Article
Mathematics
Iftikhar Ahmad, Qazi Emad Ul Haq, Muhammad Imran, Madini O. Alassafi, Rayed A. AlGhamdi
Summary: Intrusion detection in computer networks is important for communication and security domains, but remains a challenging task. This paper compares multiple techniques to develop a network intrusion detection system and proposes an AdaBoost-based approach. Experimental results show that the proposed method effectively detects different forms of network intrusions and achieves 99.3% accuracy on the UNSW-NB15 dataset.
Article
Computer Science, Interdisciplinary Applications
Santosh Kumar Sahu, Durga Prasad Mohapatra, Jitendra Kumar Rout, Kshira Sagar Sahoo, Ashish Kr Luhach
Summary: The study established a scalable framework for large-scale data processing and analytics, implemented, tuned, and evaluated popular classification methods using intrusion datasets, selected decision tree as the base classifier to study class imbalance issues.
Article
Mathematical & Computational Biology
Yue Li, Wusheng Xu, Wei Li, Ang Li, Zengjin Liu
Summary: This paper proposes a hybrid intrusion detection method that utilizes ADASYN and ID3 decision tree to improve the effectiveness of intrusion detection rate. The model based on ADASYN and ID3 decision tree achieves higher accuracy and lower false alarm rate, making it more suitable for intrusion detection tasks.
MATHEMATICAL BIOSCIENCES AND ENGINEERING
(2022)
Article
Chemistry, Analytical
Yifan Tang, Lize Gu, Leiting Wang
Summary: This paper examines the NSL-KDD dataset and proposes a Deep Stacking Network model to enhance network intrusion detection. Experimental results show that decision tree, k-nearest neighbors, deep neural network, and random forests models exhibit outstanding detection performance.
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, Artificial Intelligence
Mozamel M. Saeed
Summary: This study aims to improve the performance of classifiers in identifying signatures of unknown attacks and establishes a hybrid classifier model based on the evaluation of commonly used classifiers. A quantitative methodology was adopted to collect and interpret data, and the evaluation was conducted in virtual networked environments with traffic workloads. The study reveals that certain features make significant contributions to anomaly detection.
NEURAL COMPUTING & APPLICATIONS
(2022)
Article
Engineering, Multidisciplinary
Jianwei Liu, Yun Teng, Bo Shi, Xuefeng Ni, Weichu Xiao, Chao Wang, Hongli Liu
Summary: A hierarchical learning approach is proposed to address the imbalanced fastener sample detection issue on railways. By utilizing fastener localization, region classification, and decision tree analysis, the approach achieves high precision and recall rates in detecting fasteners.
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, Theory & Methods
Hongwei Ding, Leiyang Chen, Liang Dong, Zhongwang Fu, Xiaohui Cui
Summary: With the continuous emergence of various network attacks, ensuring network security has become increasingly important. This study proposes a tabular data sampling method to address the imbalanced learning problem caused by class imbalance. The method achieves balance by effectively undersampling normal samples and oversampling attack samples. Experimental results demonstrate excellent performance in terms of Accuracy, F1, AUC, and Recall.
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2022)
Article
Computer Science, Information Systems
Roger R. dos Santos, Eduardo K. Viegas, Altair O. Santin, Pietro Tedeschi
Summary: This paper proposes a new Federated Learning model for reliable network-based intrusion detection, which can improve the average false-positive and false-negative rates by up to 12% and 9.6% respectively without model updates, and further increase the false-positive rate by 13% while rejecting only 3.6% of events and demanding only 0.3% of events for model updates.
COMPUTERS & SECURITY
(2023)
Article
Computer Science, Information Systems
Ju-fu Cui, Hui Xia, Rui Zhang, Ben-xu Hu, Xiang-guo Cheng
Summary: The paper proposes an optimization scheme for GBDT to improve its detection precision and training efficiency, addressing issues such as imbalanced data and high dimensional data characteristics. The scheme includes using MSMOTE to address data imbalance, RFE-HCV to reduce data feature dimensionality, and FGS algorithm for parameter optimization efficiency. The experimental results show that the new scheme ensures data balance, eliminates redundant data features, and significantly improves parameter optimization efficiency.
COMPUTER COMMUNICATIONS
(2021)
Article
Computer Science, Information Systems
Cheolhee Park, Jonghoon Lee, Youngsoo Kim, Jong-Geun Park, Hyunjin Kim, Dowon Hong
Summary: As communication technology advances, concerns regarding network security have increased. Research on AI-based anomaly detection systems for network intrusion detection has been actively conducted. However, the problem of data imbalance still exists, affecting the accuracy of network threat detection. In this study, we propose a novel AI-based NIDS that efficiently resolves the data imbalance problem and improves system performance.
