Article
Computer Science, Information Systems
Mohammed M. Alani, Lara Mauri, Ernesto Damiani
Summary: As the adoption of IoT devices increases rapidly, industrial applications of IoT devices gain further popularity. This paper presents a two-stage system for the detection and classification of cyber attacks based on machine learning, aiming to enhance the security of high-risk applications such as smart grids.
INTERNET OF THINGS
(2023)
Article
Automation & Control Systems
Mohammed M. Alani, Ali Ismail Awad
Summary: The Internet of Things (IoT) has become a driving paradigm in various applications, but its security vulnerabilities and threats have negative impacts on deployment and operation. This article presents an intelligent two-layer intrusion detection system for IoT, using machine learning techniques to handle flow and packet features and minimizing time overhead by selecting significant features for accurate intrusion detection.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2023)
Article
Mathematics
Nazia Butt, Ana Shahid, Kashif Naseer Qureshi, Sajjad Haider, Ashraf Osman Ibrahim, Faisal Binzagr, Noman Arshad
Summary: This paper proposes a novel solution for anomaly-based intrusion detection for smart home networks. The proposed solution uses feature selection and hyperparameter tuning and has been experimentally demonstrated to have significant performance improvement.
Article
Computer Science, Information Systems
Xin Sun, Zhijun Tang, Mengxuan Du, Chaoping Deng, Wenbin Lin, Jinshan Chen, Qi Qi, Haifeng Zheng
Summary: This paper proposes a transformer-based intrusion detection model and integrates 5G technology into the AMI system, presenting a hierarchical federated learning intrusion detection system to protect user privacy. Experimental results demonstrate that the proposed approach outperforms other methods in terms of intrusion detection accuracy and communication cost.
Article
Computer Science, Information Systems
Ghada Abdelmoumin, Danda B. Rawat, Abdul Rahman
Summary: Intrusion detection systems (IDSs) based on deep learning outperform those based on anomaly-based machine learning techniques in detecting intrusions in the Internet of Things (IoT). This article explores the use of optimization techniques to enhance the performance of single-learner AML-IDS models, such as PCA and 1-SVM, for efficient and scalable intrusion detection in IoT. Comparative analysis of AML-IDS models for IoT is presented in terms of performance and predictability.
IEEE INTERNET OF THINGS JOURNAL
(2022)
Article
Chemistry, Multidisciplinary
Shuo Shi, Yifan Si, Zihua Li, Shuo Meng, Shuai Zhang, Hanbai Wu, Chuanwei Zhi, Weng-Fu Io, Yang Ming, Dong Wang, Bin Fei, Haitao Huang, Jianhua Hao, Jinlian Hu
Summary: Developing intelligent wearable protection systems is highly important for human health engineering. We have developed an intelligent wearable filtration system (IWFS) using advanced nanotechnology and machine learning, which exhibits reliable filtration efficiency, low pressure drop, healthcare monitoring function, and man-machine interactive capability. The IWFS has a high particle filtration efficiency of 99%, bacteria protection efficiency of 100%, and low-pressure drop of 5.8 mmH2O. It also possesses healthcare monitoring function and man-machine interactive capability, enabling real-time data collection and voice command transmission.
Article
Chemistry, Multidisciplinary
Shuo Shi, Yifan Si, Zihua Li, Shuo Meng, Shuai Zhang, Hanbai Wu, Chuanwei Zhi, Weng-Fu Io, Yang Ming, Dong Wang, Bin Fei, Haitao Huang, Jianhua Hao, Jinlian Hu
Summary: Developing intelligent wearable protection systems is highly important for human health engineering. In this study, an intelligent wearable filtration system (IWFS) was developed using advanced nanotechnology and machine learning. The IWFS exhibited high particle filtration efficiency, low pressure drop, and healthcare monitoring function, along with man-machine interactive capability.
Article
Mathematics
Mohammad Hijji, Hikmat Yar, Fath U. Min Ullah, Mohammed M. Alwakeel, Rafika Harrabi, Fahad Aradah, Faouzi Alaya Cheikh, Khan Muhammad, Muhammad Sajjad
Summary: Nowadays, people prefer to use private transport due to its low cost, comfortable ride, and personal preferences, resulting in a reduction in the use of public transportation. However, the use of personal transport has led to numerous road accidents due to drivers' conditions such as drowsiness, stress, tiredness, and age. To address this issue, an efficient deep learning-assisted intelligent fatigue and age detection system (FADS) was proposed to detect and identify different states of the driver. The system outperformed state-of-the-art techniques in experiments conducted on custom and publicly available datasets.
