Article
Computer Science, Information Systems
Shalli Rani, Himanshi Babbar, Gautam Srivastava, Thippa Reddy Gadekallu, Gaurav Dhiman
Summary: Currently, there are trillions of IoT devices in use, and even more are expected to join IoT networks in the future. These devices generate a massive amount of data, which needs to be transmitted securely over the network. However, as the number of interconnected devices increases, there are challenges such as response time, bandwidth constraints, and scalability in network design. To overcome these challenges, a distributed framework that brings computing and storage resources closer to endpoints is proposed, combining the strengths of SDNs and blockchain technology. Experimental analysis showed a 12.75% improvement in performance compared to baseline methodologies.
IEEE INTERNET OF THINGS JOURNAL
(2023)
Article
Green & Sustainable Science & Technology
Hani Alshahrani, Attiya Khan, Muhammad Rizwan, Mana Saleh Al Reshan, Adel Sulaiman, Asadullah Shaikh
Summary: The Industrial Internet of Things (IIoT) is the use of IoT in industrial management, linking and synchronizing machines and devices through software programs and third platforms to improve productivity. Despite the benefits, security remains a major concern due to the lack of reliable security mechanisms and the magnitude of security features. Attacks exploiting vulnerabilities in IIoT networks have caused financial losses, reputational damage, and theft of important information. This paper proposes an SDN-based framework with machine learning techniques for intrusion detection in an industrial IoT environment, achieving an accuracy of 99.7% in detecting attacks.
Article
Computer Science, Information Systems
Ernando Batista, Gustavo Figueiredo, Cassio Prazeres
Summary: The Internet of Things enables the coordination and orchestration of numerous physical and virtual objects connected to the Internet. This paper proposes a solution for load balancing in IoT applications using Software-Defined Networks. It addresses the challenges posed by unstable network infrastructure and processing overload on IoT devices.
JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES
(2022)
Article
Computer Science, Information Systems
Tongyang Xu
Summary: This study explores a waveform-defined security framework that differs fundamentally from traditional physical-layer security techniques. The framework is not dependent on channel conditions and is more reliable, preventing eavesdroppers from correctly identifying signal formats. By investigating three impact factors, an optimal WDS waveform pattern is obtained. The feasibility of integrating the framework into existing communication systems with minimal computational complexity is successfully demonstrated through experiments.
IEEE INTERNET OF THINGS JOURNAL
(2022)
Article
Computer Science, Information Systems
Christian Miranda Moreira, Georges Kaddoum, Jung-Yeon Baek, Bassant Selim
Summary: A task allocation framework is proposed for hierarchical software-defined fog virtual radio access networks (v-RANs) using enhanced ant colony optimization (ACO) and max-min algorithm to efficiently determine the optimal path for BBU task allocation management, minimizing transmission time for parallel task execution scheduling. Experimental results show that the approach reduces queue delay by 98.38% and 98.82% compared to the round-robin (RR) algorithm and least connection technique (LCT) respectively.
IEEE INTERNET OF THINGS JOURNAL
(2021)
Article
Engineering, Multidisciplinary
Hamoud H. Alshammari
Summary: In overpopulated nations, the need for medical treatment is increasing along with the population; healthcare difficulties are becoming more common. The population's need for high-quality care is growing despite decreasing treatment costs. This study recommends a real-time remote patient monitoring system based on the Internet of Things (IoT) to assure the accuracy of vital real-time signals.
ALEXANDRIA ENGINEERING JOURNAL
(2023)
Article
Computer Science, Information Systems
Prabhakar Krishnan, Kurunandan Jain, Rajkumar Buyya, Pandi Vijayakumar, Anand Nayyar, Muhammad Bilal, Houbing Song
Summary: In this study, we propose a software-defined framework that enhances network intrusion detection systems by utilizing manufacturer usage description (MUD) in IoT networks. By utilizing the concept of digital twins and software-defined networking, we improve the security and compliance of Industrial IoT environments. Evaluation results demonstrate that our solution outperforms existing approaches in terms of attack detection accuracy, predicting security incidents, response time, and resource usage.
