Individuals have distinctive ways of speaking and writing, and there exists a long history of linguistic and stylistic investigation into authorship attribution. Most authorship identification approaches are exclusively based on lexical measures such as vocabulary richness and lexico-syntactic features, or substantially generate relevant features for different machine learning approaches. These techniques are inefficient without suitable feature selection or large corpus. In this paper, we introduce three graph based models for the task of authorship identification, that consider the interaction of character sequences, phraseological patterns and structure of the sentences in the document to construct graphs separately for an author. For each model, all such graphs for different authors are aggregated to generate a combined weighted training graph. Then a simple graph traversal algorithm is used to compare testing graph with the training graph. The experiment is conducted on the documents of six authors collected from Bengali literature. Experimental results show that our models significantly outperform four state-of-the-art models (9.89% higher than the best baseline model) even for short training dataset.

With the rapid proliferation of network enabled hand devices Mobile Ad hoc network (MANET) is gaining tremendous popularity among the research community. Wirelessly connected mobile nodes are capable of providing a wide range of services such as GPS position indicator, nearest car parking information, word processing, internet connectivity etc. to other nodes in their vicinity. Service composition is a technique by which new services can be created by combining atomic services. The challenges of service composition mechanism have been addressed for wired infrastructure networks and internets. In this paper we address different issues of service composition considering node mobility, link failure and delay for MANET specifically architecture for dynamic service composition using distributed broker where QoS is ensured by energy and mobility prediction.

An ad hoc network is an infrastructure-less, decentralized network, consisting of a group of mobile wireless nodes, moving around freely and cooperating with each other in routing and forwarding of packets. Due to the lack of any clear line of defense, MANET is accessible to both legitimate users and malicious attackers. Among various types of attacks, it is particularly vulnerable to various denial of service (DoS) attacks. Route request flooding attack is one such distributed DoS attack, launched by compromised nodes or intruders. This triggers an acute need of flooding attack prevention mechanisms for this highly vulnerable type of network. In this paper, a reputation based scheme is proposed to resist the impact of flooding attack in MANET. This scheme observes the behavior of a node in the network periodically and limits its route request sending rate accordingly.