A game-theoretic perspective on rough set analysis
(0) Determining the correct threshold values for the probabilistic rough set approaches has been a heated issue amongthe community. Existing techniques offer no way in guaranteeing that the calculated values optimize the classification abilityof the decision rules derived from this configuration This article will formulate a game theoretic approach to calculatingthese thresholds to ensure correct approximation region size. Using payoff tables created from approximation measures andmodified conditional risk strategies, we provide the user with tolerance levels (or their loss functions. Using the tolerancevalues. new thresholds are calculated to provide crorrect classification regions. This will aid in determining a set of optimalregion threshold values for decision making.
game theory rough set analysis probabilistic rough sets
YAO Jing-tao HERBERT Joseph P
Department of Computer Science, University of Regina, Regina, Saskatchewan, S4S 0A2 Canada
国内会议
重庆
英文
291-298
2008-05-13（万方平台首次上网日期，不代表论文的发表时间）