The analysis of epidemiological data is critical to disease prevention and control programs geared toward improving, promoting, and protecting the health of communities. Various decision-making support systems have been modelled using artificial neural networks and fuzzy inferences. A neuro-fuzzy inference system based on the Takagi-Sugeno system was developed in the early 1990s that integrates the advantages of neural networks with fuzzy logic principles, such as self-learning and knowledge representation. Adaptive neuro-fuzzy inference systems are devised and evaluated here as means of characterizing the severity of a laboratory-confirmed COVID-19 case. The authors describe the underlying architecture for ANFIS with various clustering approaches, including grid partitioning, subtractive clustering, and fuzzy c-means. A total of 385 cases with eight potential predictors is used to develop, validate, and evaluate the model.
TopFuzzy Logic
Most of the real time systems are large and quite complex in nature. Modeling is a powerful tool for analyzing a real time system as it provides insight into its characteristics and facilitates its analysis. The conventional method of modeling makes use of mathematical tools that require precise information about the system. However, if we look at real-time systems in the real world, the majority of them are vague and we find it hard to gain precise information from them. A soft computing technique like fuzzy logic will be a viable alternative to hard computing techniques to model these systems.
Fuzzy logic provides a convenient way to map input spaces to output spaces, even if the boundaries between input variables are not well defined. A human brain is able to reason easily with an imprecision, partial truth, and uncertainty, but computers behave well when they have deterministic input, which is not biased or imperfect. Using fuzzy logic, one can give deterministic input to a computer by taking into account imprecisions or partial truths. The fuzzy logic will be used to quantify ill-defined words like large profit, high pressure, tall man, wealthy woman, moderate temperature, high, high to some extent, not quite high, very high and so on as a deterministic input to the mathematical equation or algorithm.
In 400 B.C., the philosopher Aristotle argued that 'every statement is either true or false'. Lofti A Zadeh pointed out in 1965 that most statements can have a value between 0 to 1, not just 0 or 1. This was accomplished by introducing the ideas of fuzzy sets and fuzzy logic. He suggested that a value of 0 to 1 would provide more meaning to the statements, particularly when there are ill-defined boundaries. Consider an example in which finite numbers of grains are picked up from a heap of rain. When does the heap no longer qualify as a heap? The classical logic may not give the exact answer to this question. With fuzzy logic, however, it is possible to explain this problem in a meaningful way using membership functions. Figure 1 illustrates how heap-ness changes as a function of the number of grains by using a scale of 0 to 1.