Title Page
Copyright and Credits
Hands-On Deep Learning for IoT
About Packt
Why subscribe?
Contributors
About the authors
About the reviewers
Packt is searching for authors like you
Preface
Who this book is for
What this book covers
To get the most out of this book
Download the example code files
Download the color images
Conventions used
Get in touch
Reviews
Section 1: IoT Ecosystems, Deep Learning Techniques, and Frameworks
The End-to-End Life Cycle of the IoT
The E2E life cycle of the IoT
The three-layer E2E IoT life cycle
The five-layer IoT E2E life cycle
IoT system architectures
IoT application domains
The importance of analytics in IoT
The motivation to use DL in IoT data analytics
The key characteristics and requirements of IoT data
Real-life examples of fast and streaming IoT data
Real-life examples of IoT big data
Summary
Reference
Deep Learning Architectures for IoT
A soft introduction to ML
Working principle of a learning algorithm
General ML rule of thumb
General issues in ML models
ML tasks
Supervised learning
Unsupervised learning
Reinforcement learning
Learning types with applications
Delving into DL
How did DL take ML to the next level?
Artificial neural networks
ANN and the human brain
A brief history of ANNs
How does an ANN learn?
Training a neural network
Weight and bias initialization
Activation functions
Neural network architectures
Deep neural networks
Autoencoders
Convolutional neural networks
Recurrent neural networks
Emergent architectures
Residual neural networks
Generative adversarial networks
Capsule networks
Neural networks for clustering analysis
DL frameworks and cloud platforms for IoT
Summary
Section 2: Hands-On Deep Learning Application Development for IoT
Image Recognition in IoT
IoT applications and image recognition
Use case one – image-based automated fault detection
Implementing use case one
Use case two – image-based smart solid waste separation
Implementing use case two
Transfer learning for image recognition in IoT
CNNs for image recognition in IoT applications
Collecting data for use case one
Exploring the dataset from use case one
Collecting data for use case two
Data exploration of use case two
Data pre-processing
Models training
Evaluating models
Model performance (use case one)
Model performance (use case two)
Summary
References
Audio/Speech/Voice Recognition in IoT
Speech/voice recognition for IoT
Use case one – voice-controlled smart light
Implementing use case one
Use case two – voice-controlled home access
Implementing use case two
DL for sound/audio recognition in IoT
ASR system model
Features extraction in ASR
DL models for ASR
CNNs and transfer learning for speech recognition in IoT applications
Collecting data
Exploring data
Data preprocessing
Models training
Evaluating models
Model performance (use case 1)
Model performance (use case 2)
Summary
References
Indoor Localization in IoT
An overview of indoor localization
Techniques for indoor localization
Fingerprinting
DL-based indoor localization for IoT
K-nearest neighbor (k-NN) classifier
AE classifier
Example – Indoor localization with Wi-Fi fingerprinting
Describing the dataset
Network construction
Implementation
Exploratory analysis
Preparing training and test sets
Creating an AE
Creating an AE classifier
Saving the trained model
Evaluating the model
Deployment techniques
Summary
Physiological and Psychological State Detection in IoT
IoT-based human physiological and psychological state detection
Use case one – remote progress monitoring of physiotherapy
Implementation of use case one
Use case two — IoT-based smart classroom
Implementation of use case two
Deep learning for human activity and emotion detection in IoT
Automatic human activity recognition system
Automated human emotion detection system
Deep learning models for HAR and emotion detection
LSTM, CNNs, and transfer learning for HAR/FER in IoT applications
Data collection
Data exploration
Data preprocessing
Model training
Use case one
Use case two
Model evaluation
Model performance (use case one)
Model performance (use case two)
Summary
References
IoT Security
Security attacks in IoT and detections
Anomaly detection and IoT security
Use case one: intelligent host intrusion detection in IoT
Implementation of use case one
Use case two: traffic-based intelligent network intrusion detection in IoT
Implementation of use case two
DL for IoT security incident detection
DNN, autoencoder, and LSTM in IoT security incidents detection
Data collection
CPU utilisation data
KDD cup 1999 IDS dataset
Data exploration
Data preprocessing
Model training
Use case one
Use case two
Model evaluation
Model performance (use case one)
Model performance (use case two)
Summary
References
Section 3: Advanced Aspects and Analytics in IoT
Predictive Maintenance for IoT
Predictive maintenance for IoT
Collecting IoT data in an industrial setting
ML techniques for predictive maintenance
Example – PM for an aircraft gas turbine engine
Describing the dataset
Exploratory analysis
Inspecting failure modes
Prediction challenges
DL for predicting RLU
Calculating cut-off times
Deep feature synthesis
ML baselines
Making predictions
Improving MAE with LSTM
Unsupervised deep feature synthesis
FAQs
Summary
Deep Learning in Healthcare IoT
IoT in healthcare
Use case one – remote management of chronic disease
Implementation of use case one
Use case two – IoT for acne detection and care
Implementation of use case two
DL for healthcare
CNN and LSTM in healthcare applications
Data collection
Use case one
Use case two
Data exploration
The ECG dataset
The acne dataset
Data preprocessing
Model training
Use case one
Use case two
Model evaluations
Model performance (use case one)
Model performance (use case two)
Summary
References
What's Next - Wrapping Up and Future Directions
What we have covered in this book?
Deployment challenges of DL solutions in resource-constrained IoT devices
Machine learning/DL perspectives
DL limitations
IoT devices, edge/fog computing, and cloud perspective
Existing solutions to support DL in resource-constrained IoT devices
Potential future solutions
Summary
References
Other Books You May Enjoy
Leave a review - let other readers know what you think