Article
Automation & Control Systems
Shahid Latif, Zil e Huma, Sajjad Shaukat Jamal, Fawad Ahmed, Jawad Ahmad, Adnan Zahid, Kia Dashtipour, Muhammad Umar Aftab, Muhammad Ahmad, Qammer Hussain Abbasi
Summary: The article proposes a lightweight dense random neural network for intrusion detection in the IoT and evaluates its performance on a new generation IoT security dataset. The findings demonstrate that the model achieves high attack detection accuracy in both binary class and multiclass classifications.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2022)
Article
Computer Science, Information Systems
Danish Javeed, Tianhan Gao, Muhammad Taimoor Khan
Summary: The Internet of Things (IoT) is a billion-dollar industry, but its prevalence makes it vulnerable to cyber attacks. Software-defined networks provide a single effective security solution to combat these threats, and algorithms can efficiently detect cyber threats and attacks while ensuring no additional burden on resource-constrained IoT devices.
Article
Computer Science, Information Systems
Isa Avci, Murat Koca
Summary: The rapid growth of IoT in smart buildings requires continuous evaluation of potential threats. In this paper, a novel algorithm is proposed to estimate DDoS attack risk factors and predict and manage cyber threats, achieving significant accuracy.
Article
Computer Science, Hardware & Architecture
Wenjuan Li, Yu Wang, Jin Li
Summary: Internet of Things (IoT) is crucial for creating smart environments like smart homes, but it is vulnerable to various attacks. To ensure security, a collaborative intrusion detection network (CIDN) is necessary. Leveraging blockchain and IPFS technology improves the filter's performance and scalability.
JOURNAL OF SYSTEMS ARCHITECTURE
(2022)
Article
Computer Science, Information Systems
Xu Chen, Liang Xiao, Wei Feng, Ning Ge, Xianbin Wang
Summary: The proliferation of DDoS attacks in IoT poses threats to security and system performance, and collaborative packet sampling can effectively detect and block such attacks.
IEEE INTERNET OF THINGS JOURNAL
(2022)
Article
Computer Science, Information Systems
Kalupahana Liyanage Kushan Sudheera, Dinil Mon Divakaran, Rhishi Pratap Singh, Mohan Gurusamy
Summary: The fast-growing IoT market has brought about a significant threat landscape, as attacks on IoT devices consist of multiple stages and are dispersed spatially and temporally. Adept, a distributed framework, is proposed to detect and identify individual attack stages in a coordinated attack through monitoring network traffic, mining correlated patterns, and employing machine learning. Extensive experiments demonstrate the effectiveness of the framework in attack-stage detection and identification.
IEEE INTERNET OF THINGS JOURNAL
(2021)
Article
Computer Science, Information Systems
Asmaa A. Elsaeidy, Abbas Jamalipour, Kumudu S. Munasinghe
Summary: Today's smart city infrastructure heavily relies on Internet of Things (IoT) technologies, which, while enabling service automation, also poses security risks. A hybrid deep learning model has been developed to detect replay and DDoS attacks in real life smart city platforms, demonstrating high accuracy rates on environmental, smart river, and smart soil datasets.
Article
Computer Science, Information Systems
Manisha Kamaldeep, Manisha Malik, Maitreyee Dutta
Summary: In the past decade, the number of Internet of Things (IoT) devices and networks has increased significantly, resulting in resource constraints on energy, memory, communication, and computation power, which often leads to neglect of security mechanisms in these networks. To address this issue, a novel data set called IoT-CIDDS was explored, consisting of 21 features and a single labeling attribute, to facilitate machine learning (ML)-based intrusion detection systems (IDS) for accurate detection of Distributed Denial-of-Service (DDoS) attacks. A feature engineering and ML framework was proposed to analyze the data set statistically and develop ML models to detect DDoS attacks in IoT-CIDDS. Experimental results showed that reducing features significantly improved the performance of ML-based IDS for detecting DDoS attacks in standardized IoT networks using 6LoWPAN stack.
