Professional Documents
Culture Documents
Textbook Advances in Computing and Data Sciences First International Conference Icacds 2016 Ghaziabad India November 11 12 2016 Revised Selected Papers 1St Edition Mayank Singh Ebook All Chapter PDF
Textbook Advances in Computing and Data Sciences First International Conference Icacds 2016 Ghaziabad India November 11 12 2016 Revised Selected Papers 1St Edition Mayank Singh Ebook All Chapter PDF
https://textbookfull.com/product/cloud-computing-and-services-
science-6th-international-conference-closer-2016-rome-italy-
april-23-25-2016-revised-selected-papers-1st-edition-markus-
helfert/
Advances in
Computing
and Data Sciences
First International Conference, ICACDS 2016
Ghaziabad, India, November 11–12, 2016
Revised Selected Papers
123
Communications
in Computer and Information Science 721
Commenced Publication in 2007
Founding and Former Series Editors:
Alfredo Cuzzocrea, Orhun Kara, Dominik Ślęzak, and Xiaokang Yang
Editorial Board
Simone Diniz Junqueira Barbosa
Pontifical Catholic University of Rio de Janeiro (PUC-Rio),
Rio de Janeiro, Brazil
Phoebe Chen
La Trobe University, Melbourne, Australia
Xiaoyong Du
Renmin University of China, Beijing, China
Joaquim Filipe
Polytechnic Institute of Setúbal, Setúbal, Portugal
Igor Kotenko
St. Petersburg Institute for Informatics and Automation of the Russian
Academy of Sciences, St. Petersburg, Russia
Ting Liu
Harbin Institute of Technology (HIT), Harbin, China
Krishna M. Sivalingam
Indian Institute of Technology Madras, Chennai, India
Takashi Washio
Osaka University, Osaka, Japan
More information about this series at http://www.springer.com/series/7899
Mayank Singh P.K. Gupta
•
Advances in
Computing
and Data Sciences
First International Conference, ICACDS 2016
Ghaziabad, India, November 11–12, 2016
Revised Selected Papers
123
Editors
Mayank Singh Arun Sharma
Krishna Engineering College Indira Gandhi Delhi Technical University
Ghaziabad, Uttar Pradesh New Delhi
India India
P.K. Gupta Tuncer Ören
Jaypee University of Information School of Electrical Engineering
Technology and Computer Science
Waknaghat, Himachal Pradesh University of Ottawa
India Ottawa, ON
Canada
Vipin Tyagi
Department of Computer Science William Grosky
and Engineering Department of Computer and Information
Jaypee University of Engineering Science
and Technology University of Michigan-Dearborn
Guna, Raghogarh, Madhya Pradesh Dearborn, MI
India USA
In the past few years, the computer science field has gone through several fundamental
changes to make computing useful in all aspects of life. State-of-the-art techniques and
computing paradigms based on research domains like big data, cloud computing, Internet
of Things, and machine learning are working as key technologies to bring comfort and
changes in one’s life. This volume contains 64 papers presented at the International
Conference on Advances in Computing and Data Sciences (ICACDS 2016) held during
November 11–12, 2016, and hosted by The Department of Computer Science and
Engineering, Krishna Engineering College, Ghaziabad (UP), India in association with
Special Interest group on Cyber Forensics of Computer Society of India.
ICACDS 2016 was an attempt to bring together researchers working in these
domains to share their knowledge and their work in front of others from around the
world. The conference was organized specifically to help the researchers, academics,
scientists and industry to derive benefits from the advances of next-generation com-
puting technologies. Invited speakers presented the latest developments and technical
solutions in the areas of advanced computing, communications, informatics, Internet of
Things (IoT), and data sciences and big data.
The Program Committee of ICACDS 2016 is extremely grateful to the authors
whose tremendous response to the call for papers resulted in over 500 papers being
submitted in five tracks in Advanced Computing, Data Sciences, Internet of Things,
Communications, and Informatics. All submitted papers went through a peer-review
process and finally 64 papers were accepted for publication in Springer’s CCIS series.