IEEE INTERNET OF THINGS JOURNAL
(2022)
Article
Computer Science, Information Systems
Manasha Saqib, Bhat Jasra, Ayaz Hassan Moon
Summary: IoT is a vast heterogeneous network that provides digital services for smart city applications. Ensuring communication security is crucial when accessing these services remotely. Both entity and message authentication are important for this purpose. While mutual authentication between subscribers and gateway nodes has received attention, there is still a need to improve mutual authentication between gateway nodes and IoT sensor nodes.
JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES
(2022)
Article
Computer Science, Information Systems
Mohana Priya Pitchai, Manikandan Ramachandran, Fadi Al-Turjman, Leonardo Mostarda
Summary: The study proposes an intelligent framework for secure transportation in Internet of Vehicles, integrating software-defined networking with cryptographic and machine learning algorithms. The framework achieves better attack detection accuracy with less delay, but is not compared with existing methods.
CMC-COMPUTERS MATERIALS & CONTINUA
(2021)
Article
Automation & Control Systems
Jalal Bhayo, Syed Attique Shah, Sufian Hameed, Awais Ahmed, Jamal Nasir, Dirk Draheim
Summary: The Internet of Things (IoT) is a complex and diverse network that is vulnerable to various security threats, especially DDoS attacks. Integrating Software Defined Networking (SDN) with IoT has emerged as a promising approach for enhancing security. Machine learning-based security frameworks offer a solution to scrutinize the behavior of IoT devices and detect DDoS attacks. In this study, a machine learning-based approach is used to detect DDoS attacks in an SDN-WISE IoT controller, achieving high accuracy rates.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2023)
Article
Computer Science, Artificial Intelligence
Murtaza Cicioglu, Ali Calhan
Summary: Software-defined networking (SDN) is a flexible paradigm that provides isolation of control and data planes, proposes control mechanisms and network programmability, and offers new solutions to traditional network infrastructure issues. In wireless communication, SDN offers hardware and vendor-independent software for routing protocols. This study proposes a machine learning-assisted routing algorithm for software-defined wireless networks, which uses historical network parameters to make real-time routing decisions and achieves better performance compared to the traditional Dijkstra algorithm.
NEURAL COMPUTING & APPLICATIONS
(2023)
Article
Automation & Control Systems
Michele Amoretti, Riccardo Pecori, Yanina Protskaya, Luca Veltri, Francesco Zanichelli
Summary: This article proposes a novel communication framework based on MQTT broker bridging for dynamic interoperability and information flow control in industrial IoT scenarios. Through implementation and evaluation on a small-scale IIoT testbed, it is proven to have linear time complexity and minimal overhead compared to standard MQTT brokers.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2021)
Article
Computer Science, Information Systems
Euijong Lee, Young-Duk Seo, Young-Gab Kim
Summary: This study proposes a self-adaptive software framework with master-slave architecture-based finite-state machine modeling for IoT systems. Model checking and cache-based mechanism are applied to achieve dynamic environmental adaptation and efficiency. Empirical evaluation and example application demonstrate the efficiency and practical usability of the proposed framework with runtime verification.
IEEE INTERNET OF THINGS JOURNAL
(2022)
Article
Computer Science, Information Systems
Camilo Lozoya, Jose Miguel Diaz, Cesar Rodriguez-Esqueda, Claudia Prieto-Resendiz, Alberto Aguilar-Gonzalez
Summary: This paper presents an embedded software development framework for IoT devices that improves efficiency and reliability, shortens learning curves and module validation time.
Article
Computer Science, Information Systems
Niloy Saha, Samaresh Bera, Sudip Misra
Summary: This paper proposes a traffic-aware QoS routing scheme in SDN-based IoT networks, utilizing both delay-sensitive and loss-sensitive routing strategies to maximize network performance. By employing a greedy algorithm to compute optimal forwarding paths and deploying flow rules at forwarding devices, the proposed scheme significantly reduces end-to-end delay and QoS violations. Extensive simulations demonstrate the scheme's effectiveness in satisfying QoS requirements for different types of flows, outperforming existing schemes in terms of reducing QoS violations.
IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTING
(2021)
Article
Automation & Control Systems
Li Yang, Abdallah Shami
Summary: With the increasing data generation speed in IoT systems, the application of machine learning and automated machine learning techniques has become vital for effective data analytics. This paper provides a review of existing methods in model selection, tuning, and updating procedures in the field of AutoML, aiming to identify optimal solutions for applying ML algorithms to IoT data analytics. A case study is conducted to demonstrate the application of AutoML to IoT anomaly detection, and the challenges and research directions in this domain are discussed and classified.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2022)
Article
Automation & Control Systems
Elena Uchiteleva, Serguei L. Primak, Marco Luccini, Ahmed Refaey Hussein, Abdallah Shami
Summary: This study introduces a novel approach for modeling multivariate time series in nonstationary industrial IoT environments, aiming to accurately predict industrial processes while reducing computational and communication overhead.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2022)
Article
Automation & Control Systems
Li Yang, Abdallah Shami
Summary: Industry 5.0 aims to maximize collaboration between humans and machines, with machines automating repetitive tasks and humans handling creative tasks. This article proposes a novel multistage automated network analytics framework for concept drift adaptation in IIoT systems, which includes dynamic data preprocessing, drift-based dynamic feature selection, dynamic model learning and selection, and window-based weighted probability averaging ensemble model. Experimental results on public IoT datasets demonstrate that this framework outperforms state-of-the-art methods for IIoT data stream analytics.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2023)
Article
Engineering, Electrical & Electronic
Sara Zimmo, Abdallah Moubayed, Ahmed Refaey Hussein, Abdallah Shami
Summary: The deployment of mobile systems is facing challenges due to the lack of licensed bands, affecting network capacity and quality of service. A proposed solution using time-domain virtualization and a scheduling algorithm successfully meets different use cases' QoS requirements and improves throughput.
INTERNATIONAL JOURNAL OF COMMUNICATION SYSTEMS
(2023)
Article
Computer Science, Information Systems
Abdallah Moubayed, Dimitrios Michael Manias, Abbas Javadtalab, Mahdi Hemmati, Yuren You, Abdallah Shami
Summary: The growth of mobile broadband, fixed broadband, and Internet of Things devices has made 5G networks a reality. The increased demand for services and surge in internet usage due to the COVID-19 pandemic further emphasizes the need for flexible 5G networks. Optical Transport Networks (OTN) have been proposed as a promising supporting technology for 5G networks at the transport level. However, deploying OTNs in 5G networks presents challenges in terms of control, management, orchestration, and security.
PHOTONIC NETWORK COMMUNICATIONS
(2023)
Editorial Material
Computer Science, Information Systems
Nur Zincir-Heywood, Robert Birke, Elias Bou-Harb, Giuliano Casale, Khalil El-Khatib, Takeru Inoue, Neeraj Kumar, Hanan Lutfiyya, Deepak Puthal, Abdallah Shami, Natalia Stakhanova, Farhana Zulkernine
Summary: Machine learning and artificial intelligence can enhance operations and management of information technology and communication by utilizing vast amounts of data flows.
IEEE TRANSACTIONS ON NETWORK AND SERVICE MANAGEMENT
(2022)
Editorial Material
Engineering, Electrical & Electronic
Abdallah Shami, Lyndon Ong
Summary: With the growth of IoT devices, managing and connecting them manually presents challenges, leading to the potential solution of zero touch networks (ZTNs). ZTNs rely on software-based modules instead of dedicated hardware and aim for machines to become more autonomous, enabling minimal human intervention in monitoring and remediation processes. As a result, ZTNs offer self-serving, self-fulfilling, and self-assuring operations.
IEEE COMMUNICATIONS MAGAZINE
(2023)
Article
Computer Science, Artificial Intelligence
Ibrahim Shaer, Abdallah Shami
Summary: Residential and industrial buildings consume a significant amount of energy, but their energy usage can be reduced by controlling their Heating, Ventilation, and Air Conditioning (HVAC) systems. A demand-based Ventilation (DCV) system considers indoor air quality and occupants' comfort to determine the operating times of ventilation systems. This paper proposes a hierarchical model for accurately predicting CO2 variations, which can act as a proxy estimator of occupancy changes and provide feedback for ventilation control improvement.