IEEE INTERNET OF THINGS JOURNAL
(2023)
Review
Computer Science, Information Systems
Esra Altulaihan, Mohammed Amin Almaiah, Ahmed Aljughaiman
Summary: The Internet of Things (IoT) is a technology that connects physical and virtual objects through the Internet for data exchange. Despite its benefits, IoT also presents information security issues that need to be addressed. Protecting data and services in the IoT environment and identifying and mitigating threats are crucial.
Article
Computer Science, Interdisciplinary Applications
Alaa Q. Raheema
Summary: Internet of Things (IoT) has played a crucial role in various sectors, but it also faces security and privacy issues. In this research, sparse convolute network is used to analyze IoT intrusion threats and attacks, and train the network to identify and track attacks, especially Distributed Denial of Service (DDoS) attacks. The network is optimized using evolutionary techniques to detect regular, error, and intrusion attempts under different conditions. The sparse network minimizes intrusion involvement in IoT data transmission, and the effectiveness of the system is evaluated through experimental results and discussion.
INTERNATIONAL JOURNAL OF ONLINE AND BIOMEDICAL ENGINEERING
(2023)
Article
Computer Science, Information Systems
Zheng Wang, Bin Liu, JingZhao Chen, WeiHua Huang, Yong Hu
Summary: This paper investigates the defense strategy of the Internet of Things (IoT) under hacker attack and proposes a multi-detector detection system based on a zero-sum stochastic game framework. The system is able to detect multiple types of network attacks and chooses between multiple detectors according to a mixed Nash equilibrium strategy that considers both the detection cost and the detection effect.
JOURNAL OF INFORMATION SECURITY AND APPLICATIONS
(2023)
Article
Computer Science, Information Systems
Wenji He, Yifeng Liu, Haipeng Yao, Tianle Mai, Ni Zhang, F. Richard Yu
Summary: The Internet of Things (IoT) has been widely applied in our daily lives in recent years, but also poses challenges in network security, particularly in addressing DDoS attacks. Current DDoS defense mechanisms face limitations, so designing a machine learning-based in-network DDoS detection framework is necessary for addressing these challenges.
IEEE INTERNET OF THINGS JOURNAL
(2021)
Article
Business
Rana Faisal Hayat, Sana Aurangzeb, Muhammad Aleem, Gautam Srivastava, Jerry Chun-Wei Lin
Summary: Distributed denial of service (DDoS) attacks and botnet-based attacks are critical security vulnerabilities in IoT environments. This article proposes a multilevel DDoS mitigation approach using blockchain technology to protect IoT devices. The proposed framework achieves significant improvements in throughput, latency, and CPU utilization compared to existing methods.
IEEE TRANSACTIONS ON ENGINEERING MANAGEMENT
(2022)
Article
Computer Science, Information Systems
Rintaro Harada, Naotaka Shibata, Shin Kaneko, Kazuaki Honda, Jun Terada, Yota Ishida, Kunio Akashi, Toshiyuki Miyachi
Summary: We propose a novel distributed denial of service (DDoS) attack suppression system that reduces the discarding of normal traffic by controlling the priority of frames in a network. Experimental results demonstrate that our system effectively prevents the discarding of normal traffic and quickly blocks attack traffic.
Article
Green & Sustainable Science & Technology
Shatha Alharbi, Afraa Attiah, Daniyal Alghazzawi
Summary: The rising popularity of the Internet of Things (IoT) has brought attention to the security concerns of IoT networks, which lack intrinsic security mechanisms due to the limited capabilities of IoT devices. Research calls for the establishment of a scalable, decentralized, and adaptive defense system for IoT networks.
Article
Computer Science, Information Systems
Amjad Khan
Summary: Speech emotion recognition (SER) is a fresh field in natural language processing, but its accuracy is still a challenge. SER is crucial for real-time applications like human-robot interaction, behavior evaluation, and virtual reality. Cross-lingual SER is particularly important for diverse cultural and linguistic interactions. However, conventional SER approaches that use the same corpus for training and testing are not suitable for multi-lingual environments. This study proposes a cross-lingual emotion recognition approach using Urdu, Italian, English, and German, achieving promising results with 91.25% accuracy on the URDU dataset using random forest and XGBoost classifiers.
