Article
Multidisciplinary Sciences
Khlood Shinan, Khalid Alsubhi, Ahmed Alzahrani, Muhammad Usman Ashraf
Summary: This paper discusses the cybersecurity threats brought about by the development of the internet, particularly through cyberattacks using botnets. By evaluating the progress in botnet detection techniques, it highlights the potential of SDN in defending against botnet attacks.
Article
Computer Science, Hardware & Architecture
Segun Popoola, Bamidele Adebisi, Mohammad Hammoudeh, Haris Gacanin, Guan Gui
Summary: This paper investigates the vulnerability of IoT devices in Smart Home Networks to complex botnet attacks and examines the effectiveness of Stacked Recurrent Neural Network (SRNN) in classifying highly imbalanced network traffic data. The results show that SRNN outperforms RNN in all classification scenarios, offering better representation of discriminating features in highly imbalanced network traffic samples and demonstrating stronger capabilities in handling overfitting issues and generalization ability.
COMPUTERS & ELECTRICAL ENGINEERING
(2021)
Article
Chemistry, Multidisciplinary
Xiaodan Yan, Ke Yan, Meezan Ur Rehman, Sami Ullah
Summary: Smart health systems integrate sensor technology with the Internet of Things to monitor patients. However, communication between edge nodes and mobile users in mobile edge computing can be vulnerable to impersonation attacks. In this study, we propose a reinforcement learning approach for detecting impersonation attacks in medical and healthcare services, which outperforms traditional techniques in dynamic environments.
APPLIED SCIENCES-BASEL
(2022)
Article
Engineering, Civil
Wei-Yu Lin, Yun-Zhu Song, Bo-Kai Ruan, Hong-Han Shuai, Chih-Ya Shen, Li-Chun Wang, Yung-Hui Li
Summary: This paper introduces a decentralized RL-based method for efficient multi-intersection traffic signal control. By utilizing each lane as a node and introducing new rewards that consider temporal information, this method achieves at least a 9.5% improvement in average travel time compared to state-of-the-art methods.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
Article
Computer Science, Information Systems
Chirag Joshi, Ranjeet Kumar Ranjan, Vishal Bharti
Summary: This paper proposes a fuzzy logic-based feature engineering method for the detection and classification of Botnet. The method shows high accuracy on the CTU-13 dataset, but further testing and improvement on different datasets are needed.
JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES
(2022)
Article
Automation & Control Systems
Moemedi Lefoane, Ibrahim Ghafir, Sohag Kabir, Irfan-Ullah Awan
Summary: The deployment of Internet of Things devices is rapidly growing worldwide, making them an integral part of national infrastructure. However, their characteristics and limitations also make them attractive targets for hackers. This article proposes two pattern-based feature selection methods for a machine learning-based botnet detection system, which have shown improved performance and reduced computational cost.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2023)
Article
Computer Science, Information Systems
Segun I. Popoola, Bamidele Adebisi, Ruth Ande, Mohammad Hammoudeh, Aderemi A. Atayero
Summary: The study developed a memory-efficient DL method, LS-DRNN, leveraging the combined advantages of LAE, SMOTE, and DRNN, and evaluated its effectiveness using the Bot-IoT dataset. Results showed that the application of LAE and SMOTE methods significantly improved classification performance in minority classes, and the LS-DRNN model outperformed state-of-the-art models.
Article
Computer Science, Information Systems
Roger R. dos Santos, Eduardo K. Viegas, Altair O. Santin, Vinicius V. Cogo
Summary: In the past few years, machine learning techniques have been used for network-based intrusion detection. However, these proposed schemes do not effectively handle the changes in network traffic over time. This paper introduces a new intrusion detection model based on reinforcement learning that can support extended periods without model updates. By applying a machine learning scheme as a reinforcement learning task and using a transfer learning technique, the proposed model achieves similar accuracy rates to traditional detection schemes with significantly fewer computational resources.
IEEE TRANSACTIONS ON NETWORK AND SERVICE MANAGEMENT
(2023)
Article
Chemistry, Analytical
Pablo Velarde-Alvarado, Hugo Gonzalez, Rafael Martinez-Pelaez, Luis J. Mena, Alberto Ochoa-Brust, Efrain Moreno-Garcia, Vanessa G. Felix, Rodolfo Ostos
Summary: This paper addresses the problem of dataset scarcity for network intrusion detection and presents a framework for generating network traffic datasets. The performance of the classifiers is evaluated using machine learning algorithms, showing good overall performance.
