Machine Learning Models and Architectures for Biomedical Signal Processing

1st Edition - November 5, 2024
Editors: Suman Lata Tripathi, Valentina Emilia Balas, Mufti Mahmud, Soumya Banerjee
Language: English
Paperback ISBN:
9 7 8 - 0 - 4 4 3 - 2 2 1 5 8 - 3
eBook ISBN:
9 7 8 - 0 - 4 4 3 - 2 2 1 5 7 - 6

Machine Learning Models and Architectures for Biomedical Signal Processing presents the fundamental concepts of machine learning techniques for bioinformatics in an intera… Read more

Purchase options

World Book Day Celebration!

Save up to 30% on books and eBooks!

Shop now

Institutional subscription on ScienceDirect

Request a sales quote

Machine Learning Models and Architectures for Biomedical Signal Processing presents the fundamental concepts of machine learning techniques for bioinformatics in an interactive way. The book investigates how efficient machine and deep learning models can support high-speed processors with reconfigurable architectures like graphic processing units (GPUs), Field programmable gate arrays (FPGAs), or any hybrid system. This great resource will be of interest to researchers working to increase the efficiency of hardware and architecture design for biomedical signal processing and signal processing techniques.

Title of Book
Cover image
Title page
Table of Contents
Copyright
List of contributors
Preface
Acknowledgments
Section I: Introduction to biomedical informatics
1. Recent trends in biomedical informatics
Abstract
1.1 Introduction
1.2 Standards and ethics in biomedical informatics
1.3 Health information management
1.4 Telemonitoring and telemedicine
1.5 Bioinformatics and genomics
1.6 Biomedical imaging informatics
1.7 Conclusion
References
2. Biomedical signal processing technique
Abstract
2.1 Introduction
2.2 Biomedical signal processing
2.3 Medicine and biomedical research
2.4 Medicine and biomedical research for the treatment of diseases
2.5 Signal processing techniques in electrocardiograms
2.6 Signal processing techniques in electroencephalograms
2.7 Signal processing techniques in electromyograms
2.8 Signal processing techniques in computed tomography
2.9 Signal processing techniques in magnetic resonance imaging
2.10 Signal processing techniques in ultrasound
2.11 Techniques used in biomedical signal processing
2.12 Time-frequency analysis technique
2.13 Wavelet transforms technique
2.14 Principal component analysis technique
2.15 Neural networks technique
2.16 Hybrid lossless and lossy compression technique for ECG signals
2.17 Automatic detection of diseases in prenatal age
2.18 Bio-signal processing system for research
2.19 Filter for biomedical signal-sensing applications
2.20 Conclusion
Abbreviations
References
3. Transfer learning-based arrhythmia classification using electrocardiogram
Abstract
3.1 Introduction
3.2 Transfer learning
3.3 TL-based arrhythmia classification
3.4 Experimental results
3.5 Discussion
3.6 Conclusion and future applications
References
Section II: Machine learning models for biomedical signal processing
4. Exploring machine learning models for biomedical signal processing: a comprehensive review
Abstract
4.1 Introduction
4.2 Electroencephalography
4.3 Electrocardiography
4.4 Electromyography
4.5 Machine learning models
4.6 Supervised learning
4.7 Unsupervised learning
4.8 Reinforcement learning
4.9 Literature review
4.10 Proposed model
4.11 Challenges
4.12 Future scope
4.13 Conclusion
Abbreviations
References
5. Machine learning for audio processing: from feature extraction to model selection
Abstract
5.1 Introduction
5.2 Feature extraction techniques
5.3 Audio segmentation and augmentation
5.4 Model selection
5.5 Applications
5.6 Conclusions and future directions
References
6. Enhancing insights: unravelling the potential of preprocessing MRI for artificial intelligence based Alzheimer's disease classification
Abstract
6.1 Introduction
6.2 Literature review
6.3 MRI preprocessing pipeline
6.4 Conclusion and future work
6.5 AI disclosure
References
7. Machine learning models for text and image processing
Abstract
7.1 Introduction
7.2 Related work
7.3 Methodologies
7.4 Experimental results and discussions
7.5 Conclusion
References
8. Assistive technology for neuro-rehabilitation applications using machine learning techniques
Abstract
8.1 Introduction
8.2 Assistive technology for rehabilitation
8.3 Assistive technology for accessing the computer for rehabilitating stroke patients
8.4 Speech recognition
8.5 Gesture recognition
8.6 Text-to-speech conversion
8.7 Robotics assistance
8.8 Remote-operated assistive devices or wearables
8.9 Advanced processors for assistive devices
