981-07-7021-1-32
• Views: 0
• Downloads: 0