Upload
stm-journals
View
22
Download
1
Embed Size (px)
Citation preview
Journal of
Artificial Intelligence
Research & Advances(JoAIRA)
September–December 2016
ISSN 2395-6720 (Online)
www.stmjournals.com
STM JOURNALSScientific Technical Medical
STM Journals, a strong initiative by Consortium E-Learning Network Private Ltd. (established 2006), was
launched in the year 2010 under the support and guidance by our esteemed Editorial and Advisory Board
Members from renowned institutes.
Objectives:
Promotion of Scientific, Technical and Medical research.
Publication of Original Research/Review, Short Articles and Case Studies through
Peer Review process.
Publishing Special Issues on Conferences.
Preparing online platform for print journals.
Empowering the libraries with online and print Journals in Scientific, Technical
and Medical domains.
Publishing and distribution of books on various subjects in the category of Nanotechnology,
Scientific and Technical Writing, and Environment, Health and Safety.
Salient Features:
A bouquet of 100+ Journals that fall under Science, Technical and Medical domains.
Employs Open Journals System (OJS)—a journal management and publishing system.
The first and one of the fastest growing publication website in India as well as in abroad
for its quality and coverage.
Rapid online submission and publication of papers, soon after their formal
acceptance/finalization.
Facilitates linking with the other authors or professionals.
Worldwide circulation and visibility.
Journal of Artificial Intelligence Research & Advances
Focus and Scope Covers
Artificial intelligence and Philosophy
Case based reasoning
Heuristic searching
Intelligent robotics
Planning and theories of action
Cognitive aspects of AI
Robotics
Journal of Artificial Intelligence Research & Advances is published (frequency: three times a year) in India by STM
Journals (division of Consortium e-Learning Network Private Ltd.) The views expressed in the articles do not necessarily
reflect of the Publisher. The publisher does not endorse the quality or value of the advertised/sponsored products
described therein. Please consult full prescribing information before issuing a prescription for any products mentioned in
this publication.
No part of this publication may be reproduced, stored in retrieval system or transmitted in any from without written
permission of the publisher.
To cite any of the material contained in this Journal, in English or translation, please use the full English reference at the
beginning of each article. To reuse any of the material, please contact STM Journals ([email protected])
ISSN: 2395-6720 (online)
STM Journals
STM Journals (division of Consortium e-Learning Network Private Ltd. ) having its Marketing office located at Office
No. 4, First Floor, CSC pocket E Market, Mayur Vihar Phase II, New Delhi-110091, India is the Publisher of Journal.
Statements and opinions expressed in the Journal reflect the views of the author(s) and are not the opinion of STM
Journals unless so stated.
Subscription Information and Order:
National Subscription:
Print - Rs 3750/- per Journal ( includes 3 print issues), Single Issue copy purchase: Rs 1500.
Online - Rs 3750/- per Journal inclusive Service Tax ( includes 3 online issues), Single Issue purchase: Rs 1500
inclusive Service Tax
Print + Online - Rs 5000/- per Journal inclusive Service Tax ( includes 3 print & online issues).
International Subscription:
Online Only- $199, Print Only-$299 (includes 3 print issues)
Online + Print-$399 (includes 3 print issues + online access of published back volumes )
To purchase print compilation of back issues please send your query at [email protected]
Subscription must be prepaid. Rates outside of India includes delivery. Prices subject to change without notice.
Mode of Payment: At par cheque, Demand draft, and RTGS (payment to be made in favor of
Consortium E-Learning Network. Pvt. ltd., payable at Delhi/New Delhi.
Online Access Policy
A). For Authors:
In order to provide maximum citation and wide publicity to the authors work, STM Journals also have Open Access
Policy, authors who would like to get their work open access can opt for Optional Open Access publication at
nominal cost as follows
India, SARC and African Countries: INR 2500 or 100 USD including single hard copy of Author's Journal.
Other Countries: USD 200 including single hard copy of Author's Journal.
B). For Subscribers:
Online access will be activated within 72 hours of receipt of the payment (working days), subject to receipt of
correct information on user details/Static IP address of the subscriber.
The access will be blocked:
If the user requests for the same and furnishes valid reasons for blocking.
Due to technical issue.
Misuse of the access rights as per the access policy.