8.10 Conclusion and future scope
Acknowledgment
Abbreviations
References
9. Deep learning architectures in computer vision based medical imaging applications with emerging challenges
Abstract
9.1 Introduction
9.2 Deep learning architectures
9.3 Applications of deep learning models in computer vision
9.4 Challenges
9.5 Conclusion
Acknowledgment
References
10. Relevance of artificial intelligence, machine learning, and biomedical devices to healthcare quality and patient outcomes
Abstract
10.1 Introduction
10.2 Artificial intelligence (AI)
10.3 Machine learning
10.4 Relationship between AI and ML
10.5 Differences between AI and ML
10.6 Internet of things (IoT)
10.7 Bio-medical engineering (BME)
10.8 AI, ML, and IoT as healthcare system foundations
10.9 The future of AI, ML, and IoT in healthcare
10.10 Conclusion
Abbreviations
References
11. Artificial intelligence-based electrocardiogram signal processing applications
Abstract
11.1 Introduction
11.2 ECG clustering
11.3 ECG classification
11.4 ECG captioning
11.5 ECG synthesis
11.6 Conclusion
References
12. Deep learning approach for the prediction of skin diseases
Abstract
12.1 Introduction
12.2 Review of literature
12.3 Methodology
12.4 Data description
12.5 Result
12.6 Conclusion
References
Section III: Brain computer interfaces (BCI)
13. Brain–computer interface
Abstract
13.1 Introduction
13.2 BCI for motor disorders
13.3 BCI for elderly and disabled persons
13.4 BCI for cognitive workload
13.5 Web-based BCIs
13.6 Case study: BCI signal processing
13.7 Conclusion future directions
References
14. Human-computer interface developments include systems that can decipher enhanced human language and contextual cues while interacting with digital devices
Abstract
14.1 Introduction
14.2 Types of BCIs
14.3 Design principles of BCI
14.4 Learning about algorithms and models while keeping neurobiology in mind
14.5 Limitations
14.6 BCI applications
14.7 Conclusion
References
15. Brain-computer interfaces for elderly and disabled persons
Abstract
15.1 Introduction
15.2 Signal acquisition and processing
15.3 Conclusion
Abbreviations
References
Section IV: Real time architecture design for biomedical signals
16. Machine learning model implementation with FPGAs
Abstract
16.1 Introduction to machine learning and FPGAs
16.2 FPGA architecture and design considerations
16.3 FPGA-based machine learning acceleration techniques
16.4 Quantization and optimization for FPGA implementations
16.5 Design space exploration and optimization
16.6 Integration with software frameworks
16.7 Case studies and applications
16.8 Challenges and future directions
16.9 Conclusion
References
17. Smart biomedical devices for smart healthcare
Abstract
17.1 Introduction
17.2 Personalized healthcare
17.3 Synchronized nursing and reporting
17.4 Conclusion
Abbreviations
References
18. FPGA implementation for explainable machine learning and deep learning models to real-time problems
Abstract
18.1 Introduction
18.2 Algorithm and models for processors
18.3 Field programmable gate array architectures
18.4 FPGA-based design challenges and applications
18.5 Techniques used for the design of FPGA-based hardware accelerators
18.6 Conclusions
Acknowledgment
References
Section V: Software and hardware-based applications for biomedical informatics
19. Software applications for biometric informatics
Abstract
19.1 Introduction
19.2 Architecture of biometric system
19.3 Application of biometrics systems
19.4 Biometrics traits comparison
19.5 Importance of biometric system
19.6 Biometric systems security
19.7 Conclusion
Abbreviations
References
20. Smart medical devices: making healthcare more intelligent
Abstract
20.1 Introduction
20.2 IoT in healthcare
20.3 Artificial intelligence in smart healthcare
20.4 Conclusion
Abbreviations
References
21. Security modules for biomedical signal processing using Internet of Things
Abstract
21.1 Introduction to biomedical signals and its processing
21.2 Electrocardiogram
21.3 Conclusion
References
22. Artificial intelligence-based diagnostic tools for cardiovascular risk prediction
Abstract
22.1 Introduction to CVD and its risk factors
22.2 Cardiovascular disease risk factors
22.3 Types of cardiovascular disease
22.4 Role of AI in healthcare
22.5 Types of AI algorithms in CVD prediction
22.6 Data sources for AI-based CVD risk prediction
22.7 Conventional AI
22.8 Future direction of AI-based CVD risk prediction
Abbreviations
References
23. Machine learning algorithm approach in risk prediction of liver cancer
Abstract
23.1 Introduction
23.2 Literature review
23.3 Methodology
23.4 Results
23.5 Conclusion
23.6 Future scope
References
Index

