Abstract
There has recently been a significant increase in the level of interest in the field of type-2 fuzzy sets and systems. Type-2 fuzzy systems offer the ability to model and reason with uncertain concepts. When faced with uncertainties type-2 fuzzy systems should, theoretically, give an increase in performance over type-1 fuzzy systems. Historically, type-2 systems have been restricted by the burden of heavy computation. Recent developments have overcome these issues making this paradigm suitable for application to many problems where uncertainty is a significant issue. This talk will present a beginners guide to type-2 systems covering:
- Basic concepts and operations – set models, set membership and inference.
- Successful applications – control and signal processing.
- Recent breakthroughs – theoretical models and hardware implementations.
- Future directions for the field.
Abstract
This talk reports on some work at De Montfort University which has looked at using fuzzy logic for modelling nursing intuition. Working with a nurse from New Zealand we looked the problem of patient assessment. The clinical reality of nursing requires nurses to make decisions arising from an ongoing holistic assessment of the patient need for nursing care, based on an extensive range of knowledge. Nurses concurrently assess patient need for nursing care in several domains of concern to nursing before deciding where the primary focus of nursing attention should be directed. Holistic nursing assessment takes a number of environmental domains of patient need into account, as well as the need for clinical intervention.
It is suggested that five domains provide the context of the patient need for nursing care and intervention. These `top level' domains are clearly imprecise and subjective and are difficult, if not impossible to measure. Added to this imprecision, there is, within each domain, a degree, or priority, of need to be determined before any required intervention is applied. These domains and priorities have been represented by type-2 fuzzy sets and we have modelled the nursing intuition in such a way that has provided a number of insights that will be discussed in this talk.
Abstract
Type-2 fuzzy logic was originally defined in 1975 but only in the last 5 years or so have there been significant applications, this is primarily due to the increased computing power available and some technical advances in terms of new algorithms for type-2 fuzzy inferencing. At the Centre for Computational Intelligence at De Montfort University we have exploited type-2 fuzzy logic in a number of applications. This talk will discuss 3 particularly diverse problems: modelling nursing intuition, mobile robot control and multi-expert decision making. From the results of this research lessons will be drawn about the advantages and disadvantages of type-2 fuzzy logic.