Showing papers in "Computer Networks in 2021"

TL;DR: An extensive and diverse classification of wearables, based on various factors, a discussion on wireless communication technologies, architectures, data processing aspects, and market status, as well as a variety of other actual information on wearable technology are provided.

TL;DR: In this paper, the authors reviewed the literature studies using CSE-CIC IDS-2018, UNSW-NB15, ISCX-2012, NSL-KDD and CIDDS-001 data sets, which are widely used to develop IDS systems.

TL;DR: A detailed survey of how the Edge and/or Cloud can be combined together to facilitate the task offloading problem is provided, with particular emphasis on the mathematical, artificial intelligence and control theory optimization approaches that can be used to satisfy the various objectives, constraints and dynamic conditions of this end-to-end application execution approach.

TL;DR: A Secured Privacy-Preserving Framework for smart agricultural UAVs is proposed and it is identified that the SP2F framework outperforms several state-of-the-art techniques in both non-blockchain and blockchain frameworks.

TL;DR: This survey conducts an in-depth analysis of popular IoT platforms from different application domains and defines a comprehensive evaluation framework that considers seven different technical comparison criteria to evaluate the different IoT platforms highlighting their distinguishing attributes on communications, security, and privacy.

TL;DR: In this paper, the authors proposed a federated learning approach for MEC-aided industrial Internet of Things (IIoT) networks, where the task offloading ratio, bandwidth allocation ratio, and transmit power were optimized using deep reinforcement learning (DRL) algorithm.

TL;DR: In this paper, the authors promote the idea that including semantic and goal-oriented aspects in future 6G networks can produce a significant leap forward in terms of system effectiveness and sustainability.

TL;DR: An algorithm based on simple online strategies that utilize an SDN controller with a global view of the network is proposed that guarantees transmission time-slot allocations for Scheduled Traffic while mitigating network congestion and ensures network stability and maximizing the flow admission to the network.

TL;DR: A fire image dataset collected by drones during a prescribed burning piled detritus in an Arizona pine forest is provided and a deep learning method is designed based on the U-Net up-Sampling and down-sampling approach to extract a fire mask from the video frames.

TL;DR: Performance evaluation results issued from Hyperledger Caliper and comparative analysis have proved the robustness and superiority of the proposed system in terms of security and privacy requirements, key features of blockchain-based healthcare systems, and performance metrics including various throughput and latency.

TL;DR: A network traffic prediction method based on SA (Simulated Annealing) optimized ARIMA, non-linear model BPNN and optimization algorithm SA can fully realize the potential of mining linear and non- linear laws of historical network traffic data, hence improving the prediction accuracy.

TL;DR: In this article, a novel intrusion detection approach for the IoT, through the adoption of a customised deep learning technique, is proposed, which utilizes a cutting-edge IoT dataset comprising IoT traces and realistic attack traffic, including denial of service, distributed denial of services, data gathering and data theft attacks.

TL;DR: In this paper, the main issues and constraints of resource allocation, signaling, practical implementation and security aspects of NOMA and its integration with 5G and upcoming wireless technologies are highlighted.

TL;DR: In-band network telemetry as discussed by the authors collects hop-by-hop network status information through business packets to achieve end-to-end visualization of network services, which has received extensive attention from academia and industry.

TL;DR: Wang et al. as mentioned in this paper proposed a dynamic scheduling method based on deep reinforcement learning (DRL), which adopted the proximal policy optimization (PPO) to find the optimal policy of the scheduling to deal with the dimension disaster of the state and action space caused by the increase of the problem scale.

TL;DR: This work surveys and classifies CCAs for 4G/5G cellular networks, and presents end-to-end CCAs that target a high throughput and a low latency over highly variable network links, and classify them according to the way they address the congestion control.

TL;DR: Powder is a city-scale, remotely accessible, end-to-end software defined platform being designed and built to address the need for experimentation at scale in real environments and provides advances in scale, realism, diversity, flexibility, and access.

TL;DR: In this paper, the authors summarized and analyzed the applications of blockchain and machine learning in industrial Internet of Things (IIoT) from three important aspects, i.e., consensus mechanism, storage and communication.

TL;DR: This work analyzed and identified that the SAKA-FC suffers from some severe vulnerabilities and presented an improved scheme to mitigate these problems while retaining its strengths, and compared with some state-of-the-art schemes.

TL;DR: In this paper, the authors explore the performance of reinforcement learning-based congestion control algorithms and present current problems with reinforcement learning based congestion control algorithm and outline challenges and trends related to learning based algorithms.

TL;DR: This paper proposes a new approach as a kangaroo-based intrusion detection system (KIDS), which is an SDN-based architecture for attack detection and malicious behaviors in the data plane, contributing to improved scalability and efficiency.

TL;DR: This work presents an in-depth analysis of attacks exploiting IEC–61850 substations and recent research efforts for detecting and preventing them, and presents an original taxonomy comprising design and evaluation aspects for substation-specific Intrusion Detection Systems.

TL;DR: This survey presents an extensive study, analysis and report of state-of-the-art works on effective traffic management including load balancing and energy-efficient routing, SDN control implementation and deployment architecture, controller security and optimal controller placement that affect traffic management.

TL;DR: In this article, a composite and efficient DDoS attack detection framework for 5G and B5G networks is proposed, which consists of a composite multilayer perceptron which was coupled with an efficient feature extraction algorithm.

TL;DR: A Software-Defined Network-based Anomaly Detection System (SDN-ADS) for edge computing-based system architecture for IoT networks, and a Trusted Authority for Edge Computing (TA-Edge) to ensure the trust of edge devices for data forwarding are proposed.

TL;DR: An energy efficient and trust based routing model is designed using proposed Exponentially-Ant Lion Whale Optimization (E-ALWO) algorithm to route the data packets to receiver using cluster head through cluster head.

TL;DR: A hierarchical packet byte-based CNN, called PBCNN, is proposed, where the first level extracts abstract features automatically from bytes in a packet in raw Pcap files, and the second level further constructs the representation from packets in a flow or session, to make full use of original data information.

TL;DR: This paper proposes one intelligent virtual resource allocation algorithm, labeled as Intell-UAV-5G, which is able to predict all possible connecting access nodes and continue the network service intelligently, and can minimize the time of service interruption, guaranteeing the service quality.

TL;DR: In this article, the authors proposed a two-layer anomaly-based network intrusion detection system (IO-IDS) based on Long Short-Term Memory (LSTM) classifier and OOVO technique for handling both frequent and infrequent network intrusions.

TL;DR: A comprehensive state-of-the-art survey of hybrid SDN from many different perspectives is presented in this paper, where the authors present an overview of the literature on hSDN.