Salah Eddine El Harrauss

Mr. Salah Eddine El Harrauss


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
13 December 2025 in Big Data and Cognitive Computing
Verified
Journal Article
Open access
PDF file
CBCharlène Béatrice Bridge-Nduwimana
Charlène Béatrice Bridge-Nduwimana
SHSalah Eddine El Harrauss
Salah Eddine El Harrauss
AOAziza EL OUAAZIZI
Aziza EL OUAAZIZI
MYMajid BEN YAKHLEF
Majid BEN YAKHLEF
Upstream processes strongly influence downstream analysis in sequential data-processing workflows, particularly in machine learning, where data quality directly affects model performance. Conventional statistical imputations often fail to capture nonlinear dependencies, while deep learning approaches typically lack uncertainty quantification. We introduce a hybrid imputation model that integrates a deep learning autoencoder with Convolutional Neural Network (CNN) layers and a Transformer-based contextual modeling architecture to address systematic variation across heterogeneous data sources. Performing multiple imputations in the autoencoder–transformer latent space and averaging representations provides implicit batch correction that suppresses context-specific remains without explicit batch identifiers. We performed experiments on datasets in which 10% of missing data was artificially introduced by completely random missing data (MCAR) and non-random missing data (MNAR) mechanisms. They demonstrated practical performance, jointly ranking first among the imputation methods evaluated. This imputation technique reduced the root mean square error (RMSE) by 50% compared to denoising autoencoders (DAE) and by 46% compared to iterative imputation (MICE). Performance was comparable for adversarial models (GAIN) and attention-based models (MIDA), and both provided interpretable uncertainty estimates (CV = 0.08–0.15). Validation on datasets from multiple sources confirmed the robustness of the technique: notably, on a forensic dataset from multiple laboratories, our imputation technique achieved a practical improvement over GAIN (0.146 vs. 0.189 RMSE), highlighting its effectiveness in mitigating batch effects.

4 May 2026 in Progress of Theoretical and Experimental Physics
Verified
Journal Article
Open access
Marwan AIT HADDOUMarwan AIT HADDOU
Marwan AIT HADDOU
MBMohamed Belfkir
Mohamed Belfkir
SHSalah Eddine El Harrauss
Salah Eddine El Harrauss
In this paper, we propose a hybrid quantum machine learning framework to improve the sensitivity of double Higgs boson searches in the $HH \rightarrow b\bar{b}\gamma \gamma$ final state at $\sqrt{s} = 13.6~\text{TeV}$. The proposed model combines parameterized quantum circuits with a classical neural network meta-model, enabling event-level features to be embedded in a quantum feature space while maintaining the optimization stability of classical learning. In our benchmark setup, the hybrid model outperforms the pure quantum implementation and improves over the XGBoost baseline while performing similarly to the graph neural network baseline, achieving an expected 95% CL upper limit on the nonresonant double Higgs boson production cross section of $1.9\times \sigma _{\text{SM}}$ and $2.1\times \sigma _{\text{SM}}$ under background normalization uncertainties of 10% and 50%, respectively. In addition, expected constraints on the Higgs boson self-coupling $\kappa _{\lambda }$ and quartic vector-boson–Higgs coupling $\kappa _{2V}$ are improved relative to the pure quantum model and competitive with the classical baselines considered in this work.