Article
Multidisciplinary Sciences
Raja Rajeswari Sethuraman, John Sanjeev Kumar Athisayam
Summary: Opinion mining, driven by the growth of social media, has become a notable task in analyzing customer reviews for decision-making. To handle the high-dimensional text data, an improved gain ratio method is used to select top-ranking features, evaluated by a Nave Bayes classifier with kernel density function. This classifier, utilizing kernel density estimation, offers higher accuracy in various benchmark datasets.
ARABIAN JOURNAL FOR SCIENCE AND ENGINEERING
(2021)
Article
Computer Science, Hardware & Architecture
Laurens D'hooge, Miel Verkerken, Tim Wauters, Bruno Volckaert, Filip De Turck
Summary: The intrusion detection field is increasingly adopting newer datasets with substantial increases in both height and width, geared towards evaluation by machine learning methods. The feature sets are primarily statistics derived from packets or flows, leading to significant bloat in the datasets due to overinclusiveness. The proposed hybrid feature selection mechanism aims to identify dominant feature sets hierarchically using statistical testing, resulting in improved effective and efficient use of the datasets.
Article
Computer Science, Theory & Methods
Anita Shiravani, Mohammad Hadi Sadreddini, Hassan Nosrati Nahook
Summary: Due to the growth of the Internet, network attacks have increased, making network security and intrusion detection systems crucial. This paper introduces a new method for selecting effective features in intrusion detection based on fuzzy numbers and correlation-based scoring methods. The proposed method eliminates inefficient features and reduces data dimensions by defining the number of features as a fuzzy number and expressing the heuristic function as a triangular fuzzy number membership function. Experimental results show that the proposed method selects fewer features than conventional methods with higher detection rates.
JOURNAL OF BIG DATA
(2023)
Article
Computer Science, Hardware & Architecture
Heather Lawrence, Uchenna Ezeobi, Orly Tauil, Jacob Nosal, Owen Redwood, Yanyan Zhuang, Gedare Bloom
Summary: This article introduces the CUPID dataset, which aims to address the limitations of existing datasets in network intrusion detection research. The CUPID dataset includes human-generated traffic with accurate labels, providing a valuable resource for training and testing machine learning algorithms used in network intrusion detection systems.
JOURNAL OF SYSTEMS ARCHITECTURE
(2022)
Article
Computer Science, Artificial Intelligence
Vitali Herrera-Semenets, Lazaro Bustio-Martinez, Raudel Hernandez-Leon, Jan van den Berg
Summary: The research proposed a novel feature selection algorithm for intrusion detection scenarios, which reduces the dimensionality of the training data set by using qualitative information provided by multiple feature selection measures, achieving greater efficacy than other feature selection algorithms for intrusion detection purposes. Future research should continue to improve the algorithm.
KNOWLEDGE-BASED SYSTEMS
(2021)
Article
Multidisciplinary Sciences
Kezhou Ren, Yifan Zeng, Zhiqin Cao, Yingchao Zhang
Summary: This paper presents a network intrusion detection model based on RFE feature extraction and deep reinforcement learning. The model improves the efficacy of intrusion detection systems through feature selection and deep reinforcement learning, and demonstrates good performance in experiments.
SCIENTIFIC REPORTS
(2022)
Article
Computer Science, Information Systems
Youseef Alotaibi, Muhammad Noman Malik, Huma Hayat Khan, Anab Batool, Saif ul Islam, Abdulmajeed Alsufyani, Saleh Alghamdi
Summary: This study analyzes the characteristics of suggestions and presents a suggestion mining extraction process using the XGBoost classifier to classify suggestive sentences from online customer reviews. The results demonstrate that the XGBoost classifier performs well in identifying online reviews, with suggestion keywords and phrases being the predominant features for suggestion extraction.
CMC-COMPUTERS MATERIALS & CONTINUA
(2021)
Article
Computer Science, Information Systems
Bayi Xu, Lei Sun, Xiuqing Mao, Ruiyang Ding, Chengwei Liu
Summary: In this study, a novel intrusion detection system is proposed to efficiently detect network anomalous traffic in IoT devices using machine learning techniques. By employing feature selection and data oversampling, the detection performance of the model is optimized, and the effectiveness of the proposed method is validated through experiments.
Article
Computer Science, Information Systems
Sydney Mambwe Kasongo
Summary: In recent years, advances in technologies such as cloud computing, vehicular networks systems, and the Internet of Things (IoT) have led to a spike in the amount of information transmitted through communication infrastructures. Consequently, attackers have increased their efforts to exploit vulnerabilities in network systems. Therefore, it is crucial to enhance the security of these network systems. This study implements an IDS framework using Machine Learning techniques and evaluates its performance using benchmark datasets.
