Qingxue Zhang1, Dian Zhou2, Xuan Zeng3. 1. Department of Electrical Engineering, University of Texas at Dallas, Richardson, TX, USA. 2. Department of Electrical EngineeringUniversity of Texas at Dallas. 3. Department of MicroelectronicsFudan University.
Abstract
OBJECTIVE: long-term wearable instantaneous heart rate (IHR) monitoring is essential to enable pervasive heart health and fitness management. In this paper, a novel framework is proposed to robustly estimate the IHR from electrocardiogram (ECG) signals corrupted by large amounts of daily motion artifacts, which are one of the major impediments against the long-term IHR monitoring. METHODS: the corrupted ECG signals are first projected to a high-dimensional phase space, where the constructed phase portraits of heartbeats are of many new geometrical properties and are expected to be powerful patterns more immune to the motion artifacts. Afterwards, a multiview dynamic time warping approach is applied on the constructed phase portraits, to effectively capture motion artifacts-induced inconsistencies and reveal heartbeats-related consistencies from corrupted signals. Finally, the phase portraits of heartbeats in the multidimensional phase space can be identified, and then, the IHR estimates are achieved. RESULTS: the proposed framework is evaluated on a wrist-ECG dataset acquired by a semicustomized platform and also a public ECG dataset. With a signal-to-noise ratio as low as -9 dB, the mean absolute error and root mean square error of the estimated IHR are 2.5 beats per minute (BPM) and 7.0 BPM, respectively. CONCLUSION: these results demonstrate that our framework can effectively identify the heartbeats from ECG signals continuously corrupted by intense and random motion artifacts and estimate the IHR. SIGNIFICANCE: the proposed framework greatly outperforms previously reported approaches and is expected to contribute to long-term IHR monitoring. OBJECTIVE: long-term wearable instantaneous heart rate (IHR) monitoring is essential to enable pervasive heart health and fitness management. In this paper, a novel framework is proposed to robustly estimate the IHR from electrocardiogram (ECG) signals corrupted by large amounts of daily motion artifacts, which are one of the major impediments against the long-term IHR monitoring. METHODS: the corrupted ECG signals are first projected to a high-dimensional phase space, where the constructed phase portraits of heartbeats are of many new geometrical properties and are expected to be powerful patterns more immune to the motion artifacts. Afterwards, a multiview dynamic time warping approach is applied on the constructed phase portraits, to effectively capture motion artifacts-induced inconsistencies and reveal heartbeats-related consistencies from corrupted signals. Finally, the phase portraits of heartbeats in the multidimensional phase space can be identified, and then, the IHR estimates are achieved. RESULTS: the proposed framework is evaluated on a wrist-ECG dataset acquired by a semicustomized platform and also a public ECG dataset. With a signal-to-noise ratio as low as -9 dB, the mean absolute error and root mean square error of the estimated IHR are 2.5 beats per minute (BPM) and 7.0 BPM, respectively. CONCLUSION: these results demonstrate that our framework can effectively identify the heartbeats from ECG signals continuously corrupted by intense and random motion artifacts and estimate the IHR. SIGNIFICANCE: the proposed framework greatly outperforms previously reported approaches and is expected to contribute to long-term IHR monitoring.
OBJECTIVE: long-term wearable instantaneous heart rate (IHR) monitoring is essential to enable pervasive heart health and fitness management. In this paper, a novel framework is proposed to robustly estimate the IHR from electrocardiogram (ECG) signals corrupted by large amounts of daily motion artifacts, which are one of the major impediments against the long-term IHR monitoring. METHODS: the corrupted ECG signals are first projected to a high-dimensional phase space, where the constructed phase portraits of heartbeats are of many new geometrical properties and are expected to be powerful patterns more immune to the motion artifacts. Afterwards, a multiview dynamic time warping approach is applied on the constructed phase portraits, to effectively capture motion artifacts-induced inconsistencies and reveal heartbeats-related consistencies from corrupted signals. Finally, the phase portraits of heartbeats in the multidimensional phase space can be identified, and then, the IHR estimates are achieved. RESULTS: the proposed framework is evaluated on a wrist-ECG dataset acquired by a semicustomized platform and also a public ECG dataset. With a signal-to-noise ratio as low as -9 dB, the mean absolute error and root mean square error of the estimated IHR are 2.5 beats per minute (BPM) and 7.0 BPM, respectively. CONCLUSION: these results demonstrate that our framework can effectively identify the heartbeats from ECG signals continuously corrupted by intense and random motion artifacts and estimate the IHR. SIGNIFICANCE: the proposed framework greatly outperforms previously reported approaches and is expected to contribute to long-term IHR monitoring. OBJECTIVE: long-term wearable instantaneous heart rate (IHR) monitoring is essential to enable pervasive heart health and fitness management. In this paper, a novel framework is proposed to robustly estimate the IHR from electrocardiogram (ECG) signals corrupted by large amounts of daily motion artifacts, which are one of the major impediments against the long-term IHR monitoring. METHODS: the corrupted ECG signals are first projected to a high-dimensional phase space, where the constructed phase portraits of heartbeats are of many new geometrical properties and are expected to be powerful patterns more immune to the motion artifacts. Afterwards, a multiview dynamic time warping approach is applied on the constructed phase portraits, to effectively capture motion artifacts-induced inconsistencies and reveal heartbeats-related consistencies from corrupted signals. Finally, the phase portraits of heartbeats in the multidimensional phase space can be identified, and then, the IHR estimates are achieved. RESULTS: the proposed framework is evaluated on a wrist-ECG dataset acquired by a semicustomized platform and also a public ECG dataset. With a signal-to-noise ratio as low as -9 dB, the mean absolute error and root mean square error of the estimated IHR are 2.5 beats per minute (BPM) and 7.0 BPM, respectively. CONCLUSION: these results demonstrate that our framework can effectively identify the heartbeats from ECG signals continuously corrupted by intense and random motion artifacts and estimate the IHR. SIGNIFICANCE: the proposed framework greatly outperforms previously reported approaches and is expected to contribute to long-term IHR monitoring.