分享到:

基于遗传算法的Bayesian网结构增量学习的研究

已建成的Bayesian网与领域环境间可能存在较大偏差,加之领域本身固有的动态变化特性,因此在观察到新数据时,改善Bayesian网的性能和优化网络结构是十分必要的.提出了一种基于遗传算法的Bayesian  (本文共6页) 阅读全文>>

吉林大学
吉林大学

基于进化算法的Bayesian网结构学习研究

Bayesian网是联合概率分布的图形表示方式,目前已成为人工智能领域中不确定问题处理的一种强有力工具。仅由人类专家建造Bayesian网是困难的,从数据中学习Bayesian网已成为近年来十分活跃的研究领域。本文提出了两种基于进化算法的Bayesian网结构学习算法。一种是基于(μ,λ)-ES进化策略的Bayesian网结构增量学习算法。该算法可以在没有旧数据的情况下,完全通过上一次学习所得出的Bayesian网及新获得的训练数据进行增量学习,克服了目前多数算法需要保存旧数据的缺点,节省了存储空间。本文还提出了一种具有较小搜索空间的Bayesian网结构学习算法,首先使用蚁群算法对变量的顺序进行学习。然后在最优变量顺序下,利用遗传算法对结构进行学习,算法中使用一种新的编码方式,使进化过程中不会产生含有环的非法结构。该算法的搜索空间小于目前多数算法的搜索空间。实验结果表明,本文提出的两种算法能有效的进行Bayesian网结构学习...  (本文共77页) 本文目录 | 阅读全文>>

《Geo-Spatial Information Science》2005年02期
Geo-Spatial Information Science

Bayesian and Geostatistical Approaches to Combining Categorical Data Derived from Visual and Digital Processing of Remotely Sensed Images

This paper seeks a synthesis of Bayesian and geostatistical approaches to combining categorical data in the context of remote sensing classification. By experiment with aerial photographs and Landsat TM data, accuracy of spectral, spatial, and combined classification results was evaluated. It was confirmed that the incorporation of spatial information in spectral classi...  (本文共9页) 阅读全文>>

《Engineering Sciences》2005年03期
Engineering Sciences

Method of Satellite Fault Diagnosis Based on Bayesian Network

Based on Bayesian network, a new method to diagnose satellite faults is presented. The Bayesian network model of physical processing of satellite is developed; the main idea...  (本文共6页) 阅读全文>>

《Journal of Beijing Institute of Technology(English Edition)》2005年01期
Journal of Beijing Institute of Technology(English Edition)

Application of Bayesian Dynamic Forecast in Anomaly Detection

A macroscopical anomaly detection method based on intrusion statistic and Bayesian dynamic forecast is presented. A large number of alert data that cannot be dealt with in time are always aggregated in control centers of large-scale i...  (本文共4页) 阅读全文>>

《International Journal of Plant Engineering and Management》2005年01期
International Journal of Plant Engineering and Management

Bayesian Diagnostic Network: A Powerful Model for Representation and Reasoning of Engineering Diagnostic Knowledge

Engineering diagnosis is essential to the operation of industrial equipment. The key to successful diagnosis is correct knowledge representation and reasoning. The Bayesian network is a powerful tool for it. This paper utilizes the Bayesian network to represent and reason diagnostic knowledge, named Bayesian diagnostic network. It pr...  (本文共8页) 阅读全文>>

《Journal of Systems Engineering and Electronics》2005年03期
Journal of Systems Engineering and Electronics

Bayesian target tracking based on particle filter

For being able to deal with the nonlinear or non Gaussian problems, particle filters have been studied by many researchers. Based on particle filter, the extended Kalman filter (EKF) proposal fu...  (本文共5页) 阅读全文>>