Bayesian Networks (BNs) are good tools for representing knowledge and reasoning under conditions of uncertainty. In general, learning Bayesian Network structure from a data-set is considered a NP-hard problem, due to ...
详细信息
ISBN:
(纸本)9781467358125
Bayesian Networks (BNs) are good tools for representing knowledge and reasoning under conditions of uncertainty. In general, learning Bayesian Network structure from a data-set is considered a NP-hard problem, due to the search space complexity. A novel structure-learning method, based on PSO (Particle Swarm Optimization) and the k2 algorithm, is presented in this paper. To learn the structure of a bayesian network, PSO here is used for searching in the space of orderings. Then the fitness of each ordering is calculated by running the k2 algorithm and returning the score of the network consistent with it. The experimental results demonstrate that our approach produces better performance compared to others BN structure learning algorithms.
Since it is an NP-hard problem to learn a Bayesian network from data, when the number of data is large, the process of learning Bayesian networks structure is prone to get into premature convergence, then obtain local...
详细信息
Since it is an NP-hard problem to learn a Bayesian network from data, when the number of data is large, the process of learning Bayesian networks structure is prone to get into premature convergence, then obtain local optimal Bayesian networks under Particle Swarm Optimization algorithm(PSO), a novel approach is proposed. The binary code quantum-behaved particle swarm optimization algorithm(BCQPSO) and Bayesian Information Criterion score(BIC) are applied to obtain an optimal Bayesian network. In order to evaluate the matching degree between Bayesian networks and original network structure, BIC score is proposed. The proposed algorithm–BCQPSO is to seek out Bayesian networks that match sample data sets and have a higher BIC score. Besides, in order to get a more optimal network structure, the process of searching has deleted cycle. The ASIA network is used to test the proposed technique, which has a better performance than k2, Maximum Weight Spanning Tree(MWST), and PSO.
Customer losing problems are concerned by telecom operators as market becoming more competitive. Based on data mining technology, Bayesian networks classifier is used in the analysis of the problems. During the proces...
详细信息
Customer losing problems are concerned by telecom operators as market becoming more competitive. Based on data mining technology, Bayesian networks classifier is used in the analysis of the problems. During the process of Bayesian networks modeling, k2 and MCMC algorithms are utilized together. Effective variables are distilled through topology of networks, and churn rules are drawn based on CPT (condition probability table), then high probability churn customer groups are obtained. Considering loss function in classifier, different criterions and their class effects are provided. In contrast with other algorithm, such as decision tree and ANN (artificial neural networks), Bayesian networks can be modeled without over-sampling, when churn rate is relatively low.
暂无评论