You are on page 1of 37

Credit Seminar

in

Shamim Hossain
IN PhD. DT
FOOD SECTOR
Dairy Technology Division, ICAR- 1
Sections

2
Introduction to Big Data

3
What is DATA ?
Facts and statistics collected together for reference or
analysis.

What is Cloud Computing ?


The practice of using a network of remote servers hosted
on the Internet to store, manage, and process data, rather
than a local server or a personal computer.
(Oxford dictionary, 2019)

4
What is BIG DATA ?
“Big data represents the information assets characterized
by such a High Volume, Velocity and Variety to require
specific technology and analytical methods for its
transformation into Value.”
(De Mauro et al., 2015)

5
Why BIG DATA?

Getting data in one place makes it easier to analyse

Using multiple criteria creates the correct context

Having a broader perspective makes unknown risks


visible
(Moorthy et al., 2015)

6
Characteristics of Big Data

7
Characteristics: 5Vs

Volume Velocity
Scale of Data Streaming Data
Value
Usefulness
of Data
Veracity
Variety
Uncertainty of
Forms of Data
Data
(Bahga et al., 2019) 8
VOLUME : Scale of Data
78 X 1015
GB

40 X 1012
GB

2010 2020
2030
(Moorthy et al., 2015)
9
VELOCITY : Speed of streaming
data

10
VARIETY: Forms of Data

Structured Data

Semi-structured Data

Unstructured data 11

(Moorthy et al., 2015)


VERACITY: Accuracy of data

Filtering

Data with noise and uncertainty Cleaned accurate data for analysis

(Moorthy et al., 2015) 12


Value: Usefulness of Data

New Idea

Business development

Revenue generation

Valuable End Uses


(Moorthy et al., 2015)13
Process of Big Data
Analysis

14
Process of Big Data Analytics

Data Collection Data Preparation Analysis Visualization


• Types
• Sensor data • Data Cleaning • Descriptive • Static
• Diagnostic
• Bio-metric data • De-duplication • Predictive • Dynamic
• Prescriptive
• Feedback • Sampling • Mode • Interactive
• Batch
• Instrumental data • Filtering • Real-time (Bahga et al., 2019)
• Interactive 15
Types of Analytics
Descriptiv • Analysing past data to present it in a summarized form which
can be easily interpreted
e • What has happened?
Analytics • Ex: Reports, alerts etc.

• Analysis of past data to diagnose the reasons as to why certain


Diagnostic events happened
• Why did it happened?
analytics • Ex: Queries, Data mining etc.
• Predicting the occurrence of an event or the likely outcome of
an event or forecasting the future values using prediction
Predictive models
analytics • What is likely to happen?
• Ex: Forecast, Simulation etc.
• Uses multiple prediction models to predict various outcomes
Prescriptive and the best course of action for each outcome
Analytics • What can we do to make it happen?
• Ex: Planning, Optimization etc. (Bahga et al., 2019) 16
Data Collection &
Preparation

Other Data Base Real-time Data Large Log Data


(hadoop.apache.org) 17
Data Analysis

Structured Query
Language (SQL)

Not- Only- Structured


Query Language Hadoop Pig
(NoSQL) (Batch Data) (Script data)

In-memory Data
Real-time Data Machine Learning Data
(hadoop.apache.org) 18
Data Visualization

Managing and Monitoring


Interface

Co-ordination among all Hadoop module

(hadoop.apache.org) 19
Other Big Data computing Providers

20
Big Data in Food Research

21
FOSCOLLAB
Better risk
Various FOSCOLL
assessment &
Databases AB
decision-making

Data Raw data & Summary statistics


Analysisreports
risk assessment
specifications as well as food raw data for food contamination
consumption and food and summary statistics for food
contamination data analysis consumption
http://apps.who.int/foscollab
22
Big Data in Food
Processing

23
Smart Dairy Procurement System

Collection Unit
Procurement Unit

(Bronson et al., 2016) 24


Process & Production Diagnosis
• Compare current operating condition and normal
operating condition
• Case-based reasoning (CBR) is used to finds solutions to
new problems based on past experience.
Solve present
problems

Data
Data Reduction

Sensors Case library


Large data library
(less efficient data retrieval) (Efficient data retrieval)
(Bahga et al., 2019)
25
Realtime Logistic tracking
Uses GPS system

Can handle a large number of fleet

Best route direction

Supply chain optimization

(etq.com) 26
Realtime product monitoring

Realtime temperature reading

Realtime pressure reading

(etq.com) 27
Inventory Management

Under Stocking Over Stocking


X Additional storage cost

X Risk of product deuteriation


Inventory

X Loss of revenue

 Real-time inventory level


Controlled by  Alert system for low inventory level
Big data  Timely replenishment of inventory
RFID Tag  Frequencies of demand
(Bronson et al., 2016) 28
Customer Satisfaction

Customer New Product


Recommendation Development

Shopping Big Data analysis Customer


History (Collaborative filtering) Preference
Sale /
Discount
Customer
Feedback

(Bronson et al., 2016) 29


Water quality monitoring

Filtration

Water Realtime Analysis Automatic monitoring


system

Realtime Feedback
(Bronson et al., 2016) 30
Store house optimization
Customer shopping pattern

Items bought together are kept in same row or


rack
Forecasting demand
Seasonal variation in demand (ice-cream in

summer)
(Bahga et al., 2019) 31
Smart Food Consumption

Safe Healthy

Smart Tag
Tag Scan Product Detail

(etq.com) 32
AMUL Applications
Mobile Application Use
Manage milk collection unit and
Amul Milk Union App
farmers activities in real-time
Amul DTS-Delivery Tracking Real-time Tracking of delivery
System logistics
Different applications for
Amul AMCS (Automated Milk Farmers, Societies & supervisors
Collection System) for summarized milk collection
data
Sales automation app for
AMUL SFA & AMUL ADA
distributer and retailers
(amul.com) 33
Conclusion

34
What we can do now?
Uploading Our research in ICAR database

(https://krishi.icar.gov.in/)

Make expert system for dairy products

(http://agridaksh.iasri.res.in/)

35
What we can do in future?
Make a complete database of dairy
products from our research

Make a common web portal for


Researcher, Industry & Consumer

Designing research projects according to


consumer & industry need

Data to Knowledge to Action


36
Thank You

37

You might also like