IoT Professional Program

Prerequisites

  • Basic knowledge of software systems
  • Basicknowledge of electronics and computer hardware

Module

Module 1- Introduction to IoT (1 hour)

  • What is IoT ?
  • How is IoT applicable for real world applications
  • Where can IoT be applied to solve real world problems
  • Some case studies
  • Overview of a IoT system and deployment view

Module 2 – All About Sensors (1h 30 min)

  • Basic function , architecture and types of sensors
  • Sensor interface to hardware
  • Different types of sensor calibration techniques
  • Powering options for sensors
  • Sensor specifications and behaviour
  • Hands on training with temperature sensor

Module 3 – Fundamentals of M2M communication – Sensor network and wireless protocols (1h 30min)

  • What is a sensor network ?
  • Wireless vs Wireline network
  • Wifi / Zigbee / Bluetooth
  • Protocol stack and comparison of Zigbee and Bluetooth (BLE)
  • Other short and long distance RF communication options for IoT
  • Demo of device control using BLE

Module 4 – IoT Communication and Protocol Stack (2 h)

  • Overview of IoT protocol stack
  • Protocols used for IoT/M2M
  • Application protocols (REST/MQTT/CoAP)
  • Layer to layer and Peer to Peer view of IoT protocol stack
  • Demo of end to end IoT application

Module 5 – IoT Cloud  Platform (2 h)

  • Role of cloud computing in IoT
  • Applications on IoT cloud
  • Popular IoT/M2M cloud platform providers
  • Different components of a IoT cloud deployment
  • Demo of IoT cloud using IBM Bluemix

Module 6 – Security in IoT Implementation (1h)

  • Why security is absolutely essential for IoT
  • Mechanism of security breach in IOT layer
  • Privacy enhancing technologies
  • Fundamental of network security
  • Encryption and cryptography implementation for IoT data
  • Secure booting
  • Device authentication
  • Firewalling and IPS
  • Updates and patches

Module 7 – Machine Learning for Intelligent IoT (2 h 30 min)

  • Introduction to Machine learning
  • Learning classification techniques
  • KNN Algorithm
  • Support Vector Machine
  • Image and video analytic for IoT
  • Fraud and alert analytic through IoT
  • Real Time Analytic/Stream Analytic
  • Scalability issues of IoT and machine learning
  • What are the architectural implementation of Machine learning for IoT ?

Module 8 – Analytics Engine for IoT (2 h)

  • Insight analytic
  • Visualization analytic
  • Structured predictive analytic
  • Unstructured predictive analytic
  • Recommendation Engine
  • Pattern detection
  • Rule/Scenario discovery — failure, fraud, optimization
  • Root cause discovery

Module 9 – IoT & Big Data (2h 30 min)

  • 4Vs of Big Data (Volume, Velocity, Variety & Veracity)
  • Why big data is important for IoT
  • Databases used for big data
  • Different tools for big data analysis
  • Hadoop and Map Reduce
  • Data Parallelism vs Task Parallelism
  • Apache Spark
  • Apache Storm