Article
Computer Science, Information Systems
T. V. Ramana, M. Thirunavukkarasan, Amin Salih Mohammed, Ganesh Gopal Devarajan, Senthil Murugan
Summary: In recent infrastructures, the Internet of Things (IoT) is crucial for connecting various actuators and sensors, but its security remains a concern. Therefore, an ambient intelligence approach is proposed for intrusion detection system (IDS). By combining reinforcement learning and deep Q-neural network, a RL-DQN model is developed to enhance the decision performance of IDS in IoT.
COMPUTER COMMUNICATIONS
(2022)
Article
Computer Science, Information Systems
Mohd Anul Haq, Mohd Abdul Rahim Khan
Summary: This study developed two novel deep neural network models to detect and classify IoT botnet attacks, improving accuracy and efficiency in IoT environments.
CMC-COMPUTERS MATERIALS & CONTINUA
(2022)
Article
Computer Science, Artificial Intelligence
Saif Al-Mashhadi, Mohammed Anbar, Iznan Hasbullah, Taief Alaa Alamiedy
Summary: This study examines the abnormality of DNS traffic during the botnet lifecycle to extract significant enriched features, which are further analyzed using two machine learning algorithms. The output of two algorithms proposes a novel hybrid rule detection model approach. The experimental results show that the proposed approach has a 99.96% accuracy and a 1.6% false-positive rate, outperforming other state-of-the-art DNS-based botnet detection approaches.
PEERJ COMPUTER SCIENCE
(2021)
Article
Engineering, Electrical & Electronic
Hafsa Benaddi, Khalil Ibrahimi, Abderrahim Benslimane, Mohammed Jouhari, Junaid Qadir
Summary: This paper proposes a DRL-based IDS for network traffics using MDP and analyzes the IDS behavior through modeling the interaction between the IDS and attacker players. The proposed DRL-IDS outperforms existing models in terms of detection rate, accuracy, and false alarms reduction.
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY
(2022)
Article
Computer Science, Information Systems
Wai Weng Lo, Gayan Kulatilleke, Mohanad Sarhan, Siamak Layeghy, Marius Portmann
Summary: In this paper, we propose XG-BoT, an explainable deep graph neural network model for botnet node detection. The model comprises a botnet detector and an explainer for automatic forensics. XG-BoT detector effectively detects malicious botnet nodes, while the explainer highlights suspicious network flows and botnet nodes for automatic network forensics.
INTERNET OF THINGS
(2023)
Article
Computer Science, Artificial Intelligence
Hao Peng, Ruitong Zhang, Shaoning Li, Yuwei Cao, Shirui Pan, Philip S. Yu
Summary: This paper presents a novel reinforced, incremental, and cross-lingual social event detection architecture, FinEvent, which models social messages into heterogeneous graphs and uses reinforcement learning algorithm to select optimal aggregation thresholds. It addresses the challenges of ambiguous event features, dispersive text contents, and multiple languages in existing event detection methods for streaming social messages, thereby improving accuracy and generalization ability.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2023)
Article
Computer Science, Hardware & Architecture
Diana Laura Aguilar, Miguel Angel Medina-Perez, Octavio Loyola-Gonzalez, Kim-Kwang Raymond Choo, Edoardo Bucheli-Susarrey
Summary: The importance of understanding and explaining the classification results in AI applications has led to a shift towards explainable AI. This article presents an interpretable autoencoder based on decision trees for categorical data, offering natural explanations for experts. Experimental findings demonstrate its effectiveness as a top-ranked anomaly detection algorithm, outperforming other models.
