A Concept Learning-based ECG Beat Detector 1 A Concept Learning-based Patient-adaptable Abnormal ECG Beat Detector for Long-term Monitoring of Heart Patients

In this chapter, a new concept learning-based approach is presented for abnormal ECG beat detection to facilitate long-term monitoring of heart patients. The novelty in our approach is the use of complementary concept – “normal” for the learning task. The concept “normal” can be learned by a ν-Support Vector Classifier (ν-SVC) using only normal ECG beats from a specific patient to relieve the doctors from annotating the training data beat by beat to train a classifier. The learned model can then be used to detect abnormal beats in the long-term ECG recording of the same patient. Experimental results on MIT/BIH arrhythmia ECG database demonstrate that such a patient-adaptable concept learning model outperforms other classifiers in the task of abnormal heart beat detection, including multi-layer feed-forward neural networks, binary support vector machines, etc., which are trained using tens of thousands of ECG beats from a large group of patients.