We are highly thankful to our potential reviewers for their efforts extended in finalizing
the high-quality papers.
The conference featured many distinguished personalities including Prof. Alexendar
Horse Norta, Tallinn University of Technology, Tallinn, Estonia; Prof. Ramesh Bansal,
University of Pretoria, South Africa; Prof. D.P. Mohaparta, NIT, Durgapur, India; Prof.
S.K. Mishra, Majmaah University, Saudi Arabia; Prof. Arun Sharma, Indira Gandhi
Delhi Technical University for Women, India; Mr. Anup Girdhar, CEO and Founder,
Sedulity Solutions & Technology, India, among many others. We are very grateful for
the participation of these speakers in making this conference a memorable event.
The Organizing Committee of ICACDS 2016 is indebted to Dr. Manoj Goel,
CAO-KIET Group, Dr. Narendra Kumar, Director, and Prof. S.B. Bajpayee, Dean of
Academic Affairs, for their confidence that they invested in us for organizing this
international conference. We also wish to thank all faculty members and staff of KEC
Ghaziabad for their support in organizing the conference and for making it a grand
success.
VI Preface
We would also like to thank the authors of all submitted papers for their hard work,
their adherence to the deadlines, and their patience with the review process. Our sincere
thanks to CSI, CSI SIG on Cyber-forensics, and DRDO for sponsoring the event.
Steering Committee
Patron
Narendra Kumar Krishna Engineering College, Ghaziabad, India
Honorary Chair
Shailendra Mishra Majmaah University, Kingdom of Saudi Arabia
General Chair
Mayank Singh Krishna Engineering College, Ghaziabad, India
Program Chair
Arun Sharma Indira Gandhi Delhi Technical University for Women,
Delhi, India
Convener
Pradeep Kumar Gupta Jaypee University of Information Technology,
Solan, India
Co-convener
Vipin Tyagi Jaypee University of Engineering and Technology,
Guna, India
Organizing Chair
Purnendu S. Pandey THDC Institute of Hydropower, Engineering
and Technology, Tehri, India
Dileep Kumar Yadav Krishna Engineering College, Ghaziabad, India
Vishwajeet Pattanaik Krishna Engineering College, Ghaziabad, India
VIII Organization
Organizing Secretary
Vipin Dewal Krishna Engineering College, Ghaziabad, India
Krista Chaudhary Krishna Engineering College, Ghaziabad, India
Karuna Lochab Krishna Engineering College, Ghaziabad, India
Pratishtha Singh Krishna Engineering College, Ghaziabad, India
Raghuvanshi
Finance Chair
S.B. Bajpayee Krishna Engineering College, Ghaziabad, India
Organizing Committee
Registration
Deepali Krishna Engineering College, India
Parikshit Joshi Krishna Engineering College, India
Ruchi Goel Krishna Engineering College, India
Shweta Goel Krishna Engineering College, India
Publication
Mayank Singh Krishna Engineering College, India
Vishwajeet Pattanaik Krishna Engineering College, India
Vipin Dewal Krishna Engineering College, India
Krista Chaudhary Krishna Engineering College, India
Cultural
Astha Gupta Krishna Engineering College, India
Sandhya Awasthi Krishna Engineering College, India
Surbhi A. Sharma Krishna Engineering College, India
Vishu Tyagi Krishna Engineering College, India
Transportation
Birendra Kumar Krishna Engineering College, India
Mohit Jain Krishna Engineering College, India
Sandeep Saxena Krishna Engineering College, India
Vimal Kr. Dwivedi Krishna Engineering College, India
Hospitality
Karuna Lochab Krishna Engineering College, India
Pramod K. Sethy Krishna Engineering College, India
Prerna Krishna Engineering College, India
Rahul Deva Krishna Engineering College, India
Organization IX
Stage Management
Krista Chaudhary Krishna Engineering College, India
Pratishtha Singh Krishna Engineering College, India
Raghuvanshi
Technical Session
Mayank Singh Krishna Engineering College, India
Vishwajeet Pattanaik Krishna Engineering College, India
Krista Chaudhary Krishna Engineering College, India
Karuna Lochab Krishna Engineering College, India
Finance
Vipin Dewal Krishna Engineering College, India
