- 【Updated on May 12, 2025】 Integration of CiNii Dissertations and CiNii Books into CiNii Research
- Trial version of CiNii Research Knowledge Graph Search feature is available on CiNii Labs
- 【Updated on June 30, 2025】Suspension and deletion of data provided by Nikkei BP
- Regarding the recording of “Research Data” and “Evidence Data”
Robust St-segment Recognition System Using Neural Networks
Description
We have developed a personal computer system for electrocardiogram (ECG) STSegment recognition based on neural networks. The system consists of preprocessor, neural networks, and recognizer. The adaptive resonance theory (ART) is employed to implement the neural networks. The preprocessor detects the R points and divides the ECG into cardiac cycles. Each cardiac cycle is inputted to the neural networks. Then, the neural networks address the approximate locations of the J point and the onset of T wave (Ton). The recognizer finds out the exact locations around the location addressed. As the process goes on, the neural networks self-organize and learn the characters of the ECG pattern which vary each patient. As a result, the system recognizes ST-segment with average of 95.7% accuracy within 15 msec error and with an average of 90.8% accuracy within 10 msec error.
Journal
-
- Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society Volume 13: 1991
-
Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society Volume 13: 1991 1432-1433, 2005-08-24
IEEE