AMAbderrahim Maizate

Abderrahim Maizate

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Abderrahim Maizate has a total of 16 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • FlowerFED-IDS: A privacy-preserving IDS with quantified privacy-utility trade-offs

    by Hamza Rafik, Abdelaziz Ettaoufik, Abderrahim Maizate

    The rise of Internet of Medical Things (IoMT) and edge computing in healthcare demands intrusion detection systems (IDS) that protect sensitive patient data without sacrificing detection quality. Federated learning (FL) enables collaborative training of such detectors without sharing raw data; however, existing FL-based IDS remain vulnerable to model inversion and poisoning attacks during client–server communication, and the compared state-of-the-art solutions implement no formal privacy mechanism. This paper presents FlowerFED-IDS, a federated IDS built on the Flower framework that unifies three mechanisms in a single stack: a hybrid 1D CNN–BiLSTM detection model, local differential privacy (LDP) that clips and perturbs model updates before transmission, and robust FedTrimmedAvg aggregation. On the CICIoMT2024 dataset, under IID partitioning as a controlled baseline, FlowerFED-IDS achieves accuracies of 96.38%, 93.03%, and 93.89% with 5, 10, and 15 clients, respectively, maintaining recall above 93% in all configurations. Under a poisoning scenario with 20% compromised clients, FedTrimmedAvg keeps accuracy within 0.5 percentage points of the honest baseline. A privacy–utility analysis over noise multipliers identifies σ = 0.10 as the operating point satisfying the 95% clinical recall floor; we report its composed budget transparently (ε = 1215 at δ = 10 −5 over 20 rounds), a quantified but loose bound providing practical protection against update-reconstruction and inference attacks rather than a strict differential-privacy guarantee. A preliminary non-IID evaluation with Dirichlet α = 0.5, further confirms that the framework remains operational under realistic data heterogeneity, with recall above the clinical threshold, at the cost of reduced early-training stability.

  • Open Access

    Energy-efficient clustering optimization for heterogeneous wireless sensor networks with K-nearest neighbors algorithm

    by Adil Hilmani, Yassine Sabri, Abderrahim Maizate, Siham Aouad, Fouad Ayoub

    Wireless sensor networks (WSNs) consist of autonomous sensing nodes whose operation relies on limited energy resources. To extend the operational lifetime of such systems, optimizing power consumption is essential. Clustering plays a key role in enhancing network stability and improving communication efficiency. This work proposes an improved clustering strategy based on the K-nearest neighbors (KNN) algorithm to reduce transmission distances in heterogeneous networks. By integrating this approach into hierarchical protocols such as Department of Electrical and Electronic Engineering (DEEC), Electrical Engineering Center (EEC), Center for Advanced Materials and Processes (CAMP), the method refines both node selection and cluster organization. Simulation results obtained using network simulator 2 (NS2) demonstrate that the modified protocols significantly reduce energy dissipation while increasing overall network lifetime. This combined approach improves system efficiency and provides a robust solution for sustainable energy management in WSNs, meeting the requirements of highly demanding applications.

  • Enhancing SDN Routing Performance Through Machine Learning Techniques

    by Ahmed Belkhadim, Zouhair Ibn Batouta, Abdelaziz Ettaoufik, Adil Hilmani, Abderrahim Maizate


  • Open Access

    Optimizing energy efficiency in wireless sensor networks with integration of Calinski-Harabasz index in K-means clusterings

    by Adil Hilmani, Yassine Sabri, Abderrahim Maizate, Siham Aouad, Fouad Ayoub

    The optimization of energy consumption and the assurance of efficient data transmission are critical factors in enhancing the longevity and performance of wireless sensor networks (WSNs). This study introduces an advanced clustering technique aimed at prolonging the network's lifespan while facilitating reliable data delivery. By integrating the Calinski-Harabasz index into the traditional K-Means clustering approach, the methodology evaluates the quality of clusters and determines the optimal number of clusters, which leads to better node organization within the network. Moreover, the selection of routing pathways from cluster heads to the base station is strategically optimized to conserve energy. Simulation results demonstrate that this novel dual enhancement technique surpasses traditional K-Means in multiple areas, including power consumption, network reliability, and successful data delivery. Consequently, the suggested advancements in cluster formation and routing substantially enhance the performance of energy-limited wireless sensor networks, boosting their robustness and reliability in practical applications.

  • Random Projection-based Anomaly Detection (RPAD) Algorithm

    by Ossama Cherkaoui, Houda Anoun, Abderrahim Maizate

    Anomaly detection is an active research topic with applications in many fields. Various methods have been proposed for anomaly detection in multivariate numerical datasets, each based on different techniques: nearest neighbors, decision trees, self-encoding neural networks, statistical methods, ensemble methods and others. However, the availability of large, high-dimensional datasets presents new challenges to anomaly detection algorithms. In particular, distance-based anomaly detection methods in high-dimensional spaces may become less efficient due to difficulties commonly referred to as the “curse of dimensionality”. In this paper, we present a new unsupervised anomaly detection algorithm for multivariate numerical data, which we call Random Projection Anomaly Detection (RPAD), that can scale to high-dimensional datasets while exhibiting sub-quadratic time complexity. RPAD takes advantage of Euclidean Locality Sensitive Hashing to estimate anomaly scores. Tests performed on 33 datasets using 14 unsupervised algorithms representing state-of-the-art and recent anomaly detection methods show that RPAD outperforms all tested algorithms in terms of execution time, with a more than 10 times improvement over competing algorithms. Additionally, RPAD achieves good performance with an average absolute deviation from the best result equal to [ ] and [ ] for average precision and precision@K metrics, respectively.