Suyash Garg Krishna Engineering College, India
Food
Gaurav Singh Krishna Engineering College, India
Jai Singh Krishna Engineering College, India
Lokesh Jain Krishna Engineering College, India
Rishu Gupta Krishna Engineering College, India
Advertising
Vishwajeet Pattanaik Krishna Engineering College, India
Vikas Mishra Krishna Engineering College, India
Editorial
Kavita Saxena Computer Society of India, India
Mayank Singh Krishna Engineering College, India
Vishwajeet Pattanaik Krishna Engineering College, India
Vipin Dewal Krishna Engineering College, India
Lokesh Jain Krishna Engineering College, India
Krista Chaudhary Krishna Engineering College, India
Karuna Lochab Krishna Engineering College, India
Shweta Suran Krishna Engineering College, India
Rishu Gupta Krishna Engineering College, India
X Organization
Advisory Board
A.K. Moudgil Krishna Engineering College, India
A.K. Nayak Computer Society of India, India
A.N. Mishra Krishna Engineering College, India
Anoop Narain Singh Krishna Engineering College, India
Anirban Basu Computer Society of India, India
Barbara Masucci Università di Salerno, Italy
Bharat Bhargava Purdue University, USA
Christos Bouras University of Patras, Greece
Deepak Garg Thapar University, India
Emilio Insfran Universitat Politecnica de Valencia
Julie Dugdale Grenoble Informatics Laboratory, France
Klaus Havelund NASA’s Jet Propulsion Laboratory, USA
Maninder Singh Thapar University, India
Mario Cataldi Université Paris 8, France
Mohammed Atiquzzaman University of Oklahoma, USA
Pavel Zezula Masaryk University, Czech Republic
Piyush Goyal Computer Society of India, India
R.K. Sharma Thapar University, India
Rajesh Bhatia PEC University of Technology, India
Ralf Wimmer University of Freiburg, Germany
S. Saraswat Krishna Engineering College, India
Sanjay Mohapatra Computer Society of India, India
Sanjeev Kumar Krishna Engineering College, India
Saurabh Aggarwal Computer Society of India, India
Sulabh Bansal Krishna Engineering College, India
Advanced Computing
Development of Secured Trust SLA Model from SLA Life Cycle Phases. . . . 102
Manjula Shanbhog, Krista Chaudhary, Mayank Singh,
and Shailendra Mishra
Communications
Informatics
Internet of Things
Data Sciences
Abstract. Location based service is an integral part of day to day life. Many
location recommendation algorithms are proposed in the past. This paper
investigates various approaches currently available for implementing location
recommendation systems.
1 Introduction
Location based service provides information and entertainment service to the user on
the move. They are convenient to use with mobile devices and can make use of the
global positioning system to ease navigation. Some of the most popular systems that
use location-based services are friend finder, shopping alerts, best restaurant and
location-based mobile marketing and advertising.
The user can add location dimensions to the location-based social networking
services. For example Foursquare, UBER, cool cab and GeoLife. It gives the infor-
mation about new locations to visitors. When a user visits the place, the users can leave
comments about a restaurant, shop etc. in a location-based social networking site.
People can find such recommendations useful. Location of user context gives knowl-
edge about an individual’s interests and behavior. This allows us to better understand
users in a social structure and the user mobility and activities in the physical world [1].
People visiting gyms might like physical exercises and users who have dinner in the
same restaurant may share a similar taste [1]. Sometimes individuals who do not have
overlaps of physical locations can still be linked, according to categories of their visited
locations that are of a similar interest, such as beaches or museums [1]. Such kind of
information is useful for targeted marketing. It also is useful for customization and
personalization of value added services provided by the service provider to users [2].
