Welcome to Scribd, the world's digital library. Read, publish, and share books and documents. See more
Download
Standard view
Full view
of .
Look up keyword
Like this
0Activity
0 of .
Results for:
No results containing your search query
P. 1
Data Mining Un-Compressed Images From Cloud With Clustering Compression Technique Using Lempel-Ziv-Welch

Data Mining Un-Compressed Images From Cloud With Clustering Compression Technique Using Lempel-Ziv-Welch

Ratings: (0)|Views: 1|Likes:
Published by ijaia
Cloud computing is a highly discussed topic in the technical and economic world, and many of the big
players of the software industry have entered the development of cloud services. Several companies’ and
organizations wants to explore the possibilities and benefits of incorporating such cloud computing
services in their business, as well as the possibilities to offer own cloud services. We are going to mine the
un-compressed image from the cloud and use k-means clustering grouping the uncompressed image and
compress it with Lempel-ziv-welch coding technique so that the un-compressed images becomes error-free
compression and spatial redundancies.
Cloud computing is a highly discussed topic in the technical and economic world, and many of the big
players of the software industry have entered the development of cloud services. Several companies’ and
organizations wants to explore the possibilities and benefits of incorporating such cloud computing
services in their business, as well as the possibilities to offer own cloud services. We are going to mine the
un-compressed image from the cloud and use k-means clustering grouping the uncompressed image and
compress it with Lempel-ziv-welch coding technique so that the un-compressed images becomes error-free
compression and spatial redundancies.

More info:

Published by: ijaia on Aug 14, 2013
Copyright:Attribution Non-commercial

Availability:

Read on Scribd mobile: iPhone, iPad and Android.
download as PDF, TXT or read online from Scribd
See more
See less

08/14/2013

pdf

text

original

 
International Journal of Artificial Intelligence & Applications (IJAIA), Vol. 4, No. 4, July 2013DOI : 10.5121/ijaia.2013.4413 145
Data Mining Un-Compressed Images from cloud with Clustering Compression technique usingLempel-Ziv-Welch
 
1
C. Parthasarathy
2
K.Srinivasan and
3
R.Saravanan
Assistant Professor,
1,2,3
Dept. of I.T, SCSVMV University, Enathur, Kanchipuram,Pin–631 561
1
sarathy286089@rediffmail.com
2
kadamsrini21@gmail.com
3
saravanan_kpm1983@yahoo.co.in
 A
 BSTRACT 
 
Cloud computing is a highly discussed topic in the technical and economic world, and many of the big players of the software industry have entered the development of cloud services. Several companies’ and organizations wants to explore the possibilities and benefits of incorporating such cloud computingservices in their business, as well as the possibilities to offer own cloud services. We are going to mine theun-compressed image from the cloud and use k-means clustering grouping the uncompressed image and compress it with Lempel-ziv-welch coding technique so that the un-compressed images becomes error-freecompression and spatial redundancies.
 
 KEYWORDS
Cloud, Compression, Image processing, Clustering
 
1.
 
I
NTRODUCTION
 
In cloud computing, the word cloud is used as a metaphor for “the Internet” so the phrase cloudcomputing means "a type of Internet-based computing," where different services -- such asservers, storage and applications -- are delivered to an organization's computers and devicesthrough the Internet.
Figure 1. Cloud Computing Model
Cloudservice(queue)CloudInfrastructure(Billing VMs)Cloud Platform(eg. web front end)Cloud storage(Eg. Data base)
 
International Journal of Artificial Intelligence & Applications (IJAIA), Vol. 4, No. 4, July 2013146
Clustering can be considered the most important unsupervised learning technique; so, as everyother problem of this kind, it deals with finding a structure in a collection of unlabeled data.Clustering is “the process of organizing objects into groups whose members are similar in someway”. A cluster is therefore a collection of objects which are “similar” between them and are“dissimilar” to the objects belonging to other clusters. The typical requirements of clustering indata mining are 1. Scalability 2. Ability to deal with different types of attributes 3. Discovery of clusters with arbitrary shape 4. Minimal requirements for domain knowledge to determine inputparameters 5. Ability to deal with noisy data 6. Incremental clustering and insensitivity to theorder of input records. 7. High dimensionality. Clustering is also called data segmentationbecause clustering partitions large data sets into groups according to their similarity.
2. K-MEANS METHOD
In this cloud we are going to cluster the un-compressed Image by centroid based technique: TheK-means algorithm takes input parameter and partitions a set of n-objects into k clusters so thatthe resulting intra-cluster similarity is high but the inter-cluster similarity is low. K-Meansalgorithm proceeds as it randomly selects k of the objects, an object is assigned to the cluster it isthe most similar, based on the distance between the object and the cluster mean. It Computes thenew mean for each cluster it iterates until the criterion function converges.The square-error criterionE =
 
| p-mi| 2 where E is the sum of the square error for allobjects ini=1 p
ɛ
Cithe data set; p is the point in space representing a given object and mi is the mean of cluster CiAlgorithm: The k-means algorithm for partitioning, where each cluster’s center is represented bythe mean value of the objects in the cluster.Input :k: the number of clustersD: a data set containing n objectsMethod:(1) arbitrarily choose k objects from D as the initial cluster centers Repeat Assign eachobject to the cluster to which the object is the most similar Based on the mean value of the objects in the cluster; Update the cluster means, i.e., calculate the mean value of theobject for Each cluster; Until no change..
 Figure 2. shows the mean m1,m2 is far away from the final boundary
 
International Journal of Artificial Intelligence & Applications (IJAIA), Vol. 4, No. 4, July 2013147Figure 3. shows how the means
m
1 and
m
2 move closer to the final boundaryFigure 4. shows different types of clusters
After the algorithm finishes, it produces these outputs:
 
A label for each data point
 
The center for each labelA label can be considered as “assigning a group”. For example, in the above image you can seefour “labels”. Each label is displayed with a different colour. All yellow points could have thelabel 0, orange could have label 1, etc.

You're Reading a Free Preview

Download
scribd
/*********** DO NOT ALTER ANYTHING BELOW THIS LINE ! ************/ var s_code=s.t();if(s_code)document.write(s_code)//-->