JOURNAL OF INFORMATION SCIENCE
(2023)
Article
Chemistry, Analytical
Rodrigo S. S. Astolfi, Daniel S. S. da Silva, Ingrid S. S. Guedes, Caio S. S. Nascimento, Robertas Damasevicius, Senthil K. K. Jagatheesaperumal, Victor Hugo C. de Albuquerque, Jose Alberto D. Leite
Summary: Finding new ways to analyze ankle injuries caused by the Anterior Talofibular Ligament (ATFL) through novel technologies is crucial for medical diagnosis. This study compares the ability of specialists to diagnose lateral tibial tuberosity advancement (LTTA) injury using computer vision analysis on magnetic resonance imaging (MRI). By utilizing image augmentation techniques and various feature extraction algorithms and classifiers, the method achieved a hit rate of 85.03% for cases with unclear morphologies, demonstrating a 22% increase over human expert-based analysis.
Article
Computer Science, Artificial Intelligence
Jaber Alyami, Amjad Rehman, Fahad Almutairi, Abdul Muiz Fayyaz, Sudipta Roy, Tanzila Saba, Alhassan Alkhurim
Summary: Early diagnosis of brain tumors is crucial for treatment planning and increasing patient survival rates. Manual diagnosis is difficult and prone to error, necessitating an automated brain tumor detection system. This research presents an efficient deep learning-based system using a deep convolutional network and salp swarm algorithm for brain tumor classification from MRI images. Preprocessing and data augmentation techniques are employed to enhance classification rate, and feature selection techniques are used to achieve optimal tumor classification accuracy.
COGNITIVE COMPUTATION
(2023)
Article
Computer Science, Interdisciplinary Applications
Shahzada Daud, Muti Ullah, Amjad Rehman, Tanzila Saba, Robertas Damasevicius, Abdul Sattar
Summary: This study utilized machine learning techniques to categorize online news articles and proposed the hyperparameter-optimized SVM method. Additionally, five other ML techniques were optimized and compared. The results showed that the optimized SVM model performed the best.
Article
Medicine, General & Internal
Virgilijus Uloza, Nora Ulozaite-Staniene, Tadas Petrauskas, Kipras Pribuisis, Tomas Blazauskas, Robertas Damasevicius, Rytis Maskeliunas
Summary: The aim of this study was to develop a universal-platform-based (UPB) application for estimating the Acoustic Voice Quality Index (AVQI) using different smartphones, and evaluate its reliability in voice quality measurement. The developed UPB Voice Screen application showed comparable results to a professional studio microphone, with almost perfect linear correlations. It demonstrated an acceptable level of precision in distinguishing between normal and pathological voices, making it a useful tool for voice assessment purposes.
JOURNAL OF CLINICAL MEDICINE
(2023)
Article
Computer Science, Information Systems
Mindaugas Vasiljevas, Robertas Damasevicius, Rytis Maskeliunas
Summary: Eye gaze interfaces enable users to control graphical user interfaces simply by looking at them, but using these interfaces can be demanding and lead to fatigue. To address these challenges, the authors propose a model based on biofeedback that allows for effective and sustainable control of computer interfaces using physiological signals. Experimental findings show that the proposed model effectively describes and explains performance dynamics during gaze control tasks, including subject variability, fatigue, and recovery.
Article
Telecommunications
Roseline Oluwaseun Ogundokun, Micheal Olaolu Arowolo, Robertas Damasevicius, Sanjay Misra
Summary: Recent advancements in blockchain and wireless communication infrastructures have made it possible to create blockchain-based systems that protect data integrity and enable secure information sharing. However, concerns about security and privacy hinder the widespread adoption of blockchain technology, particularly when it comes to sharing sensitive data. This study proposes the use of deep learning methods to detect phishing attacks in a blockchain transaction network, achieving high accuracy rates.
Article
Engineering, Multidisciplinary
Lukas Paulauskas, Andrius Paulauskas, Tomas Blazauskas, Robertas Damasevicius, Rytis Maskeliunas
Summary: Due to its engaging and mobile nature, virtual reality (VR) has been rapidly adopted in education and professional training. Augmented reality (AR) integrates VR with the real world, while mixed reality (MR) allows interaction with both digital and physical objects. This study focuses on designing and testing a VR system for kinaesthetic distance learning in a museum setting. The developed VR training program allows learners to interact with objects and perform tasks in a virtual environment, aiming to compare its effectiveness with other educational materials.
