Cognitive Sensing Technologies and Applications.

Format:

Book

Author/Creator:

Sinha, G. R., 1975-

Contributor:

Subudhi, Bidyadhar.

Fan, Chih-Peng.

Nisar, Humaira.

Series:

Control, Robotics and Sensors Series

Language:

English

Subjects (All):

Internet of things.

Physical Description:

1 online resource (455 pages)

Edition:

1st ed.

Place of Publication:

Stevenage : Institution of Engineering & Technology, 2023.

Summary:

Written by an international team of experts from a wide range of research areas, this book highlights the emerging role of cognitive sensors in a growing number of real time applications including smart health, smart cities, smart transportation, smart energy and smart agriculture.

Contents:

Intro

Title

Copyright

Contents

About the editors

Preface

1 Introduction to cognitive sensing technologies and applications

1.1 Cognitive sensing and sensors

1.1.1 Cognitive nodes and system

1.2 Cognitive IoTs (CoIT)

1.2.1 Sparse sensing

1.3 Challenges in smart sensing

1.4 Applications of cognitive sensing technologies

1.4.1 Healthcare

1.4.2 Smart grid and environment monitoring

1.4.3 Smart city

1.4.4 Graphical information system (GIS) and remote sensing

1.4.5 Smart agriculture

1.4.6 Robotics and rehabilitation

1.5 Benefits of cognitive sensing

1.6 Assistive technologies and BCI

1.7 Current research and future directions

1.7.1 Cognitive Internet of vehicle

1.7.2 Role of ML and robustness

1.7.3 Issues in IoTs

1.8 Conclusions

References

2 Hardware architectures for some sparse signal recovery approaches

2.1 Introduction

2.2 CS and sparse signals recovery

2.2.1 A gradient-based algorithm for sparse under-sampled signal reconstruction - one-dimensional approach

2.2.2 Gradient-based approach for sparse under-sampled image reconstruction

2.3 An analog hardware architecture for gradient-based reconstruction approach

2.3.1 A modified version of the 1D gradient-based approach suitable for hardware realization

2.3.2 An analog hardware architecture for a modified version of the 1D gradient-based approach

2.3.3 An OrCAD simulation

2.4 An analog architecture for the 2D gradient-based sparse reconstruction algorithm

2.4.1 An OrCAD simulation for the analog 2D gradient-based architecture

2.5 Hardware implementation of combined CS-based image filtering and reconstruction

2.6 Conclusion

3 Performance evaluation of cognitive sensor frameworks for IoT applications in healthcare and environment monitoring.

3.1 Introduction - wireless sensor networks

3.1.1 Cognitive sensors in a WSN

3.2 Cognitive sensor networks - importance and utility

3.2.1 Cognitive sensors - a historical perspective

3.2.2 Cognitive sensors - the evolution

3.3 Use of cognitive sensors in weather monitoring

3.3.1 Monitoring the environment and microclimates

3.3.2 Monitoring crops and fields

3.3.3 Green roof monitoring

3.3.4 Weather observation systems

3.3.5 Weather parameters from upper air

3.3.6 Surface weather observation

3.3.7 Wireless sensor data from anchored buoys

3.3.8 Sensors on aircraft

3.3.9 Remote sensing through satellites and radar

3.4 Cognitive sensors in environmental monitoring

3.4.1 Air - air quality, noise &amp

weather forecasting

3.4.2 Cognitive sensors in the monitoring of water quality

3.4.3 Soil - soil quality &amp

seismic monitoring

3.4.4 Sensors used in environmental pollution monitoring

3.5 Cognitive sensors in healthcare monitoring

3.5.1 Diagnostic tools - telestethoscopy

3.5.2 Monitoring blood sugar

3.5.3 Surgery

3.5.4 Monitoring elderly patients

3.5.5 Lifestyle, sleep, and wellbeing

3.5.6 Memory glass

3.5.7 Monitoring the gastro-intestinal tract

3.5.8 In vivo monitoring through implants

3.5.9 Prosthesis

3.5.10 Design features

3.6 Challenges for cognitive sensors

3.6.1 Challenges in environmental cognitive sensing

3.6.2 Challenges for cognitive sensors in healthcare

3.7 Future trends

Acknowledgements

4 Cognitive sensors for rehabilitation and therapeutic treatment

4.1 Introduction

4.2 Importance of cognitive sensors in the healthcare system

4.3 Cognitive sensors and cognitive health

4.4 Smart sensors-based technologies

4.5 Sensors

4.6 Sensor node

4.7 Sensor network

4.8 Two categories of sensor networks exist.

4.9 Operation of a sensor network

4.10 Cognitive sensing systems

4.11 Cognitive sensors

4.12 Sensory subsystem

4.13 Preprocessing subsystem

4.14 Logical subsystem

4.15 Cognitive sensor for rehabilitation and therapeutic treatment

4.16 General application of cognitive sensors

4.16.1 Healthcare

4.16.2 Smart cities

4.16.3 Home monitoring

4.16.4 Disaster management

4.16.5 Environment monitoring

4.16.6 Usefulness in education

4.17 Usefulness in neurological conditions

4.18 Limitation of cognitive sensors

4.19 Increased power consumption and sensor lifetime

4.20 Spectrum allocation

