"Smart Embedded Systems: Advances and Applications" is a comprehensive guide that demystifies the complex world of embedded technology. The book journeys through a wide range of topics from healthcare to energy management, autonomous robotics, and wireless communication, showcasing the transformative potential of intelligent embedded systems in these fields. This concise volume introduces readers to innovative techniques and their practical applications, offers a comparative analysis of wireless protocols, and provides efficient resource allocation strategies in IoT-based ecosystems. With real-world examples and in-depth case studies, it serves as an invaluable resource for students and professionals seeking to harness the power of embedded technology to shape our digital future.
Salient Features
1. The book provides a comprehensive coverage of various aspects of smart embedded systems, exploring their design, implementation, optimization, and a range of applications. This is further enhanced by in-depth discussions on hardware and software optimizations aimed at improving overall system performance.
2. A detailed examination of machine learning techniques specifically tailored for data analysis and prediction within embedded systems. This complements the exploration of cutting-edge research on the use of AI to enhance wireless communications.
3. Real-world applications of these technologies are extensively discussed, with a focus on areas such as seizure detection, noise reduction, health monitoring, diabetic care, autonomous vehicles, and communication systems. This includes a deep-dive into different wireless protocols utilized for data transfer in IoT systems.
4. This book highlights key IoT technologies and their myriad applications, extending from environmental data collection to health monitoring. This is underscored by case studies on the integration of AI and IoT in healthcare, spanning topics from anomaly detection to informed clinical decision-making. Also featured is a detailed evaluation and comparison of different system implementations and methodologies.
This book is an essential read for anyone interested in the field of embedded systems. Whether you're a student looking to broaden your knowledge base, researchers looking in-depth insights, or professionals planning to use this cutting-edge technology in real-world applications, this book offers a thorough grounding in the subject.
Author(s): Arun Kumar Sinha; Abhishek Sharma; Luiz Alberto Pasini Melek; Daniele D. Caviglia
Publisher: CRC Press
Year: 2023
Language: English
Pages: 300
Cover
Half Title
Title Page
Copyright Page
Table of Contents
Preface
Editors
Contributors
Chapter 1: A reconfigurable FPGA-based epileptic seizures detection system with 144 μs detection time
1.1 Introduction
1.2 Software-based implementation
1.2.1 EEG data
1.2.2 Segmentation
1.2.3 Feature extraction
1.2.4 RF algorithm
1.3 Hardware-based implementation
1.3.1 Feature extraction
1.3.2 RF training module
1.3.3 The RF inference module
1.3.4 Display label
1.4 Experimental results
1.4.1 Software implementation results
1.4.2 FPGA implementation results
1.5 Conclusion
Acknowledgment
References
Chapter 2: Hardware architecture for denoising of EOG signal using a differential evolution algorithm
2.1 Introduction
2.2 FIR filter architecture
2.3 Filter design for denoising of EOG signal using DE algorithm
2.4 DE algorithm with minimized coefficients
2.5 Functional verification of DE with minimized coefficient (DEWMC)-based denoised FIR filter
2.6 Synthesis results
2.7 Conclusion
References
Chapter 3: Implementation considerations for an intelligent embedded E-health system and experimental results for EEG-based activity recognition
3.1 Introduction
3.2 Embedded acquisition system for E-health
3.2.1 Hardware considerations, choices, and implementations
3.2.2 Software architecture and implementation
3.2.3 Related works
3.3 EEG-based classification of motor imagery activities
3.3.1 Segmentation
3.3.2 Neural network efficiency investigation
3.4 Conclusion
References
Chapter 4: Embedded and computational intelligence for diabetic healthcare: An overview
4.1 Introduction
4.2 Embedded intelligence glucose monitoring
4.2.1 BioSensors
4.2.2 Implanted micro systems
4.2.3 Wearable sensors
4.2.3.1 Wearable interstitial fluid (ISF) CGM
4.2.3.2 Wearable sweat CGM
4.2.3.3 Wearable tear CGM
4.2.3.4 Wearable saliva CGM
4.3 Computational intelligence in glucose monitoring
4.3.1 Machine learning
4.3.2 Recommender systems
4.3.3 Mobile and WebApp
4.3.4 TeleMedicine
4.3.5 Auto-administer therapy
4.4 Conclusion and future scope
References
Chapter 5: A semi-definite programming-based design of a robust depth control for a submersible autonomous robot through state feedback control
5.1 Introduction
