A5049891904- ECG Monitoring and Analysis
- Atrial Fibrillation Management and Outcomes
- Non-Invasive Vital Sign Monitoring
- Wireless Body Area Networks
- Context-Aware Activity Recognition Systems
- Cardiovascular and exercise physiology
- Software System Performance and Reliability
- Cardiac electrophysiology and arrhythmias
- EEG and Brain-Computer Interfaces
- Heart Rate Variability and Autonomic Control
- Green IT and Sustainability
- Analog and Mixed-Signal Circuit Design
- Venous Thromboembolism Diagnosis and Management
- Cardiac Imaging and Diagnostics
- Pain Management and Treatment
- Hemodynamic Monitoring and Therapy
- Advanced Sensor and Energy Harvesting Materials
- Anomaly Detection Techniques and Applications
- Time Series Analysis and Forecasting
- IoT and Edge/Fog Computing
École Polytechnique Fédérale de Lausanne
2016-2022
Embedded Systems (United States)
2017
Wearable devices are an unobtrusive, cost-effective means of continuous ambulatory monitoring chronic cardiovascular diseases. However, on these resource-constrained systems, electrocardiogram (ECG) processing algorithms must consume minimal power and memory, yet robustly provide accurate physiological information. This work presents REWARD, the Relative-Energy-based WeArable R-Peak Detection algorithm, which is a novel ECG R-peak detection mechanism based nonlinear filtering method called...
In the last years, need for enhancing health and preventing problems with remote monitoring is increasing. A non-invasive low-cost technique processing bio-signals vital parameters, at rest during physical activity, use of wearable PhotoPlethysmoGraphic (PPG) systems. However, in order to detect a relevant parameter, such as heart rate demanding exercises, motion artifacts must be removed from signals retrieved. this paper, we present fast easy implement algorithm estimate value which does...
In the recent Internet-of-Things (IoT) era where biomedical applications require continuous monitoring of relevant data, edge computing keeps gaining more and importance. These new architectures for include multi-core parallel capabilities that can enable prevention diagnosis treatment diseases in ambulatory or home-based setups. this article, we explore benefits parallelization heterogeneity wearable sensors context a personalized online atrial fibrillation (AF) prediction method daily...
<italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Objective:</i> Continuous monitoring of biosignals via wearable sensors has quickly expanded in the medical and wellness fields. At rest, automatic detection vital parameters is generally accurate. However, conditions such as high-intensity exercise, sudden physiological changes occur to signals, compromising robustness standard algorithms. xmlns:xlink="http://www.w3.org/1999/xlink">Methods:</i>...
In the last years, remote health monitoring is becoming an essential branch of care with rapid development wearable sensors technology. To meet demand new more complex applications and ensuring adequate battery lifetime, have evolved into multicore systems advanced power-saving capabilities additional heterogeneous components. this article, we present approach that applies optimization parallelization techniques uncovered by modern ultralow power (ULP) platforms in SW layers goal improving...
In spite of the progress in management Atrial Fibrillation (AF), this arrhythmia is one major causes stroke and heart failure.The progression pathology from a silent paroxysmal form (PAF) into sustained AF can be prevented by predicting onset PAF episodes.Moreover, since caused heterogeneous mechanisms different patients, as we demonstrate paper, patient-specific approach offers promising solution.In work, consider two ECG recordings, close to far away any episode.For each patient, extract...
Atrial Fibrillation (AF) is a type of cardiac arrhythmia that significantly increases the risk stroke and heart failure.In general, in case patients affected by AF, their electrocardiogram (ECG) shows typical pattern irregular RR intervals abnormal P waves.However, discriminating AF from normal sinus rhythm or other types rhythms remains challenging problem today.Methods: We analyze database PhysioNet/Computing Cardiology Challenge 2017 to validate our classification technique.The contains...