  • Open Access

    Artificial intelligence algorithms to predict customer satisfaction: a comparative study

    by Othman Berrada Chakour, Abdelaziz Ettaoufik, Khalid Aissaoui, Abderrahim Maizate

    Customer satisfaction is the key for every business successful. Therefore, keeping the current customer portfolio and expanding it over time is the main goal for any business. Hence, we need first to satisfy these clients. The customer satisfaction helps to retain consumers of its products, increase the life value of the customer, also make known its brand through positive word of mouth to get a better reputation and thus increase turnover. For this reason, several studies have been conducted on this subject to explore all tools and technologies that will help retain customers and reduce their churn rate. Based on various customer satisfaction studies for different types of businesses, this paper shows the review of promising research areas and artificial intelligence (AI) application models in predicting customer satisfaction. The results of this study allowed the identification of the best algorithms with the highest score of performance metrics that can be applied as part of the customer satisfaction prediction, through a detailed benchmark performed. The result shows that random forest (RF) and gradient boost (GB) algorithms in machine learning (ML) and convolutional neural network - long short-term memory (CNN-LSTM) in deep learning (DL) are giving the best performance. The most used metrics are accuracy andF1-score. In addition, DL models outperform ML models in most cases.


  • Open Access

    Integration of K-Means and Silhouette score for energy efficiency of wireless sensor networks

    by Adil Hilmani, Yassine Sabri, Abderrahim Maizate, Siham Aouad, Mohammed Koundi

    In wireless sensor networks (WSNs), optimizing energy consumption, and ensuring efficient data transmission are crucial for network longevity and performance. This paper introduces an enhanced clustering technique for WSNs that aims to extend network lifetime and ensure reliable data delivery. Instead of regular K-Means clustering, we integrate the Silhouette score method to evaluate cluster quality and decide the optimal number of clusters. This improves how nodes are grouped together in the network. Additionally, we strategically select routing paths from cluster heads to the base station that minimize energy drainage. Comprehensive simulations show our dual optimization approach outperforms standard K-Means in terms of energy efficiency, stable network organization and effective data transmission and overall, the proposed improvements to clustering and routing significantly advance energy-constrained WSNs toward more sustainable and dependable real-world applications


  • Open Access

    Security of software defined networks: evolution and challenges

    by Siham Aouad, Issam El Meghrouni, Yassine Sabri, Adil Hilmani, Abderrahim Maizate

    In software-defined networking (SDN), network traffic is managed by software controllers or application programming interfaces (APIs) rather than hardware components. It differs from traditional networks, which use switches and routers to control traffic. Using SDN, you can create and control virtual networks or traditional hardware networks. Furthermore, OpenFlow allows network administrators to control exact network behavior through centralized control of packet forwarding. For these reasons, SDN has advantages over certain security issues, unlike traditional networks. However, most of the existing vulnerabilities and security threats in the traditional network also impact the SDN network. This document presents the attacks targeting the SDN network and the solutions that protect against these attacks. In addition, we introduce a variety of SDN security controls, such as intrusion detection systems (IDS)/intrusion prevention system (IPS), and firewalls. Towards the end, we outline a conclusion and perspectives.


  • Open Access

    Energy-efficient routing protocol for wireless sensor networks based on progressive and concentric clusters

    by Adil Hilmani, Mohamed Koundi, Yassine Sabri, Abderrahim Maizate

    Smart parking is common in contemporary cities. These smart parking lots are outfitted mostly with wireless sensor networks (WSNs), which are used to detect, monitor, and collect data on the availability status of all existing parking spaces in a given area. Sensors make up WSN, which may gather, process, and transmit informations to the sink. However, the power and communication limitations of the sensors have an effect on the performance and quality of the WSNs. The decrease in the battery and the energy of the nodes causes a decrease in the life of the nodes and also of the entire WSN network. In this article, we present a routing protocol that implements an efficient and robust algorithm allowing the creation of clusters so that the base station can receive data from the entire WSN network. This protocol adopts a reliable and efficient algorithm allowing to minimize the energy dissipation of the sensors and to increase the lifetime of the WSN. In comparison to alternative parking lot management protocols already in use, the simulation results of the proposed protocol are effective and robust in terms of power consumption, data transmission reliability, and WSN network longevity.


  • Security approaches based on elliptic curve cryptography in wireless sensor networks

    by Mohammed Said Salah, Abderrahim Maizate, Mohammed Ouzzif

    Wireless sensor networks are ubiquitous in monitoring applications, medical control, environmental control and military activities... In fact, a wireless sensor network consists of a set of communicating nodes distributed over an area in order to measure a given magnitude, or receive and transmit data independently to a base station which is connected to the user via the Internet or a satellite, for example. Each node in a sensor network is an electronic device which has calculation capacity, storage, communication and power. However, attacks in wireless sensor networks can have negative impacts on critical network applications leading to the minimization of security within these networks. So it is important to secure these networks in order to maintain their effectiveness. In this paper, we have initially attempted to study approaches oriented towards cryptography and based on elliptic curves, then we have compared the performance of each method relative to others.