IEEE INTERNET OF THINGS JOURNAL
(2023)
Article
Computer Science, Information Systems
Shahneela Pitafi, Toni Anwar, I. Dewa Made Widia, Boonsit Yimwadsana
Summary: Perimeter intrusion detection systems (PIDS) are essential for safeguarding critical infrastructures. We designed a PIDS prototype using multiple sensors and applied machine learning algorithms to improve data clustering and classification. The improved algorithm showed high accuracy in two-dimensional data and we also developed a dataset for future research.
Article
Chemistry, Analytical
Ketan Kotecha, Raghav Verma, Prahalad Rao, Priyanshu Prasad, Vipul Kumar Mishra, Tapas Badal, Divyansh Jain, Deepak Garg, Shakti Sharma
Summary: In order to predict anomalies more accurately, a reasonably good network intrusion detection system requires high detection rate and low false alarm rate. This paper operates on the UNSW-NB15 Dataset to suggest various models for modern attacks. Alongside detailed modeling, comprehensive data analysis on dataset features is done for better modeling. Moreover, hypothetical ponderings on potential network intrusion detection systems including suggestions on prospective modeling and dataset generation are discussed.
Article
Computer Science, Information Systems
Kayode S. Adewole, Taofeekat T. Salau-Ibrahim, Agbotiname Lucky Imoize, Idowu Dauda Oladipo, Muyideen AbdulRaheem, Joseph Bamidele Awotunde, Abdullateef O. Balogun, Rafiu Mope Isiaka, Taye Oladele Aro
Summary: This paper compares batch learning and data streaming algorithms for intrusion detection, finding that data streaming algorithms perform significantly better than batch learning algorithms in binary classification problems.
Article
Environmental Sciences
Jamal Mabrouki, Ghizlane Fattah, Naif Al-Jadabi, Younes Abrouki, Driss Dhiba, Mourade Azrour, Souad El Hajjaji
Summary: Solar energy is widely available, free, renewable, and non-polluting, making it a simple and environmentally friendly option for producing heat. The study of energy-efficient construction is crucial for reducing greenhouse gas emissions and providing solutions for heating needs.
MODELING EARTH SYSTEMS AND ENVIRONMENT
(2022)
Article
Automation & Control Systems
Shifa Siddiqui, Muhammad Shahzad Faisal, Shahzada Khurram, Azeem Irshad, Mohammed Baz, Habib Hamam, Naeem Iqbal, Muhammad Shafiq
Summary: Play Store reviews are crucial for understanding mobile app quality and helping developers build better apps. Low-quality apps and spam reviews harm user experience and trust, damaging the reputation of Play Store. Therefore, analyzing review content and developing suitable regression models for wearable apps is of great importance.
INTELLIGENT AUTOMATION AND SOFT COMPUTING
(2022)
Article
Environmental Sciences
Mohammed Benchrifa, Jamal Mabrouki, Mohamed Elouardi, Mourade Azrour, Rachid Tadili
Summary: Climate problems and the need to reduce greenhouse gas emissions have led to research on less polluting ways of generating electricity, such as solar energy. This study focuses on the use of photovoltaic energy to meet the electricity consumption of a facility, evaluating the production and losses, as well as the economic and environmental benefits.
MODELING EARTH SYSTEMS AND ENVIRONMENT
(2023)
Article
Computer Science, Hardware & Architecture
Maryam Douiba, Said Benkirane, Azidine Guezzaz, Mourade Azrour
Summary: This paper presents an improved intrusion detection system for IoT security, utilizing machine learning and deep learning algorithms. The experimental results demonstrate excellent performance in record detection and computation time.
JOURNAL OF SUPERCOMPUTING
(2023)
Article
Green & Sustainable Science & Technology
Rajasekhar Chaganti, Azrour Mourade, Vinayakumar Ravi, Naga Vemprala, Amit Dua, Bharat Bhushan
Summary: Integrating IoT in medical applications has improved healthcare operations, but IoMT devices are vulnerable to cyber attacks. This study proposes a PSO-DNN method for intrusion detection in IoMT, achieving a 96% accuracy and showing DL models perform slightly better than ML models.
Article
Computer Science, Information Systems
Chaimae Hazman, Azidine Guezzaz, Said Benkirane, Mourade Azrour
Summary: This paper presents a novel intrusion detection framework for IoT-based smart environments, which utilizes machine learning and deep learning techniques for improved protection. The framework demonstrates good performance in experiments and is capable of accurately detecting anomalies.
CLUSTER COMPUTING-THE JOURNAL OF NETWORKS SOFTWARE TOOLS AND APPLICATIONS
(2023)
Article
Computer Science, Information Systems
Mouaad Mohy-Eddine, Azidine Guezzaz, Said Benkirane, Mourade Azrour
Summary: The development of Internet of Things has led to the emergence of Industrial IoT, which brings about more serious security vulnerabilities that require the development of intrusion detection systems. This paper proposes an intrusion detection approach using machine learning to improve detection rate and accuracy.