COMPUTER COMMUNICATIONS
(2023)
Article
Computer Science, Theory & Methods
Dylan Chou, Meng Jiang
Summary: This survey presents the challenges faced by data-driven network intrusion detection, including the authenticity and representativeness of datasets. Trends in the past decade are analyzed, and future directions are proposed, including the application of NID in cloud-based environments, designing scalable models for large network data, and collecting labeled datasets from real-world networks.
ACM COMPUTING SURVEYS
(2022)
Article
Computer Science, Information Systems
Lianming Zhang, Kui Liu, Xiaowei Xie, Wenji Bai, Baolin Wu, Pingping Dong
Summary: The paper proposes a data-driven NIDS based on feature selection and deep learning, called FS-DL. FS-DL improves detection accuracy by enhancing data quality and reducing computational load. Experimental results demonstrate that FS-DL achieves better detection performance with only a small number of features, and it has been deployed in an SDN controller for online detection of abnormal traffic.
JOURNAL OF INFORMATION SECURITY AND APPLICATIONS
(2023)
Review
Computer Science, Artificial Intelligence
Javier Maldonado, Maria Cristina Riff, Bertrand Neveu
Summary: This paper presents a review of recent advances in wrapper feature selection techniques in the field of intrusion detection. It is difficult to determine the current level of research in this area due to the large number of published papers. By providing a classification taxonomy, evaluation metrics, and discussion on attack scenarios, this paper offers a comprehensive overview of the existing research, as well as identifies open challenges and new directions.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Computer Science, Artificial Intelligence
Dzelila Mehanovic, Dino Keco, Jasmin Kevric, Samed Jukic, Adnan Miljkovic, Zerina Masetic
Summary: This study migrates genetic algorithm-based feature selection methods to a MapReduce implementation suitable for parallelization on a high number of commodity hardware units, achieving significant practical and theoretical impact. The parallelization of genetic algorithm allows for randomness-enhanced feature selection, reducing overall data preprocessing time and leading to better feature selection, outperforming existing methods in practice.
NEURAL COMPUTING & APPLICATIONS
(2021)
Article
Automation & Control Systems
Xiaokang Zhou, Yiyong Hu, Wei Liang, Jianhua Ma, Qun Jin
Summary: The article introduces a VLSTM model to address imbalance and high-dimension issues in industrial big data, which significantly improves accuracy and reduces false positives in anomaly detection.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2021)
Article
Physics, Multidisciplinary
Mikolaj Komisarek, Marek Pawlicki, Rafal Kozik, Witold Holubowicz, Michal Choras
Summary: This study fills the research gap related to identifying and investigating valuable features in the NetFlow schema for effective machine-learning-based network intrusion detection. By applying feature selection techniques on five flow-based network intrusion detection datasets, an informative feature set has been established.
Article
Computer Science, Information Systems
Bashar A. Aldeeb, Mohammed Azmi Al-Betar, Norita Md Norwawi, Khalid A. Alissa, Mutasem K. Alsmadi, Ayman A. Hazaymeh, Malek Alzaqebah
Summary: This study investigates the application of the Intelligent Water Drops (IWD) metaheuristic algorithm to the university examination timetabling problem. A hybrid approach based on IWD and local search algorithm is proposed to improve the exploitation of IWD algorithm. Experimental results demonstrate that the proposed algorithm achieved the best results compared to other approaches in multiple datasets.
JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES
(2022)
Article
Computer Science, Information Systems
Rami Mustafa A. Mohammad
Summary: The digital revolution has led to a revolution in cybercrime, making digital forensic a pressing topic. This article proposes an Enhanced Multiclass Support Vector Machine (EMSVM) model to improve classification performance and support multi-class classification. The applicability of the model in analyzing incriminating digital evidence is investigated, showing promising results.
JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES
(2022)
Article
Computer Science, Information Systems
Mutasem K. Alsmadi, Ibrahim Almarashdeh
Summary: Fish classification is a widely studied problem in the fields of image segmentation, pattern recognition, and information retrieval. This study compares and evaluates various preprocessing methods, feature extraction techniques, and classifiers, and reviews the use of relevant databases. By collecting recent research works, it provides guidance for future research directions.
JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES
(2022)
Article
Computer Science, Artificial Intelligence
RamiMustafa A. Mohammad, Malak Aljabri, Menna Aboulnour, Samiha Mirza, Ahmad Alshobaiki
Summary: The study aims to classify the mortality rate of COVID-19 patients with underlying health conditions using machine learning models. The findings provide assistance to researchers and physicians in early identification of at-risk patients and making appropriate intensive care decisions.