IEEE TRANSACTIONS ON DEPENDABLE AND SECURE COMPUTING
(2023)
Article
Computer Science, Artificial Intelligence
Qiuyun Tong, Yinbin Miao, Jian Weng, Ximeng Liu, Kim-Kwang Raymond Choo, Robert H. H. Deng
Summary: In this paper, a Verifiable Fuzzy multi-keyword Search scheme with Adaptive security (VFSA) is proposed to address the challenges of achieving result verification and adaptive security in privacy-preserving fuzzy multi-keyword search. VFSA utilizes locality sensitive hashing, twin Bloom filters, and a graph-based keyword partition algorithm to achieve adaptive sublinear retrieval. The Merkle hash tree structure and adapted multiset accumulator are used to check the correctness and completeness of search results.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2023)
Article
Computer Science, Information Systems
Xinghua Li, Qiuyun Tong, Jinwei Zhao, Yinbin Miao, Siqi Ma, Jian Weng, Jianfeng Ma, Kim-Kwang Raymond Choo
Summary: Searchable encryption allows users to efficiently retrieve encrypted cloud data. However, most existing schemes only support exact keyword search, leading to false results due to typos or format inconsistencies. Fuzzy keyword search can avoid this, but suffers from low accuracy and efficiency. Additionally, these schemes often do not consider malicious cloud servers. To address these issues, we propose an efficient and verifiable ranked fuzzy multi-keyword search scheme, VRFMS. VRFMS utilizes locality-sensitive hashing, bloom filter, and TF-IDF to implement fuzzy keyword search and sort results. It also incorporates improved bi-gram keyword transformation and uses homomorphic MAC and random challenges for result verification. Security analysis and experiments demonstrate the security and efficiency of VRFMS in practical applications.
IEEE TRANSACTIONS ON SERVICES COMPUTING
(2023)
Article
Computer Science, Artificial Intelligence
Bilal Sowan, Tzung-Pei Hong, Ahmad Al-Qerem, Mohammad Alauthman, Nasim Matar
Summary: This paper proposes an ensemble approach called Ensemble Cluster Validity Index ECVI to determine the optimal number of clusters for unsupervised learning tasks. The proposed ECVI integrates and optimizes several clustering validity indices and is used as an input parameter for the k-means clustering algorithm, resulting in improved clustering results.
APPLIED INTELLIGENCE
(2023)
Review
Business
Leili Soltanisehat, Reza Alizadeh, Haijing Hao, Kim-Kwang Raymond Choo
Summary: Blockchain has the potential to transform healthcare systems as a secure and smart transaction system. This article conducts a systematic review of 64 articles on blockchain-based healthcare systems to answer key questions about its applications, technical aspects, and future research directions. The findings reveal that most proposed systems use private blockchain and Ethereum platforms, and the majority of authors are affiliated with research institutions in the USA and China. The article also discusses potential future directions such as integrating blockchain with AI and cloud computing.
IEEE TRANSACTIONS ON ENGINEERING MANAGEMENT
(2023)
Article
Computer Science, Theory & Methods
Jiayan Shen, Peng Zeng, Kim-Kwang Raymond Choo, Chengju Li
Summary: Electronic health records (EHRs) are stored, shared, and analyzed on cloud servers. A certificateless provable data possession (PDP) scheme is proposed for cloud-based EHRs, distributing multiple copies across different servers to ensure recoverability and resist copy-summation attack. EHRs are stored in ciphertext form to ensure authorized access, and a new data structure called map version marker table (MVMT) is designed for dynamic operations and traceability. Security and performance analyses confirm the practicality and security of the proposed scheme, assuming the intractability of the computational Diffie-Hellman problem.
IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY
(2023)
Article
Computer Science, Theory & Methods
Zuan Wang, Liang Zhang, Xiaofeng Ding, Kim-Kwang Raymond Choo, Hai Jin
Summary: In this paper, we propose DynPilot, a novel solution for privacy-preserving verifiable location-based skyline queries over dynamic and encrypted datasets. We design a ciphertext-based authenticated data structure (ADS) and store the digest of the raw dataset in the blockchain to motivate cloud updates. We also present an optimized version (DSV*-tree) for efficient queries. The security and complexity of our approach are analyzed and empirical evaluations demonstrate its utility.
IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY
(2023)
Article
Computer Science, Artificial Intelligence
Mohsen Jozani, Charles Zhechao Liu, Kim-Kwang Raymond Choo
Summary: Recommendation systems are widely used in promoting product visibility and sales, but research shows that they mainly benefit market superstars, which can be detrimental to niche products. This study uses social network analysis and econometric models to examine the impact of content-based filtering recommendation systems on demand distribution in mobile app markets. The analysis of two comprehensive panel datasets from App Store and Google Play suggests that these recommendation systems favor niche items and effectively boost the market's long tail. Additionally, the quality signals provided by recommendation systems can influence consumer decision-making processes and lead to demand spillover. These findings have important implications for developers and market operators in the highly competitive mobile app market.
