A novel three-way decision method in a hybrid information system with images and its application in medical diagnosis
A novel three-way decision method in a hybrid information system with images and its application in medical diagnosis
复制标题
DOI：
10.1016/j.engappai.2020.103651
复制
发表时间：
2020-06
期刊：
影响因子：
--
通讯作者：
Zhaowen Li;Pengfei Zhang;Ningxin Xie;Gangqiang Zhang;Ching-Feng Wen
中科院分区：
文献类型：
--
作者：
Zhaowen Li;Pengfei Zhang;Ningxin Xie;Gangqiang Zhang;Ching-Feng Wen
三向决策是信息处理中有效的启发式方法，而且它为复杂问题的解决提供了一个三分作用的框架。本文结合实际应用场景，提出了一种新颖的三向决策方法并将其应用于医学诊断。首先，我们结合肾炎检查项目的特点，建立了一个信息系统，称为图像混合信息系统，包括尿色、尿结核、pH、红细胞计数、尿刺激、计算机断层扫描、白细胞计数等。其次，为了用图像描述混合信息系统中条件属性集的两个对象，我们提出了基于欧氏距离的混合距离。然后，构建了该系统引入的公差关系。另外，考虑到图像混合信息系统中存在缺失值，采用区间值数来获取损失函数。给定不同类型的参数可以反应决策者的容忍关系水平和风险偏好，决策规则以表格形式呈现。最后通过实例验证了该方法的可行性和合理性。
Three-way decisions are effective and heuristic methods in information processing, moreover, it provides a trisecting-and-acting framework for complex problem solving. In this paper, combining with the practical application scenario, we propose a novel three-way decisions approach and apply it to medical diagnosis. First, we build an information system which is called a hybrid information system with images by considering the characteristics of the examination items of nephritis, including urinary color, urinary tuberculosis, pH, red blood cell count, urinary irritation, computed tomography, white blood cell count and so on. Second, to describe two objects of the conditional attribute set in a hybrid information system with images, we propose the hybrid distance based on Euclidean distance. Then, the tolerance relation induced by this system is constructed. In addition, considering that missing values exist in a hybrid information system with images, interval-valued numbers are used to obtain the loss function. Given different types of parameters can respond the level of the tolerance relation and the risk preference of decision makers, and the decision rules are shown in tabular forms. Finally, an illustration is showed to verify the feasibility and reasonability of the proposed method.