Polyphase-Basis Discrete Cosine Transform for Real-Time Measurement of Heart Rate With CW Doppler Radar

Park, Jun-Hyeong; Ham, Jong-Wook; Park, Seungwoon; Kim, Do-Hoon; Kang, Hyunseong

doi:10.1109/tmtt.2017.2772782

Cited by 37 publications

(28 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many researches have investigated the heartbeat detection via a Doppler sensor to achieve non-contact heartbeat detection without device attachment. Some conventional methods estimate the HR based on frequency analysis by (i) Fast Fourier Transform (FFT) [10][11], (ii) Wavelet Transform (WT) [12][13], (iii) Multiple Signal Classification (MUSIC) [14] [15], and DCT [16]. In contrast, by detecting a heartbeat signal over the signal obtained through the extended signal processing, the conventional methods [17]- [23] estimate the BBI.…”

Section: Related Workmentioning

confidence: 99%

ECG Signal Reconstruction via Doppler Sensor by Hybrid Deep Learning Model With CNN and LSTM

2020

View full text Add to dashboard Cite

An Electrocardiogram (ECG) is a typical method used to detect heartbeat, and an ECG signal analysis enables the detection of some heart diseases. However, the ECG-based heartbeat detection requires device attachment, which is not preferred for daily use. A Doppler sensor could be a device used to enable the non-contact heartbeat detection. In this paper, we propose a Doppler sensor-based ECG signal reconstruction method by a hybrid deep learning model with Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM). An ECG signal can be reconstructed by relating features of a heartbeat signal obtained by a Doppler sensor to those of the ECG signal. Thus, we construct the deep learning model that extracts the spatial and temporal features from the heartbeat signal by CNN and LSTM. Based on the extracted features, the ECG signal is reconstructed. We conducted experiments to observe heartbeat against 9 healthy subjects without heart disease. The experimental results showed that our method performed ECG signal reconstruction with a correlation coefficient of 0.86 between the reconstructed and actual ECG signals, even without attaching devices. The results indicate that it is possible to remotely reconstruct an ECG signal from a heartbeat signal via a Doppler sensor.

show abstract

Section: Related Workmentioning

confidence: 99%

ECG Signal Reconstruction via Doppler Sensor by Hybrid Deep Learning Model With CNN and LSTM

2020

View full text Add to dashboard Cite

show abstract

“…In general, the Doppler sensor-based heartbeat detection aims at estimating the HR and the RRI. On the one hand, the Doppler sensorbased HR estimation is mainly based on the frequency analysis, e.g., (i) FFT [5]- [8], (ii) WT [9]- [12], (iii) MUSIC [13]- [16], and DCT (Discrete Cosine Transform) [17]. Most of the Doppler sensor-based HR estimation methods with the frequency analysis require the time windows longer than 8 s to achieve a high frequency resolution.…”

Section: Related Workmentioning

confidence: 99%

“…Thus, the use of a Doppler sensor has been investigated in the field of not only the heartbeat detection [5]- [28], but also the respiration detection [29]- [31] and the activity recognition [32]- [34]. In the Doppler sensorbased heartbeat detection, (i) the HR [5]- [17] and the RRI (R-R Interval) [18]- [27] are typically estimated. In general, the HR is estimated mainly based on the frequency analysis such as FFT (Fast Fourier Transform) and MSUIC (Multiple Signal Classification).…”

Section: Introductionmentioning

confidence: 99%

“…Although the time window longer than 8 s is generally required to achieve a high frequency resolution, the HR could change within the time window, and the fast acquisition of the HR is challenging. Thus, some researches have proposed the HR estimation methods with shorter time window [8][12] [15]- [17]. In contrast, the RRI is estimated by detecting features due to heartbeat, e.g., a peak, over the signal obtained by some advanced signal processing such as WT (Wavelet Transform) and EEMD (Ensemble Empirical Mode Decomposition).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Non-Contact Heartbeat Detection by Heartbeat Signal Reconstruction Based on Spectrogram Analysis With Convolutional LSTM

Yamamoto

Ohtsuki

2020

IEEE Access

View full text Add to dashboard Cite

Heartbeat detection is one of key techniques to monitor our health condition in daily life, and demands for this technique have increased year and year. Thanks to the non-contact and non-invasive features, various Doppler sensor-based detection methods have been investigated so far. However, the heartbeat detection accuracy of the conventional methods could get degraded due to the low SNR (Signal-to-Noise Ratio) of heartbeat components. Thus, even after some signal processing, non-heartbeat components still remain over such processed signal, which could degrade the heartbeat detection accuracy. In particular for the subjects with low HR (Heart Rate), the estimated HR tends to be higher than the ground truth HR due to such non-heartbeat components, though the conventional methods have mainly focused on the heartbeat detection against the subjects with the normal HR higher than 50 bpm (Beats Per Minute). In this paper, to accurately detect heartbeat even with low HR via a Doppler sensor, we propose a heartbeat detection method based on heartbeat signal reconstruction with convolutional LSTM (Bidirectional-Long Short-Term Memory). In the proposed method, to reconstruct a heartbeat signal based on the periodicity of heartbeat and the spectrum distribution peculiar to heartbeat, successive spectrograms that might be due to heartbeat is used as an input to convolutional LSTM. In addition, for better reconstruction of a heartbeat signal, the previously estimated RRI (R-R Interval) is also used as a feature in the proposed deep learning model with convolutional LSTM. Through the experiments, we confirmed that our proposed method accurately detected heartbeat against 17 subjects including the ones with the HR lower than 50 bpm.

show abstract

“…The power is supplied by primary cells which has only limited life so a regular replace of dead cells becomes necessary. This becomes a limitation so a wireless power transfer (WPT) technology is introduced into the implants [4].…”

Section: Introductionmentioning

confidence: 99%

Model of Implanted Electrocardiogram (ECG) Monitoring

2020

jcr

View full text Add to dashboard Cite

We developed a model of an implantable electrocardiogram (ECG) monitoring system. This device measures ECG signals, voltage of secondary cell as well as inside temperature. The users can analyze the information through software or even via mobile application. The side effects of surgery to remove implants can be removed by using wireless charging advancement. This ECG based data encryption (EDE) designs provides high security and accessibilty for IMD. All those records and data showed that EDE is the best scheme for protecting IMD.

show abstract

Polyphase-Basis Discrete Cosine Transform for Real-Time Measurement of Heart Rate With CW Doppler Radar

Cited by 37 publications

References 26 publications

ECG Signal Reconstruction via Doppler Sensor by Hybrid Deep Learning Model With CNN and LSTM

ECG Signal Reconstruction via Doppler Sensor by Hybrid Deep Learning Model With CNN and LSTM

Non-Contact Heartbeat Detection by Heartbeat Signal Reconstruction Based on Spectrogram Analysis With Convolutional LSTM

Model of Implanted Electrocardiogram (ECG) Monitoring

Contact Info

Product

Resources

About