• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.9
• /
• pp.4684-4705
• /
• 2019

Collaborative filtering recommender systems are vulnerable to shilling attacks in which malicious users may inject biased profiles to promote or demote a particular item being recommended. To tackle this problem, many robust collaborative recommendation methods have been presented. Unfortunately, the robustness of most methods is improved at the expense of prediction accuracy. In this paper, we construct a robust Bayesian probabilistic matrix factorization model for collaborative filtering recommender systems by incorporating the detection of user anomaly rating behaviors. We first detect the anomaly rating behaviors of users by the modified K-means algorithm and target item identification method to generate an indicator matrix of attack users. Then we incorporate the indicator matrix of attack users to construct a robust Bayesian probabilistic matrix factorization model and based on which a robust collaborative recommendation algorithm is devised. The experimental results on the MovieLens and Netflix datasets show that our model can significantly improve the robustness and recommendation accuracy compared with three baseline methods.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1993.06a
• /
• pp.953-955
• /
• 1993

In this paper we propose a new stability theorem and a robust stability condition for linguistic fuzzy model systems in state space. First we define a stability in linear sense. After representing the fuzzy model by a system with disturbances, A necessary and sufficient condition for the stability is derived. This condition is proved to be a sufficient condition of the fuzzy model. The Q in the Lyapunov equation is iteratively adjusted by an gradient-based algorithm to improve its stability test. Finally, stability robustness bounds of a system having modeling error is derived. An example is also included to show that the stability test is powerful.

• Journal of KIISE:Computer Systems and Theory
• /
• v.27 no.3
• /
• pp.300-312
• /
• 2000

The application areas of embedded real-time systems are very wide and so are the requirements for real-time processing and reliability of the systems. To develop embedded real-time systems effectively with its real-time and reliability properties guaranteed, an appropriate real-time model is needed. Recently, the research on real-time object-oriented model is active, which graft the concept of object-orientation on real-time systems modeling and development. In this paper, we propose dRTO (dependable Real-Time Object) model, with 5 primitive classes. These allow designers to effectively model the characteristics of real-time systems, i.e., object-orientation, real-time-ness and dependability. The dRTO model has three main features. First, it is able to model and implement the timing constraints imposed on real-time objects as well as interactions among the objects. Second, hardware and software components (including kernel) of embedded systems can be modeled in one frame. Third, it is able to represent fault detection and recovery mechanisms explicitly.

• Management & Information Systems Review
• /
• v.25
• /
• pp.371-386
• /
• 2008

In this study, the hypothesized model of internet user satisfaction in e-commerce environment is developed and the relationships among constructs in the model are examined. A Confirmatory factor analysis is employed to analyze the relationships between the multiple dependent variables and independent variables.

• International Journal of Control, Automation, and Systems
• /
• v.3 no.4
• /
• pp.631-639
• /
• 2005

In this paper, we propose a constructive realization procedure for 2D systems which may lead to a Fornasini-Marchesini local state-space model with much lower order than the existing realization procedure given by Bisiacco et al. Nontrivial examples are illustrated and the conditions for minimal realization are also discussed.

• 제어로봇시스템학회:학술대회논문집
• /
• 1996.10a
• /
• pp.239-242
• /
• 1996

A model following control system(MFCS) can give general output signals following desired ones. In previous studies, a method of nonlinear MFCS was proposed by S.Okubo[1]. In this paper, the method of nonlinear MFCS will be extended to discrete time nonlinear systems. It is easy to extend the method to discrete time systems. But in the case .gamma.=1 discrete time systems, the proof becomes difficult, because the transfer function from f(v(k)) to v(k) can't be a positive real function. In this case, to ensure that internal states are stable, a new criterion is proposed.

• International Journal of Control, Automation, and Systems
• /
• v.6 no.5
• /
• pp.785-791
• /
• 2008

This paper considers the problem of robust $H_{\infty}$ control for uncertain 2-D discrete systems in the General Model via output feedback controllers. The parameter uncertainty is assumed to be norm-bounded. The purpose is the design of output feedback controllers such that the closed-loop system is stable while satisfying a prescribed $H_{\infty}$ performance level. In terms of a linear matrix inequality, a sufficient condition for the solvability of the problem is obtained, and an explicit expression of desired output feedback controllers is given. An example is provided to demonstrate the application of the proposed method.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.12 no.3
• /
• pp.259-271
• /
• 2016

This study develops an extended model to predict customer satisfaction in easy payment systems based on information systems success model. Our data was collected from easy payment systems users and analyzed using PLS. This study selected four variables as easy payment systems characteristics(convenience, variety, security, speed) along with gender being used as a moderating variable. The results showed that convenience and security are turned out to affect customer satisfaction. Additionally, the test of difference in gender revealed that with respect to gender, moderating effects exist in security and speed. This implies that this study can provide different promotion strategies according to gender. Overall, the proposed model could be used to predict customers' willingness to pay on the easy payment systems.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.29 no.4
• /
• pp.11-40
• /
• 2004

Organizations have attempted to develop Knowledge Management Systems for achieving competitive advantage by effectively managing organizational knowledge. However, if Knowledge Management Systems are not user-oriented, organizations may not attain desired goals. That is, it must be utilized and accepted by organizational members to be successful systems. This study proposes an extended Technology Acceptance Model and empirically validates it. For that purpose, a research model is set UP that consists of antecedent variables, perception moderators, and intention to use the system. Empirical data analysis found significant relationships among research variables, as suggested in research hypotheses. The results of the analysis indicated that perceived usefulness, ease of use, job relevance and information quality should be considered as important factors in designing Knowledge Management Systems. In addition, perceived value, incentive, affect, self-efficacy, and image were found to influence the perception of users in the usage situation.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1993.06a
• /
• pp.857-860
• /
• 1993

In this paper, we apply the self generating neuro fuzzy model (SGNFM) to the dimension analysis of the chaotic time series. Firstly, we formulate a nonlinear time series identification problem with nonlinear autoregressive (NARMAX) model. Secondly, we propose an identification algorithm using SGNFM. We apply this method to the estimation of embedding dimension for chaotic time series, since the embedding dimension plays an essential role for the identification and the prediction of chaotic time series. In this estimation method, identification problems with gradually increasing embedding dimension are solved, and the identified result is used for computing correlation coefficients between the predicted time series and the observed one. We apply this method to the dimension estimation of a chaotic pulsation in a finger's capillary vessels.