Real-time HR Estimation from wrist PPG using Binary LSTMs

Wrist-worn photoplethysmography (PPG) sensors present a popular alternative to electrocardiogram recording for heart rate (HR) estimation. However, their accuracy is limited by motion artifacts inherent in ambulatory settings. In this paper, we propose a binarized neural network framework, b-CorNET, to efficiently estimate HR from single-channel wrist PPG signals during intense physical activity. The model comprises two binary convolution neural network layers followed by two binary long short-term memory (b-LSTM) layers and a dense layer working on quantized PPG data. The proposed framework achieves an MAE of 3.75±3.05 bpm when evaluated on 12 IEEE SPC subjects. Furthermore, a novel, low-complexity architecture for the b-LSTM layers is proposed and efficiently mapped on a Xilinx Virtex5 FPGA, enabling HR computation.

[1]  Eugenio Culurciello,et al.  Hardware accelerators for recurrent neural networks on FPGA , 2017, 2017 IEEE International Symposium on Circuits and Systems (ISCAS).

[2]  Colin Raffel,et al.  Lasagne: First release. , 2015 .

[3]  Zhilin Zhang,et al.  TROIKA: A General Framework for Heart Rate Monitoring Using Wrist-Type Photoplethysmographic Signals During Intensive Physical Exercise , 2014, IEEE Transactions on Biomedical Engineering.

[4]  John Salvatier,et al.  Theano: A Python framework for fast computation of mathematical expressions , 2016, ArXiv.

[5]  James T. Kwok,et al.  Loss-aware Binarization of Deep Networks , 2016, ICLR.

[6]  Yu Wang,et al.  Software-Hardware Codesign for Efficient Neural Network Acceleration , 2017, IEEE Micro.

[7]  Mario Konijnenburg,et al.  CorNET: Deep Learning Framework for PPG-Based Heart Rate Estimation and Biometric Identification in Ambulant Environment , 2019, IEEE Transactions on Biomedical Circuits and Systems.

[8]  Yoshua Bengio,et al.  BinaryNet: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1 , 2016, ArXiv.

[9]  Zhongfeng Wang,et al.  An Energy-Efficient Architecture for Binary Weight Convolutional Neural Networks , 2018, IEEE Transactions on Very Large Scale Integration (VLSI) Systems.

[10]  Katsuyuki Miyasaka,et al.  Pulse oximetry: its invention, contribution to medicine, and future tasks. , 2002, Anesthesia and analgesia.

[11]  Luca Benini,et al.  YodaNN: An Ultra-Low Power Convolutional Neural Network Accelerator Based on Binary Weights , 2016, 2016 IEEE Computer Society Annual Symposium on VLSI (ISVLSI).