Deep Learning and Signal-Processing Methods for Multisensor Data Fusion

Applications to Ambulatory Health Monitoring
Erscheinungsjahr 2026
ISBN: 978-3-031-96723-8
Verlag: Springer

Buch, Englisch, 244 Seiten, Format (B × H): 160 mm x 241 mm, Gewicht: 637 g

This book focuses on the development of multisensor fusion algorithms for wearable devices that are useful in ambulatory health monitoring using signal-processing and deep learning-based methods. The algorithms described account for the signal quality prior to fusion, in order to enable reliable inferences without contributing to additional computational overhead. The content discussed is beneficial in the broad application of multisensor fusion, as the algorithms developed or discussed in the final chapters are generalized cases of the methods developed in the initial chapters, offering relevance to the broader multisensor fusion community.

• Provides a single-source reference to the development of fusion methods and analysis of fusion algorithms
• Treats fusion as a signal-processing-based problem, applied to a wide variety of fusion applications
• Describes a step-by-step methodology for development of a generalized fusion algorithm for any application

Zielgruppe

Research

Autoren/Hrsg.

John, Arlene

Cardiff, Barry

John, Deepu

Fachgebiete

• Technische Wissenschaften Elektronik | Nachrichtentechnik Elektronik Bauelemente, Schaltkreise
• Interdisziplinäres Wissenschaften Wissenschaften: Forschung und Information Kybernetik, Systemtheorie, Komplexe Systeme
• Technische Wissenschaften Elektronik | Nachrichtentechnik Nachrichten- und Kommunikationstechnik Signalverarbeitung

Inhaltsverzeichnis

Chapter 1. Introduction.- Chapter 2. Fusion- a multi-domain topic.- Chapter 3. Signal quality indicators for ECG signals obtained from wearable IoT sensors.- Chapter 4. Multi-sensor fusion for heartrate estimation.- Chapter 5. Multimodal data fusion for heartbeat detection.- Chapter 6. Multiresolution fusion for sleep apnea detection.- Chapter 7. Multi-level fusion for atrial fibrillation detection.- Chapter 8. Conclusion.

Über Autor(innen)

Arlene John is an Assistant Professor at the Faculty of Electrical Engineering, Mathematics and Computer Science, University of Twente, the Netherlands.She received the Bachelor of Technology degree in electrical and electronics engineering from the National Institute of Technology, Calicut, India, in 2017 and the Ph.D. degree in electrical and electronic engineering from University College Dublin, Ireland, in 2022. From March–June, 2019, she was a Senior Visiting Researcher with the Beijing University of Technology, Beijing, China and she worked as a Machine Learning Mathematics Engineer at ASML Netherlands B.V. from 2022-2023.Her research focuses on the development of explainable AI technique for personalized predictions and decision-support for ehealth technology.

Barry Cardiff graduated with a B.Eng from the Electronic Engineering department in UCD in 1992 and an M.Eng.Sc (by research) thereafter. In 2011 obtained a PhD, as a mature student in the field of Digital Signal Processing (DSP) for wireless and optical communications. Worked for as a design Engineer for Nokia Mobile Phone (UK) Ltd from 1993 to 2001 working on some of world's more advanced and innovative products culminating in the role of Chief Engineer and as a contributor to the 3GPP standardization process. Moved to Ireland in 2001 to work as a Systems Architect in Silicon & Software Systems (S3 group) working mainly on embedded hardware / software development projects with applications ranging from wireless communications to hearing aids. Continued to work for S3 group for several years after a break between 2007-2011 to obtain a PhD from UCD under Prof. Tony Fagan with a thesis entitled "Detection Techniques in Vector Systems in Communications". In September 2013 joined the academic staff in UCD to complement the teaching staff both in Dublin and in a joint collaboration in Beijing (BDIC). Research interests are in the area of DSP applications mainly in communication systems both in the theoretical analysis and practical advancement of such systems. The area of power / complexity reduction techniques in circuit design, i.e. DSP algorithms for digitally assisted analog circuits, is also of current interest.

 Deepu John is an Assistant Professor at the School of Electrical and Electronics Engineering, University College Dublin, Ireland. He obtained his B.Tech degree in Electronics and Communication Engineering from the University of Kerala, India, in 2002, followed by his MSc and PhD degrees in Electrical Engineering from the National University of Singapore in 2008 and 2014, respectively. From 2014 to early 2017, he worked as a postdoctoral researcher at the Bio-Electronics Lab, National University of Singapore. Prior to this, he served as a senior engineer at Sanyo Semiconductors, Japan. He has received several awards, including the Institution of Engineers Singapore Prestigious Engineering Achievement Award, Best Design Award at the Asian Solid-State Circuit Conference (2013), and IEEE Young Professionals, Region 10 individual award. He has also served as a member of the organizing or technical committee for several IEEE conferences, such as ISCAS, BioCAS, NorCAS, ICECS, AICAS, MWSCAS, APCCAS, TENCON, ASICON, and ICTA. He is a reviewer of several IEEE journals and conferences. He has served as an Associate Editor for IEEE Internet of Things Magazine and Guest Editor for IEEE Transactions on Circuits and Systems-I and IEEE Open Journal of Circuits and Systems. Currently, he serves as an Associate Editor for IEEE Transactions on Biomedical Circuits & Systems, Wiley International Journal of Circuit Theory & Applications and as a Senior Associate Editor for IEEE Transactions on Circuits & Systems-II. His research interests include IoT/Wearable sensing, Biomedical Circuits & Systems, and Edge computing. He is a Senior Member of the IEEE.