Advertising and Commercial Reprint Inquiries: STM Journals with wide circulation and visibility offer an excellent
media for showcasing/promotion of your products/services and the events-namely, Conferences, Symposia/Seminars
etc. These journals have very high potential to deliver the message across the targeted audience regularly with each
published issue. The advertisements on bulk subscriptions, gift subscriptions or reprint purchases for distribution etc. are
also very welcome.
Lost Issue Claims: Please note the following when applying for lost or missing issues:
Claims for print copies lost will be honored only after 45 days of the dispatch date and before publication of the
next issue as per the frequency.
Tracking id for the speed post will be provided to all our subscribers and the claims for the missing Journals will
be entertained only with the proofs which will be verified at both the ends.
Claims filed due to insufficient (or no notice) of change of address will not be honored.
Change of Address of Dispatch should be intimated to STM Journals at least 2 months prior to the dispatch
schedule as per the frequency by mentioning subscriber id and the subscription id.
Refund requests will not be entertained.
Legal Disputes
All the legal disputes are subjected to Delhi Jurisdiction only. If you have any questions, please contact the Publication
Management Team: [email protected]; Tel : +91 0120-4781211.
Gargi Asha Jha
Manager (Publications)
PUBLICATION MANAGEMENT TEAM
Internal Members
External Members
Bimlesh Lochab
Assistant Professor
Department of Chemistry
School of Natural Sciences, Shiv Nadar University
Gautam Buddha Nagar, Uttar Pradesh, India
Dr. Rajiv Prakash
Professor and Coordinator
School of Materials Science and Technology
Indian Institute of Technology (BHU), Varanasi
Uttar Pradesh, India
Dr. Rakesh Kumar
Assistant Professor
Department of Applied Chemistry
BIT Mesra, Patna,
Bihar, India
Prof. S. Ramaprabhu
Alternative Energy and Nanotechnology Technology
Laboratory, Department of Physics
Indian Institute of Technology, Chennai
Tamil Nadu, India
Himani Pandey
Isha Chandra
Senior Associate Editors
Dr. Yog Raj Sood
Dean (Planning and Development)
Professor, Department of Electrical Engineering
National Institute of Technology, Hamirpur
Himachal Pradesh, India
Prof. Chris Cannings
Professor, School of Mathematics and Statistics
University of Sheffield,
Sheffield
United Kingdom
Dr. D. K. Vijaykumar
MS, MCh (Surgical Oncology), Professor and
Head Department of Surgical Oncology
Amrita Institute of Medical Sciences and Research Centre
Ponekkara, Cochin, Kerala, India
Dr. Durgadas Naik
Associate Professor (Microbiology)
Management and Science University,
University Drive, Seksyen13
Selangor, Malaysia
Prof. José María Luna Ariza
Department of Computer Sciences and
Numerical Analysis
Campus of Rabanales
University of Córdoba, Spain
Dr. Khaiser Nikam
Professor, Library and Information Science
Department of Library and Information Science
University of Mysore
Mysore, India
Quaisher J Hossain
Senior Editor
Group Managing Editor Dr. Archana Mehrotra
Managing DirectorCELNET, Delhi, India
Meenakshi Tripathi
Shivani Sharma
Chairman Mr. Puneet Mehrotra
Director
Shambhavi Mishra
Associate Editors
Sugandha Mishra
Prof. Priyavrat TharejaDirector Principal
Rayat Institute of Engineering and Information Technology
Punjab, India
Dr Baldev RajDirector, National Institute of Advanced Studies
Indian Institute of Science campus Bangalore
Karnataka, India
Former Director
Indira Gandhi Centre for Atomic Research,
Kalpakkam, Tamil Nadu, India
Dr. Pankaj PoddarSenior Scientist
Physical and Materials Chemistry Division,National Chemical Laboratory
Pune, Maharastra India
Prof. D. N. RaoProfessor and Head
Department of BiochemistryAll India Institute of Medical Sciences
New Delhi, India
Dr. Nandini Chatterjee SinghAdditional Professor
National Brain Research CentreManesar, Gurgaon
Haryana, India
Dr. Ashish RunthalaLecturer, Biological Sciences Group
Birla Institute of Technology and SciencePilani, Rajasthan,
India
