Fog Computing Based on Machine Learning: A Review

Abstract

<p>Internet of Things (IoT) systems usually produce massive amounts of data, while the number of devices connected to the internet might reach billions by now. Sending all this data over the internet will overhead the cloud and consume bandwidth. Fog computing's (FC) promising technology can solve the issue of computing and networking bottlenecks in large-scale IoT applications. This technology complements the cloud computing by providing processing power and storage to the edge of the network. However, it still suffers from performance and security issues. Thus, machine learning (ML) attracts attention for enabling FC to settle its issues. Lately, there has been a growing trend in utilizing ML to improve FC applications, like resource management, security, lessen latency and power usage. Also, intelligent FC was studied to address issues in industry 4.0, bioinformatics, blockchain and vehicular communication system. Due to the ML vital role in the FC paradigm, this work will shed light on recent studies utilized ML in a FC environment. Background knowledge about ML and FC also presented. This paper categorized the surveyed studies into three groups according to the aim of ML implementation. These studies were thoroughly reviewed and compared using sum-up tables. The results showed that not all studies used the same performance metric except those worked on security issues. In conclusion, the simulations of proposed ML models are not sufficient due to the heterogeneous nature of the FC paradigm.</p>

Leveraging Sensor Fusion and Sensor-Body Position for Activity Recognition for Wearable Mobile Technologies

“…This helped us to accurately identify the eight activities where some of them are difficult to distinguish between for the similarities among them. Different traditional and Deep learning algorithms have been applied to our dataset as found useful in several machine learning related works [39][40][41][42]. Among them, Bi-directional LSTM gives optimal accuracy.…”

Recent Advances in Evolving Computing Paradigms: Cloud, Edge, and Fog Technologies

“…The conventional cloud model falls short of fulfilling IoT application necessities due to the enormous data generated from IoT devices [ 166 ]. Transmitting the overwhelming IoT data to the cloud would cause network overhead, consuming bandwidth, and latency issues [ 167 ]. Hence, to cut back on the data transfer cost as well as network delays, service providers are steering towards the fog and edge computing [ 168 ], with an additional opportunity for enforcing security and privacy [ 169 ].…”

“…The IoT systems comprise edge equipment, sensors, and actuators with latency, bandwidth, and security necessities [ 166 ]. The fog computing technology of extending computer and storage to network’s edge solves processing and networking impediments [ 167 ], enabling rapid processing close to the data source [ 170 ]. The complexity and dynamism of fog computing with its communication networks facilitating low latency makes sophisticated computation possible in a conducive environment.…”

“…Machine learning (ML) is a promising option for intelligent data processing and inference and is a prime enabler to various IoT application domains [ 166 ], such as healthcare, smart home, smart agriculture, smart industry, smart grid, etc. It has a crucial part in designing the intelligent/smart setting for autonomous operations [ 167 ]. Machine learning has immense potential as a significant IoT technology gaining traction to provide insights for IoT applications [ 174 ].…”

Brain Stroke Lesion Segmentation Using Computed Tomography Images based on Modified U-Net Model with ResNet Blocks

“…By using an encoder-decoder architecture and a skip-connection technique, U-Net [8] may minimize the loss of background and specific details. Consequently, U-Net is useful for image segmentation processes that need a moderate quantity of data, and it has shown high efficiency in working with medical images [9][10] and other applications. Kadry et al [11] conducted an investigation on brain stroke segmentation using a Visual Geometry Group UNet (VGG-UNet).…”