Artificial Intelligence - Special issue on knowledge representation
TRACE, a graphical tool for the acquisition and detection of signal patterns
Expert Systems with Applications: An International Journal
A new method for sleep apnea classification using wavelets and feedforward neural networks
Artificial Intelligence in Medicine
A hierarchical pattern matching procedure for signal abstraction
CAEPIA'05 Proceedings of the 11th Spanish association conference on Current Topics in Artificial Intelligence
Hi-index | 0.00 |
Abstract: This paper presents a new pattern recognition approach to the identification and characterization of multiple signal patterns in the domain of Sleep Apnoea Syndrome. This approach has been employed to identify apnoeas (cessations in the sleeping patient's respiratory airflow) and to relate them with the drops in blood oxyhaemoglobin saturation they give rise to. As a starting point, our algorithms take a projection over a computational representation of the morphological criteria which characterize apnoeas and desaturations. These criteria are obtained directly from a physician. The fuzzy set theory allows us to represent and handle the vagueness of the medical knowledge on which this proposal is based, and the constraint satisfaction problem formalism supplies a computable representation for this knowledge. Thanks to the structural nature of the proposal, a detailed characterization of any event identified can be carried out; this may serve as a starting point for obtaining a deeper understanding of the physio-pathological phenomena underlying Sleep Apnoea Syndrome. It has also made it possible to construct a graphical tool with which medical staff can easily edit the criteria that define apnoeas and desaturations, meaning that apnoeas can be identified with those criteria that each physician considers most suitable.