JOURNAL OF COMPUTER VIROLOGY AND HACKING TECHNIQUES
(2023)
Article
Computer Science, Artificial Intelligence
Tarik Ahajjam, Mohammed Moutaib, Haidar Aissa, Mourad Azrour, Yousef Farhaoui, Mohammed Fattah
Summary: Artificial Intelligence is a technology based on algorithms that enable machines to make decisions for humans, enhancing user experience in various ways. Several studies have been conducted in the field of education to address student orientation and performance issues using different Machine Learning algorithms. The main goal of this article is to predict Moroccan students' performance in the Guelmim Oued Noun region using an intelligent system based on neural networks, which has proven to be one of the most effective data mining techniques.
BIG DATA MINING AND ANALYTICS
(2022)
Article
Computer Science, Artificial Intelligence
Mohamed Khalifa Boutahir, Yousef Farhaoui, Mourade Azrour, Imad Zeroual, Ahmad El Allaoui
Summary: This paper develops a set of deep learning models using feature importance algorithms to predict Direct Normal Irradiance (DNI) data. The findings demonstrate the crucial role of feature selection approaches in accurately forecasting solar radiation.
BIG DATA MINING AND ANALYTICS
(2022)
Article
Green & Sustainable Science & Technology
Hasna Hissou, Said Benkirane, Azidine Guezzaz, Mourade Azrour, Abderrahim Beni-Hssane
Summary: Solar irradiation is crucial for sustaining life on Earth and driving climate and weather systems. It provides light, heat, and energy, and its variations have significant implications for climate change. Harnessing solar energy can reduce greenhouse gas emissions, but challenges include its variability and technical difficulties in integration.
Article
Chemistry, Multidisciplinary
Sara Amaouche, Azidine Guezzaz, Said Benkirane, Mourade Azrour, Sohaib Bin Altaf Khattak, Haleem Farman, Moustafa M. Nasralla
Summary: Vehicular ad hoc networks (VANETs) are used for vehicle to vehicle (V2V) and vehicle to infrastructure (V2I) communications to improve road traffic and safety. However, VANETs face network attacks and communication challenges in dynamic environments. Therefore, securing communication in VANETs is crucial.
APPLIED SCIENCES-BASEL
(2023)
Article
Computer Science, Information Systems
Said Benkirane, Azidine Guezzaz, Mourade Azrour, Akber Abid Gardezi, Shafiq Ahmad, Abdelaty Edrees Sayed, Salman Naseer, Muhammad Shafiq
Summary: Road safety is a major concern for governments worldwide, with millions of deaths and injuries occurring on roads each year. Excessive speed in curves is a leading cause of accidents, leading to loss of vehicle stability. To address this issue, new technologies including VANET, IoT, MAS, and Embedded Systems can be used to create an efficient and intelligent system that provides drivers with real-time traffic data and helps them drive safely in dangerous areas.
CMC-COMPUTERS MATERIALS & CONTINUA
(2023)
Article
Environmental Sciences
Ghizlane Fattah, Jamal Mabrouki, Fouzia Ghrissi, Mourade Azrour
Summary: Atmospheric aerosols play a crucial role in global and local environments, impacting Earth's radiation balance, health, and cloud formation. The industrial sector, particularly the building material extraction industry, is a major source of fine particles, such as dust, sulphates, carbon black, and nitrates. Although the mechanisms of aerosol-environment interactions are complex and still not well understood, satellite atmospheric models provide insights into the spatiotemporal variability of fine particle concentrations in specific regions.
Article
Engineering, Multidisciplinary
Rizwan Taj, Feng Tao, Shahzada Khurram, Ateeq Ur Rehman, Syed Kamran Haider, Akber Abid Gardezi, Saima Kanwal
Summary: In this research, a reversible watermarking method is introduced for transmitting medical images with minimal distortion and high security. Experimental results demonstrate the robustness of the method against different attacks and its high peak signal-to-noise ratio.
CMES-COMPUTER MODELING IN ENGINEERING & SCIENCES
(2022)
Article
Environmental Sciences
Mourade Azrour, Jamal Mabrouki, Ghizlane Fattah, Azedine Guezzaz, Faissal Aziz
Summary: Water is an essential resource for human existence, but water pollution has become a serious problem affecting water quality. In this study, a model based on machine learning algorithms is developed to predict water quality index and water quality class, using four water parameters including temperature, pH, turbidity, and coliforms. Multiple regression algorithms are effective in predicting water quality index, while artificial neural network offers an efficient way to classify water quality.
MODELING EARTH SYSTEMS AND ENVIRONMENT
(2022)