Dr. Bankim Chandra RayProfessor and Ex-Head of the Department
Department of Metallurgical and Materials Engineering
National Institute of Technology, RourkelaOdisha, India
Prof. Yuwaraj Marotrao GhugalProfessor and Head
Department of Applied MechanicsGovernment College of Engineering
Vidyanagar, Karad Maharashtra, India
Dr. Hardev Singh VirkVisiting Professor, Department of Physics
University of SGGS World UniversityFatehgarh Sahib, Punjab,
IndiaFormer Director Research
DAV Institute of Engineering and TechnologyJallandhar, India
Dr. Shrikant Balkisan DhootSenior Research Scientist, Reliance Industries Limited, Mumbai, India
Former Head (Research and Development)Nurture Earth R&D Pvt Ltd., MIT Campus
Beed Bypass Road, Aurangabad Maharashtra, India
STM JOURNALS
ADVISORY BOARD
Dr. Rakesh KumarAssistant Professor
Department of Applied ChemistryBirla Institute of Technology
Patna, Bihar, India
Prof. Subash Chandra MishraProfessor
Department of Metallurgical and Materials Engineering
National Institute of Technology, RourkelaOdisha, India
Dr. Shankargouda PatilAssistant Professor
Department of Oral PathologyKLE Society's Institute of Dental Sciences
Bangalore, Karnataka, India
Prof. Sundara RamaprabhuProfessor
Department of PhysicsIndian Institute of Technology Madras
Chennai, Tamil Nadu India
Dr. Baskar KaliyamoorthyAssociate Professor
Department of Civil EngineeringNational Institute of Technology, Trichy
Tiruchirappalli, Tamil Nadu, India
STM JOURNALS
ADVISORY BOARD
Editorial Board
Prof. Nesar Ahmad Professor and Chairman
Of Computer Engineering in AMU, Aligarh.
Ke-Lin DuChief Scientist
Enjoyor Labs, Enjoyor Inc., Hangzhou, China.
Dr. Manas Ranjan Kabat DVSS University of Technology, Burla
Sambalpur-768018Odisha, India.
Dr. M. Sohel RahmanProfessor Department of Computer
Science & Engineering Bangladesh University of Engineering & Technology (BUET)
Dhaka-1000, Bangladesh.
Wen-Juan HouAssistant Professor
Department of Computer Science and Information Engineering National
Taiwan Normal University, Taiwan.
Prof. Hsu-Yung ChengAssociate Professor Department of Computer Science and Information
EngineeringNational Central University, Taiwan.
Dr. Adesh K. SharmaSenior Scientist, Dairy Economics,
Statistics & Management Division, National Dairy Research Institute (NDRI),(Deemed-
to-be University),Karnal-132 001. (Haryana) India..
Prof. Dilip Singh SisodiaAssistant Professor Department of Computer Science & Engineering
National Institute of Technology Raipur.
Dr. Ahmad Razlan Bin YusoffDeputy Dean of Research & Innovation
and Post GraduateFaculty of Manufacturing Engineering, Universiti Malaysia Pahang,
23300 Pekan, Pahang, Malaysia.
It is my privilege to present the print version of the [Volume 3 Issue 3] of our Journal of Artificial
Intelligence Research & Advances, 2016. The intension of JoAIRA is to create an atmosphere that
stimulates vision, research and growth in the area of Artifecial Intelligence.
Timely publication, honest communication, comprehensive editing and trust with authors and
readers have been the hallmark of our journals. STM Journals provide a platform for scholarly
research articles to be published in journals of international standards. STM journals strive to publish
quality paper in record time, making it a leader in service and business offerings.
The aim and scope of STM Journals is to provide an academic medium and an important reference
for the advancement and dissemination of research results that support high level learning, teaching
and research in all the Scientific, Technical and Medical domains.
Finally, I express my sincere gratitude to our Editorial/ Reviewer board, Authors and publication
team for their continued support and invaluable contributions and suggestions in the form of
authoring writeups/reviewing and providing constructive comments for the advancement of the
journals. With regards to their due continuous support and co-operation, we have been able to publish
quality Research/Reviews findings for our customers base.
I hope you will enjoy reading this issue and we welcome your feedback on any aspect of the Journal.
