Professional Documents
Culture Documents
Volume 4 Issue 3
Abstract
Content-based video extracting is very essential now-a-days. The existing data mining
algorithms are not directly applied to videos. This proposed work uses different data mining
algorithms for indexing, clustering, searching and retrieving content-based videos. A system
will be developed in which only admin can upload videos on cloud server. Videos are sorted
based on category and videos are automatically uploaded on Cloud Server on the schedule
provided by the admin. Users can watch videos online, they can download videos based on
video summary and users can rate videos that will be analyzed by the system. This system
automatically removes videos that are less popular so that user’s time will not be wasted for
watching the least rated videos. Users can share videos with other registered users without
using another platform in the proposed system.
Private cloud is a deployment model of The following algorithms are used for
implementing the above features are as
cloud computing where services will be
follows:
accessed by authorized organization or
• The clustering algorithm is used for
owner of private cloud.
sorting the videos based on categories.
Clustering is the process of collecting
Videos are automatically uploaded on
and grouping objects that belongs to
cloud server on the schedule provided by
the same class. The objects which are
the admin and videos are sorted based on
similar grouped in one cluster and
the categories. Users can search for videos
remaining dissimilar objects are
by keywords like title, date, and author so
grouped into another cluster.
that content-based videos will be retrieved.
• Indexing and prediction algorithms are
used for searching and retrieving Elbow Rule to determine the optimal
content-based videos from huge video number of clusters and calculate the
datasets based on the keywords. normalized standard deviation of course
over ground and speed over ground of
An index or database index is a data vessels in South Africa area as their
structure that is used to quickly locate and features to conduct clustering. The
access the data from a database or datasets. proposed method is supposed to evaluate
Predictive analytics is the practice of vessels’ sailing stability and used in
extracting useful information from existing detection of low-likelihood behaviours or
data sets to determine patterns and predict anomalies of vessels. The real-time
future outcomes and trends. performance of one single AIS satellite is
still very poor, which shows the
The Present Proposed Work Includes importance of establishing AIS satellite
The system proposes to maintain the constellations in the future.
repository of videos on cloud server and
videos are automatically uploaded on Shalini L and Gopali Naga Sravya [2]
cloud server on the schedule provided by collected tweets from several records and
the admin. Sorting the videos based on analyzed using several sources like fox
categories using clustering algorithm. news health, CBC health, CNN health,
Users can also watch the videos online or BBC health, everyday health, GDN health
they can also decide to download the care, good health. After analysis, tweets
videos based on the summary provided for are combined from these 16 records, the
each video. top 5 clusters of negative and positive
• Indexing and prediction algorithms are words are obtained by using K-means
used for searching and quickly clustering algorithm. The analysis is done
retrieving content-based videos from on the number of negative and positive
huge video datasets. words present in those records, and then
• Users can rate the videos so that, corresponding plot for the frequency of top
system can analyze the popularity of 40 words is obtained. They found that the
videos and this analysis is used further views of different people related to the
for deleting the least popular videos. news on health in different channels.
• Users can share videos with other
registered users without using another Igor V Anikin and Rinat M Gazimov [3],
platform in the proposed system. developed DBCSAN clustering algorithm,
which provides security of information
Related Work during all stages of the distributed data
Zhong Hanyang, Song Xin, Yan Zhenguo mining process. It would be very useful for
[1], a typical clustering algorithm called Data Mining Techniques in distributed
K-means is applied to deal with the Space- systems with big data.
based AIS(S-AIS) data received by
“TianTuo-3” satellite developed by Uma Ojha and Dr. Savita Goel [4], found
National University of Defence how precisely these data mining
Technology. In this paper, they used algorithms can predict the probability of
recurrence of the diseases among the Brian McClanahan and Swapna S Gokhale
patients on the basis of important stated [7], examined the interplay between
parameters. Experiments show that popularity ratings and video
clustering algorithms are worser predictors recommendations. They found that about
than classification algorithms. The result 40% of the video recommendations come
indicates that the decision tree (C5.0) and from categories other than that of the
SVM algorithms are the best predictor original video, with Entertainment being
with 81% accuracy on the holdout sample the most preferred cross-linked category,
popularity measures including the number
and fuzzy c-means algorithm came with
of views and comments strongly impact
the lowest accuracy of 37%. M Sivasakthi
video recommendation, video
[5]. The various supervised data mining
categorization has a higher influence on
algorithms were applied on the collected
video recommendations compared to their
data set to predict programming popularity ratings.
performance of the students that are
evaluated based on their predictive METHODOLOGY
accuracy. The results indicate that the An Execution of Proposed System
Multilayer Perception performs best with In Fig. 1, the working of proposed system
93% accuracy and therefore, multilayer is described as follows:
perception proves to be very efficient and Admin authentication process is done for
effective classifier algorithm. This analysis accessing the video datasets. Videos are
may help the Institutions to identify the automatically uploaded on Cloud Server
students who are novice programmers in on the schedule provided by the admin.
introductory programming, which further Videos are sorted based on the categories
provide base for deciding special aid or using clustering algorithms. User
focus to them. registration and authentication process is
carried out for allocating permissions [8,
Peter Brauna, Alfredo Cuzzocreab, Lam 9]. Users can search for videos by
keywords like title, date, and author so that
MV Doana, Suyoung Kima, Carson K
content-based videos will be retrieved. The
Leunga, Jose Francisco A Matundana and
indexing and prediction algorithms are
Rashpal Robby Singha [6], explored big
used for retrieving the content-based
data mining techniques for detecting
videos [10-12]. Users can also decide to
outliers or anomalies from YouTube video download the videos based on the
viewing history and data-cleaning this summary provided for each video. The
viewing log so that the user-preferred users can also watch videos online and
YouTube viewing patterns or trends can be users can rate the videos so that system
recognized and the prediction of user- can analyze the popularity of videos and
preferred YouTube videos can then be this analysis is used further for deleting the
enhanced. They used outlier detection least popular videos. Users can share
algorithm for finding anomalies for videos with other registered users without
YouTube viewing history log so that these using another platform in the proposed
anomalies can be removed. system [13-15].
User
Registration Retrieving
Searching
and Content-based
Videos by Videos
Authentication Keywords
Process
Automatically
Share videos system removes Rate Downloading
with registered least popular Videos based
Videos
users videos on Summary