IoTData Analytics Program

IoTData Analytics Fundamental Course

Prerequisites

  • Basic understanding of statistics

Price

INR 10,000

Module

Module 1: Role of Data Analytics in IoT  – 60 min

  • Role of Big Data Analytics in IoT
    • Predictive Analytics, Prescriptive analytics, Dashboarding
  • Application in different industry
    • Industrial, Healthcare, Automotive, Smart Home / Smart City

Module 2: Overview of IoT architecture and Different data models – 120 min

  • IoT Architecture
    • Edge Analytics vs. Cloud Analytics
  • Nature of data
    • Structured Data vs. Unstructured Data
    • Continuous Data vs. Discrete Data
    • Basics of Signal Processing
  • Nature of machine learning
    • Supervised learning vs. Unsupervised learning
    • Role of feedback

Module 3: Machine learning technology for IoT – 120 min

  • Classification, Clustering, Regression, dimension reduction
    • Brief preview of some Machine learning algorithms
    • K nearest neighbor
    • Support Vector Machine
    • Boosted Decision Tree

Module 4: Data Analytics choices for IoT – 120 min

  • Distributed storage and processing for IoT “big” data
    • CAP theorem – choice between consistency and availability
      • ACID criteria for structured data
      • BASE philosophy for unstructured data
    • Choice of DataBase
      • Choice for unstructured data – Cassandra, MongoDB
      • Choice for structured data

Module 5: Data Analytics lifecycle – 120 min

  • Statistical Analysis : What is statistics of a batch?
  • Extracting statistical features like skewness, kurtosis, crest factors from signal
  • Time Series analysis of the Signal
  • Model preparation
  • Training – Testing – Feedback cycle
  • Replay of Sensor data using Simulator

Module 6: Data Analytics Tool for IoT – 120 min

  • Introduction to R and R studio
    • Develop simple R code for one of the classification technologies.
    • Apply Data Analytics lifecycle on this R code.
    • Use R code for Time series analysis and finding out features of the signal like maxima, minima, mean, variance, skewness

Module 7: Difference between IoT analytics and consumer data analytics – 120 min

  • Layers of analytics-how to process a raw signal and relates to known physics and engineering
  • When to use Machine Learning and when to use statistical model
  • When not to use Machine Learning
  • Physics based model vs empirical modeling
  • Importance of domain understanding in Analytical model
  • Meta-Data

Module 8: Visualization of IoT analytics  – 120 min

  • Trend view
  • Gauge view
  • Historical view
  • Dashboard view
  • Relationship between them
  • Different stakeholders need different view
  • Common viewing software tools

Module 9:  Wrap up session – 60 min

  • Re-cap of learning in the course
  • Q & A sessions
  • Feedback session

IoTData Analytics Advanced Course

Prerequisites

  • Basic understanding of statistics

Price

INR 20,000

Module

Module 1: Role of Data Analytics in IoT  – 120 min

  • Role of Big Data Analytics in IoT
    • Predictive Analytics, Prescriptive analytics, Dashboarding
  • Application in different industry
    • Industrial, Healthcare, Automotive, Smart Home / Smart City

Module 2: Overview of IoT architecture and Different data models – 120 min

  • IoT Architecture
    • Edge Analytics vs. Cloud Analytics
  • Nature of data
    • Structured Data vs. Unstructured Data
    • Continuous Data vs. Discrete Data
    • Basics of Signal Processing
  • Nature of machine learning
    • Supervised learning vs. Unsupervised learning
    • Role of feedback

Module 3: Machine learning technology for IoT – 120 min

  • Classification, Clustering, Regression, dimension reduction
    • Brief preview of some Machine learning algorithms
    • K nearest neighbor
    • Support Vector Machine
    • Boosted Decision Tree

Module 4: Data Analytics choices for IoT – 120 min

  • Distributed storage and processing for IoT “big” data
    • CAP theorem – choice between consistency and availability
      • ACID criteria for structured data
      • BASE philosophy for unstructured data
    • Choice of DataBase
      • Choice for unstructured data – Cassandra, MongoDB
      • Choice for structured data

Module 5: Data Analytics lifecycle – 120 min

  • Statistical Analysis : What is statistics of a batch?
  • Extracting statistical features like skewness, kurtosis, crest factors from signal
  • Time Series analysis of the Signal
  • Model preparation
  • Training – Testing – Feedback cycle
  • Replay of Sensor data using Simulator

Module 6: Data Analytics Tool for IoT – 120 min

  • Introduction to R and R studio
    • Develop simple R code for one of the classification technologies.
    • Apply Data Analytics lifecycle on this R code.
    • Use R code for Time series analysis and finding out features of the signal like maxima, minima, mean, variance, skewness

Module 7: Difference between IoT analytics and consumer data analytics – 120 min

  • Layers of analytics-how to process a raw signal and relates to known physics and engineering
  • When to use Machine Learning and when to use statistical model
  • When not to use Machine Learning
  • Physics based model vs empirical modeling
  • Importance of domain understanding in Analytical model
  • Meta-Data

Module 8: Visualization of IoT analytics  – 120 min

  • Trend view
  • Gauge view
  • Historical view
  • Dashboard view
  • Relationship between them
  • Different stakeholders need different view
  • Common viewing software tools

Module 9: Video session of some of the Data Analytics application in IoT – 120 min

  • A Video session on real-life application of Data Analytics in Industrial IoT
  • A video session on Bio-Authentication / Facial recognition

Module 10: Predictive Maintenance analytics in Microsoft Azure – 240 min (Hands-on session)

  • Build sample predictive maintenance analytics in Microsoft Azure IoT platform

Module 11: Weather forecast in AWS – 240 min (Hands-on session)

  • Build sample weather forecast analytics in Amazon AWS IoT platform

Module 12: Edge Analytics at Raspberry Pi – 240 min

  • Migrate analytics from cloud platforms to edge platforms
  • Build sample temperature and humidity alert analytics in Raspberry Pi 3

Module 13: Wrap up session – 120 min

  • Re-cap of learning in the course
  • Q & A sessions
  • Feedback session