Dr. Archana Mehrotra
Managing Director
STM Journals
Director's Desk
STM JOURNALS
1. An Introduction on Virtual Reality and Its Challenges Jagannath Dixit, Shailendra Kumar, Prashant Mishra, V.S. Chandel 1
2. Goggle Mouse Afjal Ahmad, Anas Ahmad Khan, Qazi Ahmad Saeed 9
3. Social Media Blog Analysis using Watson Analytics Sindhu B. Jigali, Nirmala C.R. 15
4. Tweet Segmentation for Named Entity RecognitionKrushnadeo Tanaji Belerao 22
5. Analysis of Image CodersShefa Hasnain, Sadiya Bakhshi, Shazia Asif, Monauwer Alam 26
ContentsJournal of Artificial Intelligence Research & Advances
JoAIRA (2016) 1-8 © STM Journals 2016. All Rights Reserved Page 1
Journal of Artificial Intelligence Research & Advances ISSN: 2395-6720(online)
Volume 3, Issue 3
www.stmjournals.com
An Introduction on Virtual Reality and Its Challenges
Jagannath Dixit1, Shailendra Kumar
2,*, Prashant Mishra
3, V.S. Chandel
4
1Department of Mathematics, Integral University, Lucknow, Uttar Pradesh, India
2Department of Electronics and Communication Engineering, Integral University, Lucknow,
Uttar Pradesh, India 3Department of Physics, Bappa Sri Narain Vocational P.G. College, Lucknow, Uttar Pradesh, India
4Department of Physics, Integral University, Lucknow, Uttar Pradesh, India
Abstract In the last few years virtual reality has become most popular than other technologies. In this
paper, a short introduction of virtual reality, basic terminology, present and future of virtual
reality and application of this technology in daily life are mentioned. Virtual reality makes
users feel in a virtual environment (VE) by using computer hardware and software.
Sometimes, virtual reality (VR) is also called virtual environment (VE).
Keywords: Virtual reality, Sensorama, HMD, VCASS, BOOM, VR
INTRODUCTION
The definition of virtual reality has come from
‘virtual’ and ‘reality’. The definition of
‘virtual’ is near and ‘reality’ is what we
experience as human being. So, the term
‘virtual reality’ basically means ‘near reality’
[1]. In other words, virtual reality (VR) is the
fantasy of a three-dimensional communication,
PC produced reality, where sight, sound, and
some of the time even touch are reproduced to
make pictures, sounds, and protests that really
appear to be genuine.
Virtual reality has become enormous in the
course of recent years; however, 2016
resembles the most essential year. Virtual
reality (VR) is the utilization of personal
computer innovation to make a recreated
domain. Not at all like customary UIs, has
virtual reality put the client inside an ordeal.
Instead of viewing a screen in front of them,
users are immersed and able to interact with
three-dimension world. We know the five
senses: smell, touch, taste, sight and hearing.
These are however just our most clear sense
organs. In all actuality, people have numerous
or larger numbers of faculties than this, for
example, a feeling of adjust for instance.
Virtual reality involves giving our faculties a
personal computer produced virtual
environment that we can investigate in some
fashion.
In specialized terms, virtual truth is the term
used to depict a three-dimensional, personal
computer created environment, which can be
investigated and connected with by a man.
That individual turns out to be a piece of this
virtual world or is immersed within this
environment and whilst there, is able to
manipulate or perform a series of actions.
In present time, virtual reality gives many
opportunities to researcher and student to find
something new. Virtual reality is a better user
interface. In virtual world, most important
input device used is trackers. Trackers are
tracking three-dimensional positions.
