Khaled Nasri

Mr. Khaled Nasri


Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

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

Representative Publications

View All Publications
1 June 2025 in International Journal of Computational and Experimental Science and Engineering
Verified
Journal Article
Open access
PDF file
KNKhaled Nasri
Khaled Nasri
AMAbdelouahab Moussaoui
Abdelouahab Moussaoui
This paper presents novel hybrid architectures for Arabic handwritten character recognition, integrating capsule networks with residual neural networks (ResNets) across various embedding strategies. The proposed Custom Caps-ResNet models explore low-, mid-, high-, and multilevel capsule embeddings to synergize hierarchical feature learning with spatial relationship preservation. Evaluated on four benchmark datasets, the models achieve competitive accuracy—99.64% on OIHACDB-28 and 94.14% on Dhad—while consistently reducing test loss by up to 80% on Dhad and 66% on HMBD_V1 compared to baselines. These reductions in loss indicate enhanced prediction certainty and improved feature representation. Multilevel and mid-level embeddings perform robustly across diverse script complexities, whereas high-level embeddings excel in semantic abstraction. The variation in dataset performance reveals how capsule networks mitigate challenges in cursive connections, overlaps, and positional character forms. Overall, the integration of capsule embeddings into ResNet hierarchies leads to not only strong accuracy but also significantly more confident predictions—advancing Arabic handwriting recognition toward reliable real-world deployment.

1 June 2025 in International Journal of Computational and Experimental Science and Engineering
Verified
Journal Article
Open access
PDF file
YBYoussef Boulkhiout
Youssef Boulkhiout
AMAbdelouahab Moussaoui
Abdelouahab Moussaoui
KNKhaled Nasri
Khaled Nasri
Glioblastoma (GBM) is the most aggressive primary brain tumor in adults, marked by high recurrence rates and poor prognosis. The methylation status of the O-6-methylguanine-DNA methyltransferase (MGMT) gene promoter plays a critical role in determining treatment response and patient survival. This work provides non-invasive machine learning (ML) solution for prediction of MGMT methylation status using features of magnetic resonance imaging (MRI) scans, aiming to support personalized therapeutic strategies. The method involves a three-step pipeline: First, extraction of image features from multi-modal MR. Second, Selection of the most important common features using light gradient boosting machine (LightGBM) algorithm and categorical gradient boosting (CatBoost). then, a voting ensemble of multiple ML models is trained on the selected features to classify MGMT methylation. The model was developed using Brain Tumor Segmentation (BraTS) 2021 dataset, which includes both segmentation masks and MGMT annotations. Its performance was evaluated using accuracy, precision, sensitivity, specificity, and area under the receiver operating characteristic (ROC) curve (AUC). The model achieved an accuracy of 92.86% and AUC of 96.84%, demonstrating strong alignment with clinical outcomes and surpassing conventional methods. These findings highlight the effectiveness of features extraction from multi-modal MRI analysis, and ML-based classification for biomarker prediction. The approach offers a promising step forward in precision medicine for GBM, enabling more accurate and individualized treatment planning.

21 October 2026 in Internet of Things
Verified
Journal Article
Closed access
YBYoussef Boulkhiout
Youssef Boulkhiout
LGLakhdar Goudjil
Lakhdar Goudjil
Samir BALBALSamir BALBAL
Samir BALBAL
KNKhaled Nasri
Khaled Nasri

8 August 2026 in Statistics, Optimization & Information Computing
Verified
Journal Article
Open access
PDF file
YBYoussef Boulkhiout
Youssef Boulkhiout
Samir BALBALSamir BALBAL
Samir BALBAL
KNKhaled Nasri
Khaled Nasri
AMAbdelouahab Moussaoui
Abdelouahab Moussaoui
The rapid growth of the Internet of Things (IoT) has significantly expanded the attack surface of modern networks, generating an urgent need for robust and efficient intrusion detection mechanisms. Machine learning (ML) is a promising approach to detect cyber attacks in IoT environments by automatically learning discriminative patterns from heterogeneous, real-world traffic. In this work we provide a comparative review and a thorough empirical evaluation of ten classifiers: logistic regression, decision trees, k-nearest neighbors, support vector machines, multilayer perceptrons, Random Forests, XGBoost, LightGBM, CatBoost, and a soft-voting ensemble on the RT-IoT2022 dataset, a realistic benchmark for real-time IoT attack detection. In addition to raw performance, we measure the impact of aggressive dimensionality reduction by comparing the full 83-feature space to a compact subset of 15 features, as determined by the consensus ranking of LightGBM and CatBoost feature importances. Experiments indicate that tree-based ensembles, CatBoost, XGBoost, and LightGBM, achieve the best performance, producing accuracy and AUC values above 99.7% and 99.9%, respectively, for both feature configurations, while maintaining balanced precision and recall across different attack types. Among the non-ensemble models, k-nearest neighbours is the strongest and loses only 0.05 accuracy points under the reduction, and the multilayer perceptron is equally insensitive, whereas logistic regression and the linear SVM lose 16--17 macro-F1 points. All comparisons are supported by stratified five-fold cross-validation, 95% confidence intervals and paired McNemar and Wilcoxon tests under Holm--Bonferroni correction, by a deployment cost profile (training and per-flow inference time), by a per-class analysis of minority-attack recall after SMOTE, and by external validation on NSL-KDD. This paper summarizes the advantages, disadvantages, and deployment considerations of state-of-the-art ML techniques and provides practical guidance for the development of adaptive, lightweight, and interpretable IoT intrusion detection systems.

16 October 2026 in Cluster Computing
Verified
Journal Article
Closed access
PDF file
LGLakhdar Goudjil
Lakhdar Goudjil
KNKhaled Nasri
Khaled Nasri
CTChaima Talhi
Chaima Talhi
NDNesrine Dehli
Nesrine Dehli