A medical decision support system for disease diagnosis under uncertainty

This paper presents a decision support system (DSS) modeled by a fuzzy expert system (FES) for medical diagnosis to help physicians make better decisions. The proposed system collects comprehensive information about a disease from a group of experts. To this aim, a cross-sectional study is conducted by asking physicians’ expertise on all symptoms relevant to a disease. A fuzzy rule based system is then formed based on this information, which contains a set of significant symptoms relevant to the suspected disease. Linguistic fuzzy values are assigned to model each symptom. The input of the system is the severity level of each symptom reported by patients. The proposed FES considers two approaches to account for uncertain inputs from patients. Two case studies on kidney stone and kidney infection were conducted to demonstrate how the proposed method could be used. A group of patients were used to validate the effectiveness of the proposed expert system. The results show that the proposed fuzzy expert system is capable of diagnosing diseases with a high degree of accuracy and precision comparing to a couple of machine learning methods.     

Design a new mixed expert decision aiding system using fuzzy ELECTRE III method for vendor selection

Any decision process deals with two different concerns as its cornerstones, evaluating the alternatives and ranking them based on their performances. In any decision process, the former phase is usually the premise of the latter one. Alternatives’ evaluation is the concept that largely depends on the experts and their expertise, which increase uncertainty in the decision-making process. In addition to all proposed methods for having the experts’ knowledge as evaluations of the alternatives, utilizing expert decision support systems (EDSS) can be a sensible response to such a need. Having evaluated the alternatives in the first phase of a decision-making process, the second phase of the process deals with the ranking the alternatives based on their performances obtained from the first phase. In this paper, we discuss the architecture of a fuzzy system including both modules, utilizing fuzzy concept for dealing with the uncertainty of the problem. Concerning the problem we had been dealt with, our system comprises a fuzzy evaluation module, which is a fuzzy expert system and an appropriate tool for evaluating the existing alternatives promptly and smoothly, without the imposed time delays by the experts to propose their comments and the uncertainty of such expertise-based comments, and a fuzzy ranking module, which is a fuzzy version of ELECTRE III method ranking the alternatives based on their outranking relations and by considering the existing uncertainty in their performances. This way the final ranking is resulted from an independent fuzzy system, which has considered the existing uncertainty in the evaluations not once but twice. Our proposed system has been applied to a real case of vendor selection process in one of the greatest and the most famous companies in the Iranian oil industry, OIEC, and the results are discussed.     

Analysing network uncertainty for industrial product-service delivery: A hybrid fuzzy approach

More and more manufacturers are transitioning from product-focused operations towards global service-oriented operations through approaches such as an industrial product-service system (IPS²). These systems deliver a blend of goods, equipment and services for improved value/revenue streams and there is a need to leverage the knowledge of domain experts in evaluating the uncertainties of IPS² adoption.Along these lines, this article proposes a hybrid fuzzy methodology that leverages the knowledge of domain experts for evaluating the uncertainty of service networks that deliver an IPS². The proposed methodology conceptualises a framework of network uncertainty metrics and applies a set of fuzzy-based techniques (fuzzy Delphi, fuzzy Analytical Hierarchy Process (fuzzy AHP) and fuzzy Technique for Order of Preference by Similarity to Ideal Solution (fuzzy TOPSIS)) to evaluate levels of fuzziness for transitions from traditional product-focused operations towards service-oriented operations. The applicability of the proposed methodology is demonstrated through a case study of a stainless steel manufacturer and the limitations and generalisation potentials of the research are used to highlight future research challenges for service-oriented uncertainty evaluation.     

