IJCRR

IJCRR - 6(15), August, 2014

Pages: 24-27

Date of Publication: 10-Aug-2014

ONLINE BROADCAST COUNSEL THROUGH WORD-CLOUD GATHERING

Author: G. Rohith, M. Suma Divya, G. Anjaneyulu, A. Usha Rani, P. N. Vara Lakshmi

Category:

Abstract:A framework for recommending online videos operates by constructing user profiles as an aggregate of tag clouds and generating recommendations according to similar viewing patterns. For this the techniques used by us are the Online Video Recommendation which recommends the users according to his patterns and the data is suggested by the help of the protocols Tag- Cloud Cosine and Tag Cloud Similarity ranking. The exclusive feature of paper is it recommends offering the user an option that the user can only pay the amount for the resources which they had used by this feature users are given more advantage.

Keywords: Online Video Recommendation, Tag-Cloud Cosine, Tag Cloud Similarity ranking

Full Text:

INTRODUCTION
A wide deployment of Internet Protocol Television (IPTV), In Internet User Created Contents (UCC), and Online Digital Video (ODV) enabled the rapid increase of online Video and programs which can be selected by consumers. This was not expected when we consider the conventional Video technologies and policies. Due to these paradigm changes, thousand of video and programs are now available to consumers. In the existing limited content providers existed, such as licensed broadcasting companies and a small number of video and satellite broadcasting operators. Thus the number of movie and programs were limited. It has become difficult and time consuming to find an interesting movie video and program via the remote control or channel guide map. To refine the channel selecting processes and to satisfy the consumer’s requirements, we propose the Online Video Recommendation (ODV) system under a cloud computing environment. The proposed ODV system analyzes and uses the viewing pattern of consumers to personalize the program recommendations, and to efficiently use computing resources. A proposed framework for recommending online videos operates by constructing user profiles as an aggregate of tag clouds and generating recommendations according to similar viewing patterns. The proposed personalization method collects and analyzes the viewing patterns, such as : the target user’s viewing pattern for contents, statistical information for the overall user’s viewing patterns, a user’s private profile or preference information through the analysis of a user’s computing environment, a communication service, and implemented in personal computer .

A REVIEW
a. Video Suggestion and Discovery for YouTube: International World Wide Web Since the launch of the YouTube for offering the online video services from 2005 it is estimated around 45000 people are visiting the YouTube and this popularity has created an up down trend to the organization to maintain the data and currently there is no any satisfactory mechanism to label videos with the majority of their content. To exacerbate the difficulty, the tags that exist on YouTube videos are generally quite small; they only capture a small sample of the content. b. The influence of online product recommendations on consumers’ online choices: From Retailer’s the capacity to offer consumers a flexible and personalized relationship is probably one of the most important. It allows them to provide more information and reduces the time consuming task but there are no accurate methods to find the exact product that helps the user to find what he wants as even though there are many recommendation systems available but they aren’t seems to be most promising among the certain consumers. c. Informed Recommender Agent: Conference on Web Intelligence and Intelligent Agent Technology Consumer reviews, opinions and shared experiences in the use of a product form a powerful Source of information about consumer preferences that can be used for making recommendations Product review forums and discussion groups are popular ways for consumers to exchange their experiences with a product. There is growing evidence that such forums inform and influence. d. Recommendation Systems in other streams: There are many streams in the engineering and each group definitely uses an recommendation system to produce the best and accurate results according to the output and while coming to the Mechanical Engineering the technique or recommendation system used by them to produce best results is Non Destructive Testing which helps the designers to produce the best results without the damage of the materials and the use of recommendation systems has been popular from many years in all the streams and they are used effectively and it is gaining a good popularity in the stream of computers in the present generation.

