Mohammed Fattah

Mohammed Fattah

Auto-generated profile, based on publicly available information

Mohammed Fattah

Sidi Mohamed Ben Abdellah University

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
12 May 2022 in IEEE Access
Verified
Journal Article
Open access
AMAsmae Mamane
Asmae Mamane
MFMohammed Fattah
Mohammed Fattah
MGMohammed El Ghazi
Mohammed El Ghazi
MBMoulhime El Bekkali
Moulhime El Bekkali
YBYounes Balboul
Younes Balboul
MSMazer Said
Mazer Said
Over the years, several research groups have been developing effective and efficient scheduling algorithms to enhance the quality of service of mobile communication networks. The arrival of the fifth generation of mobile networks (5G) has demonstrated the importance of advanced scheduling techniques to manage the limited frequency spectrum available while achieving 5G transmission requirements. This issue has been picked up extensively within the research community due to the increasing demand for mobile communications and the desire for a fully connected world. Consequently, the scientific community has developed novel approaches and varied scheduling schemes to meet the needs of various applications and scenario conditions. In this context, this paper presents an overview of the state-of-the-art methods, highlights seminal and innovative research, and investigates the current state of 5G radio resource management. This review of literature compares emerging strategy methods based on their metrics, analyzes their performances, and emphasizes the existing works with a vision for the future of modern 5G and upcoming networks in terms of radio resource allocation to provide a thorough introspection of the literature. Furthermore, gaining a better understanding of the radio resource management state-of-the-art would provide valuable information for future work and might be helpful for new researchers in the field.

1 August 2023 in International Journal of Electrical and Computer Engineering (IJECE)
Verified
Journal Article
Open access
PDF file
SDSalah-Eddine Didi
Salah-Eddine Didi
IHImane Halkhams
Imane Halkhams
AEAbdelhafid Es-Saqy
Abdelhafid Es-Saqy
MFMohammed Fattah
Mohammed Fattah
YBYounes Balboul
Younes Balboul
MBMoulhime El Bekkali
Moulhime El Bekkali
This paper presents a study and an array design consisting of two microstrip patch antennas connected in series in a 2×1 form. This antenna provides better performance for the fifth-generation (5G) wireless communication system. The microstrip line feeding technique realizes the design of this antenna. This feed offers the best bandwidth, is easy to model, and has low spurious radiation. The distance between the feed line and the patch can adapt to the antenna’s impedance. In addition, the antenna array proposed in this paper is designed and simulated using the high frequency structure simulator (HFSS) simulation software at the operating frequency of 28 GHz for the 5G band. The support material used is Rogers RT/duroid® 5880, with relative permittivity of 2.2, a thickness of h=0.5 mm, and a loss tangent of 0.0009. The simulation results obtained in this research paper are as: reflection coefficient: -35.91 dB, standing wave ratio (SWR): 1.032, bandwidth: 1.43 GHz, gain: 9.42 dB, directivity: 9.47 dB, radiated power: 29.94 dBm, accepted the power: 29.99 dBm, radiation efficiency: 29.95, efficiency: 99.83%. This proposed antenna array has achieved better performance than other antenna arrays recently published in scientific journals regarding bandwidth, beam gain, reflection coefficient, SWR, radiated power, accepted power, and efficiency. Therefore, this antenna array will likely become an important competitor for many uses within the 5G wireless applications.

1 February 2024 in Indonesian Journal of Electrical Engineering and Computer Science
Verified
Journal Article
Open access
PDF file
MMMohammed Moutaib
Mohammed Moutaib
MFMohammed Fattah
Mohammed Fattah
Yousef FarhaouiYousef Farhaoui
Yousef Farhaoui
BABadraddine AGHOUTANE
Badraddine AGHOUTANE
MBMoulhime El Bekkali
Moulhime El Bekkali
Monitoring fetal health during pregnancy ensures safe delivery and the newborn’s well-being. The fetal electrocardiogram (fetal ECG) is a valuable tool for assessing fetal cardiac health, but interpretation of ECG data can be challenging due to its complexity and variability. In this work, we explore the application of machine learning, particularly random forest, to predict and analyze fetal ECGs. With its ability to manage large datasets and provide precise insights, random forest is a promising solution for this challenge. By comparing our random forest-based approach with other standard machine learning techniques such as artificial neural network (ANN), support vector machines (SVM), and recurrent neural networks (RNN), we observed that our solution outperformed these methods in accuracy, robustness, and reliability. This article details the methodology used, the implementation of the algorithm, as well as the comparative results obtained. Emphasis is placed on the benefits of random forest in this specific medical context, highlighting its potential as a future tool for fetal ECG prediction. Ultimately, our research suggests a shift toward random forest-based solutions for more efficient and accurate analysis of fetal ECGs, with direct implications for clinical practice and fetal well-being.