Review
Energy & Fuels
Guangchun Ruan, Haiwang Zhong, Guanglun Zhang, Yiliu He, Xuan Wang, Tianjiao Pu
Summary: With recent dramatic breakthroughs, machine learning has shown great potential in upgrading the toolbox for power system optimization. Understanding the strengths and limitations of machine learning approaches is crucial in deciding when and how to deploy them to boost optimization performance. This paper focuses on the coordination between machine learning approaches and optimization models and evaluates how data-driven analysis can improve rule-based optimization.
CSEE JOURNAL OF POWER AND ENERGY SYSTEMS
(2021)
Article
Computer Science, Information Systems
Sugandh Seth, Kuljit Kaur Chahal, Gurvinder Singh
Summary: The study presents a unique ensemble framework for detecting different attack categories effectively. By ranking the detection ability of various base classifiers, a better attack detection rate is achieved.
Article
Energy & Fuels
Tong Yu, Kai Da, Zhiwen Wang, Ying Ling, Xin Li, Dongmei Bin, Chunyan Yang
Summary: The smart grid of the future requires the ability to intelligently detect and respond to cyberattacks. This study proposes an evolving intrusion detection model that uses the gray wolf algorithm to train artificial neural networks, achieving the smallest mean square error. This approach effectively addresses issues such as cyberattacks, failure forecast, and diagnosis in the smart grid energy sector.
FRONTIERS IN ENERGY RESEARCH
(2022)
Review
Engineering, Multidisciplinary
Sami Ben Slama
Summary: Smart Grid technology is efficient in solving energy demand, storage, and power transmission. The integration of IoT technology in Smart Grids is critical for digitization and efficient performance. Edge Computing addresses the challenge of big data in IoT by processing data close to linked sensors. This paper reviews edge computing solutions for the Smart Grid and discusses information/digital technologies and AI scheduling techniques in the Prosumer smart Grid.
AIN SHAMS ENGINEERING JOURNAL
(2022)
Review
Materials Science, Multidisciplinary
Hongsen Niu, Feifei Yin, Eun-Seong Kim, Wenxiao Wang, Do-Young Yoon, Cong Wang, Junge Liang, Yang Li, Nam-Young Kim
Summary: Intelligent perception refers to the ability of flexible sensors, with the assistance of artificial intelligence (AI)-driven brain, to achieve memory, learning, judgment, and reasoning about external information, similar to the human brain. Machine learning (ML) algorithms enable intelligent perception systems to match or even surpass human perception systems due to their superiority in data processing and intelligent recognition. However, the precision and fidelity of acquired data in these systems are inevitably affected by the dynamic and irregular surfaces that the built-in flexible sensors need to work on. In recent years, the integration of functional materials and innovative structures into flexible sensors has made progress in addressing these challenges, leading to accurate perception and reasoning in various scenarios with the help of ML algorithms. This review comprehensively discusses the representative materials and structures for constructing flexible sensors, summarizes the research progress of intelligent perception systems based on flexible sensors and ML algorithms, and highlights the potential for new opportunities in next-stage AI development at their intersection.
Article
Computer Science, Information Systems
Amir El-Ghamry, Ashraf Darwish, Aboul Ella Hassanien
Summary: Smart farming is an advanced approach to managing a farm, which involves monitoring crop health and productivity using technology and information. The Internet of Things enables smart farming by collecting and storing data, but also exposes it to cyber-attacks. Therefore, an intrusion detection system that can adapt to the challenges of IoT networks in agriculture is crucial.
INTERNET OF THINGS
(2023)
Review
Engineering, Industrial
Meng Zhang, Fei Tao, Ying Zuo, Feng Xiang, Lihui Wang, A. Y. C. Nee
Summary: Intelligent algorithms play a crucial role in smart manufacturing by providing optimal solutions to improve manufacturing processes. This paper comprehensively surveys and analyzes relevant literature to identify the top ten commonly used algorithms and studies their application issues and challenges. These findings are of great significance for the development and application of smart manufacturing.
