Ubiquitous personal heart rate long distance transmission to the treatment centers based on smart mobile phone application

Krasauskas, Zygimantas; Telksnys, Laimutis

doi:10.1109/aieee.2015.7367297

Cited by 1 publication

(2 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The simulation is carried on a system with the following configuration 7 The simulation setup is used here for accelerating ECG simulations. Our final approach is envisioned to be running on a neuromorphic chip such as the CxQuad [37] for real-time ECG-based estimation.…”

Section: Spiking Neural Network Simulation Setupmentioning

confidence: 99%

“…ECG sensors [4,5] attached to these devices monitor the electrical potential caused by the systolic activity of heart and then propagated through cardiac muscles. The recorded electrical data are postprocessed, either locally on the sensor [6] or on a device [7] attached to the sensor to estimate heart-rate. QRS pattern identification (see Figure 1) from ECG is fundamental to heart-rate estimation.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Unsupervised heart-rate estimation in wearables with Liquid states and a probabilistic readout

et al. 2018

View full text Add to dashboard Cite

Heart-rate estimation is a fundamental feature of modern wearable devices. In this paper we propose a machine intelligent approach for heart-rate estimation from electrocardiogram (ECG) data collected using wearable devices. The novelty of our approach lies in (1) encoding spatio-temporal properties of ECG signals directly into spike train and using this to excite recurrently connected spiking neurons in a Liquid State Machine computation model; (2) a novel learning algorithm; and (3) an intelligently designed unsupervised readout based on Fuzzy c-Means clustering of spike responses from a subset of neurons (Liquid states), selected using particle swarm optimization.Our approach differs from existing works by learning directly from ECG signals (allowing personalization), without requiring costly data annotations. Additionally, our approach can be easily implemented on state-of-the-art spiking-based neuromorphic systems, offering high accuracy, yet significantly low energy footprint, leading to an extended battery life of wearable devices. We validated our approach with CARLsim, a GPU accelerated spiking neural network simulator modeling Izhikevich spiking neurons with Spike Timing Dependent Plasticity (STDP) and homeostatic scaling. A range of subjects are considered from in-house clinical trials and public ECG databases.Results show high accuracy and low energy footprint in heart-rate estimation across * Corresponding author

show abstract

Section: Spiking Neural Network Simulation Setupmentioning

confidence: 99%