1. ANALYTICS FOR IOT: MAKING SENSE OF DATA FROM SENSORS
Muralidhar Somisetty, CTO, Innohabit TechnologiesFeb 17, 2017 IIoT Course @ IISc CCE
2. Our Vision & Mission: “Innovation as Habit”
We Innovate by building Compelling Products.
We Build Other’s Innovations with our Technical Competencies and Cutting-Edge Solutions.
We Offer Business Services by setting up and operating businesses.
We Trigger Innovations through Start-up Mentoring programs.
Making Ideas Actionable
A Contextual Intelligence Platform with
Machine Learning Analytics to offer
solutions for IoT, Retail and Enterprises.
A SaaS Product for Product Leaders.
India’s First Product Management
Software in the market.
(Cisco)
Predictive
Network Health
Analytics
(Cisco)
Smart Waste
Management
with IoT/Analytics.
Muralidhar Somisetty
Technologist, Entrepreneur, Product Evangelist, Mentor and Certified Yoga Instructor.
Current (Work): CTO, Innohabit Technologies. Member, IEEE Computer Society, Bangalore.
Past (Work) : Senior Engineering and Product Management Leader at Cisco Systems, India.
Education: B.Tech,ECE (NIT @ Warangal) & M.S Computer Science (University of Illinois @ Urbana Champaign)
Experience: Telecom, OSS, SaaS, Network Analytics, Machine Learning(ML) & Internet-of-Things (IoT).
3. Our Company Vision and Mission
We Build
Amazing Products
Innovative
We Setup
Businesses
Build, Operate and Transfer
We Build
Your Innovations
Partner for Solutions
We Trigger
Innovations
Mentoring Innovators
“Innovation is our Habit”
8. Ethical AI : Effort on to make AI an Angel.
Source: OpenAI.com
9. Let us step back and go through the journey ….
What is Big-Data?
What is Data Analytics?
How BI, Analytics & AI are related to each other?
What is the Value of Analytics in Industrial IoT?
What is the role of Analytics in IoT?
10. “Welcome to the Internet of Customers. Behind every app, every device, and every connection, is a
customer. Billions of them. And each and every one is speeding toward the future.” Salesforce.com
11. BIG-DATA
Big data is the term for a collection of data sets so large and complex that it
becomes difficult to process using on-hand database management tools or
traditional data processing applications.
Social MediaMobile Internet of Things /
Sensors
Video and Media
Web
Cloud
12.
13. Volume (Scale)
13
Earthscope:
67 terabytes of data
From 0.8 zettabytes to 35.2 Zettabytes of data
LHC: 15 petabytes of data
Imagine the volume of data from 104
satellites launched by ISRO…
14.
15. HOW BIG-DATA IS DIFFERENT FROM TRADITIONAL DATABASE?
• Structured /Relational Data
• Cost goes up with data size/growth
• Well defined models & schemas
• ERP, CRM, SCM, BI, App data
Traditional data management
Big Data
• Unstructured data
• Scaling at low costs
• Flexibility and complex analytics
• Distributed processing
16. WHAT IS DATA ANALYTICS?
Data Analytics is the science (and art!) of applying statistical techniques to
large data sets to obtain actionable insights for making smart decisions.
It is the process to uncover hidden patterns, unknown correlations, trends,
and any other useful business information
It is Business Intelligence on steroids.
19. “It is the intelligence of machines and the branch of computer science that aims to create it. It
is the study and design of intelligent agents, where an intelligent agent is a system that
perceives it environment and takes actions to maximize the chances of success.”
21. Machine Learning
A subfield of computer science (CS) and artificial intelligence (AI) that deals with the construction and
study of systems that can learn from data, rather than follow only explicitly programmed instructions.”
26. CRM
Retaile
r
System
s
Data
Sources
Data
Integration
Data
Storage
Data
Analytics
Data
Visualization/
Insights
POS Data NFC Tags
IoT
Sensor
sBrand Partners Bluetooth
Beacons
Wi-Fi
Public
Data
Customers
Data Connectors ETL JobsAPIs Streaming Data Queues
NoSQL Big-Data
Traditional Data warehouse
(Like Oracle, Teradata)
Streaming, Analytics Engine Machine LearningAnalytical Models Deep Learning
Visualization Tools
Dwell-Time Analysis
FootFall Demographics
Campaign Effectiveness
A Typical Big-Data Analytics Technology Stack
34. Why is Analytics important in IoT context?
Making sense from endless sea of data from
sensors is humanly impossible.
(Automate) Decision Making
Operations Efficiency
Preventive Maintenance
Supply Chain Optimization
Competitive Edge
OPEX Savings
…
…
35. When AI meets IoT
Artificial Intelligence provides us the framework and tools to go beyond trivial
real-time decision and automation use cases for IoT.
36. Home Automation: Autonomous Vacuum Cleaners
• Learns Home Layout and Remembers It.
• Adapts to Different Surfaces or New Items
• Improvises on movement pattern for efficiency
• Knows when to recharge and automatically docks itself
• Smart IoT Device controlled via remote Mobile App
• Piezoelectric , Optical Onboard Sensors
• Employs Machine Learning to Adapt and Improvise.
Machine Learning in Action
37. Smart Retail: Brick is the IoT AND Mortar is Data Analytics
Source: Cisco IoT Retal White Paper
41. AI to IA: Value of Data Analytics in Industrial IoT
In the industrial space, there is a great deal of interest in using analytics to optimize asset maintenance,
production operations, supply chain, product design, field service, and other areas.
42. Top Analytics Applications in Industrial IoT
Top-3
Source: https://iot-analytics.com/product/industrial-analytics-report-201617/
43. Benefits of Analytics Adoption in Industrial IoT
Top-3
Source: https://iot-analytics.com/product/industrial-analytics-report-201617/
44. “The cars are going around the track with thousands of sensors and every time it goes past the pit
wall they download a load of data, and the race engineers tell the driver how to drive in
response to that data. That’s what we’ve got to do to our factories, we need to have that pit
wall somewhere to make sure that your machinery, your systems are working better than the
next guy’s.”
- Ken Young, Manufacturing Technology Centre, UK