TY - GEN
T1 - Fractional Fourier Transform Based QRS Complex Detection in ECG Signal
AU - Yaqoob, Touseef
AU - Aziz, Saira
AU - Ahmed, Sajid
AU - Amin, Osama
AU - Alouini, Mohamed-Slim
N1 - KAUST Repository Item: Exported on 2020-10-01
PY - 2020
Y1 - 2020
N2 - By exploiting fractional-Fourier-transform (FrFT), a novel technique for the QRS complex detection is proposed. The application of the FrFT rotates the Electrocardiograph (ECG) signal in the time-frequency plane. We claim this rotation can give simple and effective QRS complex detection even in the presence of versatile artifacts, such as left-bundle-branch-block, right-bundle-branch-block, and negative polarization. In this work, in the first step, the noise and baseline drifts are removed by applying a wavelet transform on the given ECG signal. While, in the next step, the clean ECG signal is passed through the proposed algorithm, which rotates the ECG signal in the time-frequency plane and detects the QRS complex very easily. The proposed algorithm validated over the 48 signals of the MIT-BIH arrhythmia database, and it yielded 26 false-positive and only five false-negatives compared to the 80 and 42, the best result reported so far.
AB - By exploiting fractional-Fourier-transform (FrFT), a novel technique for the QRS complex detection is proposed. The application of the FrFT rotates the Electrocardiograph (ECG) signal in the time-frequency plane. We claim this rotation can give simple and effective QRS complex detection even in the presence of versatile artifacts, such as left-bundle-branch-block, right-bundle-branch-block, and negative polarization. In this work, in the first step, the noise and baseline drifts are removed by applying a wavelet transform on the given ECG signal. While, in the next step, the clean ECG signal is passed through the proposed algorithm, which rotates the ECG signal in the time-frequency plane and detects the QRS complex very easily. The proposed algorithm validated over the 48 signals of the MIT-BIH arrhythmia database, and it yielded 26 false-positive and only five false-negatives compared to the 80 and 42, the best result reported so far.
UR - http://hdl.handle.net/10754/662743
UR - https://ieeexplore.ieee.org/document/9052939/
U2 - 10.1109/ICASSP40776.2020.9052939
DO - 10.1109/ICASSP40776.2020.9052939
M3 - Conference contribution
SN - 978-1-5090-6632-2
BT - ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
PB - IEEE
ER -