Abstract:
The recognition of clinically significant trends in monitored signals plays an important
role in many medical diagnostic applications. A template-based system technique to
identify characteristic patterns in time-series data is described, based on fuzzy
logic. Fuzzy set theory allows the creation of fuzzy templates from linguistic rules.
The resulting fuzzy template system can accommodate multiple time signals, relative
or absolute trends, and automatically generates a normalised “goodness of fit” score.
The template approach was originally developed for monitoring during anaesthesia but
has the potential to be useful in other domains that require temporal pattern recognition.
Keywords:
Temporal Pattern Recognition - Fault Detection and Diagnosis - Fuzzy Templates
