A Novel Resource Management Framework for Fog Computing by Using Machine Learning Algorithm

Abstract

With the development of edge devices and mobile devices, the authenticated fast access for the networks is necessary and important. To make the edge and mobile devices smart, fast, and for the better quality of service (QoS), fog computing is an efficient way. Fog computing is providing the way for resource provisioning, service providers, high response time, and the best solution for mobile network traffic. In this chapter, the proposed method is for handling the fog resource management using efficient offloading mechanism. Offloading is done based on machine learning prediction technology and also by using the KNN algorithm to identify the nearest fog nodes to offload. The proposed method minimizes the energy consumption, latency and improves the QoS for edge devices, IoT devices, and mobile devices.

Reconstruction of synthetic aperture radar data using hybrid compressive sensing and deep neural network algorithm

“…The complex-valued SLC input image is stacked as per Equation (15). Then, the 4D covariance matrix is estimated from the SLC image followed by interferogram generation and spectrum estimation.…”

“…The implementation and evaluation of STAC on a commodity mobile device compared to several baselines show promising performance 14 . The data‐driven method can also be used to for scheduling in the computing applications 15 . The multivariate relevant vector regression model is the spare and robust model that can handle the high‐dimensional and nonlinear data to reduce the overfitting problem in the forest biomass estimation using radar image 16 .…”

“…14 The data-driven method can also be used to for scheduling in the computing applications. 15 The multivariate relevant vector regression model is the spare and robust model that can handle the high-dimensional and nonlinear data to reduce the overfitting problem in the forest biomass estimation using radar image. 16 The modified water cloud model combines the potential of SAR and optical data to estimate the biophysical parameters of wheat crops.…”