A Novel Non-Invasive Estimation of Respiration Rate From Motion Corrupted Photoplethysmograph Signal Using Machine Learning Model

Shuzan, Md. Nazmul Islam; Chowdhury, Moajjem Hossain; Hossain, Md Shafayet; Chowdhury, Muhammad E. H.; Reaz, Mamun Bin Ibne; Uddin, Mohammad Monir; Khandakar, Amith; Mahbub, Zaid Bin; Ali, Sawal Hamid Md

doi:10.1109/access.2021.3095380

Cited by 34 publications

(13 citation statements)

References 51 publications

(38 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Additionally, the use of shorter windows increases the likelihood that the breathing rate is stable throughout the window. This is especially important when the breathing rate is estimated during physical activities with high-intensity motion, since the PPG signal can be easily affected by physical movement [ 27 ].…”

Section: Resultsmentioning

confidence: 99%

“…Even though ML has already infiltrated many domains of health informatics [ 26 ], its efficiency in the field of breathing rate estimation from wearable sensors data has not been thoroughly explored; studies that have attempted to estimate breathing rate from PPG data using ML have been scarcely published. Shuzan et al [ 27 ] proposed an ML method for breathing rate estimation from PPG data based on Gaussian process regression. They extracted several statistical and time-domain features from pre-processed PPG signals, with a window size of 32 s, as well as from their first and second derivatives.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Breathing Rate Estimation from Head-Worn Photoplethysmography Sensor Data Using Machine Learning

Stankoski

Kiprijanovska

Mavridou

et al. 2022

Sensors

View full text Add to dashboard Cite

Breathing rate is considered one of the fundamental vital signs and a highly informative indicator of physiological state. Given that the monitoring of heart activity is less complex than the monitoring of breathing, a variety of algorithms have been developed to estimate breathing activity from heart activity. However, estimating breathing rate from heart activity outside of laboratory conditions is still a challenge. The challenge is even greater when new wearable devices with novel sensor placements are being used. In this paper, we present a novel algorithm for breathing rate estimation from photoplethysmography (PPG) data acquired from a head-worn virtual reality mask equipped with a PPG sensor placed on the forehead of a subject. The algorithm is based on advanced signal processing and machine learning techniques and includes a novel quality assessment and motion artifacts removal procedure. The proposed algorithm is evaluated and compared to existing approaches from the related work using two separate datasets that contains data from a total of 37 subjects overall. Numerous experiments show that the proposed algorithm outperforms the compared algorithms, achieving a mean absolute error of 1.38 breaths per minute and a Pearson’s correlation coefficient of 0.86. These results indicate that reliable estimation of breathing rate is possible based on PPG data acquired from a head-worn device.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Breathing Rate Estimation from Head-Worn Photoplethysmography Sensor Data Using Machine Learning

Stankoski

Kiprijanovska

Mavridou

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…Modern electronics have signal processing circuitry that can easily preprocess signals to get rid of this type of distortions before using them for BP prediction [67]. Moreover, for real-time, continuous BP monitoring, instead of the regressor, LSTM can be used instead according to these recent studies [37,[40][41][42]. This approach will perform well given that the input features to the LSTM layers are optimal.…”

Section: Discussionmentioning

confidence: 99%

“…On the other hand, to the best of our knowledge, the U-Net architecture has rarely been used just for feature extraction while acting as an autoencoder. These studies [37,[40][41][42] tried to extract features from PPG and/or ECG signals using generic CNNs and used those features on LSTM models to predict BP. Features were extracted separately from PPG and ECG and both were put into LSTM networks to separately predict SBP and diastolic blood pressure (DBP).…”

Section: Introductionmentioning

confidence: 99%

A Shallow U-Net Architecture for Reliably Predicting Blood Pressure (BP) from Photoplethysmogram (PPG) and Electrocardiogram (ECG) Signals

