No abstract

No abstract

Opportunistic network is a type of Delay TolerantNetwork which is characterized by intermittent connectivity amongst the nodes and communication largely depends upon the mobility of the participating nodes. The network being highly dynamic, traditional MANET protocols cannot be applied and the nodes must adhere to store-carry-forward mechanism. Nodes do not have the information about the network topology, number of participating nodes and the location of the destination node. Hence, message transfer reliability largely depends upon the mobility pattern of the nodes. In this paper we have tried to find the impact of RWP (Random Waypoint) mobility on packet delivery ratio. We estimate mobility factors like number of node encounters, contact duration(link time) and inter-contact time which in turn depends upon parameters like playfield area (total network area), number of nodes, node velocity, bit-rate and RF range of the nodes. We also propose a restricted form of RWP mobility model, called the affinity based mobility model. The network scenario consists of a source and a destination node that are located at two extreme corners of the square playfield (to keep a maximum distance between them) and exchange data packets with the aid of mobile 'helper' nodes. The source node and the destination node are static. The mobile nodes only help in relaying the message. We prove how affinity based mobility model helps in augmenting the network reliability thereby increasing the message delivery ratio and reduce message delivery latency.

No abstract

The high R-naught factor of SARS-CoV-2 has created a race against time for mankind and it necessitates rapid containment actions to control the spread. In such scenario short term accurate spatiotemporal predictions can help understanding the dynamics of the spread in a geographic region and identify hotspots. We propose an ensemble of convolutional LSTM based spatiotemporal model to forecast spread of the epidemic with high resolution and accuracy in a large geographic region. A data preparation method is proposed to convert spatial causal features into set of 2D images with or without temporal component. The model has been trained with available data for USA and Italy. It achieved 5.57% and 0.3% mean absolute percent error for total number of predicted infection cases in a 5day prediction period for USA and Italy respectively.