EL IDRISSI Nezha

Prof. EL IDRISSI Nezha


Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
1 January 2021 in International Journal on Smart Sensing and Intelligent Systems
Verified
Journal Article
Open access
PDF file
ENEL IDRISSI Nezha
EL IDRISSI Nezha
NANajid Abdellah
Najid Abdellah
EHEl Alami Hassan
El Alami Hassan
Clustering is an efficient technique to organize network resources efficiently and, in wireless sensor Networks (WSNs) communications it is used to group sensors with similar characteristics managed by a selected sensor called a Cluster Head (CH). Thus, this paper presents a new approach, namely Energy-Aware Clustering and Efficient Cluster Head Selection (EAC-ECHS) to optimize the performances of WSNs in terms of the network lifetime and enhance energy consumption. In EAC-ECHS, the sensor network is divided into an inter grid and fair clustered Grids. Furthermore, for each clustered Grid, the CH selection is based on the residual energy of sensor, distance to neighbors, and distance to the base station. Simulation experiments have been conducted to examine the performance of EAC-ECHS and previous approaches, and the results demonstrate that EAC-ECHS approach achieves the design objectives in terms energy consumption, network lifetime, and packet delivery ratio.

29 September 2026 in Future Internet
Verified
Journal Article
Open access
PDF file
MFMohamed Ali Fakri
Mohamed Ali Fakri
ANAbdellah NAJID
Abdellah NAJID
RSRachid ben said
Rachid ben said
ENEL IDRISSI Nezha
EL IDRISSI Nezha
Deep learning intrusion detection systems perform well when traffic is merely separated into normal and malicious, but fine-grained recognition of the specific attack family remains difficult in Internet of Things (IoT) environments because of severe class imbalance and overlapping feature distributions. This work proposes an attention-enhanced CNN-BiLSTM fusion model for the multi-class classification of IoT attacks over eight families. A convolutional branch extracts local feature interactions, whereas a bidirectional Long Short-Term Memory (BiLSTM) branch reads the standardized flow descriptor as an ordered sequence and encodes dependencies among non-adjacent feature segments in both directions. Multi-head self-attention and a bidirectional cross-attention block let the two representations interact dynamically and suppress redundant information. Class imbalance is addressed with a focal loss and class-balanced weighting. The framework was evaluated on the large-scale CIC-IoT2023 benchmark under an eight-class taxonomy. On more than 3.5 × 105 test flows, the proposed model reached 99.06% accuracy and a 98.99% weighted F1-score, outperforming standalone CNN, LSTM, CNN-LSTM, and CNN-BiLSTM baselines retrained on the same corrected data pipeline under an identical objective and budget.