This paper contains an analysis of various techniques that can be used to recommend
the location.
2 Literature Review
Zhou and Wang [3] used both the temporal influence and geographical influence.
Temporal pattern is represented by the temporal curve. It extracts a temporal pattern
from category information of check-in data. They consider the category to be a coffee
shop. The temporal curve represents the user check in behavior for a particular time in a
day. The similarity between two users is calculated by the distance between two
temporal curves. If two users have a similar temporal curve that means they might share
a common interest and have co-related check-in behavior. Coupling method is used to
find the difference between two temporal curves. To determine the temporal influence
collaborative filtering method is used. The geographical influence measures the prob-
ability of checking into a location based on the distance of that location to user’s home
location. Spatial probability function filters out those locations that are not relevant to
the user. Precision and recall are used to measure the performance of the system. It
compares the performance with the probability category based location recommenda-
tion and periodic mobility model. The advantage of the system is that it recommends
the location to the user at a given time of the day by using the category information.
This system however has not considered the social tie between users to build the
category information.
Jia-Dong et al. [4] describe a personalized location recommendation system which
returns the top k locations with highest visiting probability. It used kernel density
estimation and fast Gaussian transform technique. Advantages of the Kernel Density
Estimation is that it is applicable to arbitrary distribution and requires few samples to
give good density estimation. Fast Gaussian Transform is used for pattern recognition
[4]. It predicts the probability of the user to visit new location when the user gives
home location and a set of the check-in locations. Here a comparative study of the
Non-negative Matrix Factorization, Multicenter Gaussian model and power law dis-
tribution is done based on the precision and recall. Precision is the ratio of the number
of the discovered location to the number of k recommended location. The recall is the
ratio of the number of the discovered locations to the number of the positive locations.
Discovered location is the number of the visited location by the user in training dataset.
The positive location is the number of the visited locations by the user in testing
dataset. The dataset containing information of the check-in details of the user is taken
from the Foursquare and Gowalla. The advantage is that it models the personalized
geographical influence on user’s check-in behavior in order to accurately predict the
probability of the user visiting a new location. This technique gives the good output in
the cold start of the system with the minimum amount of the data. The limitation of the
system is that it does not provide any information about the location. It is mostly
probabilistic model that depends on probability.
Lin et al. [5] designed an integration framework of three algorithms, which are
(i) User based collaborative filtering, (ii) Collaborative filtering based on social influ-
ence and (iii) Naive Bayesian classifier. They calculated the distance between the user’s
current location and the recommended location and compared it with the distance limit
parameter of the recommended location. The distance limit parameter of the recom-
mended location can be set by the user. User preference is calculated by user-based
A Survey on Location Recommendation Systems 5
collaborative filtering. This algorithm, considers users current location, distance limit
factor and user residence. It checks that the recommended location distance is less than
the distance limit parameter. It then recommends the top ‘n’ locations to the user. They
divided cold start problem into new users and new location. The new user does not
have any previous history so Navies Bayesian cannot be used here. It requires at least
two previous records of each dataset. For the new location, there are no check-in
records of the user. For the cold start, it gives the average accuracy. The accuracy and
the precision is calculated and compared. The accuracy of the user based collaborative
filtering based on social influence and the naïve Bayesian classifier is better than all
other methods. The limitations of this system is that the cold start problem and spare
data reduce the accuracy.
