Khyati Marwah

Abstract-VoIP services are getting more and more popular day by day. In order to meet the users demand for such services irrespective of users location requires wide area wireless coverage.To this extent, wireless mesh networks have been considered as practical and inexpensive solution.In order to improve the performance of VoIP services, techniques like packet aggregation are done. This paper focuses on finding the effect of packet aggregation on various parameters like aggregation delay, end to end delay and MOS etc. Results obtained through simulations done on Qualnet Simulator concludes that packet aggregation is justified upto a certain extent only as after that most of the users get dissatisfied.

Abstract-VoIP services are getting more and more popular day by day. In order to meet the users demand for such services irrespective of users location requires wide area wireless coverage .To this extent, wireless mesh networks have been considered as practical and inexpensive solution .In order to improve the performance of VoIP services, techniques like packet aggregation are done . This paper focuses on finding the effect of packet aggregation on various parameters like aggregation delay, end to end delay and MOS etc. Results obtained through simulations done on Qualnet Simulator concludes that packet aggregation is justified upto a certain extent only as after that most of the users get dissatisfied.

Prevalent intellective systems assist the driver in the navigation errands by taking some simple and intricate decisions based upon available input information. Such decisions should be astute and prompt to provide realistic behaviour in real-life navigation scenarios decisions. Proposed unified Convolutional Neural Network framework presents a novel approach for better performance of navigation related autonomous systems.The suggested work is an extension to authors previous work in which best input features for decision making neural network were obtained by shortlisting eleven texture metrics out of thirty-six metrics using state of art algorithmsUnification of Best Feature Selection Method (our previous work) and Principal Component Analysis Technique was done to find out the most pertinent neural network inputs. CNN framework has been used here to provide a simple decision that is either to move or stop at a particular instant based on finalized inputs. It was found that the co...

Nowadays, intelligent systems are quite common to assist the driver in its navigation chores. But, if accurate information is not provided to the driver on time then it is of no use and the delay can even lead to disastrous consequences. To improve behavioral realism in real life navigation scenarios we need intelligent and speedy decisions. Such decisions rely on the information being extracted from real-time images. We need to select the best available features/information that can be used as neural network inputs and ultimately predict the next move of the vehicle. Little work has been done on selection of best features of navigation images and research needs to be done in this gray area as its results have direct impact on the classification accuracy and generalized performance of automotive navigation planning. This article proposes a novel approach to find the best possible set of features from real-time navigation images by using Boruta Algorithm and Earth Algorithm so as to ...