4.21 Interference management

4.22 Future scope of cognitive sensors

4.23 Conclusion

5 An ensemble machine learning-based intelligent system for human activity recognition using sensory data

5.1 Introduction

5.2 Methodology

5.2.1 Data segmentation

5.2.2 Empirical mode decomposition

5.2.3 Classification based on ensembles model

5.2.4 Experimental dataset

5.3 Experimental results

5.3.1 Comparisons with other machine learning algorithms

5.3.2 Comparison with previous studies

5.3.3 Comparisons of computation time

5.4 Conclusion

6 Challenges in the acquisition of non-invasive brain signals - electroencephalographic signals (EEG)

6.1 Introduction to nervous system

6.2 Types of brain signals

6.2.1 Neuronal recordings

6.2.2 Electrocorticographic (ECoG) signals

6.2.3 EEG signals

6.3 Artifacts in EEG

6.3.1 Physiological artifacts

6.3.2 Non-physiological artifacts

6.3.3 Gait-related artifacts

6.4 Methods to remove artifacts

6.4.1 Adaptive filtering

6.4.2 BSS - ICA

6.4.3 Wavelet transform approach

6.4.4 Hybrid approaches: ICA-wavelet

6.4.5 Riemannian geometry

6.4.6 Deep learning approaches.

6.5 Challenges in using commercial EEG headsets

6.5.1 Single channel headsets

6.5.2 Multi-channel headsets

6.6 Conclusion

7 Cognitive task and workload classification using EEG signal

7.1 Introduction

7.1.1 Neural basis of EEG

7.1.2 EEG measurement

7.2 Study selection

7.2.1 Inclusion and exclusion criteria

7.2.2 Data summary measures

7.3 Cognitive tasks and workload classification

7.3.1 Cognitive tasks for generating workload

7.3.2 EEG preprocessing and signal analysis

7.3.3 Workload classification

7.3.4 Case study on publicly available MW dataset

7.4 Discussion

7.4.1 Are there any specific cognitive tasks, mostly used for MW classification using EEG?

7.4.2 Choice of EEG features and ML classifiers

7.4.3 Is there any particular DNN architecture, appropriate for MW classification using EEG?

7.5 Conclusion

8 Automatic detection of Parkinson's disease using non-linear signal decomposition and machine learning techniques

8.1 Introduction

8.2 Material and methods

8.2.1 Dataset

8.2.2 Empirical wavelet transform (EWT)

8.2.3 Features

8.2.4 Non-linear machine learning techniques

8.3 Results

8.4 Conclusion

9 A review on gait kinematics acquisition sensors and its advancements in IoT and machine learning

9.1 Introduction

9.2 Search methodology and review process

9.3 Laboratory systems

9.3.1 Direct kinematics

9.3.2 Inverse kinematics

9.4 Wearable systems

9.4.1 Literature review - wearable systems with mathematical modeling

9.4.2 Wearable systems with ML

9.5 Wearable sensors-based IoT systems

9.6 Summary

10 Cognitive IoT sensors for smart industrial and biomedical applications

10.1 Introduction

10.2 IoT outline

10.3 Smart industrial

10.4 Biomedical.

10.5 Issues and challenges

10.6 Conclusions

11 Intelligent automation using IoT and machine learning

11.1 Introduction

11.1.1 IoT

11.1.2 History behind IoT

11.1.3 ML

11.1.4 Data analysis in IoT using ML algorithms

11.1.5 Existing ML algorithms and their use cases in IoT

11.2 Physical design of IoT

11.2.1 IoT protocols

11.3 IoT-enabling technologies

11.3.1 Cloud computing

11.3.2 Big data analytics

11.3.3 Embedded systems

11.4 Physical components used in IoT

11.4.1 Relay switch

11.4.2 Sensors

11.4.3 Microcontrollers

11.4.4 Radio frequency identification (RFID) tags

11.5 Smart applications of IoT embedded with ML

11.5.1 Smart homes

11.5.2 Smart cities

11.5.3 Environment

11.5.4 Energy

11.5.5 Retail

11.5.6 Smart logistics

11.5.7 Agriculture

11.5.8 Smart industries

11.5.9 Health and lifestyle monitoring

11.5.10 Smart transportation

11.5.11 Smart maintenance

11.5.12 Disaster management

11.5.13 Health care

11.5.14 Military

11.5.15 Business intelligence

11.5.16 Aviation industry

11.5.17 Childcare and elderly care

11.6 Conclusion

11.7 Further scope and limitations

12 Recent trends in applications of cognitive sensors for smart manufacturing and control

12.1 Introduction

12.1.1 Instrumentation and control systems in manufacturing and control

12.1.2 Sensors used in industrial automation

12.2 Types of industrial sensors

12.2.1 Temperature sensors

12.2.2 Force sensors

12.2.3 Flow sensors

12.2.4 Pressure sensors

12.2.5 Strain sensors

12.2.6 Torque sensors

12.2.7 Vibration or seismic sensors

12.2.8 Angular velocity sensors

12.2.9 Level measurement sensors

12.2.10 Position or linear velocity sensors

12.2.11 Radiation sensors

12.2.12 Gyroscopes

12.2.13 Limit switches.

12.3 Adapting standard commercial sensors for IIoT in cyber physical systems.

Notes:

Description based on publisher supplied metadata and other sources.

Other Format:

Print version: Sinha, G. R. Cognitive Sensing Technologies and Applications

ISBN:

9781839536908

183953690X

OCLC:

1392342973