نقشه های شناختی فازی خاکستری مبتنی بر سیستم پشتیبانی تصمیم گیری برای برنامه ریزی

Recently, Fuzzy Grey Cognitive Map (FGCM) has been proposed as a FCM extension. It is based on Grey System Theory, that it is focused on solving problems with high uncertainty, under discrete incomplete and small data sets. The FGCM nodes are variables, representing grey concepts. The relationships between nodes are represented by directed edges. An edge linking two nodes models the grey causal influence of the causal variable on the effect variable. Since FGCMs are hybrid methods mixing Grey Systems and Fuzzy Cognitive Maps, each cause is measured by its grey intensity. An improved construction process of FGCMs is presented in this study, proposing an intensity value to assign the vibration of the grey causal influence, thus to handle the trust of the causal influence on the effect variable initially prescribed by experts’ suggestions. The explored methodology is implemented in a well-known medical decision making problem pertaining to the problem of radiotherapy treatment planning selection, where the FCMs have previously proved their usefulness in decision support. Through the examined medical problem, the FGCMs demonstrate their functioning and dynamic capabilities to approximate better human decision making.

Cognitive Maps [1] are signed digraphs designed to capture the causal assertions of a person with respect to a certain domain and then use them to analyze the effects of alternatives, e.g.: policies or business decisions in respect to achieving certain goals. A Fuzzy Cognitive Map (FCM) is a graphical representation consisting of nodes indicating the most relevant factors of a decisional environment; and links between these nodes model the relationships between those ones [11]. FCM is a modeling methodology for complex decision systems [7], [17] and [27], which has originated from the combination of fuzzy logic and neural networks. A FCM describes the behavior of a system in terms of concepts; each concept representing an entity, a state, a variable, or a characteristic of the system [5], [23], [26], [30] and [32]. FCMs constitute neuro-fuzzy systems, which are able to incorporate experts’ knowledge [10], [11], [13], [16], [20] and [24]. Recently, a FCM extension, called Fuzzy Grey Cognitive Map (FGCM), has been proposed by Salmeron [25]. FGCM is based on Grey System Theory (GST). The improved results obtained with the FGCM in comparison with the conventional FCM approach on an Information Technology application [25] motivated us to investigate an enhanced FGCM model for decision support. The model presented in this paper co-evaluates human hesitancy through greyness not only in the definition of the causal relations between the concepts, but also in the definition of the concept values. The proposed methodology of FGCMs is applied to a two-level integrated decision support tool, constructed to handle the complex problem of making decisions in radiation therapy treatment. The tool consists of a clinical treatment simulation tool and a supervisor decision making tool based both on FGCMs, using the construction process. Fuzzy Grey Cognitive Map-based Decision Support System (FGCM-DSS) results are meaningful as weight and concepts values are measured by their grey intensity to describe more reliable than the causal influences among concepts as well as the concepts steady states and encourage our research towards this type of Decision Support Systems in medicine. The outline of this paper is as follow. Section 2 presents briefly the Grey System Theory. Section 3 describes the Fuzzy Grey Cognitive Map technique and its advantages over classical Fuzzy Cognitive Map. Section 4 shows the medical problems and their experimental analysis. In Section 5, the results with the discussion follow, and Section 6 concludes the paper and discusses the usefulness of the new methodology for FGCMs. Finally, an appendix shows several tables with all the relevant problem’s data.

This study presents the results of a research on the problem of modeling medical knowledge and capturing the system’s behavior for decision support of radiotherapy treatment planning by using the new approach of FGCMs. More specific, this work proposes a decision support tool based on FGCM formalism for assessing radiotherapy decision making by proposing acceptable system behavior through updated weights that include the inherent uncertainty and fuzziness present in the medical domain. Our proposal represent a worthy approach that exhibits several advantages over the FCM one. It enables modeling of the uncertainty and experts’ hesitancy introduced in the description of the causal relations between the concepts of the cognitive map and in the description of the problem’s components. It is more general and approximate human decision making better than FCM. The output of the process includes a greyness measurement representing the uncertainty associated to the solution. Moreover, FGCMs are able to manage new kinds of relationships regarding FCM. The scope of the proposed methodology was not to achieve better accuracies or results compared with the FCM approaches, but to introduce a novel framework based on the FGCM-DSS that enhanced by greyness in concepts and edges values. Through the results, the prospective performance of the decision support framework based on FGCMs is emerged and encourage us continue towards the direction on including greyness in concepts and causal influences among concepts, thus making decisions contributing to more intelligent systems.