Application of simulated annealing fuzzy model tuning to umbilicalcord acid-base interpretation

Fuzzy logic and fuzzy set theory provide an important framework for representing and managing imprecision and uncertainty in medical expert systems, but the need remains to optimize such systems to enhance performance. The paper presents a general technique for optimizing fuzzy models in fuzzy expert systems (FESs) by simulated annealing (SA) and N-dimensional hill climbing simplex method. The application of the technique to a FES for the interpretation of the acid-base balance of blood in the umbilical cord of newborn infants is presented. The Spearman rank order correlation statistic was used to assess and to compare the performance of a commercially available crisp expert system, an initial FES, and a tuned FES with experienced clinicians. Results showed that without tuning, the performance of the crisp system was significantly better (correlation of 0.80) than the FES (correlation of 0.67). The performance of the tuned FES was better than the crisp system and effectively indistinguishable from the clinicians (correlation of 0.93) on training data and was the best of the expert systems on validation data. Unlike most applications of fuzzy logic where all fuzzy sets have normalized heights of unity, in this application it was found that a reduction in the height of some fuzzy sets was effective in enhancing performance. This suggests that the height of fuzzy sets may be a generally useful parameter in tuning FESs     

Multi-criteria group decision making under uncertainty with application to air traffic safety

There are many methods for solving problems of multi-criteria group decision making under uncertainty conditions. It is quite often that decision makers cannot formulate unequivocally their individual preference relations between variants. Analysing the causes of a serious aircraft incident is an example where a group of experts is required to have a very detailed yet interdisciplinary knowledge. Obviously, each expert has only a fraction of such knowledge. Hence, experts can make fuzzy evaluations when they are not sure about them or it is not possible to gain full knowledge. There is a need for a method that in such a case takes into account the strength of preference expressed in the significance of each criterion. Both the significance of criteria and the scores assigned to variants can be represented using fuzzy expressions.The proposed method reflects the problems of decision making when both objective (represented using non-fuzzy expressions) and subjective (represented using linguistic expressions) criteria, are involved. The proposed method enables to obtain a solution without having to conduct negotiations between decision makers. This is of advantage when there is a risk that some experts will be dominated by others. The method not only helps define a single preferred solution but also create the preference relation within a group. By applying this method, it is possible to reproduce the actual preference relations of individual decision makers. Presenting them to decision makers may induce them to change their evaluation of the weights of criteria or how they score variants.     

A model based on 2-tuple fuzzy linguistic representation and Analytic Hierarchy Process for supplier segmentation using qualitative and quantitative criteria

The literature on supply base segmentation has increasingly adopted multi-criteria decision making (MCDM) techniques into recently proposed models. However, most proposals segment the supply base from the standpoint of the purchased item, which prevents them from providing guidelines that are specific to each supplier. Some authors have attempted to overcome these limitations by putting forward portfolio models based on the relationship with suppliers. These approaches use fuzzy variables and MCDM methods that take qualitative judgements by experts as the only input for decision making. However, many companies have databases with historical data about the performance of past transactions with suppliers that should be considered by expert systems that aim to comprehensively evaluate suppliers’ performance. This paper seeks to address this gap by proposing a segmentation model based on the relationship with suppliers capable of aggregating quantitative and qualitative criteria. Analytic Hierarchy Process (AHP) was used to determine the relative importance of each criteria. Fuzzy 2-tuple, a prominent computing with word (CWW) approach, was used to evaluate suppliers with a mixture of historical quantitative data and qualitative judgements by purchasing experts. An illustrative application of the proposed model was carried out in the pharmaceutical supply center (PSC) of a teaching hospital. The proposed model can be viewed as a decision support system capable of aggregating the qualitative judgements of experts and quantitative historical performance measures, thus providing guidelines to improve the relationship between suppliers and the buyer firm.     

