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

✍ Scribed by Amita Kapoor

• Publisher: Packt Publishing
• Year: 2019
• Tongue: English
• Leaves: 383
• Category: Library

✦ Synopsis

Build smarter systems by combining artificial intelligence and the Internet of Things―two of the most talked about topics today

Key Features

• Leverage the power of Python libraries such as TensorFlow and Keras to work with real-time IoT data
• Process IoT data and predict outcomes in real time to build smart IoT models
• Cover practical case studies on industrial IoT, smart cities, and home automation

Book Description

There are many applications that use data science and analytics to gain insights from terabytes of data. These apps, however, do not address the challenge of continually discovering patterns for IoT data. In Hands-On Artificial Intelligence for IoT, we cover various aspects of artificial intelligence (AI) and its implementation to make your IoT solutions smarter.

This book starts by covering the process of gathering and preprocessing IoT data gathered from distributed sources. You will learn different AI techniques such as machine learning, deep learning, reinforcement learning, and natural language processing to build smart IoT systems. You will also leverage the power of AI to handle real-time data coming from wearable devices. As you progress through the book, techniques for building models that work with different kinds of data generated and consumed by IoT devices such as time series, images, and audio will be covered. Useful case studies on four major application areas of IoT solutions are a key focal point of this book. In the concluding chapters, you will leverage the power of widely used Python libraries, TensorFlow and Keras, to build different kinds of smart AI models.

By the end of this book, you will be able to build smart AI-powered IoT apps with confidence.

What you will learn

• Apply different AI techniques including machine learning and deep learning using TensorFlow and Keras
• Access and process data from various distributed sources
• Perform supervised and unsupervised machine learning for IoT data
• Implement distributed processing of IoT data over Apache Spark using the MLLib and H2O.ai platforms
• Forecast time-series data using deep learning methods
• Implementing AI from case studies in Personal IoT, Industrial IoT, and Smart Cities
• Gain unique insights from data obtained from wearable devices and smart devices

Who this book is for

If you are a data science professional or a machine learning developer looking to build smart systems for IoT, Hands-On Artificial Intelligence for IoT is for you. If you want to learn how popular artificial intelligence (AI) techniques can be used in the Internet of Things domain, this book will also be of benefit. A basic understanding of machine learning concepts will be required to get the best out of this book.

Table of Contents

1. Principles and Foundations of IoT and AI
2. Data Access and Distributed Processing for IoT
3. Machine Learning for IoT
4. Deep Learning for IoT
5. Genetic Algorithms for IoT
6. Reinforcement Learning for IoT
7. GAN for IoT
8. Distributed AI for IoT
9. Personal and Home and IoT
10. AI for Industrial IoT
11. AI for Smart Cities IoT
12. Combining It All Together

✦ Table of Contents

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