We can divide virtual reality into three groups
according to the degree of immersion
interactivity. These three groups are:
immersive system, non-immersive system and
hybrid virtual reality system. Immersive
systems change our view of the real world
with the PC produced pictures that connect to
the position and introduction of the client's
head. A non-immersive system leaves the
users visually aware of the real world but is
able to observe the virtual world through
JoAIRA (2016) 9-14 © STM Journals 2016. All Rights Reserved Page 9
Journal of Artificial Intelligence Research & Advances ISSN: 2395-6720(online)
Volume 3, Issue 3
www.stmjournals.com
Goggle Mouse
Afjal Ahmad, Anas Ahmad Khan, Qazi Ahmad Saeed* Department of Electronics and Communications, Integral University, Lucknow, India
Abstract The essential thought of the undertaking is to fabricate Goggle by utilizing human machine
interface which can be utilized to control mouse by utilizing head-tilt and eye-flicker. This
mouse-copying gadget can be observed to be most helpful by physically debilitated and
incapacitated persons who can no longer control the PCs by utilizing their hands. Since the
gadget depends on person's head and eye movements, it can be utilized even by patients who
are incapacitated from below the shoulder. There is less energy required for head movement
and eye flickering. That's why user won't get drained from utilizing this gadget. In this gadget
or goggle we are utilizing 2D-accelerometer for identifying the head movement, by this, the
movement of the cursor has been finished. A photograph sensor distinguishes eye flickering.
The infrared handset comprises of a 935 nm IR transmitter and a phototransistor mounted on
a similar unit. This identifies a solid increment in the reflected signal upon deliberate long
squint when contrasted with ordinary eye flicker. Duplicate hands and legs have been ended
up being very helpful and palatable for a set number of exercises. Presently, computer can be
easily found at home. The disappointment of these manufactured appendages in empowering
the amputees to effectively handle a PC is obvious since one can practice a constrained
control on the mechanical appendages connected. Besides, numerous amputees have an
occupation and work in workplaces wherein they need to utilize a PC. Consequently, gadget
ought to be considered which would permit simple and cover control up PC.
Keywords: Handicapped, mouse, Goggle, accelerometer, micro controller
INTRODUCTION To build up a human machine interface
copying capacity of a mouse for incapacitated
or handicapped people. Since the gadget
depends on client's head and eye
developments, it can be utilized even by the
patients who are deadened from shoulder
descending [1, 2]. Straightforward head
development doesn't require an excessive
amount of vitality, and neither eyes squinting.
Subsequently, client won't get drained from
utilizing this gadget. We utilize accelerometer
to distinguish the development. At the point
when the leader of the client is tilted up/down
or left/right, the perusing from the
accelerometer is subtracted from the
estimation of a pre-characterize reference
point.
The distinction decides the level of head tilt. A
photograph sensor identifies eye flickering.
The infrared handset comprises of a 935 nm
IR transmitter and a phototransistor mounted
on a similar unit. This distinguishes a solid
increment in the reflected flag upon purposeful
long squint when contrasted with ordinary eye
flicker. The yield of both the sensors is given
to the ADC input and after switch on the
microcontroller. After the signs are translated
by the microcontroller, mouse guidelines are
sent to the PCs. The handled advanced data is
transmitted to the PC through the serial port.
Since numerous years, different artificial limbs
and administrations are offered worldwide to
individuals who have lasting or long haul
weakness. Fake hands and legs have been
turned out to be very compelling and attractive
for a set number of exercises.
Presently a-days, a PC is a typical thing at
home [3, 4]. The disappointment of these
simulated appendages in empowering the
amputees to effectively handle a PC is
apparent since one can practice a restricted
control on the mechanical appendages joined.
In addition, numerous amputees have a
vocation and work in workplaces wherein they
need to utilize a PC. Consequently, gadget
ought to be considered which would permit
simple and cover control up PC. Along these
JoAIRA (2016) 15-21 © STM Journals 2016. All Rights Reserved Page 15
Journal of Artificial Intelligence Research & Advances ISSN: 2395-6720(online)
Volume 3, Issue 3
www.stmjournals.com
Social Media Blog Analysis using Watson Analytics
Sindhu B. Jigali*, Nirmala C.R. Department of Computer Science and Engineering, Bapuji Institute of Engineering and Technology,
Davanagere, Karnataka, India
Abstract Analytics is defined as the discovery, interpretation, and communication of meaningful
patterns in data. A blog is a discussion or informational website published on the world wide
web consisting of discrete, often informal diary-style text entries and may contain
unstructured or semi-structured data. The analysis of unstructured data types is current
challenge, getting attention in industry. Challenges include analysis, capture, data curation,
search, sharing, storage, transfer, visualization and information privacy. Watson analytics is
a cloud based smart data discovery tool from IBM analytics. Watson solutions aim to
enhance, scale, and accelerate human expertise, targeting a wide range of complex
challenges. AlchemyAPI is a collection of APIs that offer text analysis through natural
language processing. The keyword extraction API works on URL’s, HTML documents and
plain text. It automatically detects the language of the content and then performs the
appropriate analysis. AlchemyAPI’s keyword extraction algorithm employs sophisticated
statistical algorithms and natural language processing technology aided with machine
learning techniques to analyze the content and identify the relevant keywords. The proposed
blog analyzer application uses the Alchemy_API’s keyword extraction service, accepts the
URL’s of the blogs and processes the content by employing sophisticated statistical algorithms
and natural language processing aided with machine learning techniques, to retrieve the
related/relevant and rank the keywords of the input content.