DECISION SUPPORT SYSTEMS
(2023)
Article
Computer Science, Hardware & Architecture
Qi Feng, Debiao He, Min Luo, Xinyi Huang, Kim-Kwang Raymond Choo
Summary: In this paper, we propose an Efficient and Privacy-preserving Real-time Incentive system for CrowdsEnsing (EPRICE), designed to estimate the reliability of sensing data in a privacy-preserving setting. The theoretical analysis demonstrates that our proposed system achieves a high level of privacy-preserving for real-time reward distribution and supports practical privacy-preserving properties. The experimental findings show that our proposed EPRICE system significantly decreases the computation costs by three orders of magnitude compared with other competing schemes.
IEEE TRANSACTIONS ON COMPUTERS
(2023)
Article
Computer Science, Hardware & Architecture
Yi Ding, Fuyuan Tan, Ji Geng, Zhen Qin, Mingsheng Cao, Kim-Kwang Raymond Choo, Zhiguang Qin
Summary: This article focuses on the understanding and defense of universal adversarial example attack on image classification models. The differences between adversarial examples in two adversarial datasets and clean examples in ImageNet are analyzed, and the possibility of using these findings to resist adversarial attacks is explored. Experiments are conducted to determine the attack capability of the universal adversarial dataset on the classification model, providing a better understanding of adversarial defenses over pretrained classification models from an interpretation perspective.
IEEE TRANSACTIONS ON DEPENDABLE AND SECURE COMPUTING
(2023)
Article
Computer Science, Theory & Methods
Peiying Zhang, Ning Chen, Shibao Li, Kim-Kwang Raymond Choo, Chunxiao Jiang, Sheng Wu
Summary: Network Virtualization (NV) is an emerging technique to overcome network rigidity. Existing works perform unsatisfactorily in multi-domain physical network modeling. This study proposes using Federated Learning (FL) to model Virtual Network Embedding (VNE) and presents an architecture based on Horizontal Federated Learning (HFL) to address the challenges of dynamic and heterogeneous multi-domain physical networks. The superiority of HFL-VNE is proved through simulation experiments and comparisons with related works.
IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY
(2023)
Article
Computer Science, Hardware & Architecture
Yi Chen, Zoran Salcic, Hongxia Wang, Kim-Kwang Raymond Choo, Xuyun Zhang
Summary: This article proposes a joint distortion-based non-additive cost assignment method to reduce distortion drift and improve security in video steganography. Extensive experiments show that the proposed method achieves enhanced security and visual stego video quality.
IEEE TRANSACTIONS ON DEPENDABLE AND SECURE COMPUTING
(2023)
Article
Computer Science, Hardware & Architecture
Jun Zhou, Nan Wu, Yisong Wang, Shouzhen Gu, Zhenfu Cao, Xiaolei Dong, Kim-Kwang Raymond Choo
Summary: Federated learning is popular for addressing challenges caused by data islands. However, in edge computing, resource-constrained devices may compromise security. This paper proposes a differentially private federated learning model for edge computing, which uses anomaly detection and differential privacy technology to protect privacy and achieve a balance between security, efficiency, and accuracy.
IEEE TRANSACTIONS ON DEPENDABLE AND SECURE COMPUTING
(2023)
Article
Computer Science, Information Systems
Khalid M. O. Nahar, Mohammad Alauthman, Saud Yonbawi, Ammar Almomani
Summary: Social media networks play a vital role in our daily lives, but they also bring forth various issues. Cyberbullying, a global crisis, affects both the victims and society as a whole. This study proposes a methodology that utilizes supervised machine learning algorithms (SVM, Naive Bayes, Logistic regression, and random forest) to detect bullying, harassment, and hate-related texts, as well as unsupervised natural language processing techniques like latent Dirichlet allocation to predict associated topics. The classifiers are evaluated using accuracy, precision, recall, and F1 score, resulting in high accuracies ranging from 93.1% to 95%.
CMC-COMPUTERS MATERIALS & CONTINUA
(2023)
Article
Computer Science, Information Systems
Ammar Almomani, Mohammed Alweshah, Waleed Alomoush, Mohammad Alauthman, Aseel Jabai, Anwar Abbass, Ghufran Hamad, Meral Abdalla, Brij B. Gupta
Summary: Voice classification is essential for creating intelligent systems that assist with student exams, criminal identification, and security systems. The research aims to develop a system that can predict and classify gender, age, and accent, resulting in the proposal of a new system called Classifying Voice Gender, Age, and Accent (CVGAA). By incorporating rhythm-based features and using backpropagation and bagging algorithms, the voice recognition system's accuracy is significantly improved, with the Bagging algorithm achieving the highest accuracy of 55.39% in the voice common dataset and 78.94% in speech accent for age classification and accent accuracy.
