A method for automated temporal knowledge acquisition applied to sleep-related breathing disorders

This paper presents a method for the discovery of temporal patterns in mult ivariate time series and their conversion into a linguistic knowledge repre sentation applied to sleep-related breathing disorders. The main idea ties in introducing several abstraction levels that allow a step-wise identifica tion of temporal patterns. Self-organizing neural networks are used to disc over elementary patterns in the time series. Machine learning (NIL) algorit hms use the results of the neural networks to automatically generate a rule -based description. At the next levels, temporal grammatical rules are infe rred. This method covers one of the main "bottlenecks" in the design of kno wledge-based systems, namely, the knowledge acquisition problem. An evaluat ion of the rules lead to an overall sensitivity of 0.762, and a specificity of 0.758. (C) 2001 Elsevier Science B.V. All rights reserved.