Optimized Algorithms and Machine Learning Techniques for Biosignal Processing on Ultra-Low-Power Computing Platforms - Doctor of Philosophy thesis

Aug 5, 2026

Upload by Ophelia

Recent advances in electronic systems have enabled implantable and wearable devices for continuous health monitoring by extracting physiological parameters from biosignals such as ECG and EEG. Biosignal applications span from consumer fitness to medical-grade diagnostics, yet biosignal processing must resolve a critical trade-off between computational power and energy efficiency to support long battery life. This thesis presents an end-to-end framework to optimize energy use while running complex signal processing on resource-constrained embedded devices through optimized architectures, low-power strategies, and machine-learning methods.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages118

Reading Time4 h 57 min

AccessFree to download

Acknowledgments

Abstract

List of Figures

List of Tables

Introduction

Contributions & Thesis Structure

Background

Biomedical Applications based on ECG and EEG Signals

Time-Series Biosignal Data Analysis

Microcontrollers of Interest

Embedding Networks: Compression & Deployment

ECG Applications - Efficient Transforms and Heart Rate Detection Algorithm

Signal Description and Acquisition

Efficient Transforms

Optimized Heart Rate Detection System

DOTTORATO DI RICERCA IN Ingegneria Elettronica, Telecomunicazioni e Tecnologie dell’Informazione Ciclo XXXVII Settore Concorsuale: 09/H1 – SISTEMI DI ELABORAZIONE DELLE INFORMAZIONI Settore Scientifico Disciplinare: ING-INF/05-INFORMATICA Optimized Algorithms and Machine Learning Techniques for Biosignal Processing on Ultra-Low-Power Computing Platforms Presentata da: BENEDETTA MAZZONI Coordinatore Dottorato Prof. DAVIDE DARDARI Supervisore Prof. LUCA BENINI Esame finale anno 2025 ALMA MATER STUDIORUM-UNIVERSITY OF BOLOGNA Optimized Algorithms and Machine Learning Techniques for Biosignal Processing on Ultra-Low-Power Computing Platforms by Benedetta Mazzoni A thesis submitted for the degree of Doctor of Philosophy in the Faculty of Engineering Department of Electrical, Electronic, and Information Engineering (DEI) February 2025 I wish to dedicate this thesis to my lovely family. Acknowledgments I wish to thank Prof. Luca Benini for the opportunity to pursue my Ph.D. in his research group and for his constant guidance. I specifically appreciated Prof. Giuseppe Tagliavini and Prof. Simone Benatti for their persevering supervision, their teachings, and the motivation they gave me. I thank them for the support and independence they gave me. I thank Prof. Andrea Cossettini for welcoming me and following my work to his PULP group at ETH for a visiting research period. I also thank GreenWaves Technologies for the preview access to the GAP SDK. In closing, I would like to express my gratitude to all my colleagues at the EEESLab for creating an enjoyable and inspiring environment. Abstract In recent years, advancements in electronic systems have driven the development of implantable and wearable devices that facilitate continuous health monitoring through the extraction of physiological parameters from biosignals, such as Electrocardiogram (ECG) and Electroencephalogram (EEG) . Biosignal-based applications have become central to various fields, ranging from fitness to medical-grade diagnostics. However, implementing biosignal processing presents significant challenges, notably in achieving a balance between computational power and energy efficiency, which is essential for extended battery life in portable devices. This thesis contributes to this field by presenting a framework of end-to-end methodologies designed to optimize energy efficiency in executing computationally intensive signal processing tasks on resource-constrained embedded devices. Through a combination of optimized system architectures, low-power processing strategies, and machine learning-based algorithms, the thesis offers novel solutions for achieving highperformance ExG signal analysis within strict energy budgets. Key aspects include the design of Analog Front Ends (AFEs) to ensure high-fidelity signal capture with minimal energy draw, as well as optimizing digital processors to handle complex operations such as filtering, feature extraction, and pattern classification within limited memory and processing power. Additionally, this research explores the adaptation of machine learning algorithms, such as CNNs and TCNs, for edge-based biosignal processing, emphasizing model compression to reduce computational overhead. The research demonstrates a sustainable solution for real-time biosignal processing on ultra-low-power (ULP) parallel platforms, offering significant advantages over traditional MCUs in both energy efficiency and processing capability. To validate the proposed methodologies, the thesis investigates two primary case studies. The first focuses on ECG signal processing and classification, showcasing how on-device computation minimizes data transmission and latency, thereby improving privacy, energy efficiency, and responsiveness. The second evaluates ear-EEG as a promising alternative to conventional, full-scalp EEG, demonstrating its viability in mobile health applications. This dissertat

FAQs

What main problem does the thesis address for biosignal processing?

It addresses the balance between computational power and energy efficiency required to run biosignal processing on resource-constrained portable devices with long battery life.

How does the thesis improve on-device ExG signal analysis under strict energy budgets?

It combines optimized system architectures, low-power processing strategies, and machine-learning-based algorithms to perform high-performance analysis within limited energy.

What case studies validate the proposed methodologies?

One case study focuses on ECG signal processing and classification, showing reduced transmission and latency on-device, while the second evaluates ear-EEG as an alternative to full-scalp EEG for mobile health.

Aug 5, 2026

Upload by Ophelia