Using the characteristics of chaotic dynamics in the knowledge base of decision support system

Author(s):  
Gennadii Saprykin ◽  
Juliia Kobytska ◽  
Ludmila Kirichenko
2021 ◽  
Vol 11 (1) ◽  
pp. 126-136
Author(s):  
V.V. Antonov ◽  
◽  
K.A. Konev

The article discusses a decision support method using a knowledge base. The relevance of the study of issues related to decision-making in typical situations is shown. In order to increase the effectiveness of management activities, the is-sues of system integration of the regulatory framework, ontological model and knowledge base of the intelligent sub-system of decision support within the framework of the business process are considered. In support of the proposed method, a model has been formed for replenishing the knowledge base both at the structural and analytical levels, which demonstrates the connection between the most important elements of the system: the ontological model, the knowledge base and the normative subsystem. An example of using the proposed scheme is shown. To demonstrate the model of functioning of the decision support system, an algorithm for replenishing the knowledge base is proposed and described. As a conceptual basis for the formal description of the model, operations for working with knowledge are described in the set-theoretic aspect. The principles of adaptation of the ontological model as an information object for linking with the knowledge base are considered. The conceptual diagram of the general structure of the ontological model for making decisions within the framework of the business process as a set of interrelated concepts is proposed and demonstrated. An information model of a specialized database has been developed and presented, serving as a technical basis for building a knowledge base of a decision support system in a typical situation, its main structural el-ements, the principles of their interrelation and an approach to ensuring the consistency of its internal structure are de-scribed.


2017 ◽  
Vol 2017 ◽  
pp. 1-8 ◽  
Author(s):  
Yicheng Jiang ◽  
Bensheng Qiu ◽  
Chunsheng Xu ◽  
Chuanfu Li

In many clinical decision support systems, a two-layer knowledge base model (disease-symptom) of rule reasoning is used. This model often does not express knowledge very well since it simply infers disease from the presence of certain symptoms. In this study, we propose a three-layer knowledge base model (disease-symptom-property) to utilize more useful information in inference. The system iteratively calculates the probability of patients who may suffer from diseases based on a multisymptom naive Bayes algorithm, in which the specificity of these disease symptoms is weighted by the estimation of the degree of contribution to diagnose the disease. It significantly reduces the dependencies between attributes to apply the naive Bayes algorithm more properly. Then, the online learning process for parameter optimization of the inference engine was completed. At last, our decision support system utilizing the three-layer model was formally evaluated by two experienced doctors. By comparisons between prediction results and clinical results, our system can provide effective clinical recommendations to doctors. Moreover, we found that the three-layer model can improve the accuracy of predictions compared with the two-layer model. In light of some of the limitations of this study, we also identify and discuss several areas that need continued improvement.


Sign in / Sign up

Export Citation Format

Share Document