5.2 Modeling of SAR in depth plane
5.2.1 Problem statement
5.3 Design of robust optimal control
5.3.1 Robust optimal state feedback for polytopic SAR system
5.3.1.1 Preliminaries: LMI-based LQR controller
5.3.1.2 Robust LMI-based optimal controller
5.4 Results and discussion
5.5 Conclusion
Acknowledgments
References
Chapter 6: Embedded system with in-memory compute neuromorphic accelerator for multiple applications
6.1 Introduction
6.2 Accelerator for in-memory compute applications
6.2.1 Background
6.2.2 Design and implementation of standard 32×40×10 in-memory compute architecture
6.2.2.1 Working principle
6.2.3 Potential benefits of the accelerator in various applications
6.3 In-memory compute accelerator: An embedded system perspective for multiple applications
6.3.1 Climate technology
6.3.2 Social sciences
6.3.3 Medical sciences
6.3.4 Finance technology
6.3.5 Gaming technology (GT)
6.4 Results and discussion
6.4.1 Parametric analysis of ideal resistive memory and swish activation function
6.4.2 Inference analysis for the in-memory compute accelerator
6.4.3 Training analysis for the in-memory compute accelerator
6.5 Conclusion
References
Chapter 7: Artificial intelligence-driven radio channel capacity in 5G and 6G wireless communication systems in the presence of vegetation: Prospect and challenges
7.1 Introduction
7.2 Radio wave attenuation due to vegetation
7.3 Embedded architecture: AI-DR vegetation attenuation prediction system
7.4 SCC prediction
7.5 Conclusions
Acknowledgments
References
Chapter 8: Smart cabin for office using embedded systems and sensors
8.1 Introduction
8.1.1 Smart office
8.1.2 Motivation
8.1.3 Objectives
8.2 Cabin security
8.2.1 Fingerprint verification
8.2.2 Face verification
8.2.3 Speech verification
8.3 Ambiance monitor
8.3.1 Temperature and relative humidity
8.3.2 Carbon dioxide
8.3.3 Total volatile organic compound (TVOC)
8.3.4 Air pressure
8.3.5 Dust level
8.4 Well-being monitor
8.4.1 Physical health
8.4.2 Mental health
8.4.2.1 Fatigue state
8.4.2.2 Emotional state
8.5 Data transmission and display
8.6 Results
8.7 Conclusion
Acknowledgments
References
Chapter 9: Wireless protocols for swarm of sensors: Sigfox, Lorawan, and Nb-IoT
9.1 Introduction
9.1.1 Basic communication infrastructure
9.2 Sigfox
9.2.1 Overview
9.2.2 Regions of operation
9.2.3 Technical characteristics
9.2.4 Sigfox diversity
9.2.5 Network architecture
9.2.6 Message system
9.2.7 Summary of characteristics
9.3 Lorawan
9.3.1 Overview
9.3.2 Characteristics
9.3.3 Uplink and downlink communication
9.3.4 Classes of operation
9.3.5 Network architecture
9.3.6 Message system
9.3.7 Characteristics summary
9.4 Nb-IoT
9.4.1 Overview
9.4.2 Characteristics
9.4.3 Message system
9.5 Conclusion
References
Chapter 10: Design and test of thermal energy harvester for self-powered autonomous electronic load
10.1 Introduction
10.1.1 Calculation of the maximum power conversion efficiency
10.2 Low-voltage starter
10.2.1 Enhanced swing ring oscillator
10.2.2 Dickson charge pump
10.2.3 AC model of ESRO
10.2.4 Important formulas for the LVS block
10.3 Power equations for convertor operating in DCM
10.3.1 Boost convertor
10.3.2 Maximum extraction of power from a low-voltage source V TEG
10.3.3 Sizing auxiliary and main stage inductors
10.4 Peripheral circuits
10.4.1 Current starved ring oscillator
10.4.2 Reference generator and node sensing network
10.4.3 Zero current switching network
10.4.4 Control logic
10.5 Test and measurement
10.5.1 Inductors for ESRO coupled with DCP
10.6 Conclusion
Acknowledgments
References
Chapter 11: Managing concept drift in IoT health data streams: A dynamic adaptive weighted ensemble approach
11.1 Introduction
11.1.1 Concept of drift
11.1.2 Significance of adaptive learning in IoT with machine learning for health data
11.2 Literature survey
11.2.1 Drift phenomenon
11.2.2 Adaptive learning models towards IoT
11.3 Methodology
11.3.1 Dataset description
11.3.2 Data preprocessing
11.3.3 Implementation of DAWE
11.3.3.1 Base learners
11.3.3.2 Proposed ensemble strategy for DAWE
11.4 Experimental results
11.5 Discussion and future scope
11.6 Conclusions
Acknowledgments
References
Chapter 12: GraLSTM: A distributed learning model for efficient IoT resource allocation in healthcare
12.1 Introduction
12.1.1 How is IoT useful for the healthcare sector?
12.1.2 Open discussion and challenges in IoT- AI with EHR
12.1.3 Recent trends in IoT health with AI
12.2 Literature survey
12.2.1 IoT towards decision-making
12.2.2 Paradigm shift in anomaly detection
12.2.3 Resource allocation with parallelization and distributed learning
12.3 Methodology
12.3.1 Dataset description
12.3.2 Structured graph for anomaly detection
12.3.3 GraLSTM model
12.3.4 GraLSTM-IoT resource allocation
12.4 Experimental results
12.5 Conclusion
Acknowledgments
References
Index
