A Cardiac Pacing System Based on Fuzzy Logic. A Self-Tuning Effect of Membership Functions.:A Self-Tuning Effect of Membership Functions

概要

論文の詳細を見る
It is a time-consuming task to optimize the membership functions in fuzzy-logic-based cardiac pacing system. This paper describes a self-tuning method of membership functions and validates its feasibility in a double-sensor system which has the minute ventilation and oxygen saturation level as the guides for rate regulation. The agreement between the pacing rates (fuzzy-rates) calculated with 3 linguistic labels for each parameter and the target rates were not satisfactory, but it was improved significantly by tuning the membership functions. Higher estimated value was obtained in comparison with the case using 5 linguistic labels for each parameter. Time required for the self-tuning process was about 40 seconds (386CPU, 20MHz) which was fast enough for the system. Smaller numbers of linguistic labels results in the smaller numbers of rules, which is beneficial in the implantable cardiac pacemakers with limited memory capacity. A self-tuning method of reasoning rules is now under study.
一般社団法人日本生体医工学会の論文