Suman Lata Tripathi

Suman Lata Tripathi completed her PhD in the area of microelectronics and VLSI from MNNIT, Allahabad. She was also a remote post-doc researcher at Nottingham Trent University, London, UK in 2022. She is a Professor at Lovely Professional University with more than 19 years of experience in academics. She has published more than 89 research papers in refereed journals and conferences. She has also published 13 Indian patents and 2 copyrights. She has organized several workshops, summer internships, and expert lectures for students. She has worked as a session chair, conference steering committee member, editorial board member, and peer reviewer in international/national conferences. She received the “Research Excellence Award” in 2019 and “Research Appreciation Award” in 2020, 2021 at Lovely Professional University, India. She also received funded projects from SERB DST under the scheme TARE in the area of Microelectronics devices. She has edited or authored more than 15 books in different areas of Electronics and electrical engineering. Her areas of expertise includes microelectronics device modeling and characterization, low power VLSI circuit design, VLSI design of testing, and advanced FET design for IoT, Embedded System Design, reconfigurable architecture with FPGAs and biomedical applications.

Affiliations and expertise

Lovely Professional University, Phagwara, Punjab, India

Valentina Emilia Balas

Valentina E. Balas is a Professor in the Department of Automatics and Applied Software at the Faculty of Engineering, “Aurel Vlaicu” University of Arad, Romania. She holds a PhD Cum Laude, in Applied Electronics and Telecommunications from Polytechnic University of Timisoara. Dr. Balas is the author of more than 350 research papers. Her research interests are in intelligent systems, fuzzy control, soft computing, smart sensors, information fusion, modeling, and simulation. She is a member of the editorial boards of several national and international journals and evaluator expert for national, international projects, and PhD thesis. Dr. Balas is the Director of Intelligent Systems Research Centre and Director of the Department of International Relations, Programs, and Projects in Aurel Vlaicu University of Arad. She is the recipient of the "Tudor Tanasescu" Prize from the Romanian Academy for contributions in the field of soft computing methods (2019).

Affiliations and expertise

Professor, Department of Automatics and Applied Software at the Faculty of Engineering, “Aurel Vlaicu” University of Arad, Romania, and Academy of Romanian Scientists, Romania

