Reference; Chapter 2: 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.

• Cover
• Title Page
• Copyright and Credits
• About Packt
• Contributors
• Table of Contents
• Preface
• Section 1: IoT Ecosystems, Deep Learning Techniques, and Frameworks
• Chapter 1: 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
• Chapter 2: 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
• Chapter 3: 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
• Chapter 4: 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
• Chapter 5: 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
• Chapter 6: 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
• Chapter 7: 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
• Chapter 8: 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
• Chapter 9: 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
• Chapter 10: 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
• Index