Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Abdelrahman Eid has a total of 27 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Interpretable Machine Learning for Benchmarking DFT Electron Affinity Predictions: A Generalized Additive Model Approach

    by Ismail Badran, Abdelrahman Eid, Motasem Far, Nadeen Abbas, Raghad Tayeh, Sahar Salman, Yasmeen Hamdan

    Electron affinity (EA) is vital for understanding charge transfer, redox reactions, and material design across chemistry and materials science. This study introduces a novel methodology that integrates interpretable machine learning with density functional theory (DFT) to provide a guideline for EA predictions. Using Generalized Additive Models (GAM), we reveal how functionals, basis sets, and molecular species interact in complex and nonlinear ways, offering insights that are not accessible through conventional analyses. A curated dataset of 47 atoms and molecules was used to assess the predictive performance of nine functionals across five basis sets. The results show that basis set selection has a more pronounced effect on EA prediction accuracy than functional choice, with the “ augmented ” ma‐def2‐SVP basis set, particularly in combination with B3LYP, providing the most reliable predictions. In contrast, the “ unaugmented ” def2‐TZVP and def2‐SVP basis sets frequently introduced large errors and high variability. The GAM framework identified species‐specific challenges, especially for Cl 2 , NH 3 , and CN, and demonstrated that although statistically significant differences exist among functionals, their performance in predicting EA values is largely equivalent from a chemical perspective. The GAM‐based ranking showed a spread of 1.6 kJ/mol among the average predicted deviations of the tested functionals, indicating that their practical differences are small from a chemical perspective under the studied conditions. This interpretable machine learning approach therefore provides a transparent and reproducible strategy for guiding the selection of DFT methods for EA calculations. To our knowledge, this is the first study to apply interpretable ML to systematically investigate and challenge generalized assumptions in EA benchmarking, establishing a data‐driven framework for practical decision‐making in computational chemistry.

  • Stochastic simulations for graphs and machine learning

    by Abdelrahman Eid

    Simulations stochastiques pour les graphes et l'apprentissage automatique: Bien qu’il ne soit pas pratique d’étudier la population dans de nombreux domaines et applications, l’échantillonnage est une méthode nécessaire permettant d’inférer l’information.Cette thèse est consacrée au développement des algorithmes d’échantillonnage probabiliste pour déduire l’ensemble de la population lorsqu’elle est trop grande ou impossible à obtenir.Les techniques Monte Carlo par chaîne de markov (MCMC) sont l’un des outils les plus importants pour l’échantillonnage à partir de distributions de probabilités surtout lorsque ces distributions ont des constantes de normalisation difficiles à évaluer.Le travail de cette thèse s’intéresse principalement aux techniques d’échantillonnage pour les graphes. Deux méthodes pour échantillonner des sous-arbres uniformes à partir de graphes en utilisant les algorithmes de Metropolis-Hastings sont présentées dans le chapitre 2. Les méthodes proposées visent à échantillonner les arbres selon une distribution à partir d’un graphe où les sommets sont marqués. L’efficacité de ces méthodes est prouvée mathématiquement. De plus, des études de simulation ont été menées et ont confirmé les résultats théoriques de convergence vers la distribution d’équilibre.En continuant à travailler sur l’échantillonnage des graphes, une méthode est présentée au chapitre 3 pour échantillonner des ensembles de sommets similaires dans un graphe arbitraire non orienté en utilisant les propriétés des processus des points permanents PPP. Notre algorithme d’échantillonnage des ensembles de k sommets est conçu pour surmonter le problème de la complexité de calcul lors du calcul du permanent par échantillonnage d’une distribution conjointe dont la distribution marginale est un kPPP.Enfin, dans le chapitre 4, nous utilisons les définitions des méthodes MCMC et de la vitesse de convergence pour estimer la bande passante du noyau utilisée pour la classification dans l’apprentissage machine supervisé. Une méthode simple et rapide appelée KBER est présentée pour estimer la bande passante du noyau de la fonction de base radiale RBF en utilisant la courbure moyenne de Ricci de graphes.

