Introduction to Big Data

Ir. Slamet Riyadi, ST, MSc, PhD

Contents
• Data, Information & Knowledge
• Big Data Definition & Characteristics
• Applications
• Big Data Analytics
• Trends and Challenges
 • uninterpreted items, often referred to as data elements. An example might be
Data a person’s weight. Without additional data elements such as height, age, overall
well-being it would be impossible to interpret the significance of an individual
number.

• a group of data elements that have been organized and processed so that one
can interpret the significance of the data elements. For example, height,
Information weight, age, and gender are data elements that can be used to calculate the
BMI. The BMI can be used to determine if the individual is underweight,
overweight, normal weight or obese.

• built on a formalization of the relationships and interrelationships between data and

information. A knowledge base makes it possible to understand that an individual may
have a calculated BMI that is over 30 and not be obese. At this time, several automated
decision support systems included a knowledge base and a set of rules for applying the
Knowledge knowledge base in a specific situation. For example, the knowledge base may include the
following information. A fever or elevated temperature often begins with a chill. At the
beginning of the chill the patient’s temperature may be normal or even sub-normal but in
30 minutes it is likely the patient will have spiked a temp. A rule might read: if a patient
complains of chills, then take the patient’s temperature and repeat in 30 minutes.

Nelson (2019)
 • Ability to apply knowledge to human problems
• A fever or elevated temperature often begins with a chill. At
the beginning of the chill the patient’s temperature may be
Apply normal or even sub-normal but in 30 minutes it is likely the
patient will have spiked a temp. A rule might read: if a
ESS
Wisdom patient complains of chills, then take the patient’s
temperature and repeat in 30 minutes.
• built on a formalization of the relationships and
interrelationships between data and information
DSS • A knowledge base makes it possible to understand that an
Knowledge Context
individual may have a calculated BMI that is over 30 and not
be obese.
• a group of data elements that have been organized and
processed so that one can interpret the significance of the
MIS data elements.
Information Meaning • height, weight, age, and gender are data elements that can
be used to calculate the BMI. The BMI can be used to
determine if the individual is underweight, overweight,
normal weight or obese.
TPS
• uninterpreted items, often referred to as data elements.
Data Raw • a person’s weight. Without additional data elements such as
height, age, overall well-being it would be impossible to
interpret the significance of an individual number.
Nelson (2019)
Edureka.co
Edureka.co
https://data2x.org
Medium.com
 Why Agriculture needs Big Data?
The world’s population will reach 10
billion by 2050 à Modern agriculture
production must increase up to 70%

Traditional farming relied on managing

fields based on volatile predictions and
intuition. à Modern farming marries
satellite data, sensors, drones and GPS
mapping tools to provide field insights
for farmers and enhance food
production to a new level of
productivity.

The more information there is, the more accurate analytics and insights will become.
Data-flair.training
 KEY BENEFITS of BIG DATA in AGRICULTURE

Faster delivery of goods to Real-time decisions and

Improved forecasting of Preventive and predictive
distribution centers and alerts based on data from
yields and production. maintenance of equipment
consumers. fields and equipment.

Identifying correlations
between farm field,
More efficient energy usage Improved decision making New pricing programs to
weather, and commodity
and greater operational based on production and help match demand
data for more efficient
efficiency. business performance data with available supply.
irrigation, fertilization, and
harvesting of crops.

N-ix.com
Types of Big Data Analytics
Prescriptive
Descriptive Analytics Predictive Analytics Diagnostic Analytics
Analytics
• “What has • “What could • “What should we • “Why did it
happened?” happen?” do?” happen?”
• Uses data • Uses statistical • Uses optimization • used to determine
aggregation and models and and simulation why something
data mining to forecasts algorithms to happened in the
provide insight into techniques advice on possible past to understand
the past outcomes the root causes of
the events.
Edureka.co
Mandava (2017)
 10 Big Data Challenges
• Managing large volume of • Evaluating and selecting big
data from disparate data technologies
sources
• Finding and fixing data • Hiring and retaining
quality issues workers with big data skills
• Dealing with data • Keeping bid data costs in
integration and control
preparation complexities
• Scaling big data systems • Governing big data
efficiently and cost- environment
effectively
• Ensuring data context and
• Generating business use cases are understood
insight

Tatvasoft.com