Browsing by Author "Zgheib, Rita"
Now showing 1 - 9 of 9
Results Per Page
Sort Options
Item Autoencoder-based Intrusion Detection System(Institute of Electrical and Electronics Engineers Inc., 2021) Kamalov, Firuz; Zgheib, Rita; Leung, Ho Hon; Al-Gindy, Ahmed; Moussa, SherifGiven the dependence of the modern society on networks, the importance of effective intrusion detection systems (IDS) cannot be underestimated. In this paper, we consider an autoencoder-based IDS for detecting distributed denial of service attacks (DDoS). The advantage of autoencoders over traditional machine learning methods is the ability to train on unlabeled data. As a result, autoencoders are well-suited for detecting unknown attacks. The key idea of the proposed approach is that anomalous traffic flows will have higher reconstruction loss which can be used to flag the intrusions. The results of numerical experiments show that the proposed method outperforms benchmark unsupervised algorithms in detecting DDoS attacks. © 2021 IEEE.Item Comparative analysis of activation functions in neural networks(Institute of Electrical and Electronics Engineers Inc., 2021) Kamalov, Firuz; Nazir, Amril; Safaraliev, Murodbek; Cherukuri, Aswani Kumar; Zgheib, RitaAlthough the impact of activations on the accuracy of neural networks has been covered in the literature, there is little discussion about the relationship between the activations and the geometry of neural network model. In this paper, we examine the effects of various activation functions on the geometry of the model within the feature space. In particular, we investigate the relationship between the activations in the hidden and output layers, the geometry of the trained neural network model, and the model performance. We present visualizations of the trained neural network models to help researchers better understand and intuit the effects of activation functions on the models. © 2021 IEEE.Item Cyber Security Strategies While Safeguarding Information Systems in Public/Private Sectors(Springer Science and Business Media Deutschland GmbH, 2022) Al Mehairi, Alya; Zgheib, Rita; Abdellatif, Tamer Mohamed; Conchon, EmmanuelMany private and public organizations in the UAE and around the world are facing challenges in protecting their information and systems from external cyber-attacks due to the increase in the usage of computer networks within worldwide businesses. The objective of this research study is to explore the strategies that are implemented by the public and private sectors in the UAE to safeguard their data and information systems from cyber-attacks. The findings of the study indicated that public organizations in the UAE do have effective strategies in place to safeguard their information and systems against any cyber-attacks. These strategies include providing adequate training to their employees to create awareness among them and developing robust cyber security strategies in line with the UAE National Cyber Security strategy framework. Public and some private organizations are vigilant in assessing, identifying, and mitigating cyber security risks and threats through well-designed organizational strategies. The research also concludes that protecting the information system can reduce cyber threats and can lead to improved business practices. The findings of this study will lay the foundations for other private and public sectors to use them in their organizational practices, which will help them to decrease the data breaches, and protect their company and customers’ confidential data, thereby reducing the cost and risk of cyber-attacks. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.Item Diagnosing COVID-19 on Limited Data: A Comparative Study of Machine Learning Methods(Springer Science and Business Media Deutschland GmbH, 2021) Zgheib, Rita; Kamalov, Firuz; Chahbandarian, Ghazar; El Labban, OsmanGiven the enormous impact of COVID-19, effective and early detection of the virus is a crucial research question. In this paper, we compare the effectiveness of several machine learning algorithms in detecting COVID-19 virus based on patient’s age, gender, and nationality. The results of the experiments show that neural networks, support vector machines, and gradient boosting decision tree models achieve an 89% accuracy, and the random forest model produces an 87% accuracy in the identification of the COVID-19 cases. © 2021, Springer Nature Switzerland AG.Item Feature selection for intrusion detection systems(Institute of Electrical and Electronics Engineers Inc., 2020-12) Kamalov, Firuz; Moussa, Sherif; Zgheib, Rita; Mashaal, OmarIn this paper, we analyze existing feature selection methods to identify the key elements of network traffic data that allow intrusion detection. In addition, we propose a new feature selection method that addresses the challenge of considering continuous input features and discrete target values. We show that the proposed method performs well against the benchmark selection methods. We use our findings to develop a highly effective machine learning-based detection systems that achieves 99.9% accuracy in distinguishing between DDoS and benign signals. We believe that our results can be useful to experts who are interested in designing and building automated intrusion detection systems. ©2020 IEEE.Item Neural Networks Architecture for COVID-19 Early Detection(2021) Zgheib, Rita; Chahbandarian, Ghazar; Kamalov, Firuz; Labban, Osman ElCoronavirus fight seems far from being won. Governments are trying to balance the necessity to enforce restrictions on travel outside the home and the impact of these restrictions on the economy. Healthcare workers are overloaded, a considerable number of unnecessary and costly PCR tests are performed to serve as a certificate to go to work. At this stage, going back to everyday life safely requires the companies and public places to adopt AI-based solutions to assist the public authorities and the hospitals with the COVID detection. The most important issue that we tackle in this paper is the prediction to be very accurate. As a result, we propose an AI system based on Neural Networks (NN) method to predict whether a person has caught COVID19 disease or not. In this study, we used a real data set of 9416 patients tested for COVID19 at a hospital in Dubai. After training the NN model, the average error function of the neural network was equal to 0.01, and the accuracy of the prediction of whether a person has COVID or not was 97.6%. © 2021 IEEE.Item A scalable semantic framework for IoT healthcare applications(Springer Science and Business Media Deutschland GmbH, 2023-05) Zgheib, Rita; Kristiansen, Stein; Conchon, Emmanuel; Plageman, Thomas; Goebel, Vera; Bastide, RémiItem Toward a knowledge graph for medical diagnosis: issues and usage scenarios(Elsevier, 2022-01-01) De Nicola, Antonio; Zgheib, Rita; Taglino, FrancescoItem Towards an ML-based semantic IoT for pandemic management: A survey of enabling technologies for COVID-19(Elsevier B.V., 2023-04-01) Zgheib, Rita; Chahbandarian, Ghazar; Kamalov, Firuz; Messiry, Haythem El; Al-Gindy, Ahmed