Veningston and Shanmugalakshmi [6] gives location aware review in order to
understand user experience and in future to suggest a location according to their interest
when they are visiting new places. The input parameters are user location, time the
query is issued, the maximum distance the user will travel and a query string. It
maintains a user profile. User specific parameter is determined by the probability of the
user issuing a query and searching the information on the topic. The user profile
contains the terms present in user search history. The system applies Bayes theorem. It
uses Kullback-Leibler Divergence between two contextual models to measure the
similarity between two contexts is information gain. The Doctor recommendation
system authors proposed is built to choose the physician who best suits their need. It is
privacy aware recommendation system. User modeling contains standardized electronic
patient health records. Document modeling is done on the description of the education
resource. The advantages are the similarity matching is done for selection of the
resource based on rules given by experts to present personalized resources to users. The
limitation of this system is that the use of spare data reduces the accuracy of the
recommendation technique.
Bagci and Karagoz [7] designed a random walk based context aware activity
recommendation algorithm for the location-based social network. It is an activity based
algorithm in which they consider the social, personal and spatial context of the user.
The authors propose a graph model to represent the location-based social network [7].
They proposed the algorithm with friend based and expert based recommendation
algorithm. It builds the subgraph and gives the input to activity recommendation
system and measures its efficiency by calculating the precision and recall. It compares
with other techniques like popularity based recommendation, friend-based recom-
mendation, and expert based recommendation. From the comparison of this technique;
the random walk based context aware activity recommendation gives better precision,
recall and f measure. In [7], algorithm populates a subgraph according to the current
context of the user and performs a random walk on this graph to rank the activities. For
each location coordinate in the Foursquare dataset, they queried; it is checked whether
such a location exists in the Foursquare database. If such a location exists then its
category is utilized as activity information. Next; an updated dataset that contains
activity information in addition to user and location information is obtained.
Jiang et al. [8] considered the area of interest as standard deviation ellipse which
consists of point sets. In Content-Based Recommendations, users will prefer a location
near where he or she used to be. The system assumed that the locations recommended
6 M. Narvekar et al.
to the user will always fall within standard deviation ellipse. Whereas; Collaborative
Filtering Recommendation involves evaluating the similarity between users. For
evaluating similarity, they proposed two approaches viz. (i) Standard Deviation Ellipse:
Locations recommended by user’s higher similar value have higher priority than those
having lower similar value. (ii) Cosine Distance: While constructing utility matrix;
limited data is considered and cosine distance is calculated based on it. However,
recommendations made by this system may not reliably every time; as recommenda-
tions are made considering the large geographical area. The limitation of the system is
that it lacks finer location granularity in the recommendation.
Gupta and Singh [9] describes the restaurant recommendation system. In this, the
system retrieves the past history of the user by Foursquare account or Facebook. It
maintains the user profile and restaurant database. In [9] system first locates the user
using Google geolocation API, it then searches the nearby restaurant and then rec-
ommends the restaurant to the user. This whole process is done online. When the user
checks in at a particular restaurant it is then added in the restaurant database. User
profile and interest are stored. According to the user profile and interest, the restaurant
is recommended to the user. This process is done offline so there is no wastage of
power and bandwidth. It needs to integrate ‘Facebook places’ to get user’s past visits
data. Most recent information on recommended restaurants should be searched online
to look for offers and discounts. Locating the user’s friends in vicinity for recom-
mendation is also incorporated.
Jin et al. [10] combines the feature of the foursquare and yelp. Location recom-
mendation is done using collaborative filtering. The system uses binary rating for each
location. If the user checks into a location, it is marked as 1 or else as 0. The user
similarity with the other user is calculated using cosine similarity. In this privacy
recommendation engine, data is shared among the specific group of people. It consists
of the server side privacy recommendation engine (S-PRE) and client-side privacy
recommendation engine (C-PRE). S-PRE can be helpful in the cold start problem for a
new user because it contains the record of the anonymous user. In this C-PRE client
can make the change to whom their data can be visible. The main goal of this privacy is
to allow the user to selectively and securely share their location with the other user
and/or service providers. It performs encryption for private sharing between the parties.
The advantages of this system is that the accuracy of the recommendation system is
good. Collaborative filtering algorithm performs well even with less data. In this
system authors aim to give the recommendation system; the data which the user wants
to share with others.
