NAS-PPG: PPG-Based Heart Rate Estimation Using Neural Architecture Search

Song, Seok Bin; Nam, Jung Woo; Kim, Jin Heon

doi:10.1109/jsen.2021.3073047

Cited by 29 publications

(10 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These models achieve comparable results to model-driven approaches by employing a CNN front-end and an LSTM-RNN-based method to combine multiple time samples. Additionally, a Neural Architecture Search (NAS) technique was applied [48] recently to the heart rate tracking problem. It discovered that a CNN+LSTM network achieved a mean absolute error of 6.02 bpm on the benchmark PPG-DaLiA dataset [43].…”

Section: Related Workmentioning

confidence: 99%

Privacy Preserving Heart Rate Estimation from ECG and PPG Signals for Application in Remote Healthcare

Islam,

Imtiaz

2023

Preprint

View full text Add to dashboard Cite

In this work, we develop a computationally-light and robust neural network model for estimating heart rate for applications in remote healthcare systems. More specifically, we develop a model that can be trained on consumer-grade graphics processing units (GPUs) and can be deployed on edge devices for swift inference. To this end, we propose a hybrid model based on convolutional neural network (CNN) and bidirectional long short-term memory (BiLSTM) architectures for estimating heart rate from ECG and PPG signals. Considering the sensitive nature of the ECG signals, we ensure a formal privacy guarantee – differential privacy, for the model training. We perform a tight accounting of the overall privacy budget of our training algorithm using the Rényi Differential Privacy technique. We demonstrate that our model outperforms state-of-the-art networks on a benchmark dataset for both ECG and PPG signals, despite having much smaller number of trainable parameters, and consequently much smaller training and inference times. Additionally, our CNN-BiLSTM architecture can provide excellent heart rate estimation performance even under strict privacy constraints. Last but not the least, we develop a prototype Arduino-based data collection system that is low-cost and efficient, and therefore, useful for providing access to modern healthcare services to the people living in remote areas.

show abstract

Section: Related Workmentioning

confidence: 99%

Privacy Preserving Heart Rate Estimation from ECG and PPG Signals for Application in Remote Healthcare

Islam,

Imtiaz

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…CorNET [17] and its variant for highly constrained devices, BinaryCorNET [18] have been introduced to reduce model complexity, achieving comparable results to model-driven methods on the SPC dataset using a deep architecture with a CNN front-end and a long-short term memory (LSTM) RNN to combine multiple time samples. Finally, a Neural Architecture Search (NAS) approach has been recently applied to the HR tracking problem in [25], finding a CNN+LSTM network that achieves 6.02 BPM of MAE on Dalia, while also reducing the complexity of the algorithm compared to [10], but being still too large for MCU deployment (800k floating-point parameters). Indeed, deep NN models typically have large memory footprints and high computational complexity.…”

Section: Related Workmentioning

confidence: 99%

“…It includes two PPG channels, from green and red LEDs respectively, (only the former is available in the public version of the dataset), coupled with 3D acceleration data and with the reference ECG signal. In order to compare fairly with previous approaches on this dataset [10], [25], we employ all publicly available data, i.e. the PPG signal from the green LED and the 3D acceleration.…”

Section: A the Ppg-dalia Datasetmentioning

confidence: 99%

Q-PPG: Energy-Efficient PPG-Based Heart Rate Monitoring on Wearable Devices

Burrello

Pagliari

Risso

et al. 2021

IEEE Trans. Biomed. Circuits Syst.

View full text Add to dashboard Cite

Hearth Rate (HR) monitoring is increasingly performed in wrist-worn devices using low-cost photoplethysmography (PPG) sensors. However, Motion Artifacts (MAs) caused by movements of the subject's arm affect the performance of PPG-based HR tracking. This is typically addressed coupling the PPG signal with acceleration measurements from an inertial sensor. Unfortunately, most standard approaches of this kind rely on hand-tuned parameters, which impair their generalization capabilities and their applicability to real data in the field. In contrast, methods based on deep learning, despite their better generalization, are considered to be too complex to deploy on wearable devices.In this work, we tackle these limitations, proposing a design space exploration methodology to automatically generate a rich family of deep Temporal Convolutional Networks (TCNs) for HR monitoring, all derived from a single "seed" model. Our flow involves a cascade of two Neural Architecture Search (NAS) tools and a hardware-friendly quantizer, whose combination yields both highly accurate and extremely lightweight models. When tested on the PPG-Dalia dataset, our most accurate model sets a new state-of-the-art in Mean Absolute Error. Furthermore, we deploy our TCNs on an embedded platform featuring a STM32WB55 microcontroller, demonstrating their suitability for real-time execution. Our most accurate quantized network achieves 4.41 Beats Per Minute (BPM) of Mean Absolute Error (MAE), with an energy consumption of 47.65 mJ and a memory footprint of 412 kB. At the same time, the smallest network that obtains a MAE < 8 BPM, among those generated by our flow, has a memory footprint of 1.9 kB and consumes just 1.79 mJ per inference.

show abstract

“…An accuracy of 76% was achieved in the testing data. Song et al [15] estimated the heart rate using two different PPG datasets. The optimized Deep Learning model achieved a mean absolute error of 6.02 beats per minute.…”

Section: Related Workmentioning

confidence: 99%

The Application of Deep Learning Algorithms for PPG Signal Processing and Classification

Esgalhado

Fernandes²,

Vassilenko

et al. 2021

Computers

View full text Add to dashboard Cite

Photoplethysmography (PPG) is widely used in wearable devices due to its conveniency and cost-effective nature. From this signal, several biomarkers can be collected, such as heart and respiration rate. For the usual acquisition scenarios, PPG is an artefact-ridden signal, which mandates the need for the designated classification algorithms to be able to reduce the noise component effect on the classification. Within the selected classification algorithm, the hyperparameters’ adjustment is of utmost importance. This study aimed to develop a deep learning model for robust PPG wave detection, which includes finding each beat’s temporal limits, from which the peak can be determined. A study database consisting of 1100 records was created from experimental PPG measurements performed in 47 participants. Different deep learning models were implemented to classify the PPG: Long Short-Term Memory (LSTM), Bidirectional LSTM, and Convolutional Neural Network (CNN). The Bidirectional LSTM and the CNN-LSTM were investigated, using the PPG Synchrosqueezed Fourier Transform (SSFT) as the models’ input. Accuracy, precision, recall, and F1-score were evaluated for all models. The CNN-LSTM algorithm, with an SSFT input, was the best performing model with accuracy, precision, and recall of 0.894, 0.923, and 0.914, respectively. This model has shown to be competent in PPG detection and delineation tasks, under noise-corrupted signals, which justifies the use of this innovative approach.

show abstract

NAS-PPG: PPG-Based Heart Rate Estimation Using Neural Architecture Search

Cited by 29 publications

References 35 publications

Privacy Preserving Heart Rate Estimation from ECG and PPG Signals for Application in Remote Healthcare

Privacy Preserving Heart Rate Estimation from ECG and PPG Signals for Application in Remote Healthcare

Q-PPG: Energy-Efficient PPG-Based Heart Rate Monitoring on Wearable Devices

The Application of Deep Learning Algorithms for PPG Signal Processing and Classification

Contact Info

Product

Resources

About