Automated and precise heartbeat detection in ballistocardiography signals using bidirectional LSTM

Zhang, Shiyu; Zhang, Hai Hong; Lin, Zhiping

doi:10.1016/j.fraope.2022.05.001

Cited by 4 publications

(2 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…LSTM network is a powerful tool for handling long-term dependencies in sequential data [17], and have enabled significant advances in a wide range of applications involving time series data processing. Multidimensional features obtained by 1D-CNN were flattened into a one-dimensional feature vector through flatten layer and used as the input of the LSTM layer.…”

Section: Cnn-lstm Modelmentioning

confidence: 99%

Real-time heart rate estimation using PVDF flexible piezoelectric sensor based on machine learning

Luo

Fang

Dong

et al. 2023

Second International Conference on Advanced Manufacturing Technology and Manufacturing Systems (ICAMTMS 2023)

View full text Add to dashboard Cite

To achieve non-invasive, non-contact, and real-time heart rate monitoring, proposed a pulse signal acquisition system using PVDF (Polyvinylidene Fluoride) piezoelectric film. In order to address the issue of errors in heart rate extraction caused by differences in the morphology of pulse signals across individuals or in different states, the K-means clustering algorithm was innovatively used to locate the peak of pulse waveforms in different states and constructed a heart rate data set. Realtime heart rate monitoring by training a large number of pulse signal samples with the proposed CNN-LSTM network model. Experimental results demonstrated that the performance metrics of this model, including the MAE (Mean Absolute Error), RMSE (Root Mean Square Error), and R 2 (Coefficient of Determination), are 0.2517, 0.3395, and 0.9863, respectively. the maximum error between the proposed system and the standard instrument within 3 minutes was only 1.55 beats/minute, indicating that the system exhibits high accuracy and reliability, and holds great potential for applications in heart rate detection.

show abstract

Section: Cnn-lstm Modelmentioning

confidence: 99%

Real-time heart rate estimation using PVDF flexible piezoelectric sensor based on machine learning

Luo

Fang

Dong

et al. 2023

Second International Conference on Advanced Manufacturing Technology and Manufacturing Systems (ICAMTMS 2023)

View full text Add to dashboard Cite

show abstract

“…Furthermore, in [69], heartbeats were located on the kinetic energy waveform, which was obtained as the ensemble averaging of SCG and GCG signals. Deep learning methods for biosignal analysis [72][73][74] have also been proposed for ECG-free heartbeat detection in SCG [75] and BCG [76] signals, but not in GCG signals.…”

Section: Introductionmentioning

confidence: 99%

Heartbeat Detection in Gyrocardiography Signals without Concurrent ECG Tracings

Parlato

Centracchio

Esposito

et al. 2023

Sensors

View full text Add to dashboard Cite

A heartbeat generates tiny mechanical vibrations, mainly due to the opening and closing of heart valves. These vibrations can be recorded by accelerometers and gyroscopes applied on a subject’s chest. In particular, the local 3D linear accelerations and 3D angular velocities of the chest wall are referred to as seismocardiograms (SCG) and gyrocardiograms (GCG), respectively. These signals usually exhibit a low signal-to-noise ratio, as well as non-negligible amplitude and morphological changes due to changes in posture and the sensors’ location, respiratory activity, as well as other sources of intra-subject and inter-subject variability. These factors make heartbeat detection a complex task; therefore, a reference electrocardiogram (ECG) lead is usually acquired in SCG and GCG studies to ensure correct localization of heartbeats. Recently, a template matching technique based on cross correlation has proven to be particularly effective in recognizing individual heartbeats in SCG signals. This study aims to verify the performance of this technique when applied on GCG signals. Tests were conducted on a public database consisting of SCG, GCG, and ECG signals recorded synchronously on 100 patients with valvular heart diseases. The results show that the template matching technique identified heartbeats in GCG signals with a sensitivity and positive predictive value (PPV) of 87% and 92%, respectively. Regression, correlation, and Bland–Altman analyses carried out on inter-beat intervals obtained from GCG and ECG (assumed as reference) reported a slope of 0.995, an intercept of 4.06 ms (R2 > 0.99), a Pearson’s correlation coefficient of 0.9993, and limits of agreement of about ±13 ms with a negligible bias. A comparison with the results of a previous study obtained on SCG signals from the same database revealed that GCG enabled effective cardiac monitoring in significantly more patients than SCG (95 vs. 77). This result suggests that GCG could ensure more robust and reliable cardiac monitoring in patients with heart diseases with respect to SCG.

show abstract

Application of Novel SN-1DCNN-LSTM framework in small sample oil and gas pipeline leakage detection

Gao,

Hao,

Zhang

et al. 2024

Franklin Open

View full text Add to dashboard Cite

Automated and precise heartbeat detection in ballistocardiography signals using bidirectional LSTM

Cited by 4 publications

References 24 publications

Real-time heart rate estimation using PVDF flexible piezoelectric sensor based on machine learning

Real-time heart rate estimation using PVDF flexible piezoelectric sensor based on machine learning

Heartbeat Detection in Gyrocardiography Signals without Concurrent ECG Tracings

Application of Novel SN-1DCNN-LSTM framework in small sample oil and gas pipeline leakage detection

Contact Info

Product

Resources

About