19 May 2023 in IEEE Access
Verified
Journal Article
Open access
MFMacoumba Fall
Macoumba Fall
YBYounes Balboul
Younes Balboul
MFMohammed Fattah
Mohammed Fattah
MSMazer Said
Mazer Said
MBMoulhime El Bekkali
Moulhime El Bekkali
AKAhmed D. Kora
Ahmed D. Kora
The 5th generation of mobile communications, currently being rolled out, aims to improve network performance and efficiency over the older generations. With mmWaves, densified cell deployment is necessary for 5G networks, increasing capacity and improving network coverage. This imposes a considerable increase in the energy consumption of the 5G stations, which not only increases operating expenses for operators but also burdens the environment. Optimizing the energy consumption of 5G networks would be necessary to curb the energy curve. In this context, this paper presents a new algorithm, called Energy Consumption Optimization Algorithm (ECOA), which combines cell selection and standby techniques to optimize energy consumption while preserving network performance. A comparison is conducted between ECOA and standard cell selection modes to evaluate the performance of the conventional approach. Our algorithm exhibits good performance, particularly in high-density, high-load scenarios. For instance, in a site with 25 Pico base stations serving 500 users, our algorithm achieves an average throughput of 23 Mb/s per user while consuming 1750.75 W of energy. This represents a 2.44% increase in energy consumption compared to the optimal solution.

1 January 2019 in Procedia Computer Science
Verified
Journal Article
Open access
MBMarwa Boumaiz
Marwa Boumaiz
MGM. EL Ghazi
M. EL Ghazi
SMS. Mazer
S. Mazer
MFM. Fattah
M. Fattah
ABA. Bouayad
A. Bouayad
YBY. Balboul
Y. Balboul

1 September 2024 in IAES International Journal of Artificial Intelligence (IJ-AI)
Verified
Journal Article
Open access
PDF file
YRYahya Rbah
Yahya Rbah
MMMohammed Mahfoudi
Mohammed Mahfoudi
YBYounes Balboul
Younes Balboul
KCKaouthar Chetioui
Kaouthar Chetioui
MFMohammed Fattah
Mohammed Fattah
BBBenaissa Bernoussi
Benaissa Bernoussi
The risk of cyber-attacks has increased significantly with the rapid development of the Internet of Medical Things (IoMT). The proliferation of IoMT devices in healthcare facilities has made conventional intrusion detection approaches challenging to employ. Our study proposes a novel hybrid framework leveraging Software Defined Network (SDN) controllers and deep learning techniques, specifically Convolutional Neural Networks (CNN) and Bidirectional Long-Term Memory (Bi-LSTM), to address these challenges. Our framework introduces a unique combination of SDN and deep learning, allowing for dynamic and efficient management of IoMT security. The integration of CNN and Bi-LSTM enables the system to handle diverse data types encountered in IoMT, offering a comprehensive approach to threat detection. Unlike traditional methods, our hybrid solution adapts seamlessly to the evolving threat landscape of healthcare IoT systems. The urgency of our research is affirmed by the critical need to fortify IoMT security amid escalating cyber threats. The conventional methods struggle to cope with the complex nature of IoMT networks, making our exploration of a hybrid SDN-based deep learning framework imperative. With a background in cybersecurity and a dedicated focus on healthcare IoT, we recognize the urgency to develop a solution that not only enhances detection accuracy but also ensures real-time responsiveness in healthcare settings. The proposed method has been validated using the “IoT-Healthcare security” dataset, revealing its efficacy in detecting numerous frequent threats and outperforming current state-of-the-art techniques in terms of high detection accuracy of 99.97% and less than 1.8 (s) in terms of speed efficiency.