3. Objective
• The main objective the research is to analyze
the role of biometric in reducing the size of
big data.
4. Introduction
• Biometric devices are not only use for security but it is also use to
present personal identification. Everybody in this world have unique
biometric features, these biometric features provides the person
availability with the certain conditions.
• The digital world today is totally based on Authentication and
Authorization which sincerely need to focus on availability on time,
where growth in data tends to become Big Data.
• Unique Record entry in database no doubt reduces the duplicity but
still same attribute values are require to present again and again
for person identification.
• The Biometric Authentication is a solution to this problem, here the
multiple attributes like (Name, Father’s Name, Mother’s Name,
Hometown, etc.) values by single biometric feature like(Fingerprint,
Face Image, Iris Scan, etc).
5. Need for Data Reduction
• Big Data Systems include social media data aggregators
industrial senor networks, scientific experimental systems,
connected health, and several other application areas.
• The data collection from large-scale local and remote
sensing devices and networks, Internet-enabled data
streams, and/or devices, system and networks-logs bring
massively heterogeneous, multi format, aggregated, and
continuous big data stream.
• Effectively handling the big data stream to store, index,
and query the data sources for lateral data processing are
among the key challenges being address by researchers.
6. 6 Vs of Big Data
• Volume: The data size characterizes the volume of big data.
• Velocity: The velocity of big data is determined by the frequency of data
streams which are entering in big data systems.
• Varity: It collects data stream from multiple data sources which produce
data streams in multiple formats.
• Veracity: The utility of big data systems increases when the data streams
are collected from reliable and trustworthy sources.
• Variability: Since all data sources in big data systems do not generate the
data streams with same speed and same quality.
• Value: The value property of big data defines the utility, usability, and
usefulness of big data systems.
7. Literature Review:
Big Data Reduction Method
• The research done by Muhammad Habib and Prem Prakash
Jayaraman, on “Big Data Reduction Methods”, gave this
idea to use Biometric in Reducing the size of Big Data.
• Data Reduction methods for big data vary from pure
dimension reduction technique to:
– compression based data reduction methods
– algorithms for preprocessing
– cluster-level data deduplication
– redundancy elimination
– implementation of network (graph) theory.
• The dimension reduction techniques are useful to handle
the heterogeneity and massiveness of big data by reducing
millions-variable data into manageble size.
8. Literature Review:
Big Data Challenges
• Shafagat Mahmudova form IIT published the
research titled ‘Big Data Challenges in Biometric
Technology’.
– The study provides information about big data and
advanced cloud technologies in the field of biometric
technology.
– The big data contain three types of High speed and
large volume of data:
• Structured Data: relational data
• Semi structured data: XML data
• Unstructured data: Word, PDF and others.
9. Literature Review:
Big Data with Biometric
• Through the use of Big Data Technologies, Japanese
developers began to apply the software to recognize
the person in the black lit of buyers of some stores,
who ware identified as thieves or complaints.
• The police in Tampa, Florida State use Big Data
Technology called Superbowl XXXV software to identify
criminals basing on the scanned image of face.
• Universities and airports in US also use Big Data in the
field of Biometric Technologies for the identification of
people, recognition with Big Data Technologies.[1]
• Lambda labs uses its Big Data Technology used for face
recognition software for Google Glass. [2]
10. References
1. “Big Data Challenges in Biometric Technology”,
Shafagat Mahmudova, IJEME. 2016.
2. “Deep Learning application and challenges in big data
analytics”, Chunyan Q. Wei Z.,Journal of Big Data,
USA, 2015.
3. “Big Data Reduction Methods: A Survey”, Muhammad
Habib, University of Malaya, Malaysia, Springer, 2016.
4. Cloud based Big Data Analytics Framework for Face
Recognition in Social Networks using Machine
Learning, Vinay A, Rituparna J, ISBCC, 2015.