Abstract: Peer-to-peer (P2P) network systems gain a huge popularity due to their scalability and reliability in architectures and search facilities. Basically, most of the real world P2P network is unstructured. Due to their unstructured nature it is often impossible to pre-define the searching criteria. As a solution, flooding scheme is used in most cases. But one major limitation of flooding is its query overhead and unnecessary use of bandwidth. In this paper, we propose a novel mechanism to improve the search efficiency in unstructured P2P networks. The method is based on feedback biased walk. Instead of keeping only the feedback report a peer keeps measuring its rank among the neighbors, this algorithm maintains another rank index for a peer that indicates the reliability to make a successful query hit through that peer. Cumulative Feedback-biased Walk (CF-walk) removes the limitations of unstructured P2P networks based on flooding point and cache based searching, improves the hit rate in c

• Publication Date: 05-May-2013
• DOI: 10.15224/978-981-07-6261-2-33
• Views: 0
• Downloads: 0

Abstract: Clustering is the process of grouping data into a set of disjoint classes called cluster. It is an effective technique used to classify collection of data into groups of related objects. K-means clustering algorithm is one of the most widely used clustering techniques. The main puzzle of K-means is initialization of centroids. Clustering performance of the K-means totally depends upon the correctness of the initial centroids. In general, K-means randomly selects initial centroids which often show in poor clustering results. This paper has proposed a new approach to optimizing the designation of initial centroids for K-means clustering. We propose a new approach for selecting initial centroids of K-means based on the weighted score of the dataset. According to our experimental results the new approach of K-means clustering algorithm reduces the total number of iterations, improve the time complexity and also it has the higher accuracy than the standard k-means clustering algorithm.

• Publication Date: 05-May-2013
• DOI: 10.15224/978-981-07-6261-2-32
• Views: 0
• Downloads: 0