Philippe Renevey

Wrist-located pulse detection using IR signals, activity and nonlinear artifact cancellation

We present a new integrated device for monitoring heart rate at the wrist using an optical measure. Motion robustness is obtained by using accurate motion reference signals of 3D low noise accelerometers together with dual channel optical sensing. Nonlinear modelling allows to remove the motion contributions in the optical signals and the spatial diversity of the sensors is used to remove reciprocal contributions in the two channels. Finally a statistical estimation, based on physiological properties of the heart, gives a robust estimation of the heart rate. Qualitative and quantitative performance evaluation of the performances on real signals clearly show that the proposed system gives an accurate estimation of the heart rate, even under intense physical activity.

Parametric estimation of pulse arrival time: a robust approach to pulse wave velocity

Pulse wave velocity (PWV) is a surrogate of arterial stiffness and represents a non-invasive marker of cardiovascular risk. The non-invasive measurement of PWV requires tracking the arrival time of pressure pulses recorded in vivo, commonly referred to as pulse arrival time (PAT). In the state of the art, PAT is estimated by identifying a characteristic point of the pressure pulse waveform. This paper demonstrates that for ambulatory scenarios, where signal-to-noise ratios are below 10 dB, the performance in terms of repeatability of PAT measurements through characteristic points identification degrades drastically. Hence, we introduce a novel family of PAT estimators based on the parametric modeling of the anacrotic phase of a pressure pulse. In particular, we propose a parametric PAT estimator (TANH) that depicts high correlation with the Complior(R) characteristic point D1 (CC = 0.99), increases noise robustness and reduces by a five-fold factor the number of heartbeats required to obtain reliable PAT measurements.

SVM-based recursive feature elimination to compare phase synchronization computed from broadband and narrowband EEG signals in brain-computer interfaces

To allow motor-disabled people for communication, Brain-Computer Interfaces (BCIs) are being developed. Such a communication does not depend on the brains normal output pathways of peripheral nerves and muscles, but is based on analysis of recorded brain activity. In this paper, we compare the performance of power features and phase locking values (PLVs) computed from broadband and narrowband filtered EEG signals for discriminating 3 mental tasks in the framework of a BCI. EEG signals were recorded from 5 subjects while performing the 3 mental tasks left- and right-hand movement imagination and word generation. To reduce the total amount of features, the most discriminative features were selected in a 2-step feature selection procedure by SVM-based recursive feature elimination.Significance tests demonstrated that band power features were more discriminative when they were computed in the narrower frequency band 8-12 Hz. In case of PLV features, the discrimination of mental tasks was significantly better when they were computed from the broader 8-30 Hz frequency band, as compared to the narrower bands 8-12, 13-18 and 19-30 Hz.

Statistical estimation of unreliable features for robust speech recognition

This paper addresses the problem of robust speech recognition in noisy conditions in the framework of hidden Markov models (HMMs) and missing feature techniques. It presents a new statistical approach to detection and estimation of unreliable features based on a probabilistic measure and Gaussian mixture model (GMM). In the estimation process, the GMM is compensated using parameters of the statistical model of additive background noise. The GMM means are used to replace the unreliable features. The GMM based technique is less complex than the corresponding HMM based estimation and gives similar improvement in the recognition performance. Once unreliable features are replaced by the estimated clean speech features, the entire set of spectral features can be transformed to the other feature domain characterized by higher baseline recognition rate (e.g. MFCCs) for final recognition using continuous density hidden Markov models (CDHMMs) with diagonal covariance matrices.

Evaluation of the beat-to-beat detection accuracy of PulseOn wearable optical heart rate monitor.

Heart rate variability (HRV) provides significant information about the health status of an individual. Optical heart rate monitoring is a comfortable alternative to ECG based heart rate monitoring. However, most available optical heart rate monitoring devices do not supply beat-to-beat detection accuracy required by proper HRV analysis. We evaluate the beat-to-beat detection accuracy of a recent wrist-worn optical heart rate monitoring device, PulseOn (PO). Ten subjects (8 male and 2 female; 35.9±10.3 years old) participated in the study. HRV was recorded with PO and Firstbeat Bodyguard 2 (BG2) device, which was used as an ECG based reference. HRV was recorded during sleep. As compared to BG2, PO detected on average 99.57% of the heartbeats (0.43% of beats missed) and had 0.72% extra beat detection rate, with 5.94 ms mean absolute error (MAE) in beat-to-beat intervals (RRI) as compared to the ECG based RRI BG2. Mean RMSSD difference between PO and BG2 derived HRV was 3.1 ms. Therefore, PO provides an accurate method for long term HRV monitoring during sleep.

