SaW: Video Analysis in Social Media with Web-based Mobile Grid Computing
ABSTRACT
The burgeoning capabilities of Web browsers to exploit full-featured devices can turn the huge pool of social connected users into a powerful network of processing assets.HTML5 and JavaScript stacks support the deployment of social client-side processing infrastructure, while WebGL and WebCLfill the gap to gain full GPU and multi-CPU performance. Mobile Grid and Mobile Cloud Computing solutions leverage smart devices to relieve the processing tasks to be performed by the service infrastructure. Motivated to gain cost-efficiency, a social network service provider can outsource the video analysis to elements of a mobile grid as an infrastructure to complement an elastic cloud service. As long as users access to videos, batch image analysis tasks are dispatched from the server, executed in the background of the client-side hardware, and finally, results are consolidated by the server. This paper presents SaW (Social atWork) to provide a pure Web-based solution as a mobile grid to complement a cloud media service for image analysis on videos. Index Terms—Distributed computing, image analysis, multimedia databases, multimedia systems, social media, web-based architecture
EXISTING SYSTEM:
THE social media paradigm has led to a significant rise in the volume of user generated content managed by social networks with millions of users accessing services, each of them often using multiple devices at the same time. Service providers aim to engage audience, eager for contents, by boosting the media relevance. To this end, a deeper automatic tagging enables better matching of user interests with the content database and reveals underlying connections between items, such as applying face detection mechanisms or content based indexing to find related videos. Image analysis algorithms empower automatic retrieval of salience features but they also involve computing-intensive functions. Therefore, the processing requirements grow substantially when all the media items comprising the social network database are analyzed. Here, on the one hand big data challenges arise when social services have continuously increasing databases, while on the other hand more and more processing resources are required to analyze all the content. Grid and Cloud technologies provide High Performance Computing systems that aim to satisfy these requirements. However, as pointed in, other under-explored alternatives could enhance the trade-off between infrastructure cost, elapsed time and energy saving. It would depend on the number of available processing nodes, the inherent characteristics of the tasks to be performed in parallel and the data volume.
PROPOSED SYSTEM:
This section presents the related work, providing a definition of the Internet-based computing models and focusing on the different topics addressed by distributed computing: the interoperability, the task distribution managing, the parallel processing capabilities and the different data structures. A. Computing Models This section describes the main involved concepts in terms of Internet-based computing, where shared resources, data and information are provided to computers to reach a common goal. Grid Computing: Grid Computing has been an important paradigm in distributed systems for the last two decades. Basically, a grid is a network system where computing tasks are distributed to use non-dedicated computing resources, which may include servers or client computers. The high potential of the nowadays abundant and frequently idle client hardware boosts the opportunistic and delay-tolerant use of client resources in the grid. In this volunteer computingSETI@home is the most popular example. SETI@home approach has been the pioneer of big data grid infrastructure staking benefit of Internet-connected computers of volunteers. SETI@home has spread the collaborative network model to other unselfish research in areas such as astronomy, climate, astrophysics, mathematics, genetics, molecular biology and cryptography where volunteers and donors share the computing time from personal devices. Mobile Grid Computing: Grid Computing is characterized the heterogeneity of the resources in both amount and nature, by the sporadic availability, churn and unreliability of the devices, and by their anonymity and lack of trust. These issues are more relevant in Mobile Grid Computing (MGC), where computing resources include mobile devices with wireless communications, and therefore prone to disconnections and other eventualities. Cloud Computing: More recently, Cloud Computing, a new paradigm of distributed computing where virtualized computing resources are provided on-demand, has experienced a dramatic growth. Nowadays the cloud is a cost saving opportunity for many enterprises and many cloud vendors. Amazon is a popular cloud service provider with solutions like Amazon Simple Storage Service S3 and the Elastic Cloud Computing EC2 as an interface to them. Eucalyptus is an open source cloud implementation on top of Amazon EC2.
CONCLUSION:
In this paper we have introduced the concept of Social artwork, SaW, which aims to complement a Web-based social media service with all the idle devices, mostly mobiles that usually have underexploited resources while accessing the service. SaW proposes a Mobile as an Infrastructure Provider(MaaIP) model, creating a system related to Mobile Grid Computing concept with the available CPU and GPU resources of the different client devices, to complement a virtualized cloud server providing the social media service. Aimed to achieve enhanced and automatic media tagging over social media datasets, SaW fosters background dispatching of media analysis over connected clients, providing a high elasticity and dealing with the availability of the resources related to the spontaneous presence of users.
REFERENCES:
[1] D. Neumann, C. Bodenstein, O. F. Rana, and R. Krishnaswamy, “Stacee:enhancing storage clouds using edge devices,” in Proceedings of the 1stACM/IEEE workshop on Autonomic computing in economics. ACM,2011, pp. 19–26.
[2] S. P. Ahuja and J. R. Myers, “A survey on wireless grid computing,”The Journal of Supercomputing, vol. 37, no. 1, pp. 3–21, 2006.
[3] D. Huang, T. Xing, and H. Wu, “Mobile cloud computing servicemodels: a user-centric approach,” Network, IEEE, vol. 27, no. 5, pp.6–11, 2013.
[4] M. Anttonen, A. Salminen, T. Mikkonen, and A. Taivalsaari, “Transformingthe web into a real application platform: new technologies,emerging trends and missing pieces,” in Proceedings of the 2011 ACMSymposium on Applied Computing. ACM, 2011, pp. 800–807.
[5] “Xamarin Website,” https://www.xamarin.com/, [Online; accessed 16-February-2017].
[6] “PhoneGap Website,” http://phonegap.com/, [Online; accessed 16-February-2017].
[7] “Apache Cordova Website,” https://cordova.apache.org/, [Online; accessed16-February-2017].
[8] W. Jeon, T. Brutch, and S. Gibbs, “Webcl for hardware-accelerated webapplications,” in TIZEN Developer Conference May, 2012, pp. 7–9
.[9] J. J. Garrett et al., “Ajax: A new approach to web applications,” 2005.
[10] I. Fette and A. Melnikov, “The websocket protocol,” 2011.