Neuro-rough Sets for Modeling Conflict between China and Its Neighboring Countries

According to the rough set theory, this paper introduced a neuro-rough model and extends this to a probabilistic domain using a Bayesian framework, trained using a Markov Chain Monte Carlo simulation and the Metropolis algorithms. Firstly, rough set theory was presented, including the granulation of rough set membership function, the network weight formula of probability and rough set formulation. Secondly, the neuro-rough set that was discussed exploits the generalization capacity of neural networks and the transparency advantages of rough set theory. Thirdly, the neuro-rough model was then compared with the genetic algorithm optimized rough set model for the case of modeling of militarized interstate dispute data. Finally, it proposed to construct a neuro-rough model to model interstate conflict between China and its neighboring countries.