Fuzzy filtering of noisy sensor data

Removal of noise sensor data is a very important task in the design of a computer-based instrumentation system. This paper presents a new family of nonlinear digital filters based on a fuzzy logic approach. The proposed operators, called PWL-FIRE filters, are able to perform a very effective noise cancellation without degrading the data structure. The design of such filters and the analysis of their basic properties are described in detail. The experimental results show that the proposed filters perform better than other operators in the literature.