Wen-ying and Guo-ming [11] used collaborative filtering algorithm for the rec-
ommendation. They used a Rule-based recommendation for the cold start problem.
Collaborative filtering recommendation cannot solve the cold start problem. User
preference is divided into two-factor subjective factor and objective factor. Subjective
factor is the personal preference and habits of the user. Objective factor is the current
time, current location and current weather. Location based recommendation system
need to use the recommendation algorithm which has the ability to handle multiple
discrete attributes. User profile information, context information, restaurant informa-
tion, restaurant characteristic and usage log record is maintained. The advantages of
Another random document with
no related content on Scribd:
The Project Gutenberg eBook of Itämaalaisia
haaveiluja
This ebook is for the use of anyone anywhere in the United States
and most other parts of the world at no cost and with almost no
restrictions whatsoever. You may copy it, give it away or re-use it
under the terms of the Project Gutenberg License included with this
ebook or online at www.gutenberg.org. If you are not located in the
United States, you will have to check the laws of the country where
you are located before using this eBook.
Language: Finnish
Kirj.
Valfrid Hedman
HAAVEILUJA
Kesää kosiskellen
Etelän tyttärelle
Vienoa kaipuuta
Itämainen tunnelma
Unelmatar
Ihanteelle etelässä
Vapain tuntein
Kaksi kukkaa
Eevan omena
Haaremin helmi
Armeniatar
Lohdutus
Himo ja lempi
Saaronin ruusu
Luopio
Immen osto
Unikukkia
Pohja ja etelä
Käärmeen kuiskeet
Kangastus
Synnyinmaata muistellessa
Eri värit
SEKASOINTUJA
Eri muodot
Vertaus
Aistillisia nautintoja
Mietelmä
Kuohujen kuiskeet
Myrkkyä halajan
Ukkonen
Vellamon neidot
Valhallassa
Kultakaupunki
Islaamin taivas
Nirvana
Olympolaisia
Houreita
Pieni vertaus
Ystävyys ja lempi
Harhaileva fantasiia
Sydämen morsian
Lemmen kuiskeita idästä
ARABIALAINEN YÖ
Arabialainen yö
RUNOJEN KÄÄNNÖKSIÄ
Israelin unelma
Kun oksat akkunahan lyö
Toivo
Kirjoitus kiven kyljessä
Haluni
Iltasoittelu
Tavoittelua
Pikkutyttö
Valkoverinen
Evrikómi
Nuoren naisen haudalla
Lemmityn huulet
Sykintää
Intohimojen puutarhassa
HAAVEILUJA
Kesää kosiskellen
Olen syntynyt tuiskussa talvien säässä, mun tuuditti
tuuloset unta, oli hongat ne huurassa, järvet ne jäässä ja
vaippana valkosta lunta.
Etelän tyttärelle
Vienoa kaipuuta
Itämainen tunnelma
Unelmatar
Ihanteelle etelässä
Sä minut hurmaat, mä sua lemmin, sä kesän kirkkahan
kukka! tuo tenho katse kuin hiili hehkuu ja sysimusta on
tukka.
Ei sinisilmiä etelässä,
ei keltakutrien kultaa,
vaan tummat tummien kulmain alta
ne säihkyy tunnetta, tulta.
Vapain tuntein
On onni toivehissa:
kun toivot täyttyneet
ei ole, niin ei myöskään
ne ole päättyneet.
Eevan omena
Haaremin helmi
Armeniatar
Lohdutus
Himo ja lempi
Saaronin ruusu
Luopio
Immen osto
Kun Persiassa harhailin mä pienen kylän tiellä, näin neidon
nuoren, notkean ja ihanaisen siellä.
Se viehätti, se kiihotti,
tää tenho itämainen:
jo sydämeni lumosi
Iraanin sorja nainen.
Unikukkia
Pohja ja Etelä
Käärmeen kuiskeet
Kangastus
Synnyinmaata muistellessa