Evaluation of accuracy and reliability of PulseOn optical heart rate monitoring device.

PulseOn is a wrist-worn optical heart rate (HR) monitor based on photoplethysmography. It utilizes multi-wavelength technology and optimized sensor geometry to monitor blood flow at different depths of skin tissue, and it dynamically adapts to an optimal measurement depth in different conditions. Movement artefacts are reduced by adaptive movement-cancellation algorithms and optimized mechanics, which stabilize the sensor-to-skin contact. In this paper, we evaluated the accuracy and reliability of PulseOn technology against ECG-derived HR in laboratory conditions during a wide range of physical activities and also during outdoor sports. In addition, we compared the performance to another on-the-shelf wrist-worn consumer product Mio LINK®. The results showed PulseOn reliability (% of time with error <;10bpm) of 94.5% with accuracy (100% - mean absolute percentage error) 96.6% as compared to ECG (vs 86.6% and 94.4% for Mio LINK®, correspondingly) during laboratory protocol. Similar or better reliability and accuracy was seen during normal outdoor sports activities. The results show that PulseOn provides reliability and accuracy similar to traditional chest strap ECG HR monitors during cardiovascular exercise.

Wearable biosensing: signal processing and communication architectures issues

Mutation testing – a fault-based technique for software testing – is a computationally expensive approach. One of the powerful methods to improve the performance of mutation without reducing effectiveness is to employ parallel processing, where mutants and tests are executed in parallel. This approach reduces the total time needed to accomplish the mutation analysis. This paper proposes three strategies for parallel execution of mutants on multicore machines using the Parallel Computing Toolbox (PCT) with the Matlab Distributed Computing Server. It aims to demonstrate that the computationally intensive software testing schemes, such as mutation, can be facilitated by using parallel processing. The experiments were carried out on eight different Simulink models. The results represented the efficiency of the proposed approaches in terms of execution time during the testing process. Keywords—mutant execution, mutation testing, parallel processing, software testing.

Validation of a wrist monitor for accurate estimation of RR intervals during sleep

While the incidence of sleep disorders is continuously increasing in western societies, there is a clear demand for technologies to asses sleep-related parameters in ambulatory scenarios. The present study introduces a novel concept of accurate sensor to measure RR intervals via the analysis of photo-plethysmographic signals recorded at the wrist. In a cohort of 26 subjects undergoing full night polysomnography, the wrist device provided RR interval estimates in agreement with RR intervals as measured from standard electrocardiographic time series. The study showed an overall agreement between both approaches of 0.05 ± 18 ms. The novel wrist sensor opens the door towards a new generation of comfortable and easy-to-use sleep monitors.

Application of Optical Heart Rate Monitoring

The present chapter is dedicated to a novel family of sensors used for heart-rate monitoring. Based on the so-called photoplethysmographic technology, optical heart-rate monitors open the door to the comfortable and continuous monitoring of health status during daily life. Either integrated within a wrist-worn device, an arm band, or a chest patch, optical heart-rate monitors are capable of accurately measuring heart rate by assessing the arterial pulsatility of underlying skin vascular beds. After reviewing the physical and physiological background of the photoplethysmographic phenomenon, this chapter copes with the design of optical heart-rate sensors and monitors in terms of optomechanical properties and signal processing and motion artifact issues. The performance of recently launched commercial optical heart-rate monitors is briefly addressed in the context of sport activities, daily life periods, and clinical applications.

Physical activity profiling: Activity-specific step counting and energy expenditure models using 3D wrist acceleration

In this paper, we present the evaluation of a new physical activity profiling system embedded in a wrist-located device. We propose a step counting and an energy expenditure (EE) method, and evaluate their accuracy against gold standard references. To this end, we used an actimetry sensor on the waist and an indirect calorimetry monitoring device on a population of 13 subjects to obtain step count and metabolic equivalent task (kcal/kg/h) referenced values. The subjects followed a protocol that spanned a given set of activities (lying, standing, walking, running) at a wide range of intensities. The performance of the EE model was characterized by a root-mean-square error (RMSE) of 1.22±0.34kcal/min, and step-count model at regular walking/running speeds by 0.71±0.06step/10sec.