A CASE-BASED DECISION SUPPORT SYSTEM FOR INDIVIDUAL STRESS DIAGNOSIS USING FUZZY SIMILARITY MATCHING

Stress diagnosis based on finger temperature (FT) signals is receiving increasing interest in the psycho-physiological domain. However, in practice, it is difficult and tedious for a clinician and particularly less experienced clinicians to understand, interpret, and analyze complex, lengthy sequential measurements to make a diagnosis and treatment plan. The paper presents a case-based decision support system to assist clinicians in performing such tasks. Case-based reasoning (CBR) is applied as the main methodology to facilitate experience reuse and decision explanation by retrieving previous similar temperature profiles. Further fuzzy techniques are also employed and incorporated into the CBR system to handle vagueness, uncertainty inherently existing in clinicians reasoning as well as imprecision of feature values. Thirty-nine time series from 24 patients have been used to evaluate the approach (matching algorithms) and an expert has ranked and estimated similarity. On average goodness-of-fit for the fuzzy matching algorithm is 90% in ranking and 81% in similarity estimation that shows a level of performance close to an experienced expert. Therefore, we have suggested that a fuzzy matching algorithm in combination with CBR is a valuable approach in domains, where the fuzzy matching model similarity and case preference is consistent with the views of domain expert. This combination is also valuable, where domain experts are aware that the crisp values they use have a possibility distribution that can be estimated by the expert and is used when experienced experts reason about similarity. This is the case in the psycho-physiological domain and experienced experts can estimate this distribution of feature values and use them in their reasoning and explanation process.     

Aggregating linguistic expert knowledge in type-2 fuzzy ontologies

In many industrial contexts, knowledge and data provided by experts are imprecise as there seems to be an understanding that “experts do not need precise details as they understand anyway what is meant”. The imprecision inherent in the knowledge that experts acquire in their practice require decision support tools that can be tailored to the specific application contexts to aid complex decisions. As a specific example, expert knowledge expressed in linguistic terms is not precisely structured and concepts are not defined specifically enough in order to be easy to use and process. If we want to represent and use expert knowledge for knowledge-based systems on a general level, that is easily adaptable, we need to find ways to represent and process knowledge elements; our approach is to use interval-valued fuzzy sets, fuzzy ontology and aggregation operators. We show that these instruments will offer us a novel approach for aggregation of imprecise data to obtain actionable knowledge to aid complex decisions. The framework is described and the approach is shown through the context of a fuzzy wine ontology; the problem formulation resembles many features of important and complex decision making problems found in different industries. We describe the potential application of the framework in the case of paper machine maintenance. A web-based application is introduced to better demonstrate the benefits decision-makers can receive from the proposed framework. Additionally, we present an approach to utilize the framework in finding consensual solutions in situations involving several experts.     

A new approach to testing an integrated water systems model using qualitative scenarios

Integrated systems models have been developed over decades, aiming to support the decision-makers in the planning and managing of natural resources. The inherent model complexity, lack of knowledge about the linkages among model components, scarcity of field data, and uncertainty involved with internal and external factors of the real system call their practical usefulness into doubt. Validation tests designed for such models are just immature, and are argued to have some characteristics that differ from the ones used for validating other types of models. A new approach for testing integrated water systems models is proposed, and applied to test the RaMCo model. Expert knowledge is elicited in the form of qualitative scenarios and translated into quantitative projections using fuzzy set theory. Trend line comparison of the projections made by the RaMCO model and the qualitative projections based on expert knowledge revealed an insufficient number of land-use types adopted by the RaMCo model. This insufficiency makes the model inadequate to describe the consequences of the changes in socio-economic factors and policy options on the erosion from the catchment and the sediment yields at the inlet of a storage lake.     

Fuzzy temporal reasoning for process supervision

Abstract: Process supervision consists of following the temporal evolution (change) of process behaviours. This task has usually been performed based on the knowledge and experience of domain experts and operators. Actually, these experts and operators almost always express their experience and knowledge about process evolution in an imprecise, fuzzy and vague way. A good supervision system should be capable of dealing at once with two different kinds of knowledge: time and uncertainty.
For many years, time and uncertainty have been two of the most important topics in Artificial Intelligence research and applications. Many approaches have been proposed to deal with either one or the other. Among the various approaches for time, reified logic has been considered as the most influent one. Possibilistic logic, on the other hand, has shown its ability to handle uncertain knowledge and information. This paper describes an approach for managing temporal uncertainty based on fuzzy logic and possibility theory. A fuzzy temporal expert system shell has been developed to perform process supervision tasks.     