OVERVIEW OF DRAW BREATH SYSTEM
In the existing system the online Trading is being hosted on Stand Alone Server. This Causes bottleneck in the process of system implementation and it is very difficult to reuse algorithm module. Payment for combination of Physical Hosting and Hardware is demanded by the Web hosting Provider on monthly basis, increasing total cost and the lack of scalability in Dedicated Servers and inter-Server Adaptability becomes difficult all these problems lead to lack of Free Scripts and Install of additional features and many other problems are being raised they are threat to over cost and many other.

BRIEF DESCRIPTION ABOUT THE SYSTEM WE RECOMMEND
The main aspect and idea that we propose is described briefly by the help of an small diagram The above design of the recommended system explains the main idea of our system and these contains various program of studies.

1. Individuals Internet Terminals:
In the Individuals Internet Terminals here after the word is represented as “IIT”, user come to register or login the device and automatically user weblog history create for the target user. The User Behavior Monitor here after the word is represented as “UBM” continuously monitors a consumer’s behavior pattern and manages pattern information. The UBM retrieves weblog history information from devices such as a personal computer, mobile phone, and notebook. The UBM stores a consumer’s pattern information to the Private Computing Cloud here after the word is represented as “PCC”. Thus, a consumer’s information is independent of the device locations, and the consumer can be consistently supported over heterogeneous devices and locations.

2. Media Storage Cloud:
The Media storage Cloud here after the word is represented as “MSC” is a cloud computing based storage for media contents which are broadcast over hundreds of broadcasting channels. Content Vendors here after the word is represented as “CV” such as licensed broadcasting companies, small to medium operators, and content producers, store their own media contents on the media storage cloud. Service Agents here after the word is represented as “SAs” provide contents to consumers from the MSC, and generate statistical information, including a consumer’s preference for contents based on the consumer’s profile and analysis of their viewing history. MSC updates the user profiles at the Private Computing Cloud.

3 Private Computing Cloud:
The PCC monitors the target consumer’s personal profile. The PCC supports management, scheduling, security, pri- vacy control of the consumer profile, and the required resources. In the proposed system, each intelligent device individually transfers weblog history to the PCC. The Profile Manager here after the word is represented as “PM” then analyzes the combined weblog, and creates the consumer profile based on this weblog. The proposed PCC can identify the consumer’s preference in a short amount of time, and provide a recommended channel list at initial time. Tags can be aggregated in various ways to characterize an entity of User interest tag information is referred to as a tag cloud, which is usually displayed in alphabetical order and visually weighted by font size. The PCC is also independent of the device location, and can provide Consistent profile information according to the consumer for various devices.

4. Recommendation system:
A content-based recommendations system recommends the most likely matched item, then compares the recommendation list to a user’s previous input data or compared to preference items. A content-based recommendations system is based on information searching and generally uses a rating method which is used in the information searching. To measures for computing the user similarity, namely tag cloud-based cosine here after the word is represented as “TCC” and tag cloud similarity rank here after the word is represented as “TCSR”. The Profile Filtering Agent here after the word is represented as “PFA” creates a personalized channel profile based on the accumulated viewed content list by using a content based filtering.

5. Multimedia Broadcasting System:
The Multimedia Broadcasting System here after the word is represented as “MBS” provides broadcasting functionalities. An interface agent enables the consumer in the selecting and viewing of media content at the requested time, from the various channels via the large volume of available content through the set-top box, which includes the Personal Digital Recorder here after the word is represented as “PDR”. Additionally, all of the consumed channel list and history is accumulated at the setup box.

6. Utility Counter:
The Utility Counter hereafter the word is represented as “UC” is the one that is responsible for counting the consumer usage after the selection of the option Pay Peruse. After the termination of the UC window it shows the total count used by the consumer and costs the data according to the usage.

The Urged System:
As the existing systems are proposing methodologies of high time consuming and insufficient in the space management and the maintenance of these system become difficult day-by-day on both the financial and general ways and these problems are overcame by the design that we propose. The urged system mainly describes the Cloud based online trading platform possessing high flexibility, high reliability, low-level transparency, security features and the proposed tag cloud recommendation approaches, TCC and TCSR, outperformed the other recommenders and the methods that are used are To measures for computing the user similarity, namely tag cloud-based cosine (TCC) and tag cloud similarity rank (TCSR). The Profile Filtering Agent (PFA) creates a personalized channel profile based on the accumulated viewed content list by using a content based filtering.

