book

Smart Embedded Systems

Name: Smart Embedded Systems
ISBN: 9781003810353

by Arun Sinha, Abhishek Sharma, Luiz Alberto Pasini Melek, Daniele Caviglia

December 2023

Intermediate to advanced

298 pages

7h 37m

English

CRC Press

Read now

Unlock full access

Cover Page
Half Title page
Title Page
Copyright Page
Contents
Preface
Editors
Contributors
Chapter 1 A reconfigurable FPGA-based epileptic seizures detection system with 144 μs detection time
1.1 Introduction1.2 Software-based implementation1.2.1 EEG data1.2.2 Segmentation1.2.3 Feature extraction1.2.4 RF algorithm1.3 Hardware-based implementation1.3.1 Feature extraction1.3.2 RF training module1.3.3 The RF inference module1.3.4 Display label1.4 Experimental results1.4.1 Software implementation results1.4.2 FPGA implementation results1.5 ConclusionAcknowledgmentReferences
Chapter 2 Hardware architecture for denoising of EOG signal using a differential evolution algorithm
2.1 Introduction2.2 FIR filter architecture2.3 Filter design for denoising of EOG signal using DE algorithm2.4 DE algorithm with minimized coefficients2.5 Functional verification of DE with minimized coefficient (DEWMC)-based denoised FIR filter2.6 Synthesis results2.7 ConclusionReferences

Chapter 3 Implementation considerations for an intelligent embedded E-health system and experimental results for EEG-based activity recognition
3.1 Introduction3.2 Embedded acquisition system for E-health3.2.1 Hardware considerations, choices, and implementations3.2.2 Software architecture and implementation3.2.3 Related works3.3 EEG-based classification of motor imagery activities3.3.1 Segmentation3.3.2 Neural network efficiency investigation3.4 ConclusionReferences
Chapter 4 Embedded and computational intelligence for diabetic healthcare: An overview
4.1 Introduction4.2 Embedded intelligence glucose monitoring4.2.1 BioSensors4.2.2 Implanted micro systems4.2.3 Wearable sensors4.3 Computational intelligence in glucose monitoring4.3.1 Machine learning4.3.2 Recommender systems4.3.3 Mobile and WebApp4.3.4 TeleMedicine4.3.5 Auto-administer therapy4.4 Conclusion and future scopeReferences
Chapter 5 A semi-definite programming-based design of a robust depth control for a submersible autonomous robot through state feedback control
5.1 Introduction5.2 Modeling of SAR in depth plane5.2.1 Problem statement5.3 Design of robust optimal control5.3.1 Robust optimal state feedback for polytopic SAR system5.4 Results and discussion5.5 ConclusionAcknowledgmentsReferences
Chapter 6 Embedded system with in-memory compute neuromorphic accelerator for multiple applications
6.1 Introduction6.2 Accelerator for in-memory compute applications6.2.1 Background6.2.2 Design and implementation of standard 32×40×10 in-memory compute architecture6.2.3 Potential benefits of the accelerator in various applications6.3 In-memory compute accelerator: An embedded system perspective for multiple applications6.3.1 Climate technology6.3.2 Social sciences6.3.3 Medical sciences6.3.4 Finance technology6.3.5 Gaming technology (GT)6.4 Results and discussion6.4.1 Parametric analysis of ideal resistive memory and swish activation function6.4.2 Inference analysis for the in-memory compute accelerator6.4.3 Training analysis for the in-memory compute accelerator6.5 ConclusionReferences
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 Introduction7.2 Radio wave attenuation due to vegetation7.3 Embedded architecture: AI-DR vegetation attenuation prediction system7.4 SCC prediction7.5 ConclusionsAcknowledgmentsReferences
Chapter 8 Smart cabin for office using embedded systems and sensors
8.1 Introduction8.1.1 Smart office8.1.2 Motivation8.1.3 Objectives8.2 Cabin security8.2.1 Fingerprint verification8.2.2 Face verification8.2.3 Speech verification8.3 Ambiance monitor8.3.1 Temperature and relative humidity8.3.2 Carbon dioxide8.3.3 Total volatile organic compound (TVOC)8.3.4 Air pressure8.3.5 Dust level8.4 Well-being monitor8.4.1 Physical health8.4.2 Mental health8.5 Data transmission and display8.6 Results8.7 ConclusionAcknowledgmentsReferences
Chapter 9 Wireless protocols for swarm of sensors: Sigfox, Lorawan, and Nb-IoT
9.1 Introduction9.1.1 Basic communication infrastructure9.2 Sigfox9.2.1 Overview9.2.2 Regions of operation9.2.3 Technical characteristics9.2.4 Sigfox diversity9.2.5 Network architecture9.2.6 Message system9.2.7 Summary of characteristics9.3 Lorawan9.3.1 Overview9.3.2 Characteristics9.3.3 Uplink and downlink communication9.3.4 Classes of operation9.3.5 Network architecture9.3.6 Message system9.3.7 Characteristics summary9.4 Nb-IoT9.4.1 Overview9.4.2 Characteristics9.4.3 Message system9.5 ConclusionReferences
Chapter 10 Design and test of thermal energy harvester for self-powered autonomous electronic load
10.1 Introduction10.1.1 Calculation of the maximum power conversion efficiency10.2 Low-voltage starter10.2.1 Enhanced swing ring oscillator10.2.2 Dickson charge pump10.2.3 AC model of ESRO10.2.4 Important formulas for the LVS block10.3 Power equations for convertor operating in DCM10.3.1 Boost convertor10.3.2 Maximum extraction of power from a low-voltage source VTEG10.3.3 Sizing auxiliary and main stage inductors10.4 Peripheral circuits10.4.1 Current starved ring oscillator10.4.2 Reference generator and node sensing network10.4.3 Zero current switching network10.4.4 Control logic10.5 Test and measurement10.5.1 Inductors for ESRO coupled with DCP10.6 ConclusionAcknowledgmentsReferences
Chapter 11 Managing concept drift in IoT health data streams: A dynamic adaptive weighted ensemble approach
11.1 Introduction11.1.1 Concept of drift11.1.2 Significance of adaptive learning in IoT with machine learning for health data11.2 Literature survey11.2.1 Drift phenomenon11.2.2 Adaptive learning models towards IoT11.3 Methodology11.3.1 Dataset description11.3.2 Data preprocessing11.3.3 Implementation of DAWE11.4 Experimental results11.5 Discussion and future scope11.6 ConclusionsAcknowledgmentsReferences
Chapter 12 GraLSTM: A distributed learning model for efficient IoT resource allocation in healthcare
12.1 Introduction12.1.1 How is IoT useful for the healthcare sector?12.1.2 Open discussion and challenges in IoT- AI with EHR12.1.3 Recent trends in IoT health with AI12.2 Literature survey12.2.1 IoT towards decision-making12.2.2 Paradigm shift in anomaly detection12.2.3 Resource allocation with parallelization and distributed learning12.3 Methodology12.3.1 Dataset description12.3.2 Structured graph for anomaly detection12.3.3 GraLSTM model12.3.4 GraLSTM-IoT resource allocation12.4 Experimental results12.5 ConclusionAcknowledgmentsReferences
Index