Article
Telecommunications
Dimitrios Michael Manias, Abbas Javadtalab, Joe Naoum-Sawaya, Abdallah Shami
Summary: As next-generation networks continue to develop, the importance of Optical Transport Networks (OTNs) in meeting the performance requirements of future networks becomes evident. These networks are characterized by their focus on data and the integration of artificial intelligence. The efficient and timely transportation of new data is crucial. This paper outlines the role of OTNs in future networking generations, discusses emerging OTN technologies, and explores the impact of intelligence on OTN management and orchestration. Challenges, opportunities for innovation, and a use case illustrating the impact of network dynamicity and demand uncertainty on OTN MANO decisions are also presented.
JOURNAL OF SENSOR AND ACTUATOR NETWORKS
(2023)
Article
Computer Science, Information Systems
Ibrahim Shaer, Abdallah Shami
Summary: This paper proposes the Correlation-based FL (CorrFL) approach to address the challenges faced by the Federated Learning paradigm, including model heterogeneity and unavailability of IoT nodes. CorrFL projects model weights to a common latent space and minimizes reconstruction loss while maximizing model correlation. Experimental results demonstrate that CorrFL outperforms the benchmark model in every evaluation criterion.
IEEE TRANSACTIONS ON NETWORK AND SERVICE MANAGEMENT
(2023)
Article
Computer Science, Software Engineering
Sulaiman Aburakhia, Abdallah Shami
Summary: Classical Predictive Maintenance (PdM) methods rely on supervised learning with labeled data, which can be limited in terms of size and type for training predictive maintenance models. The proposed Similarity-Based PdM (SB-PdM) software addresses this challenge by using similarity measures instead of supervised classification. Experimental results have shown the effectiveness of SB-PdM software in achieving high accuracy with moderate computational resources.
Proceedings Paper
Computer Science, Artificial Intelligence
Sulaiman Aburakhia, Tareq Tayeh, Ryan Myers, Abdallah Shami
Summary: This paper proposes a similarity-based framework for predictive maintenance of rotating machinery. It generates reference vibration signals for each operational state and uses statistical time analysis, FFT, and STFT to extract features. Three similarity metrics are used to measure the similarity between test signals and reference signals. Experimental results confirm the effectiveness of similarity-based approaches in achieving high accuracy with moderate computational requirements, and indicate that using FFT features with cosine similarity leads to better performance.
2022 5TH INTERNATIONAL CONFERENCE ON COMMUNICATIONS, SIGNAL PROCESSING, AND THEIR APPLICATIONS (ICCSPA)
(2022)
Proceedings Paper
Computer Science, Information Systems
Li Yang, Abdallah Shami, Gary Stevens, Stephen de Rusett
Summary: This article introduces a new ensemble IDS framework for the detection of malicious attacks in IoV. The framework determines the best model using machine learning methods and makes accurate decisions by combining confidence values, effectively detecting various types of network attacks.
2022 IEEE GLOBAL COMMUNICATIONS CONFERENCE (GLOBECOM 2022)
(2022)
Proceedings Paper
Computer Science, Information Systems
Dimitrios Michael Manias, Ali Chouman, Abdallah Shami
Summary: Data-driven approaches are promising solutions for efficient network performances. They don't rely on accurate models and provide flexibility in system parameters, making them feasible for learning-based algorithms in mobile wireless networks. This paper focuses on demonstrating a working system prototype of the 5G Core network and Network Data Analytics Function (NWDAF), and explores network-generated data to gain insights for future opportunities and works.
2022 IEEE GLOBAL COMMUNICATIONS CONFERENCE (GLOBECOM 2022)
(2022)
Proceedings Paper
Computer Science, Theory & Methods
Maryam Mohseni, Soodeh Nikan, Abdallah Shami
Summary: This paper conducts a deep-learning based analysis and forecasting of telecommunication traffic. The results show that the fully connected sequential network and one-dimensional convolutional neural network have comparable forecasting performance. However, the one-dimensional convolutional neural network is smaller with fewer parameters, resulting in less complexity and faster execution time.
2022 IEEE CANADIAN CONFERENCE ON ELECTRICAL AND COMPUTER ENGINEERING (CCECE)
(2022)