D
Deepak Kumar Sharma
Researcher at Netaji Subhas Institute of Technology
Publications - 139
Citations - 1173
Deepak Kumar Sharma is an academic researcher from Netaji Subhas Institute of Technology. The author has contributed to research in topics: Routing protocol & Computer science. The author has an hindex of 13, co-authored 125 publications receiving 691 citations. Previous affiliations of Deepak Kumar Sharma include University of Delhi & Information Technology University.
Papers
More filters
Journal ArticleDOI
A Machine Learning-Based Protocol for Efficient Routing in Opportunistic Networks
Deepak Kumar Sharma,Sanjay Kumar Dhurandher,Isaac Woungang,Rohit Kumar Srivastava,Anhad Mohananey,Joel J. P. C. Rodrigues +5 more
TL;DR: Simulation results show that MLProph outperforms PROPHET+, a probabilistic-based routing protocol for OppNets, in terms of number of successful deliveries, dropped messages, overhead, and hop count, at the cost of small increases in buffer time and buffer occupancy values.
Proceedings ArticleDOI
HBPR: History Based Prediction for Routing in Infrastructure-less Opportunistic Networks
TL;DR: A novel History Based Prediction Routing protocol for infrastructure-less OppNets which utilizes the behavioral information of the nodes to find the best next node for routing and is compared with the Epidemic routing protocol.
Journal ArticleDOI
kROp: k-Means clustering based routing protocol for opportunistic networks
TL;DR: A context-aware routing protocol named kROp is proposed, which uses a variety of network features generated dynamically for making routing decisions and utilizes unsupervised machine learning in the form of an optimized k-Means clustering algorithm to train on these features and make next hop selection decisions.
Journal ArticleDOI
GAER: genetic algorithm-based energy-efficient routing protocol for infrastructure-less opportunistic networks
TL;DR: A novel routing protocol named genetic algorithm-based energy-efficient routing (GAER) protocol for infrastructure-less Oppnets is proposed, which uses a node’s personal information, and then applies the genetic algorithm (GA) to select a better next hop among a group of neighbour nodes for the message to be routed to the destination.
Journal ArticleDOI
GMMR: A Gaussian mixture model based unsupervised machine learning approach for optimal routing in opportunistic IoT networks
TL;DR: Gaussian Mixture Models, an ML based soft clustering mechanism, is used to develop the proposed routing protocol called GMMR, a routing protocol that combines the advantages of both context-aware and context-free routing protocols.