The Need for Fuzzy AI

Artificial intelligence (AI) is once again a topic of huge interest for computer scientists around the world. Whilst advances in the capability of machines are being made all around the world at an incredible rate, there is also increasing focus on the need for computerised systems to be able to explain their decisions, at least to some degree. It is also clear that data and knowledge in the real world are characterised by uncertainty. Fuzzy systems can provide decision support, which both handle uncertainty and have explicit representations of uncertain knowledge and inference processes. However, it is not yet clear how any decision support systems, including those featuring fuzzy methods, should be evaluated as to whether their use is permitted. This paper presents a conceptual framework of indistinguishability as the key component of the evaluation of computerised decision support systems. Case studies are presented in which it has been clearly demonstrated that human expert performance is less than perfect, together with techniques that may enable fuzzy systems to emulate human-level performance including variability. In conclusion, this paper argues for the need for " fuzzy AI” in two senses: (i) the need for fuzzy methodologies (in the technical sense of Zadeh’s fuzzy sets and systems) as knowledge-based systems to represent and reason with uncertainty; and (ii) the need for fuzziness (in the non-technical sense) with an acceptance of imperfect performance in evaluating AI systems.      

电机自动装配线故障诊断模糊专家系统

为了对电机自动装配线上的故障进行正确有效的诊断，基于其工艺流程，运用模糊逻辑与专家系统知识，利用Visual C 以及Visual Foxpro作为编程工具，作者开发了用于装配线的故障诊断模糊专家系统（简称FES），该系统包括用户接口，知识库，推进机和历史记录数据库，采取模糊前向基于规则推理策略，并能根据可信度预测故障严重性。     

Multicriteria decision making in energy planning using a modified fuzzy TOPSIS methodology

Energy planning is a complex issue which takes technical, economic, environmental and social attributes into account. Selection of the best energy technology requires the consideration of conflicting quantitative and qualitative evaluation criteria. When decision-makers’ judgments are under uncertainty, it is relatively difficult for them to provide exact numerical values. The fuzzy set theory is a strong tool which can deal with the uncertainty in case of subjective, incomplete, and vague information. It is easier for an energy planning expert to make an evaluation by using linguistic terms. In this paper, a modified fuzzy TOPSIS methodology is proposed for the selection of the best energy technology alternative. TOPSIS is a multicriteria decision making (MCDM) technique which determines the best alternative by calculating the distances from the positive and negative ideal solutions according to the evaluation scores of the experts. In the proposed methodology, the weights of the selection criteria are determined by fuzzy pairwise comparison matrices. The methodology is applied to an energy planning decision-making problem.     

多专家注释的视杯和视盘不确定性量化

现有基于深度学习的视杯和视盘分割方法在模型训练时,仅使用图像的单个注释或从多个注释中获取唯一的注释信息,忽略原始多专家标注中嵌入的一致性或差异性信息,从而导致模型和预测结果过度自信等问题。提出一种基于多解码器不确定性感知体系的模型MUA-Net。通过引入专业知识推断模块,将各个专家注释的专业知识水平作为先验知识嵌入编码器和解码器的瓶颈中,以形成包含专家线索的高级语义特征。利用可同时学习多个注释的多解码器结构调节多专家之间的分歧,重构多专家注释过程,并对不确定或分歧区域进行量化。提出一种双分支软注意机制,增强多解码器分割预测的模糊区域,得到最终校准的分割结果。实验结果表明,该模型在RIGA数据集上能以较高的不确定性预测合理的区域,与MRNet模型相比,该模型在视杯分割中的平均精度、Dice系数、交并比分别提升了0.75、0.39、0.41个百分点。     

