TY - JOUR
T1 - Unsupervised heart-rate estimation in wearables with Liquid states and a probabilistic readout
AU - Das, Anup
AU - Pradhapan, Paruthi
AU - Groenendaal, Willemijn
AU - Adiraju, Prathyusha
AU - Rajan, Raj Thilak
AU - Catthoor, Francky
AU - Schaafsma, Siebren
AU - Krichmar, Jeffrey L.
AU - Dutt, Nikil
AU - Van Hoof, Chris
PY - 2018
Y1 - 2018
N2 - Heart-rate estimation is a fundamental feature of modern wearable devices. In this paper we propose a machine learning technique to estimate heart-rate 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 is considered from in-house clinical trials and public ECG databases. Results show high accuracy and low energy footprint in heart-rate estimation across subjects with and without cardiac irregularities, signifying the strong potential of this approach to be integrated in future wearable devices.
AB - Heart-rate estimation is a fundamental feature of modern wearable devices. In this paper we propose a machine learning technique to estimate heart-rate 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 is considered from in-house clinical trials and public ECG databases. Results show high accuracy and low energy footprint in heart-rate estimation across subjects with and without cardiac irregularities, signifying the strong potential of this approach to be integrated in future wearable devices.
KW - Electrocardiogram (ECG)
KW - Fuzzy c-Means clustering
KW - Homeostatic plasticity
KW - Liquid state machine
KW - Spike timing dependent plasticity (STDP)
KW - Spiking neural networks
UR - http://www.scopus.com/inward/record.url?scp=85041467934&partnerID=8YFLogxK
U2 - 10.1016/j.neunet.2017.12.015
DO - 10.1016/j.neunet.2017.12.015
M3 - Article
C2 - 29414535
AN - SCOPUS:85041467934
SN - 0893-6080
VL - 99
SP - 134
EP - 147
JO - Neural Networks
JF - Neural Networks
ER -