Adaptive Retrieval in a P2P Cloud Datacenter - Multimedia Database Retrieval: Technology and Applications - page 208

Chapter 8
Adaptive Retrieval in a P2P Cloud Datacenter

Abstract This chapter presents indexing and retrieval methods for image and
video on cloud datacenters. The application is based on a peer-to-peer (P2P)
network in both structured and unstructured network organizations. Firstly, a cluster-
identification search system is developed on the Chord layers to organize nodes as
a structured peer-to-peer network. The system derives automatic clustering for the
organization of nodes in a distributed hash table for effective node searching and
retrieval of multimedia objects. Secondly, pseudo-relevance feedback using the self-
organizing tree map is implemented for image database retrieval on a P2P network.
The query processing is carried out on an unstructured P2P network, through the
discovery of a community of neighbors and by performing automatic retrieval within
the nodes of the community. Thirdly, based on the unstructured P2P network, the
adaptive cosine network is also implemented for video database retrieval.

8.1 Introduction

In a cloud datacenter, multimedia objects are distributed over the nodes in an
overlay network. The searching of these objects requires a large number of query
transactions. Retrieval of a particular multimedia object involves finding the relevant
nodes owning objects potentially relevant to the query, concatenating relevant
objects, and obtaining a shortlist of relevant objects in an accurate manner. In
this regard, automation is highly appropriate for clustering multimedia objects and
indexing nodes in a distributed hash table (DHT) for computing in a cloud network.
In addition, for achieving accurate re-ranking of multimedia objects, automatic
clustering offers pseudo labeling used by the relevance feedback process. This
further minimizes bandwidth since the transferring of training files can be avoided.
This chapter starts with a presentation of a peer-to-peer (P2P) architecture
of a distributed database system in Sect. 8.2 , and a presentation of the cluster-
identification search system (CSS) in Sect. 8.3 . The (CSS) organizes the nodes in
the network as a structured P2P network. It involves the process of partitioning
multimedia objects into disjoint groups, using a self-organizing tree map (SOTM).
Here, the performance of cluster discovery depends on two key factors: the number
of clusters and the topology of node-vectors. The automatic clustering allows the
partition of nodes on the network in the DHT and Chord layers, according to the