CMC-COMPUTERS MATERIALS & CONTINUA
(2023)
Article
Computer Science, Hardware & Architecture
Zihang Zhen, Xiaoding Wang, Hui Lin, Sahil Garg, Prabhat Kumar, M. Shamim Hossain
Summary: In this paper, a blockchain architecture based on dynamic state sharding (DSSBD) is proposed to solve the problems caused by cross-shard transactions and reconfiguration. By utilizing deep reinforcement learning, the number of shards, block spacing, and block size can be dynamically adjusted to improve the performance of the blockchain. The experimental results show that the crowdsourcing system with DSSBD has better performance in terms of throughput, latency, balancing, cross-shard transaction proportion, and node reconfiguration proportion, while ensuring security.
JOURNAL OF NETWORK AND COMPUTER APPLICATIONS
(2024)
Article
Computer Science, Hardware & Architecture
Gabriel F. C. de Queiroz, Jose F. de Rezende, Valmir C. Barbosa
Summary: Multi-access Edge Computing (MEC) is a technology that enables faster task processing at the network edge by deploying servers closer to end users. This paper proposes the FlexDO algorithm to solve the DAG application partitioning and offloading problem, and compares it with other solutions to demonstrate its superior performance in various test scenarios.
JOURNAL OF NETWORK AND COMPUTER APPLICATIONS
(2024)
Article
Computer Science, Hardware & Architecture
Shahid Latif, Wadii Boulila, Anis Koubaa, Zhuo Zou, Jawad Ahmad
Summary: In the field of Industrial Internet of Things (IIoT), networks are increasingly vulnerable to cyberattacks. This research introduces an optimized Intrusion Detection System based on Deep Transfer Learning (DTL) for heterogeneous IIoT networks, combining Convolutional Neural Networks (CNNs), Genetic Algorithms (GA), and ensemble techniques. Through rigorous evaluation, the framework achieves exceptional performance and accurate detection of various cyberattacks.
JOURNAL OF NETWORK AND COMPUTER APPLICATIONS
(2024)
Article
Computer Science, Hardware & Architecture
Rongji Liao, Yuan Zhang, Jinyao Yan, Yang Cai, Narisu Tao
Summary: This paper proposes a joint control approach called STOP to guarantee user-perceived deadline using curriculum-guided deep reinforcement learning. Experimental results show that the STOP scheme achieves a significantly higher average arrival ratio in NS-3.
JOURNAL OF NETWORK AND COMPUTER APPLICATIONS
(2024)
Article
Computer Science, Hardware & Architecture
Miguel Rodriguez-Perez, Sergio Herreria-Alonso, J. Carlos Lopez-Ardao, Raul F. Rodriguez-Rubio
Summary: This paper presents an implementation of an active queue management (AQM) algorithm for the Named-Data Networking (NDN) architecture and its application in congestion control protocols. By utilizing the congestion mark field in NDN packets, information about each transmission queue is encoded to achieve a scalable AQM solution.
JOURNAL OF NETWORK AND COMPUTER APPLICATIONS
(2024)
Article
Computer Science, Hardware & Architecture
Angel Canete, Mercedes Amor, Lidia Fuentes
Summary: This paper proposes an energy-aware placement of service function chains of Virtual Network Functions (VNFs) and a resource-allocation solution for heterogeneous edge infrastructures. The solution has been integrated with an open source management and orchestration project and has been successfully applied to augmented reality services, achieving significant reduction in power consumption and ensuring quality of service compliance.
JOURNAL OF NETWORK AND COMPUTER APPLICATIONS
(2024)
Article
Computer Science, Hardware & Architecture
Sachin Kadam, Kaustubh S. Bhargao, Gaurav S. Kasbekar
Summary: This paper discusses the problem of estimating the node cardinality of each node type in a heterogeneous wireless network. Two schemes, HSRC-M1 and HSRC-M2, are proposed to rapidly estimate the number of nodes of each type. The accuracy and efficiency of these schemes are proven through mathematical analysis and simulation experiments.
JOURNAL OF NETWORK AND COMPUTER APPLICATIONS
(2024)
Article
Computer Science, Hardware & Architecture
Jean Nestor M. Dahj, Kingsley A. Ogudo, Leandro Boonzaaier
Summary: The launch of commercial 5G networks has opened up opportunities for heavy data users and highspeed applications, but traditional monitoring and evaluation techniques have limitations in the 5G networks. This paper presents a cost-effective hybrid analytical approach for detecting and evaluating user experience in real-time 5G networks, using statistical methods to calculate the user quality index.
