Fuzzy Lattice Reasoning (FLR) Classification Using Similarity Measures

Summary. In this work, we show that the underlying inclusion measure used by fuzzy lattice reasoning (FLR) classiffiers can be extended to various similarity and distance measures often used in cluster analysis. We show that for the cosine similarity measures, we can weigh the contribution of each attribute found in the data set. Furthermore, we show that evolutionary algorithms such as genetic algorithms, tabu search, particle swarm optimization, and differential evolution can be used to weigh the importance of each attribute and that this weighting can provide additional improvements over simply using the similarity measure. We present experimental evidence that the proposed techniques imply significant improvements.