Applying quality index criterion for flexible multi-detection of heartbeat using features of multimodal data

Introduction: In many conditions contaminated signals and noises can distort electrocardiogram (ECG) signals, so synchronously measured signals could enhance analyzing the heart rate variability. Therefore, the algorithm should be able to identify reliable and optimal segment of these multimodal signals in order to accurately locate the heart beats. Aims: This paper presents a flexible and multichannel feature extractor and classifier for the purpose of locate heartbeats by using the multi-channel recording from PhysioNet Challenge 2014 database. Methods: In this study, for feature extraction from multimodal data the common heartbeat detectors are used in other studies are employed, but the exhausted results are promising which indicates the importance and efficiency of the proposed fusion strategy and the decision of when fusion should be done as ECG itself is the best indicator of heartbeat detection. For fusion, after segmentation of waveforms, if ECG assumed to be noisy, an index is assigned to each signal based on periodicity of the extracted features and estimation of noises of detailed coefficients of discrete wavelet transform. The signal whose index is highest is processed in that segment. Results: The presented approach was evaluated by 200 recording of multimodal dataset provided for the PhysioNet/Computing in Cardiology Challenge 2014, and the average accuracy of the 95.39% was obtained.