Mufti Mahmud

Mufti Mahmud is an Associate Professor of Cognitive Computing at the Department of Computer Science of Nottingham Trent University (NTU). Dr. Mahmud was appointed to the USET, University Shadow Executive Team, in 2022, providing specialist input to the University Executive Team and Vice-Chancellor on strategic policy and direction matters related to Equality, Diversity & Inclusion (EDI). He is the Coordinator of the Computer Science and Informatics Unit of Assessment of Research Excellence Framework at NTU and the deputy group leader of the Interactive Systems Research Group (ISRG) and the Cognitive Computing & Brain Informatics (CCBI) research group. He is also an active member of the Computing and Informatics Research Centre (CIRC) and the Medical Technologies Innovation Facility (MTIF). He is a member of the NTU Distance Learning Governance, Operation and Steering committee as well as the International Mobility Committee and serves as an independent end-point assessor for the Level 6 BSc (Hons) in Digital & Technology Solutions Professional Degree Apprenticeship, and an expert of the online master's degree in computer science. He led the teaching of the Big Data and its Infrastructures (Postgraduate – on-campus and online delivery) module. He is a Fellow of the Higher Education Academy, a Senior Member of the Institute of Electrical and Electronics Engineers (IEEE) and the Association of Computing Machinery (ACM), and a professional member of the British Computer Society (BCS).

Affiliations and expertise

Department of Computer Science and Engineering, Nottingham Trent University, UK

Soumya Banerjee

Soumya (SM-IEEE) was an invited Research professor and at present as Senior Associated Researcher at Conservatoire National des Arts et Métiers (CNAM), Laboratoire CEDRIC and INRIA–EVA (the French National Institute for computer science) Paris since November 2018. He is also the Chief Technology Officer of MUST-B2B, Paris, along with associated senior researcher activities and. Projects at INRIA, Paris, where he is developing of Deep hybrid learning based recommendation and unsupervised machine learning for business Eco-system and communication systems. In addition to, he is the director research & innovation of Trasna-Solutions, Arklow Ireland at their center of excellence with UCC Cork and Govt. of Ireland. He is having several projects and product implementation on private Blockchain, e-SIM and smart manufacturing & logistics. Prior to that he was senior Associate Professor, Computer Sc.& Engg., Birla Institute of Technology Mesra, India, vising research professor at CNRS –INSA de Lyon, Lyon, France (2016), Invited Research professor at TU-Ostrava, Cz Republic respectively (2015). He also spends several years with MSR Seattle, USA, in Cognizant Technology Solution, ICICI InfoTech both in India, southeast Asia and Europe almost a decade. Dr. Banerjee completed his Bachelors in Engg. (at present VNIT Nagpur) in Computer Sc. (Hons.), did his masters from IISC Bangalore (MS- Research) and Ph.D in Computer Science and Engg. from Birla Institute of Technology, Mesra, India on Stigmergic optimization with Hybrid Intelligence in 2008-2009. He has more than 130 international journal publications including 32 book chapters and 55 International top level conference proceedings published from Elsevier Science, IEEE Transactions, ACM, Springer– Verlag Germany, CRC Press, and Idea Publication USA to his credit covering machine learning, security measures, prediction and data analytics, bio inspired intelligence, soft computing and optimization, hybrid intelligence, social networking applications and social media, Wiki analysis, machine learning with complex system and evolutionary computing. He also guided more than 10 Ph.D scholars in India and abroad. Dr. Banerjee had also developed a new artificial agent known as emotional ant colony for crowd modelling with European patent. Now he is having a patent in process with French govt. of business recommendation and ML. He is also an active project participant and consultant in IRIDIA (The National Lab of Computational Intelligence), Belgium, and Simula lab. Norway. He was leading a project as academic consultant with Yahoo Research Spain, and also envisaged new project on graph mining on FaceBook Friends analysis network from FaceBook UK and Luxemburg. He is involved also in several technical consultancy at France with Netflix, Germany (University of Stuttgart) and Ireland.

Affiliations and expertise

Senior Associated Researcher, Conservatoire National des Arts et Métiers (CNAM), Laboratoire CEDRIC and INRIA–EVA (the French National Institute for computer science) Paris, France

Life Sciences

Physical Sciences & Engineering

Social Sciences & Humanities

Health

Machine Learning Models and Architectures for Biomedical Signal Processing

Purchase options

World Book Day Celebration!

Institutional subscription on ScienceDirect

Suman Lata Tripathi

Valentina Emilia Balas

Mufti Mahmud

Soumya Banerjee

Related books