Cloud Computing
In computer networking, cloud computing is computing that involves a large number of computers connected through a communication network such as the Internet, similar to utility computing. In science, cloud computing is a synonym for distributed computing over a network, and means the ability to run a program or application on many connected computers at the same time. A computing platform distributed in large-scale data center. Uses Virtualization technology to dynamically and transparently supply virtual Computing and storage resources. Reusability and extensibility of this framework component. In common usage, the term “the cloud” is essentially a metaphor for the Internet. Marketers have further popularized the phrase “in the cloud” to refer to software, platforms and infrastructure that are sold “as a service”, i.e. remotely through the Internet. Typically, the seller has actual energy-consuming servers which host products and services from a remote location, so end-users don’t have to; they can simply log on to the network without installing anything. The major models of cloud computing service are known as so In common usage, the term “the cloud” is essentially a metaphor for the Internet. Marketers have further popularized the phrase “in the cloud” to refer to software, platforms and infrastructure that are sold “as a service”, i.e. remotely through the Internet. Typically, the seller has actual energy-consuming servers which host products and services from a remote location, so end-users don’t have to; they can simply log on to the network without installing anything. The major models of cloud computing service are known as software as a service, platform as a service, and infrastructure as a service. These cloud services may be offered in a public, private or hybrid network.[3] Google, Amazon, Oracle Cloud, Salesforce, Zoho and Microsoft Azure are some well-known cloud vendors.

CONCLUSION
This paper presents techniques that are much more useful for generating the recommendations for the user profile by the help of the system. And the paper proposes the technique of cloud computing for the well organizing the database by tagging the user profiles. The experimental results suggest that the proposed approach is flexible and is able to generate acceptable segmentation results automatically by the use of the protocols such a Tag Cloud Cosine and Tag cloud Similarity ranking which are mainly hosted by the Online Video recommendation under the environment of Cloud Computing

References:

1. The TV-Anytime, “TV-Anytime Forum,” [Online]. Available: http://www.tv-anytime.org,2004.

2. P. Resnick and H. R. Varian, “Recommender systems,” communications of the ACM, vol. 40, no. 3, pp. 56-58, Mar. 1997.

3. Online].Available: http://en.wikipedia.org/wiki/Cloud_Computing.

4. Personalized DTV Program Recommendation System under a Cloud Computing Environment by SeungGwan Lee, Daeho Lee, and Sungwon Lee,Member, IEEE.

5. G. Adomavicius and A. Tuzhilin, “Toward the Next Generation of Recommender Systems: A Survey of the State-of-the-Art and Possible Extensions,” IEEE Trans. Knowledge and Data Eng., vol. 17, no. 6, 2005, pp. 734-749.

6. R. Kohavi, B. Becker, and D. Sommerfield, “Improving Simple Bayes,” Proc. European Conf. Machine Learning (ECML), Springer, 1997.

7. M. Dubinko et al., “Visualizing Tags Over Time,” ACM Trans. the Web, vol. 1, no. 2, 2007.

8. D. Yamamoto et al., “Video Scene Annotation Based on Web Social Activities,” IEEE Multimedia, vol. 15, no. 3, 2008, pp. 22-32.

9. J. Park, B-C. Choi, and K. Kim, “A Vector Space Approach to Tag Cloud Similarity Ranking,” Information Processing Letters, vol. 110, nos. 12-13, 2010, pp. 489-496. 10. S. Park, S. Kang, and Y. Kim, “A channel recommendation system in mobile environment,”IEEE Trans. Consum. Electron., vol. 52, no. 1, pp. 33-39, Feb. 2006.