Keywords: Blog, keywords, Watson analytics, Alchemy API, keyword extraction service
*Author for Correspondence E-mail: [email protected]
INTRODUCTION Big data applies to the information that cannot
be processed or analyzed using traditional
processes or tools. Organizations have access
to a wealth of information but they don’t know
how to get value out of it because it is sitting
in its most raw form, unstructured or semi-
structured format [1]. According to the survey
conducted by IBM, it is found that half of the
business leaders today realize that they don’t
have access to the insights that they need to
fulfill their jobs [1]. Characteristics of Big data
are; volume, velocity, variety, validity,
veracity, volatility and viability.
Volume
It is the quantity of generated and stored data.
The size of the data determines the value and
potential insight- and whether it can actually be
considered big data or not [2]. The volume of
big data is very high and it is much difficult to
manage the data with traditional database
systems.
Velocity
Velocity refers to the rate at which the data is
being generated continuously from various
sources. Now a days social networking sites
are producing data in high volume with high
velocity, which requires a fast and real time
processing to manage this data.
Variety
Big data is very heterogeneous in nature. This
data can be structured, semi-structured and
unstructured. Data being generated from
different sources in different formats are stored
to process and analyze [1].
Validity
As the volume of the data is very high, validity
is the most important requirement to fetch the
accurate and relevant data for analysis
purpose. This valid data would enhance the
decision support system [1].
JoAIRA (2016) 22-25 © STM Journals 2016. All Rights Reserved Page 22
Journal of Artificial Intelligence Research & Advances ISSN: 2395-6720(online)
Volume 3, Issue 3
www.stmjournals.com
Tweet Segmentation for Named Entity Recognition
Krushnadeo Tanaji Belerao*
Department of Computer Science and Engineering, Shri Jagdishprasad Jhabarmal Tibrewala
University, Jhunjhunu, Rajasthan, India
Abstract Twitter is having lots of users to allocate and distribute a large amount of recent information,
various submission in Information Retrieval-IR and Natural Language Processing-NLP
undergo harshly through the deafening and tinny kind of tweets. We recommend tweet
segmentation framework in a group, called HybridSeg. By dividing tweets with significant
segments, the background information is conserved and simply extract with the downstream
applications. HybridSeg search the best segmentation of a tweet by increasing the addition of
the stickiness score. Two tweet data sets is an experiment; it shows that tweet segmentation
quality is extensively increased by learning both global as well as local contexts compared by
using global context alone. Additional accuracy is able to name entity recognition by putting
segment-based part-of-speech (POS) tagging.
Keywords: Information Retrieval, Natural language Processing, Named Entity Recognition
(NER), Part of Speech (POS)
MOTIVATION To increase the quality of tweet and finding
the named entity. User may create tweets as
Earthquake or now it is shaking, designed for
earthquake or shaking might be keywords, but
user might also make tweets such as we are
going to Earthquake conference, or someone
is shaking hands with me [1].
Existing System
Currently we have lots of social networking
sites. But we are using all sites for update
states, videos and sharing photos and so on.
There are no alert for floods, earthquakes, bad
weather situation. Also the segmented data are
not summarized so it increases the redundancy
and there will be a loss of time [2].
Disadvantages of System
Time loss.
Quality of message reduced.
Twitter, is a one of the social type of media,
has seen tremendous growth in recent years. It
has attracted very large interests from both
industry and academic world [2]. Many
private and public sector have been described
to observe Twitter stream to bring together
and realize user's opinions about
organizations. To understand the user
discussion we collect the tweet and preprocess
the collected tweet and perform the part of
speech (POS) [3, 4].