Content preview from Smart Embedded Systems

Chapter 6 Embedded system with in-memory compute neuromorphic accelerator for multiple applications

Afroz Fatima and Abhijit Pethe

Birla Institute of Technology and Science Pilani, Pilani, India

DOI: 10.1201/9781032628059-6

6.1 Introduction

An embedded system, as the name suggests, is the combination of a processor (single/multi-core), memory and several peripheral devices that define/execute a task within a larger entity/system, often electronic or mechanical. Recent advances in the area of neuromorphic embedded systems have introduced many parallel core architectures. A recently reported research example is the spiking neural network architecture, often referred to as SpiNNaker, designed with 57,600 processing nodes, each with 18 ARM968 ...

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.

Read now

Unlock full access

More than 5,000 organizations count on O’Reilly

O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.

Julian F.

Head of Cybersecurity

I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.

Addison B.

Field Engineer

I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.

Amir M.

Data Platform Tech Lead

I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.

Mark W.

Embedded Software Engineer

Publisher Resources

ISBN: 9781003810353

Cloud Computing

Data Engineering

Data Science

AI & ML

Programming Languages

Software Architecture

IT/Ops

Security

Design

Business

Soft Skills

Smart Embedded Systems

by Arun Sinha, Abhishek Sharma, Luiz Alberto Pasini Melek, Daniele Caviglia

Chapter 6 Embedded system with in-memory compute neuromorphic accelerator for multiple applications

6.1 Introduction

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.