CorNET: Deep Learning Framework for PPG-Based Heart Rate Estimation and Biometric Identification in Ambulant Environment

Biswas, Dwaipayan; Everson, Luke; Liu, Muqing; Panwar, Madhuri; Verhoef, Bram-Ernst; Patki, Shrishail; Kim, Chris H.; Acharyya, Amit; Hoof, Chris Van; Konijnenburg, Mario; Helleputte, Nick Van

doi:10.1109/tbcas.2019.2892297

Cited by 235 publications

(128 citation statements)

References 38 publications

Supporting

Mentioning

121

Contrasting

Unclassified

Order By: Relevance

“…The proposed DNN is capable of authenticating individuals based on heartbeat biometric collected through PPG sensors and has shown a 96% accuracy on 12 individuals. An extension of this work has been developed as a framework, called CorNET [12], for ambulant environments using custom sensors. It also uses a combination of CNN and LSTM, and presented 96% accuracy on 20 individuals (while doing different, voluntary physical activities).…”

Section: Heart-based Biometricsmentioning

confidence: 99%

Biometric Systems Utilising Health Data from Wearable Devices

et al. 2020

View full text Add to dashboard Cite

Health data is being increasingly sensed from the health-based wearable Internet of Things (IoT) devices, providing much-needed fitness and health tracking. However, data generated also presents opportunities within computer security, specifically w ith b iometric s ystems u sed f or i dentification an d authentication purposes. This paper performs a systematic review of health-based IoT data collected from wearable IoT technology. This involved performing research in the underlying data sources, what they are collected for in terms of their health monitoring, and the underlying data characteristics. Furthermore, it explores existing work in computer security using these data sources, identifying key themes of work, key limitations and challenges. Finally, key opportunities are provided as summaries to the potential of health-based IoT data, highlighting challenges that are yet to be addressed, which motivate areas of future work. CCS Concepts: • Security and privacy → Biometrics.

show abstract

Section: Heart-based Biometricsmentioning

confidence: 99%

Biometric Systems Utilising Health Data from Wearable Devices

et al. 2020

View full text Add to dashboard Cite

show abstract

“…From a different perspective, raw and spectral features were successfully extracted from SCG traces by means of Convolutional Neural Networks (CNN), leading to personalized heart biometrics [26]. Moreover, recent work [27] extended this approach to PPG (PhotoPlethysmoGram) signals, using wearable sensors. Furthermore, authors in [28] propose a multi-resolution CNN in the wavelet domain that extracts features independent of phase shifts.…”

Section: Related Workmentioning

confidence: 99%

Detection and Analysis of Heartbeats in Seismocardiogram Signals

Mora

Cocconcelli

Matrella

et al. 2020

Sensors

View full text Add to dashboard Cite

This paper presents an unsupervised methodology to analyze SeismoCardioGram (SCG) signals. Starting from raw accelerometric data, heartbeat complexes are extracted and annotated, using a two-step procedure. An unsupervised calibration procedure is added to better adapt to different user patterns. Results show that the performance scores achieved by the proposed methodology improve over related literature: on average, 98.5% sensitivity and 98.6% precision are achieved in beat detection, whereas RMS (Root Mean Square) error in heartbeat interval estimation is as low as 4.6 ms. This allows SCG heartbeat complexes to be reliably extracted. Then, the morphological information of such waveforms is further processed by means of a modular Convolutional Variational AutoEncoder network, aiming at extracting compressed, meaningful representation. After unsupervised training, the VAE network is able to recognize different signal morphologies, associating each user to its specific patterns with high accuracy, as indicated by specific performance metrics (including adjusted random and mutual information score, completeness, and homogeneity). Finally, a Linear Model is used to interpret the results of clustering in the learned latent space, highlighting the impact of different VAE architectural parameters (i.e., number of stacked convolutional units and dimension of latent space).

show abstract

“…Zhang et al [14], [21] proposed pre-and post-processing algorithms to achieve an average estimated error of 2.34 bpm [14] using signal decomposition for eliminating noise from motion artifacts, sparse signal reconstruction, and spectrum peak tracking. The authors achieve 1.28 bpm estimated error using joint sparse spectrum reconstruction using the multiple measure- [22] proposed a deep learning-based approach. Using two convolutional neural networks (CNN) layers, two long-short term memory (LSTM) layers, and a dense layer, their approach achieves 1.47 bpm average estimation error for data collected from 20 subjects.…”

Section: Related Workmentioning

confidence: 99%

On-Device Filter Design for Self-Identifying Inaccurate Heart Rate Readings on Wrist-Worn PPG Sensors

Ahn

Ra²,

Yoon

et al. 2020

IEEE Access

View full text Add to dashboard Cite

The ubiquitous deployment of smart wearable devices brings promises for an effective implementation of various healthcare applications in our everyday living environments. However, given that these applications ask for accurate and reliable sensing results of vital signs, there is a need to understand the accuracy of commercial-off-the-shelf wearable devices' healthcare sensing components (e.g., heart rate sensors). This work presents a thorough investigation on the accuracy of heart rate sensors equipped on three different widely used smartwatch platforms. We show that heart rate readings can easily diverge from the ground truth when users are actively moving. Moreover, we show that the accelerometer is not an effective secondary sensing modality of predicting the accuracy of such smartwatch-embedded sensors. Instead, we show that the photoplethysmography (PPG) sensor's light intensity readings are an plausible indicator for determining the accuracy of optical sensor-based heart rate readings. Based on such observations, this work presents a lightweight Viterbi-algorithm-based Hidden Markov Model to design a filter that identifies reliable heart rate measurements using only the limited computational resources available on smartwatches. Our evaluations with data collected from four participants show that the accuracy of our proposed scheme can be as high as 98%. By enabling the smartwatch to self-filter misleading measurements from being healthcare application inputs, we see this work as an essential module for catalyzing novel ubiquitous healthcare applications.

show abstract

CorNET: Deep Learning Framework for PPG-Based Heart Rate Estimation and Biometric Identification in Ambulant Environment

Cited by 235 publications

References 38 publications

Biometric Systems Utilising Health Data from Wearable Devices

Biometric Systems Utilising Health Data from Wearable Devices

Detection and Analysis of Heartbeats in Seismocardiogram Signals

On-Device Filter Design for Self-Identifying Inaccurate Heart Rate Readings on Wrist-Worn PPG Sensors

Contact Info

Product

Resources

About