A TECHNIQUE FOR HANDLING FUZZY DECISION-MAKING PROBLEMS CONCERNING TWO KINDS OF UNCERTAINTY

A new technique for handling fuzzy decision-making problems concerning two kinds of uncertainty is introduced, which supplies a more efficient tool for the building of some expert systems. It uses a similarity measure of fuzzy sets and threshold to determine whether a rule should be fired, and a modification function MF is used to modify the deduced consequent. The strength of confirmation CF of every production rule, which is given by a system or experts, is different and is used to modify the consequent once more. Finally, an efficient algorithm is proposed and some numerical examples are presented.     

基于半定量概率图模型的溯因分析方法

复杂工业系统的故障原因定位可协助操作人员快速调整设备运行参数,保障生产高效稳定地运行.铝电解过程机理复杂且外部因素干扰多,信息具有不确定性特征,难以建立精确的定量模型,而定性分析的准确度不高.为此,本文针对铝电解溯因过程的层次性、相关性、不确定性的特点,构建了一种基于半定量概率图模型的溯因分析框架,将定量和定性分析相结合,通过不确定理论对信息进行处理和描述,采用图形符号可视化知识变量间的因果关系,再基于概率图模型的推理方法实现不确定性条件下的溯因诊断,为实现铝电解异常槽况的原因分析与定位提供了理论支撑.     

基于专家主观信息的学术期刊评价方法研究

该文侧重于学术期刊定性属性的评价方法研究。学术期刊定性属性特征通常具有模糊性,因而往往需要由专家给出主观判断。通过建立基准语言等级评价集合,提出了将专家给出的关于各定性属性的主观评价信息规范化为基准语言等级评价集合并集成的综合评价方法。最后通过计算可以得到学术期刊的综合评价值,进而使得学术期刊评价尽可能的公平化。     

基于着色Petri网模糊专家系统的研究

针对变电站无功控制模糊专家系统知识表示不确定性及规则数量多的特点,文章以模糊、着色Petri网为基础,提出了一种基于模糊着色Petri网的知识表示与规则获取方法。该方法利用Petri网的图形化环境特点,将模糊规则库的不同变量用不同的颜色加以区分,不同规则中的同一个变量用该变量的颜色集表示,构成一个模糊着色Petri网模型。充分利用着色Petri网的特点,对推理过程进行了仔细研究,并提出一种基于着色模糊Petri网的启发式搜索策略。将其用于变电站无功控制的模糊专家系统中,结果表明,基于着色Petri网的模糊知识表示和获取方法,对于大型、复杂变电站模糊专家控制系统是非常有效的。     

Support logic programming

This article describes a support logic programming system which uses a theory of support pairs to model various forms of uncertainty. It should find application to designing expert systems and is of a query language type like Prolog. Uncertainty associated with facts and rules is represented by a pair of supports and uses ideas from Zadeh's fuzzy set theory and Shafer's evidence theory. A calculus is derived for such a system and various models of interpretation given. the article provides a form of knowledge representation and inference under uncertainty suitable for expert systems and a closed world assumption is not assumed. Facts not in the knowledge base are uncertain rather than assumed to be false.     

Dealing with heterogeneous information in engineering evaluation processes

Before selecting a design for a large engineering system several design proposals are evaluated studying different key aspects. In such a design assessment process, different criteria need to be evaluated, which can be of both of a quantitative and qualitative nature, and the knowledge provided by experts may be vague and/or incomplete. Consequently, the assessment problems may include different types of information (numerical, linguistic, interval-valued). Experts are usually forced to provide knowledge in the same domain and scale, resulting in higher levels of uncertainty. In this paper, we propose a flexible framework that can be used to model the assessment problems in different domains and scales. A fuzzy evaluation process in the proposed framework is investigated to deal with uncertainty and manage heterogeneous information in engineering evaluation processes.