My main research interests are understanding of neural and behavioral modeling of visual perception by assessing the different mechanisms guiding it, and efficient implementations of large-scale scientific problems on commodity graphical processing units (GPUs). Over the last couple of years, I have been focusing on diverse research areas with the goal of developing my understanding and interest in internet of things, data science and machine learning in particular for intelligent systems using large-scale datasets.
Visual perception, visual attention, machine learning, computer vision, internet of vehicles, distributed systems
With the advancement of the Internet of Things (IoT), the role of edge devices has been increased. The smart devices offload the heavy computation tasks to nearby edge locations to reduce the computation and network delay. However, the edge location covers a significant number of end devices; thus, not possible to provide quality of services (QoS) to all the requested devices. Further, under extreme conditions, the backend cloud data centers are used to entertain the requests; however, this can cause communication delay, thus, not suited for delay-sensitive applications. In this paper, we proposed a distributed fog computing paradigm where the roadside units (RSUs) are used to schedule offloading tasks on nearby fog vehicles. Due to limited resources at RSU, we proposed a blockchain-based task assignment to fog vehicles. The blockchain is used to maintain the credibility index of every fog vehicles. Every RSU act as a miner, which can perform a transaction on a distributed ledger based on consensus model. Numerical results demonstrate the effectiveness of the proposed scheme.
In this study, we propose a fog collaboration framework where the fog devices are placed at the micro-level with a collaboration based on a pricing model. The model is dynamically fluctuates based on the current workload; therefore, while offloading, the fog agent located at every fog location collaborates to find the suitable fog resource to outsource the task.