Proposed System
Tweets are sent for information,
communication and also sharing. The named
entities and semantic phrase is well conserved
in tweets. The global context taken from Web
pages, (e.g., Microsoft Web N-Gram corpus)
or Wikipedia helps to recognize the important
segments in tweets. The method realizing the
planned framework that solely relies on global
context is represented by HybridSegWeb.
Tweets are highly time-sensitive; a variety of
emerging phrases such as “She Playing”
cannot be getting in external knowledge bases
[5]. Though, taking into consideration a
numerous tweets generated in short span,
(e.g., a day) having the phrase, it is not
problematic to identify “She running” as a
meaningful segment and valid. We investigate
two local contexts, namely local linguistic
characteristics and local collocation. Note that
tweets from various official accounts of news
agencies, advertisers are likely well written
and organizations.
JoAIRA (2016) 26-30 © STM Journals 2016. All Rights Reserved Page 26
Journal of Artificial Intelligence Research & Advances ISSN: 2395-6720(online)
Volume 3, Issue 3
www.stmjournals.com
Analysis of Image Coders
Shefa Hasnain*, Sadiya Bakhshi, Shazia Asif, Monauwer Alam Electronics and Communication Department, Integral University, Lucknow, Uttar Pradesh, India
Abstract In this paper we work on the performance analysis of well-known image compression
algorithm i.e., wavelet based image compression which is Set Partition in Hierarchical Tree
(SPIHT) and also no list SPIHT (NLS). As SPIHT uses three variable lists which require large
hardware implementation and hence extra cost and high encoding and decoding time is
required but NLS use marker instead of list which are placed on lower nodes of insignificant
tree hence it requires less hardware and hence it is less complex then SPIHT and time of
decoding and encoding is also inferior to SPIHT. The algorithm are implemented in MATLAB
and compared using the parameter peak signal to noise ratio PSNR, encoding time and
decoding time. Using the NLS technique the image obtained has less encoding as well as
decoding time as compared to SPIHT but in context SNR SPIHT is better.
Keywords: SPIHT, NLS, PSNR, Performance analysis, Bits per pixel
INTRODUCTION The SPIHT algorithm is a generalization of the
Embedded Zero Wavelet (EZW) algorithm
proposed by Amir Said and William Pearlman
[1]. In EZW we transmit a lot of information
for little cost when we declare an entire
subtree to be insignificant and all the
coefficients in it with a zero tree label zero.
The SPIHT algorithms use a partitioning of the
trees in a manner that tends to keep
insignificant coefficient together in large
subset. The partitioning decision are binary
decision that are transmitted to the decoder,
providing a significance map encoding that is
more efficient than EZW.
SPIHT uses three variable lists
List of significant pixel (LSP)
List of insignificant pixels (LIP)
List of insignificant set (LIS)
No List SPIHT (NLS) uses the same set
structures and partitioning rules as SPIHT. The
trees are tested for significance breadth first.
Significance tests are related in a different
order than SPIHT because SPIHT performs
significance tests roughly breadth first, while
NLS performs the tests strictly breadth first.
Because the set splitting rules are the same,
each coder produces the exact same output
bits, though in a different order.
SPIHT ALGORITHM We need to know about some data notation
before describing the algorithms. SPHIT
algorithm use data structure which is similar to
that used by EZW algorithm but still it is not
that much same. Again divide the coefficient
into trees which formulate from the lowest
resolution band. These coefficients are
grouped into array of 22 matrixes which
except for coefficient in band 1 are offspring’s
of a coefficient of a lower resolution band.
The coefficient which is in lower band
resolution (Figure 1) is also divided into array
of 2x2 matrixes. The coefficient which is in
top most left corner of the array doesn’t have
any offspring.
Algorithm
Let Sn(t) is a function which decides the set of
significance bit with respect to the threshold
2n.
Sn(t), if max(i,j){[Ci,j]} ≥ 2n
0, else
Whereas ci, j is the wavelet coefficient.
Journal of
Artificial Intelligence
Research & Advances(JoAIRA)
September–December 2016
ISSN 2395-6720 (Online)
www.stmjournals.com
STM JOURNALSScientific Technical Medical