Hands-On Artificial Intelligence for IoT: Expert machine learning and deep learning techniques for developing smarter IoT systems

Cover
Title Page
Copyright and Credits
Dedication
About Packt
Contributors
Table of Contents
Preface
Chapter 1: Principles and Foundations of IoT and AI
	What is IoT 101?
		IoT reference model
		IoT platforms
		IoT verticals
	Big data and IoT
	Infusion of AI – data science in IoT
		Cross-industry standard process for data mining
		AI platforms and IoT platforms
	Tools used in this book
		TensorFlow
		Keras
		Datasets
			The combined cycle power plant dataset
			Wine quality dataset
			Air quality data
	Summary
Chapter 2: Data Access and Distributed Processing for IoT
	TXT format
		Using TXT files in Python
	CSV format
		Working with CSV files with the csv module
		Working with CSV files with the pandas module
		Working with CSV files with the NumPy module
	XLSX format
		Using OpenPyXl for XLSX files
		Using pandas with XLSX files
	Working with the JSON format
		Using JSON files with the JSON module
		JSON files with the pandas module
	HDF5 format
		Using HDF5 with PyTables
		Using HDF5 with pandas
		Using HDF5 with h5py
	SQL data
		The SQLite database engine
		The MySQL database engine
	NoSQL data
	HDFS
		Using hdfs3 with HDFS
		Using PyArrow's filesystem interface for HDFS
	Summary
Chapter 3: Machine Learning for IoT
	ML and IoT
	Learning paradigms
	Prediction using linear regression
		Electrical power output prediction using regression
	Logistic regression for classification
		Cross-entropy loss function
		Classifying wine using logistic regressor
	Classification using support vector machines
		Maximum margin hyperplane
		Kernel trick
		Classifying wine using SVM
	Naive Bayes
		Gaussian Naive Bayes for wine quality
	Decision trees
		Decision trees in scikit
		Decision trees in action
	Ensemble learning
		Voting classifier
		Bagging and pasting
	Improving your model – tips and tricks
		Feature scaling to resolve uneven data scale
		Overfitting
			Regularization
			Cross-validation
		No Free Lunch theorem
		Hyperparameter tuning and grid search
	Summary
Chapter 4: Deep Learning for IoT
	Deep learning 101
		Deep learning—why now?
		Artificial neuron
		Modelling single neuron in TensorFlow
	Multilayered perceptrons for regression and classification
		The backpropagation algorithm
		Energy output prediction using MLPs in TensorFlow
		Wine quality classification using MLPs in TensorFlow
	Convolutional neural networks
		Different layers of CNN
			The convolution layer
			Pooling layer
		Some popular CNN model
		LeNet to recognize handwritten digits
	Recurrent neural networks
		Long short-term memory
		Gated recurrent unit
	Autoencoders
		Denoising autoencoders
		Variational autoencoders
	Summary
Chapter 5: Genetic Algorithms for IoT
	Optimization
		Deterministic and analytic methods
			Gradient descent method
			Newton-Raphson method
		Natural optimization methods
			Simulated annealing
			Particle Swarm Optimization
			Genetic algorithms
	Introduction to genetic algorithms
		The genetic algorithm
			Crossover
			Mutation
		Pros and cons
			Advantages
			Disadvantages
	Coding genetic algorithms using Distributed Evolutionary Algorithms in Python
		Guess the word
		Genetic algorithm for CNN architecture
		Genetic algorithm for LSTM optimization
	Summary
Chapter 6: Reinforcement Learning for IoT
	Introduction
		RL terminology
			Deep reinforcement learning
		Some successful applications
	Simulated environments
		OpenAI gym
	Q-learning
		Taxi drop-off using Q-tables
	Q-Network
		Taxi drop-off using Q-Network
		DQN to play an Atari game
		Double DQN
		Dueling DQN
	Policy gradients
		Why policy gradients?
		Pong using policy gradients
		The actor-critic algorithm
	Summary
Chapter 7: Generative Models for IoT
	Introduction
	Generating images using VAEs
		VAEs in TensorFlow
	GANs
		Implementing a vanilla GAN in TensorFlow
		Deep Convolutional GANs 
		Variants of GAN and its cool applications
			Cycle GAN
			Applications of GANs
	Summary
Chapter 8: Distributed AI for IoT
	Introduction
		Spark components
	Apache MLlib
		Regression in MLlib
		Classification in MLlib
		Transfer learning using SparkDL
	Introducing H2O.ai
		H2O AutoML
		Regression in H2O
		Classification in H20
	Summary
Chapter 9: Personal and Home IoT
	Personal IoT
		SuperShoes by MIT
		Continuous glucose monitoring
			Hypoglycemia prediction using CGM data
		Heart monitor
		Digital assistants
	IoT and smart homes
		Human activity recognition
			HAR using wearable sensors
			HAR from videos
		Smart lighting
		Home surveillance
	Summary
Chapter 10: AI for the Industrial IoT
	Introduction to AI-powered industrial IoT
		Some interesting use cases
	Predictive maintenance using AI
		Predictive maintenance using Long Short-Term Memory
		Predictive maintenance advantages and disadvantages
	Electrical load forecasting in industry
		STLF using LSTM
	Summary
Chapter 11: AI for Smart Cities IoT
	Why do we need smart cities?
	Components of a smart city
		Smart traffic management
		Smart parking
		Smart waste management
		Smart policing
		Smart lighting
		Smart governance
	Adapting IoT for smart cities and the necessary steps
		Cities with open data
			Atlanta city Metropolitan Atlanta Rapid Transit Authority data
			Chicago Array of Things data
		Detecting crime using San Francisco crime data
	Challenges and benefits
	Summary
Chapter 12: Combining It All Together
	Processing different types of data
		Time series modeling
		Preprocessing textual data
		Data augmentation for images
		Handling videos files
		Audio files as input data
	Computing in the cloud
		AWS
		Google Cloud Platform
		Microsoft Azure
	Summary
Other Books You May Enjoy
Index