  • Open Access

    Adaptive Data-Driven Framework for Unsupervised Learning of Air Pollution in Urban Micro-Environments

    by Abdelrahman Eid, Shehdeh Jodeh, Raghad Eid, Ghadir Hanbali, Abdelkhaleq Chakir, Estelle Roth

    (1) Background: Urban traffic micro-environments show strong spatial and temporal variability. Short and intensive campaigns remain a practical approach for understanding exposure patterns in complex environments, but they need clear and interpretable summaries that are not limited to simple site or time segmentation. (2) Methods: We carried out a multi-site campaign across five traffic-affected micro-environments, where measurements covered several pollutants, gases, and meteorological variables. A machine learning framework was introduced to learn interpretable operational regimes as recurring multivariate states using clustering with stability checks, and then we evaluated their added explanatory value and cross-site transfer using a strict site hold-out design to avoid information leakage. (3) Results: Five regimes were identified, representing combinations of emission intensity and ventilation strength. Incorporating regime information increased the explanatory power of simple NO2 models and allowed the imputation of missing H2S day using regime-aware random forest with an R2 near 0.97. Regime labels remained identifiable using reduced sensor sets, while cross-site forecasting transferred well for NO2 but was limited for PM, indicating stronger local effects for particles. (4) Conclusions: Operational-regime learning can transform short multivariate campaigns into practical and interpretable summaries of urban air pollution, while supporting data recovery and cautious model transfer.


  • Open Access

    Hybrid phenotype-guided modeling across algorithm–feature regimes with application to ICU mortality prediction for Acinetobacter baumannii

    by Abdelrahman Eid, Rasha Khayyat, Shadi Abu Alwafa, Hadi Rabee

    Acinetobacter baumannii causes severe intensive care unit (ICU) infections with high mortality, yet most prediction tools rely on risk scores or supervised machine learning (ML) and overlook hidden patient subgroups. This study applied a hybrid machine learning framework combining unsupervised clustering and supervised prediction to refine ICU mortality estimation and evaluate whether incorporating phenotype information enhances performance. Patient phenotypes were identified using clustering, and cluster membership was incorporated as an additional predictive feature. ML models were trained with and without cluster membership under two feature settings: full-feature models including all variables and reduced-feature models limited to significant predictors identified within the clusters. The resulting phenotypes were clinically distinct and strongly associated with mortality, demonstrating that data-driven patient grouping can provide complementary prognostic information. Incorporating phenotype membership improved predictive accuracy in a context-dependent manner, varying by feature regime and the learning algorithm. This study introduces a novel framework for phenotype-guided critical care modeling that bridges unsupervised and supervised learning, advancing personalized critical care and supporting global efforts to reduce preventable ICU mortality.


  • Open Access

    Multi-Output Machine-Learning Prediction of Volatile Organic Compounds (VOCs): Learning from Co-Emitted VOCs

    by Abdelrahman Eid, Shehdeh Jodeh, Ghadir Hanbali, Mohammad Hawawreh, Abdelkhaleq Chakir, Estelle Roth

    Volatile Organic Compounds (VOCs) are important contributors to indoor and occupational air pollution, such as environments involving the extensive use of paints and solvents. The routine measurement of VOCs is often limited by resource constraints, creating a need for indirect estimation techniques. This work presents the need for a predictive framework that offers a practical, interpretable alternative to a full-spectrum chemical analysis and supports early exposure detection in resource-limited settings, contributing to environmental health monitoring and occupational risk assessment. This study explores the capability of machine learning to simultaneously predict the concentrations of five paint-related VOCs using other co-emitted VOCs along with demographic variables. Three models—Multi-Output Gaussian Process Regression (MOGP), CatBoost Multi-Output Regressor, and Multi-Output Neural Networks—were calibrated and each achieved a high predictive performance. Further, a feature importance analysis is conducted and showed that certain VOCs and some demographic variables consistently influenced the predictions across all models, pointing to common exposure determinants for individuals, regardless of their specific exposure setting. Additionally, a subgroup analysis identified the exposure disparities across demographic groups, supporting targeted risk mitigation efforts.


  • The Metrological Qualification of Commercial VOC Multisensor Systems: A Mandatory Step Prior to Indoor Air Quality Monitoring

    by Marie Verriele, David Umba, Abdelrahman Eid, Sabine Crunaire, Nathalie Redon, Nadine Locoge