JOURNAL OF MANUFACTURING SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
V. D. Ambeth Kumar, S. Sharmila, Abhishek Kumar, A. K. Bashir, Mamoon Rashid, Sachin Kumar Gupta, Waleed S. Alnumay
Summary: Postpartum haemorrhage (PPH) is a significant and potentially fatal complication of childbirth worldwide. This research proposes an automation system using wearable devices to predict the risk of PPH in pregnant women by measuring various parameters. Based on the predicted risk, medical attention is provided through an Internet of Things infrastructure.
NEURAL COMPUTING & APPLICATIONS
(2023)
Article
Engineering, Civil
Yibing Liu, Lijun Huo, Jun Wu, Ali Kashif Bashir
Summary: As city boundaries expand and vehicles increase, the transportation system faces increasing overload, which has negative effects on people's commutes and overall work and life. However, with the development of 6G-driven Intelligent Transportation Systems (ITS), it becomes possible to alleviate urban congestion. Existing solutions are limited in their ability to optimize traffic efficiently. Therefore, we propose the Direction Decide as a Service (DDaaS) scheme, which incorporates a novel three-layer service architecture, improved modeling and aggregation methods, and a dynamic traffic control algorithm to effectively reduce traffic congestion.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
Article
Engineering, Civil
Rashid Abbasi, Ali Kashif Bashir, Hasan J. Alyamani, Farhan Amin, Jaehyeok Doh, Jianwen Chen
Summary: This paper provides a comprehensive analysis of 3D Point-Cloud (3DPC) processing and learning in AV systems, highlighting its importance in smart mobility and autonomous driving, as well as the need to address open problems in this field.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
Article
Engineering, Civil
Yi Sun, Keping Yu, Ali Kashif Bashir, Xin Liao
Summary: This article focuses on the issue of protecting image privacy in intelligent transportation systems. It introduces a Rearrangement-Arnold Cat Map (R-ACM) algorithm and proposes an efficient Bit-level Image Encryption Algorithm (Bl-IEA) based on R-ACM. Experimental results demonstrate that Bl-IEA has a strong ability to resist different attacks, making it suitable for time-limited intelligent transportation applications.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
Review
Chemistry, Analytical
Usman Tariq, Irfan Ahmed, Ali Kashif Bashir, Kamran Shaukat
Summary: The emergence of IoT technology has brought both vast possibilities and new vulnerabilities to connected systems. Developing a secure IoT ecosystem requires a systematic approach to identify and mitigate security threats, with cybersecurity research playing a critical role. The primary challenge is defending against both known and unknown attacks, and concerns regarding connectivity, communication, and management protocols need to be addressed. This research paper provides a comprehensive review of current IoT security concepts, analyzing prevalent security concerns and establishing security goals for specific IoT use cases.
Article
Computer Science, Information Systems
Jingwei Liu, Weiyang Jiang, Rong Sun, Ali Kashif Bashir, Mohammad Dahman Alshehri, Qiaozhi Hua, Keping Yu
Summary: Electronic Medical Records (EMRs) are valuable research materials for AI and machine learning. Traditional centralized data sharing architectures cannot balance privacy and traceability effectively. Our proposed scheme using decentralized blockchain allows trackable anonymous remote healthcare data storing and sharing, providing efficient overall performance.
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
(2023)
Article
Green & Sustainable Science & Technology
Rashid Abbasi, Ali Kashif Bashir, Alaa Omran Almagrabi, Md Belal Bin Heyat, Ge Yuan
Summary: Future sustainable energy-efficient computing solutions in e-healthcare, smart cities, and intelligent robotics applications benefit from the internet of things and cloud computing. Reversible Data Hiding in Encrypted Images (RDHEI) is being used in 6G technology for privacy protection. In this research, a sustainable, energy-efficient, multi-MSB-based dynamic quadtree partition with enhanced Huffman coding is proposed, resulting in optimum embedding capacity.
SUSTAINABLE ENERGY TECHNOLOGIES AND ASSESSMENTS
(2023)
Article
Chemistry, Analytical
Himanshi Babbar, Shalli Rani, Dipak Kumar Sah, Salman A. Alqahtani, Ali Kashif Bashir
Summary: Predicting attacks in Android malware devices using machine learning for recommender systems-based IoT can be achieved by applying various machine-learning techniques. This study proposes an internet-based framework for predicting and recommending Android malware on IoT devices. The suggested system utilizes static analysis and the K-Nearest Neighbor machine-learning model, achieving a prediction rate of 93% in real-world applications to minimize energy utilization.
