IoT Data Analytics using Python

Preface

Necessity of Analytics Across IoT

• Introduction
• Internet of Things and Industrial Internet of Things 
• Industrial Revolution and Industry 4.0
• IoT Data Analytics
• IoT Data Analytics for Digital Transformation
• Hardware Devices for IoT Data Analytics
• Data Pipeline for Analytics
• Python: The Go-to Language for Analytics
• Conclusion
• Points to Remember

Up and Running with Data Analytics Fundamentals

• Introduction
• Data Analysis Methods and Frameworks
• How to Perform Data Analysis
• Conclusion
• Points to Remember

Setting Up IoT Analytics Environment

• Introduction
• Why Python Language
• Installation and Configuration of Python IDE
• Installation and Configuration of Apache Kafka
• Installation and Configuration of MQTT
• Installation and Configuration of PostgresSQL
• Important Python Packages Used
• Basics of Python Language with Examples
• Data Analysis using Python
• Data Wrangling with Python
• Data Visualization using Python
• Conclusion
• Points to Remember

Managing Data Pipeline and Cleaning

• Introduction
• IoT Data Formats
• Realtime Streaming and Data Pipeline
• IoT Dataflow
• Data Simulation and Digital Twin
• Data Simulation
• Digital Twin
• IoT Simulator Tools
• IoT Data Simulator Python Implementation
• Data Cleansing Implementation in Python
• Data Transformation Rule Implementation in Python
• Conclusion
• Points to Remember

Designing Data Lake and Executing Data Transformation

• Introduction
• Data Lake Concept
• IoT Real-time Data Streaming
• Building Data Pipeline to the Raw Zone
• Transformation Zone of the Data Lake
• Building KPIs and Metrics
• Conclusion
• Points to Remember

Implementing Descriptive Analytics Using Pandas

• Introduction
• Descriptive Data Analysis
• Download Wind Turbine Dataset
• Time Series Analysis
• Testing Methods for Time Series Data
• Conclusion
• Points to Remember

Time Series Forecasting and Predictions

• Introduction
• Data Smoothing
• Data Lag Identification
• Autocorrelation and Partial Autocorrection
• Forecasting using AR Model
• Moving Average
• ARIMA
• Time Series Feature Extraction 
• Automatic Time Series 
• Storing Wind Turbine Predictions
• Analytical Base Table
• Conclusion
• Points to Remember

Monitoring and Preventive Maintenance

• Introduction
• Condition Monitoring
• Condition Based Maintenance
• Corrective Maintenance
• Preventive Maintenance
• Text Mining the Product Manual
• Automating the Creation of Maintenance Ticket
• Conclusion 
• Points to Remember

Model Deployment on Edge Devices

• Introduction
• Objectives
• Introduction to Edge Computing and Analytics
• Simulators for IoT Systems
• Installation and Configuration of Edge Devices
• Installation and Configuration of FastAPI
• Model Building and Reuse
• Expose Models using FastAPI
• Deploying Machine Learning Model
• Concept of Continuous Learning
• Concept of Adaptive Learning
• Conclusion
• Points to Remember

Understanding Edge Computing with MicroPython

• Introduction
• Concepts of Edge Computing
• Concepts of Edge Analytics 
• Introduction to Edge Platform
• Data Flow from Edge to Cloud 
• Use Cases for Edge Analytics
• MicroPython for Edge Computing
• Invoking ML Models using MicroPython
• Conclusion 
• Points to Remember

IoT Analytics for Self -driving Vehicles

• Introduction 
• CRISP-DM Framework
• Business Understanding of Self-driving Vehicles
• Data Collection and Understanding
• Data Preparation and Feature Engineering
• Modeling and Evaluation
• Deployment of Machine Learning Models
• Conclusion 
• Points to Remember