    The use of multi-sensor array systems has become commonplace in indoor air quality or individual exposure applications. Nevertheless, there is a lack of reliable data, as qualification protocols are sparsely applied by end-users to multi-sensor commercial systems prior to field or lab implementation. This is especially the case with regard to VOC monitoring, although they are ubiquitous species of indoor environment. The aim of the present work is to propose an all-encompassing qualification protocol, suitable for a wide range of multi-sensor systems, able to assess the metrological performance regarding indoor VOCs. Furthermore, it provides data on metrological performance for 45 replicas of 5 types of sensors, 4 metal oxides and 1 electrochemical, embedded in a single system, under controlled conditions. Multi-sensor systems were exposed to 6 single VOCs, with their mixture representative of indoor pollution (formaldehyde, acetaldehyde, acetone, ethanol, limonene) in a 1:1 scale experimental room. Metrological performances were retrieved from the correlation curves established by comparison with the responses of a reference analyzer. The results show that the electrochemical sensor, supposedly dedicated to total VOCs, is acetone-blind and underestimates the effective quantity of TVOCs by a factor of 3. Metal oxide sensors, chosen for their reliability in establishing pollution source fingerprints, indicate effectively differentiated sensitivities by type of VOC, but without homogeneity by chemical family. A pre-processing of the data is required to overcome their non-linear responses depending on the concentration range. These results provide crucial insights for the interpretation of field campaign data retrieved from multi-sensor arrays.


  • Open Access

    Method Development for Detecting Low Level Volatile Organic Compounds (VOCs) among Workers and Residents from a Carpentry Work Shop in a Palestinian Village

    by Shehdeh Jodeh, Abdelkhaleq Chakir, Ghadir Hanbali, Estelle Roth, Abdelrahman Eid

    Volatile organic compounds (VOCs) are considered a major public health concern in industrial location areas. The presence of exposure to (VOCs) has raised concern regarding the health effects caused by chronic human exposure as this will increase cancer diseases in the village. An analytical method has been developed and modified to help us detect 38 VOCs in the blood of 38 volunteers who are related to a carpentry shop at the parts-per-trillion level. To measure and evaluate the potential risk, several devices, such as portable passive monitors and air-collected samples, in addition to blood concentration, were used to study three different occupational groups. Ten of the volunteers are employees at the shop, 10 volunteers live very close to the shop, and 10 of them are students in an elementary school very close to the shop. In this study, we developed an automated analytical method using headspace (HS) together with solid-phase microextraction (SPME) connected to capillary gas chromatography (GC) equipped with quadrupole mass spectrometry (MS). The detection limits for the method used were measured in the range from 0.001 to 0.15 ng/L, using linear calibration curves that have three orders of magnitude. The detected concentrations ranged from 3 ng L−1 for trichloroethene to 91 ng L−1 for toluene and 270 ng L−1 for 2,4-diisocyanate, which was derived from the paint solvents used for the wood in the carpentry shop and the paints on the walls. More than half of all assessed species (80%) had mean concentration values less than 50 ng L−1, which is the maximum allowed for most VOCs. The major chemical types among the compounds quantified will be those we found in our previous study in the surrounding air of a carpentry workshop in Deir Ballout in Palestine, which were toluene diisocyanate and butyl cyanate. Some were found to be highly present air. Most of the measurements were below the guidelines of the World Health Organization (WHO). Despite the fact that this study only involved a small number of smokers, smoking was found to be connected with several blood and breath components. This group includes unsaturated hydrocarbons (1,3-butadiene, 1,3-pentadiene, 2-butene), furans (2,5-dimethylfuran), and acetonitrile. The proposed classification of measured species into systemic (blood-borne) and exogenous volatiles is strictly hypothetical, as some species may have several origins.


  • KBER: A kernel bandwidth estimate using the Ricci curvature

    by Abdelrahman Eid, Nicolas Wicker

    The choice of a bandwidth can affect dramatically the accuracy of classification methods relying on it. Recently, a large number of methods to choose the bandwidth have been developed. This article presents a simple method called KBER to estimate the bandwidth using the average Ricci curvature of ɛ− graphs. The Radial Basis Function kernel (RBF) has been chosen in our work for its simplicity and its popularity in this kind of research; it is also possible to apply our method to any kernel with the same kind of parameter.


  • Open Access

    A Metropolis-Hastings Sampling of Subtrees in Graphs

    by Abdelrahman Munther Eid, Hiroshi Mamitsuka, Nicolas Wicker

    This article presents two methods to sample uniform subtrees from graphs using Metropolis-Hastings algorithms. One method is an independent Metropolis-Hastings and the other one is a type of add-and-delete MCMC. In addition to the theoretical contributions, we present simulation studies which confirm the theoretical convergence results on our methods by monitoring the convergence of our Markov chains to the equilibrium distribution.