► Describes hybrid expert system approaches specifically connectionist and neuro-fuzzy system. ► Classifies 91 articles published between 1988 and 2010. ► Evaluation on system structure, algorithms, ...applications and building/implementation tools.
This paper is a statistical analysis of hybrid expert system approaches and their applications but more specifically connectionist and neuro-fuzzy system oriented articles are considered. The current survey of hybrid expert systems is based on the classification of articles from 1988 to 2010. Present analysis includes 91 articles from related academic journals, conference proceedings and literature reviews. Our results show an increase in the number of recent publications which is an indication of gaining popularity on the part of hybrid expert systems. This increase in the articles is mainly in neuro-fuzzy and rough neural expert systems’ areas. We also observe that many new industrial applications are developed using hybrid expert systems recently.
•We theoretically describe the expert systems.•We investigate the fuzzy, medical and wearable expert system variations.•We highlight the expert systems advantages and issues.•We emphasize the ...importance of expert system validation.•We describe in depth some expert system applications in the medical field.
The aim of this review is to provide a broad overview of the state-of-the-art works mainly published in the last ten years on expert systems applied in different medical domains.
Being able to support and sometimes substitute experts, an expert system may be a precious ally for medical diagnoses. Medical expert system applications provide physicians and patients with an immediate access to knowledge and advice, rooting their flexibility into their knowledge bases, rule sets and graphical interfaces. To be trusted by their users, medical expert systems should follow some criteria, which we investigate along with their different realization, from fuzzy logic to wearable solutions for out-of-clinical-environment care. We also consider the advantages of approaching diagnoses and alert systems through an artificial intelligence counterpart, without forgetting the importance of a good validation to assess the system functionality.
Therefore, we show the heterogeneity of the solutions proposed by the literature, bounded to the specific needs a medical expert system is called to answer, the common lack of a system validation and the possible benefits deriving from these systems application.
The article analyzes the company's need to create a prototype for the development of expert systems. Expert systems and tools for their creation were examined, functions and software for the creation ...of an expert system that met the needs of the company were determined. The expert system design and programming processes, system performance testing and system documentation preparation, installation of the system on the server are described.