Embedded system design with filter bank and fuzzy classification approach to critical cardiac abnormalities detection

Embedded Electrocardiogram (E-ECG) based health diagnosis of cardiac diseases has been a saturated area of research and almost any known heart-condition can be detected and diagnosed by doctors in the hospital setting. However, these approaches fall extremely short when attempting to design an automatic detection system to do the same. The situation becomes even more difficult when the measurement system is being designed for a ubiquitous application, in which the patient is not confined to the hospital and the device is attached to him/her externally while the person is involved in daily chores. Hence the presented work covers the algorithm, classification technique and testing the some of cardiac conditions that can be monitored and detected by the embedded system to produce warning signals inorder to inform the concerned healthcare persons, when the signs of such conditions when begins to show. Due to the compact nature of such systems, the detection and classification techniques have to be extremely simple in order to be processed in the small memory of the microcontroller of the ubiquitous system. The paper also presents an embedded system which calculates the energy levels of the diseases with the combination of digital filters and Fuzzy classifications implemented at look-up table level in order to preserve the simplicity of the system.