Pawlak originally developed rough sets to be used in the same situations as Zadeh’s better-known fuzzy sets [1]. Although they are less popular than fuzzy sets, they do have a devoted following and are proven to be a good tool when properly applied.

This volume is the ninth in a series of transactions on the theory and applications of rough sets. It contains 26 papers on rough sets, ranging from the mathematically abstract--such as “Context algebras, context frames, and their discrete duality” by E. Orlowska and I. Rewitzky--to the very applied--such as “Automatic rhythm retrieval from musical files” by B. Kostek et al. The most extensive contribution is J. Bazan’s monograph-length (over 250 pages) study: “Hierarchical classifiers for complex spatio-temporal concepts.”

As in all large collections of papers of this type, the quality and significance of the contributions vary considerably. Some of the papers are mathematically rigorous or report on implementations of rough set theory to concrete problems. Other papers include long definitions and exaggerated claims, with little actual substance to justify them. However, the book emphasizes that rough set theory is a viable tool in artificial intelligence and other areas of data handling under conditions of uncertainty, which makes it worth keeping in one’s mental toolbox.