Mahmud¹,

Ibtehaz²,

Khandakar³

et al. 2022

Sensors

Self Cite

View full text Add to dashboard Cite

Cardiovascular diseases are the most common causes of death around the world. To detect and treat heart-related diseases, continuous blood pressure (BP) monitoring along with many other parameters are required. Several invasive and non-invasive methods have been developed for this purpose. Most existing methods used in hospitals for continuous monitoring of BP are invasive. On the contrary, cuff-based BP monitoring methods, which can predict systolic blood pressure (SBP) and diastolic blood pressure (DBP), cannot be used for continuous monitoring. Several studies attempted to predict BP from non-invasively collectible signals such as photoplethysmograms (PPG) and electrocardiograms (ECG), which can be used for continuous monitoring. In this study, we explored the applicability of autoencoders in predicting BP from PPG and ECG signals. The investigation was carried out on 12,000 instances of 942 patients of the MIMIC-II dataset, and it was found that a very shallow, one-dimensional autoencoder can extract the relevant features to predict the SBP and DBP with state-of-the-art performance on a very large dataset. An independent test set from a portion of the MIMIC-II dataset provided a mean absolute error (MAE) of 2.333 and 0.713 for SBP and DBP, respectively. On an external dataset of 40 subjects, the model trained on the MIMIC-II dataset provided an MAE of 2.728 and 1.166 for SBP and DBP, respectively. For both the cases, the results met British Hypertension Society (BHS) Grade A and surpassed the studies from the current literature.

show abstract

“…In all these three methods, single-channel EEG and fNIRS signals were decomposed into 5,10 and 15 IMFs separately and investigated resulting in nine different approaches. It should also be mentioned here that the VMD algorithm was used in removing motion artifacts from motion corrupted PPG signal [54] in our previous work which showed the potential of using VMD for these bio-signals. VMD in combination with PCA and CCA is the novel contribution of this research work which reduces motion artifacts from EEG and fNIRS signals.…”

Section: Introductionmentioning

confidence: 97%

Motion Artifacts Correction From EEG and fNIRS Signals Using Novel Multiresolution Analysis

et al. 2022

Self Cite

View full text Add to dashboard Cite

Physiological signal measurement and processing is increasingly becoming popular in the ambulatory setting as the hospital-centric treatment is moving towards wearable and ubiquitous monitoring. Most of the physiological signals are highly susceptible to various types of noises especially movement artifacts. The electroencephalogram (EEG) and functional near-infrared spectroscopy (fNIRS) signals are no exception to this motion artifacts, which becomes particularly prominent in the ambulatory setting. Since successful detection of various neurological disorders is greatly dependent upon clean EEG and fNIRS signals, it is a matter of utmost importance to remove motion artifacts from these two signal modalities using reliable and robust methods. This paper proposes three multiresolution analysis techniques: i) Variational mode decomposition (VMD), ii) VMD in combination with principal component analysis (VMD-PCA), and iii) VMD in combination with canonical correlation analysis (VMD-CCA), for motion artifact correction from single-channel EEG and fNIRS signals. The efficacy of these novel techniques is validated using the difference in the signal to noise ratio (𝛥𝛥𝛥𝛥𝛥𝛥𝛥𝛥) and percentage reduction in motion artifacts (𝜂𝜂). Among the three proposed novel methods, VMD-CCA decomposed with 15 intrinsic mode functions (IMFs) has shown the best denoising performance for EEG signals producing an average 𝛥𝛥𝛥𝛥𝛥𝛥𝛥𝛥 and 𝜂𝜂 values of 23.81 dB and 57.01%, respectively for all 23 EEG recordings. On the other hand, for the available 16 fNIRS recordings, VMD-CCA using 10 IMFs produced an average 𝛥𝛥𝛥𝛥𝛥𝛥𝛥𝛥 and 𝜂𝜂 values of 15.97 dB and 39.01%, respectively. The results reported using the proposed methods outperform most of the existing state-of-the-art techniques.

show abstract

A Novel Non-Invasive Estimation of Respiration Rate From Motion Corrupted Photoplethysmograph Signal Using Machine Learning Model

Cited by 34 publications

References 51 publications

Breathing Rate Estimation from Head-Worn Photoplethysmography Sensor Data Using Machine Learning

Breathing Rate Estimation from Head-Worn Photoplethysmography Sensor Data Using Machine Learning

A Shallow U-Net Architecture for Reliably Predicting Blood Pressure (BP) from Photoplethysmogram (PPG) and Electrocardiogram (ECG) Signals

Motion Artifacts Correction From EEG and fNIRS Signals Using Novel Multiresolution Analysis

Contact Info

Product

Resources

About