Article
Computer Science, Information Systems
Peng He, Chunhui Lan, Ali Kashif Bashir, Dapeng Wu, Ruyan Wang, Rupak Kharel, Keping Yu
Summary: In this article, a three-layer federated learning architecture is proposed to reduce training latency and improve efficiency in medical image classification while ensuring data privacy.
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
(2023)
Article
Computer Science, Hardware & Architecture
Yi Zhou, Jun Wu, Xi Lin, Ali Kashif Bashir, Yasser D. Al-Otaibi, Hansong Xu
Summary: Digital twin (DT) technology is increasingly used in the Internet of Vehicles environment, but efficiency and security remain major challenges. Existing research on efficient migration methods of DT models in the field of DT-based autonomous driving treats the migration process as a blackbox. This study proposes three different migration strategies for efficient migration of DT models between edge computing nodes, and evaluates their efficiency in terms of migration time using the autonomous driving simulation platform CARLA in different network environments. Additionally, the study analyzes potential security issues during the migration process and proposes corresponding defense methods against cyberattacks.
IEEE CONSUMER ELECTRONICS MAGAZINE
(2023)
Article
Engineering, Electrical & Electronic
Jiang Zhu, Jun Wu, Ali Kashif Bashir, Qianqian Pan, Wu Yang
Summary: This paper proposes a blockchain-empowered privacy-preserving federated learning method for remote sensing image classification, which can defend against encrypted model poisoning attacks. By using the methods of proof of accuracy and secure aggregation, the proposed scheme achieves high accuracy even in the presence of malicious attackers. Experimental results demonstrate the superiority of the scheme in defending against model poisoning attacks.
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2023)
Article
Telecommunications
Chintan Patel, Ali Kashif Bashir, Ahmad Ali AlZubi, Rutvij Jhaveri
Summary: Industrial Internet of Things (IIoT) aims to improve services in various industries. Security, especially authentication and access control, is a major challenge for IIoT. This paper presents a secure authentication scheme based on Elliptic Curve Cryptography (ECC) that is efficient, reliable, and trustworthy compared to existing schemes. The proposed scheme is evaluated based on communication cost, computation cost, and security index and shows superior performance.
DIGITAL COMMUNICATIONS AND NETWORKS
(2023)
Article
Engineering, Electrical & Electronic
Zihong Li, Yang Hong, Ali Kashif Bashir, Yasser D. Al-Otaibi, Jun Wu
Summary: With the widespread use of the intelligent Internet of Things (IoT) in beyond 5G, wireless federated learning (WFL) has gained attention for enabling knowledge sharing among distributed edge devices. However, existing WFL schemes face challenges under unstable wireless channel conditions, including parameter disturbance, low efficiency in traditional edge devices, and inability to optimize complex operations. To address these challenges, a software-defined GPU-CPU empowered efficient WFL architecture with embedding LDPC communication coding is proposed, which shows improved anti-interference ability and GPU-CPU acceleration during wireless transmission.
IEEE OPEN JOURNAL OF THE COMMUNICATIONS SOCIETY
(2023)
Article
Computer Science, Cybernetics
Ganesh Gopal Devarajan, Senthil Murugan Nagarajan, Sardar Irfanullah Amanullah, S. A. Sahaaya Arul Mary, Ali Kashif Bashir
Summary: Social networking websites are the best platforms for news dissemination, but they also lead to the spread of fake news. Traditional detection methods focus on content analysis, while current researchers explore the social features of news. We propose an AI-assisted fake news detection model using deep natural language processing. The model includes four layers: publisher layer, social media networking layer, enabled edge layer, and cloud layer. Our model achieves an average accuracy of 99.72% and an F1 score of 98.33%, outperforming existing methods, based on evaluation using three datasets (Buzzface, FakeNewsNet, and Twitter).
IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS
(2023)
Article
Telecommunications
Muhammad Ali Naeem, Yousaf Bin Zikria, Rashid Ali, Usman Tariq, Yahui Meng, Ali Kashif Bashir
Summary: This paper comprehensively discusses fog computing, Internet of Things (IoTs), and the issues of data security and dissemination in fog computing. Various caching schemes are proposed to address the problems in fog computing, and machine learning-based approaches for cache security and management are explored, as well as potential future research directions.
DIGITAL COMMUNICATIONS AND NETWORKS
(2023)
