Imran Rao

A Smart City is characterized mainly as an efficient, technologically advanced, green, and socially informed city. An intelligent transportation system (ITS) is a subset area of smart cities that enhances the safety and mobility of road vehicles. It essentially makes travel more convenient, time-efficient and improves the citizens’ quality of life. Accurate and real-time traffic prediction enables law enforcement agencies with well-informed about traffic congestion. However, accurate traffic prediction has been considered a challenging issue. Traffic prediction has restrictions on road network topology and the patterns of dynamic change in time-series data. We propose a novel deep learning framework GCST-GRU, called graph convolutional Spatio-temporal gated recurrent unit, to determine the next traffic state from traffic data. The proposed model learns complex topological structures by capturing a) spatial dependencies from data by using the graph convolution operator, and b) temporal dependencies by using the GRU neural network. Experimental results demonstrate that our framework can obtain complex Spatio-temporal correlations efficiently from the traffic network and perform better than state-of-the-art baseline models on a real-world traffic dataset. The graphical visualization by using convolution operation over the neural network shows that the model outperforms the reachability of the 3-hops neighbor effect in the traffic data graph. Additionally, the training time of the proposed framework is better than the existing state-of-the-art deep learning studies.

The large scale and dynamic nature of a distributed system makes it difficult to collect the attributes of the individual nodes in the network. In these systems, often an aggregate (e.g. AVG, COUNT, MIN, MAX, SUM etc) of these attributes is adequate. Epidemic-style protocols are one of the popular approaches to estimate aggregates in such systems. In existing epidemic-style aggregation protocols the accuracy of the estimated aggregate at local nodes heavily depends upon synchronization of aggregation rounds. To enforce synchronization in these protocols, length of aggregation round should be long enough so that all the nodes in the system complete their aggregation information exchange. In this paper, we study the impacts of asynchrony in epidemic-style aggregation protocols. We present a simple asynchronous technique to estimate system aggregates in a distributed system. Based upon this technique, we analyze two popular existing epidemic-style aggregation protocols, Push-Pull and Push-Sum. Through detailed simulations, we evaluate accuracy and cost of asynchronous version of these protocols. We found that to obtain an estimate of the true system aggregate, aggregation protocols do not need to be synchronized and hence an efficient estimate can be obtained in lesser time.