JOURNAL OF NETWORK AND COMPUTER APPLICATIONS
(2024)
Article
Computer Science, Hardware & Architecture
Ali Nauman, Haya Mesfer Alshahrani, Nadhem Nemri, Kamal M. Othman, Nojood O. Aljehane, Mashael Maashi, Ashit Kumar Dutta, Mohammed Assiri, Wali Ullah Khan
Summary: The integration of terrestrial and satellite wireless communication networks offers a practical solution to enhance network coverage, connectivity, and cost-effectiveness. This study introduces a resource allocation framework that leverages local cache pool deployments and non-orthogonal multiple access (NOMA) to improve energy efficiency. Through the use of a multi-agent enabled deep deterministic policy gradient algorithm (MADDPG), the proposed approach optimizes user association, cache design, and transmission power control, resulting in enhanced energy efficiency and reduced time delays compared to existing methods.
JOURNAL OF NETWORK AND COMPUTER APPLICATIONS
(2024)
Article
Computer Science, Hardware & Architecture
Wu Chen, Jiayi Zhu, Jiajia Liu, Hongzhi Guo
Summary: With advancements in technology, large-scale drone swarms will be widely used in commercial and military fields. Current application methods are mainly divided into autonomous methods and controlled methods. This paper proposes a new framework for global coordination through local interaction.
JOURNAL OF NETWORK AND COMPUTER APPLICATIONS
(2024)
Article
Computer Science, Hardware & Architecture
Peiying Zhang, Zhihu Luo, Neeraj Kumar, Mohsen Guizani, Hongxia Zhang, Jian Wang
Summary: With the development of Industry 5.0, the demand for network access devices is increasing, especially in areas such as financial transactions, drone control, and telemedicine where low latency is crucial. However, traditional network architectures limit the construction of low-latency networks due to the tight coupling of control and data forwarding functions. To overcome this problem, researchers propose a constraint escalation virtual network embedding algorithm assisted by Graph Convolutional Networks (GCN), which automatically extracts network features and accelerates the learning process to improve network performance.
JOURNAL OF NETWORK AND COMPUTER APPLICATIONS
(2024)
Review
Computer Science, Hardware & Architecture
P. Anitha, H. S. Vimala, J. Shreyas
Summary: Congestion control is crucial for maintaining network stability, reliability, and performance in IoT. It ensures that critical applications can operate seamlessly and that IoT devices can communicate efficiently without overwhelming the network. Congestion control algorithms ensure that the network operates within its capacity, preventing network overload and maintaining network performance.
JOURNAL OF NETWORK AND COMPUTER APPLICATIONS
(2024)
Article
Computer Science, Hardware & Architecture
Shunmugapriya Ramanathan, Abhishek Bhattacharyya, Koteswararao Kondepu, Andrea Fumagalli
Summary: This article presents an experiment that achieves live migration of a containerized 5G Central Unit module using modified open-source migration software. By comparing different migration techniques, it is found that the hybrid migration technique can reduce end-user service recovery time by 36% compared to the traditional cold migration technique.
JOURNAL OF NETWORK AND COMPUTER APPLICATIONS
(2024)
Article
Computer Science, Hardware & Architecture
Fatma Foad Ashrif, Elankovan A. Sundararajan, Rami Ahmad, Mohammad Kamrul Hasan, Elaheh Yadegaridehkordi
Summary: This article introduces the development and current status of authentication protocols in 6LoWPAN, and proposes an innovative perspective to fill the research gap. The article comprehensively surveys and evaluates AKA protocols, analyzing their suitability in wireless sensor networks and the Internet of Things, and proposes future research directions and issues.
JOURNAL OF NETWORK AND COMPUTER APPLICATIONS
(2024)
Article
Computer Science, Hardware & Architecture
Pranjal Kumar Nandi, Md. Rejaul Islam Reaj, Sujan Sarker, Md. Abdur Razzaque, Md. Mamun-or-Rashid, Palash Roy
Summary: This paper proposes a task offloading policy for IoT devices to a mobile edge computing system, aiming to balance device utility and execution cost. A meta heuristic approach is developed to solve the offloading problem, and the results show its potential in terms of task execution latency, energy consumption, utility per unit cost, and task drop rate.
JOURNAL OF NETWORK AND COMPUTER APPLICATIONS
(2024)