In recent times, there has been rapid growth in Vehicular Ad hoc Network (VANETs) research work. The VANETs communication paradigm that emanated from the Mobile Ad hoc Networks (MANETs) [1-3]. It is apparent that VANETs is very different from MANETs due to the nature of topology and resource capability. In MANETs, nodes are more scattered in a randomized manner, while VANETs has a defined pathway, which is the road. In addition, MANETs is constrained with limited resources such as battery, memory, and process, which is not the same for VANETs. The VANETs has two major communication type namely, Vehicle to Vehicle (V2V) and Vehicle to Infrastructure (V2I) [4-6]. The V2V is a complete ad hoc based network, which signifies communication only between vehicles. While the V2I involves the use of Road Side Units (RSUs) to aid communication among vehicles on the road. The Video streaming in VANETs has also been related to cloud computing and Internet of Things (IoT) [7-10]. Some of the application domain of VANETs include safety, infotainment, monitoring. Looking at the application areas, video streaming can be applied in these areas. In the aspect of safety, the incidence of a scenario can be captured by another vehicle or an on-road RSU and transmit to vehicles moving towards the direction of the incidence. This would enable drivers navigating towards the direction to take a swift decision on whether to change route or not. The infotainment is more related to the video streaming services. Video streams can be forwarded to drivers on highways to notify them of good services, which is nearby their navigation location. This good and services include grocery shops, highway filling stations, nearby emergency clinics, restrooms, restaurants, lodging hotels. This will go a long way improving businesses and provide firsthand information to the road users. In addition, video streaming can be used to monitor the surroundings, because vehicles are used
Back Propagation (BP) algorithm is one of the oldest learning techniques used by Artificial Neural Networks (ANN). It has successfully been implemented in various practical problems. However, the algorithm still faces some drawbacks such as getting easily stuck at local minima and needs longer time to converge on an acceptable solution. Recently, the introduction of Second Order Methods has shown a significant improvement on the learning in BP but it still has some drawbacks such as slow convergence and complexity. To overcome these limitations, this research proposed a modified approach for BP by introducing the Conjugate Gradient and Quasi-Newton which were Second Order methods together with 'gain' parameter. The performances of the proposed approach is evaluated in terms of lowest number of epochs, lowest CPU time and highest accuracy on five benchmark classification datasets such as Glass, Horse, 7Bit Parity, Indian Liver Patient and Lung Cancer. The results show that the proposed Second Order methods with 'gain' performed better than the BP algorithm.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.