Ad-hoc mobile/802.11 networks are fully considered as networks with no fixed physical line connections. Ad-hoc networks have no fixed topology due to the movement of the end nodes. All the nodes in ad-hoc networks are mobile. Each node taking part in this network can act as host and router which can send and receive data. In this type of situations some kind of routing protocols are needed for these mobile nodes to fully operate and function properly. Ad-hoc network has some common features, which need some routing protocol. The most significant one is the dynamic routing protocols, which quickly change the topology. Reactive routing protocols search a route to destination/remote device on needed basis. Proactive protocols maintain the whole routing table at each node. In order to show the performance, NS2 network simulator has been used. The purpose of this study is to show the performance of two widely known ad-hoc routing protocols, AODV and DSR, in terms of packet delivery ratio, average end-to-end delay and routing overhead by changing the mobility. The simulation has been carried out using NS2 2.29 as the simulation platform.

Customer churn is a focal concern for most of the services based companies which have fixed operating costs. Among various industries which suffer from this issue, telecommunications industry can be considered at the top of the list. In order to counter this problem one must recognize the churners before they churn. This work develops an effective and efficient model which has the ability to predict the future churners for broadband internet services. For this purpose Genetic Programming (GP) is employed to evolve a suitable classifier by using the customer based features. Genetic Programming (GP) is population based heuristic used to solve complex multimodal optimization problems. It is an evolutionary approach use the Darwinian principle of natural selection (survival of the fittest) analogs with various naturally occurring operations, including crossover (sexual recombination), mutation (to randomly perturbed or change the respective gene value) and gene duplication. The intelligence induced in the system not only generalizes the model for a variety of real world applications but also make it adaptable for dynamic environment. Comprehensive experimentations are performed in order to validate the effectiveness and robustness of the proposed system. It is clear from the experimental results that the proposed system outperforms other state of the art churn prediction techniques.