An experience based linear general type-2 fuzzy logic approach for Computing With Words

In this paper, we present an approach to interpret the Computing With Words (CWWs) paradigm merging the advancements from neuroscience, psychology and artificial intelligence. The presented approach will incorporate fuzzy composite concepts (FCCs), a special case of linguistic weighted average (LWA) and case-based reasoning (CBR). The focus of the paper is on the inception of the CWWs paradigm to bridge the gap between the human and machine intelligence. The investigation of FCCs processing is performed using linear general type-2 (LGT2) and interval type-2 (IT2) fuzzy sets. The results show that LGT2 fuzzy sets outperform IT2 fuzzy sets in the processing time of complete rule base evaluation, in providing better modeling of the human perceptual judgment, and in producing richer range of output intervals.