Article
Computer Science, Information Systems
Amjad Rehman, Tanzila Saba, Muhammad Mujahid, Faten S. Alamri, Narmine ElHakim
Summary: Parkinson's disease is a prevalent neurological disorder that poses a challenging task in early detection due to a shortage of trained neurologists. This study collected voice data from Parkinson's disease patients to investigate the diagnostic significance of speech abnormalities. By addressing the issue of imbalanced datasets using sampling techniques, a hybrid model achieved high accuracy, precision, recall, and f1 score in detecting Parkinson's disease.
Article
Medicine, General & Internal
Muhammad Mujahid, Amjad Rehman, Teg Alam, Faten S. Alamri, Suliman Mohamed Fati, Tanzila Saba
Summary: Alzheimer's disease is an incurable neurological disorder that leads to a gradual decline in cognitive abilities. Early detection and accurate diagnosis can significantly mitigate symptoms. Deep learning, with its automatic feature extraction and optimized training process, provides a promising approach for diagnosing the disease.
Article
Computer Science, Interdisciplinary Applications
Rytis Maskeliunas, Robertas Damasevicius, Tomas Blazauskas, Jakub Swacha, Ricardo Queiros, Jose Carlos Paiva
Summary: This paper highlights the untapped potential of PWAs in creating engaging and personalized learning experiences in programming education. The authors propose a Framework for Gamification in Programming Education (FGPE) that integrates PWAs with a gamified exercise selection model to provide adaptive learning experiences. The study examines the mobile user experience of FGPE PLE in different countries, showing promising results in revolutionizing programming education.
Article
Information Science & Library Science
Robertas Damasevicius, Ligita Zailskaite-Jakste
Summary: This paper analyzes the impact of the ongoing war in Ukraine on the productivity and collaboration networks of Ukrainian academics. The findings highlight the decline in diversity of international collaborations among Ukrainian researchers. The study emphasizes the necessity of international research collaboration in mitigating the detrimental effects of national crises and emergencies.
Article
Computer Science, Information Systems
Zohaib Ahmad, Tariq Mahmood, Teg Alam, Amjad Rehman, Tanzila Saba
Summary: This article introduces the echo state network (ESN) as an advanced reservoir computing technique for handling time-dependent data, and demonstrates its effectiveness in time series prediction tasks. It also presents the binary improved gravitational search algorithm (BIGSA) echo state network (BIGSA-ESN) as a hybrid model that enhances the generalization abilities of ESN by reducing redundant reservoir output features through feature selection. The results of experiments on benchmark time-series datasets and a real-world scenario illustrate the superiority of the proposed technique over conventional evolutionary methods.
Article
Computer Science, Information Systems
Amjad Rehman, Ali Raza, Faten S. Alamri, Bayan Alghofaily, Tanzila Saba
Summary: Osteoarthritis is a common joint disease causing deterioration and impacting millions worldwide. It develops over time from joint wear and tears, leading to degeneration of joint cartilage, bone-to-bone contact, stiffness, discomfort, and restricted movement. The condition not only affects physical abilities but can also lead to psychological distress. Early detection is crucial for improving quality of life. In this study, a model using advanced deep learning and machine learning techniques, including a novel transfer learning-based feature engineering technique CRK, was developed to diagnose osteoarthritis in knee X-ray images with high accuracy (99%). The model's performance was validated through hyperparameter optimization and k-fold-based cross-validation.
Article
Computer Science, Information Systems
Zaid Nidhal Khudhair, Ahmed Nidhal Khdiar, Nidhal K. El Abbadi, Farhan Mohamed, Tanzila Saba, Faten S. Alamri, Amjad Rehman
Summary: Color information is not useful for distinguishing important edges and features in many applications. A new method based on singular value decomposition is introduced to transform an RGB image into grayscale, allowing for flexibility in producing gray images with varying contrasts. This method preserves more color information and accurately captures the intensity values of the image compared to traditional grayscale conversion methods, resulting in loss of color information. It has been found to be the most efficient method when compared to a similar approach of converting color images to grayscale.