Pradhan M, Provan G, Henrion M
Institute of Decision Systems Research, Los Altos, CA 94022.
Proc Annu Symp Comput Appl Med Care. 1994:775-9.
We present an experimental analysis of two parameters that are important in knowledge engineering for large belief networks. We conducted the experiments on a network derived from the Internist-1 medical knowledge base. In this network, a generalization of the noisy-OR gate is used to model causal independence for the multivalued variables, and leak probabilities are used to represent the nonspecified causes of intermediate states and findings. We study two network parameters, (1) the parameter governing the assignment of probability values to the network, and (2) the parameter denoting whether the network nodes represent variables with two or more than two values. The experimental results demonstrate that the binary simplification computes diagnoses with similar accuracy to the full multivalued network. We discuss the implications of these parameters, as well other network parameters, for knowledge engineering for medical applications.
我们对大型信念网络知识工程中两个重要的参数进行了实验分析。我们在源自内科医生-1医学知识库的网络上进行了实验。在这个网络中，噪声或门的一种推广形式被用于对多值变量的因果独立性进行建模，并且泄漏概率被用于表示中间状态和发现的未指定原因。我们研究了两个网络参数，（1）用于为网络分配概率值的参数，以及（2）表示网络节点代表具有两个还是两个以上值的变量的参数。实验结果表明，二元简化计算诊断的准确性与完整的多值网络相似。我们讨论了这些参数以及其他网络参数对医学应用知识工程的影响。