APPLIED COMPUTATIONAL INTELLIGENCE AND SOFT COMPUTING
(2022)
Article
Computer Science, Information Systems
Malak Aljabri, Amal A. Alahmadi, Rami Mustafa A. Mohammad, Menna Aboulnour, Dorieh M. Alomari, Sultan H. Almotiri
Summary: Network security is becoming increasingly important due to unprecedented challenges. Analyzing firewall logs is difficult, but AI and ML can help. This study builds multiclass models using ML and DL to analyze firewall logs and classify actions in response to cyberattacks. Experimental results show that the proposed models significantly improve firewall classification rate.
Article
Computer Science, Information Systems
Malek Alzaqebah, Sana Jawarneh, Maram Alwohaibi, Mutasem K. Alsmadi, Ibrahim Almarashdeh, Rami Mustafa A. Mohammad
Summary: The BSO algorithm is a novel swarm intelligence algorithm that simulates the brainstorming process of humans. By introducing a new updating strategy and integrating the LAHC algorithm, the BSO algorithm shows better performance in terms of search and convergence speed compared to other algorithms based on experimental results.
JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES
(2022)
Article
Mathematical & Computational Biology
Malak Aljabri, Fahd Alhaidari, Rami Mustafa A. Mohammad, Dina H. Alhamed, Hanan S. Altamimi, Sara Mhd. Bachar Chrouf
Summary: This study examined the use of machine learning and deep learning models to detect malicious websites, performed feature engineering and analysis on a dataset, with results showing Naive Bayes as the best model for this task.
COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE
(2022)
Article
Computer Science, Information Systems
Osama A. M. Khashan, Nour M. Khafajah, Waleed Alomoush, Mohammad Alshinwan, Sultan Samer Atawneh, Mutasem K. K. Alsmadi
Summary: Securing multimedia data on disk drives is a major concern due to their increasing volumes and security flaws. Existing cryptographic schemes have limitations in terms of computational costs and flexibility. Dynamic encryption file systems can mitigate these limitations by automating encryption operations with higher security. However, most current cryptographic file systems overlook the unique features of multimedia data and vulnerabilities in key management and multi-user sharing.
Article
Computer Science, Information Systems
Farah Shahid, Atif Mehmood, Rizwan Khan, Ahmad AL Smadi, Muhammad Yaqub, Mutasem K. Alsmadi, Zhonglong Zheng
Summary: This paper proposes two methods to address the issue of missing values in wind power forecasting and builds a hybrid wind energy forecasting system. The experimental results show that the use of PkNN algorithm integrated with regression-based Convolutional LSTM is more efficient in prediction compared to other deep neural network models.
JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES
(2023)
Review
Computer Science, Information Systems
Malak Aljabri, Hanan S. Altamimi, Shahd A. Albelali, Maimunah Al-Harbi, Haya T. Alhuraib, Najd K. Alotaibi, Amal A. Alahmadi, Fahd Alhaidari, Rami Mustafa A. Mohammad, Khaled Salah
Summary: The digital world has made significant advancements in recent years, especially on the Internet, where most of our activities now take place. However, this progress has also led to a rising risk of cyberattacks, particularly through the use of malicious URLs. These URLs trick inexperienced users into giving away sensitive information, resulting in billions of dollars in losses each year. This paper provides an extensive literature review on the techniques used to detect malicious URLs using machine learning models, addressing the limitations, detection technologies, feature types, and datasets used. Additionally, the paper highlights the lack of studies on detecting malicious Arabic websites and suggests directions for future research. Finally, the paper presents challenges that can impact the quality of malicious URL detectors, along with potential solutions.
Article
Computer Science, Information Systems
Mutasem K. Alsmadi, Ghaith M. Jaradat, Malek Alzaqebah, Ibrahim ALmarashdeh, Fahad A. Alghamdi, Rami Mustafa A. Mohammad, Nahier Aldhafferi, Abdullah Alqahtani
Summary: Timetabling problem is an important step in raising industrial productivity, and the Particle Swarm Optimization (PSO) algorithm has been proven effective in solving such problems. This research paper proposes an enhanced hybrid dynamic adaptive PSO algorithm for sports timetabling, which has shown a robust and consistent performance in generating feasible timetables within a reasonable computational time.
CMC-COMPUTERS MATERIALS & CONTINUA
(2022)
Article
Computer Science, Information Systems
Manal Mohamed Alhejazi, Rami Mustafa A. Mohammad
Summary: The Internet of Things (IoT) has the potential to significantly improve our lifestyle, but also comes with serious risks. To enhance IoT security, the focus has turned to blockchain as an innovative technique for securing IoT networks and data sharing. Blockchain's decentralization and tamperproof features have proven to be effective and promising for IoT security.
INFORMATION SECURITY JOURNAL
(2022)