Unsupervised pattern mining from symbolic temporal data
ACM SIGKDD Explorations Newsletter - Special issue on data mining for health informatics
| Hi-index | 0.00 |
The paper proposes a method for expressing the matching degree of two arbitrary intervals through a fuzzy relation having the properties of reflexivity and symmetry. This method could be useful in situations when one has to compare two entities whose attributes are expressed through intervals and give a measure of their matching degree. Such a real world situation occurs in the mechanical engineering, namely in the steel selection process, when the designer has to determine the steels that are equivalent to a given one. This situation is described, as an application, in the final part of the paper.