MBMohamed Bahaj

Mohamed Bahaj

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Mohamed Bahaj has a total of 20 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Integrating BERT fine-tuning and genetic algorithm for superior depression detection in social media

    by Abd Allah Aouragh, Mohamed Bahaj, Fouad Toufik

    Early detection of depression is crucial for minimizing its adverse effects on mental and physical health. Recent advancements in natural language processing facilitate the large-scale analysis of social media texts to identify depressive tendencies. Our study introduces a novel approach by integrating a genetic algorithm for hyperparameter tuning, optimizing the classification performance beyond conventional methods. We provide a comprehensive comparison of vectorization techniques, including term frequency-inverse document frequency (TF-IDF), Word2Vec, and a fine-tuned bidirectional encoder representation from transformers (BERT) model specifically adapted to our dataset. Using a dataset of 7,731 entries, we implemented standard pre-processing steps such as stop word removal and lemmatization before vectorizing the text. Five machine learning algorithms—decision tree, logistic regression, random forest, gradient boosting, and support vector machine—were evaluated, with hyperparameter tuning performed using a genetic algorithm. The highest accuracy (95.99%) and F1-score (95.91%) were achieved with the combination of fine-tuned BERT, support vector machine, and genetic algorithm optimization. This study demonstrates the advantages of integrating BERT fine-tuning with genetic optimization, outperforming traditional TF-IDF and Word2Vec approaches in depression detection.

  • Open Access

    Balancing and metaheuristic techniques for improving machine learning models in brain stroke prediction

    by Abd Allah Aouragh, Mohamed Bahaj, Fouad Toufik

    A brain stroke, medically referred to as a stroke, represents a critical condition triggered by the disruption of blood flow to a region of the brain. Early detection of stroke is crucial to prevent fatal complications. In this study, we worked with an unbalanced dataset of 4981 entries on stroke, which we balanced using the K-means synthetic minority over-sampling technique (KMeansSMOTE) algorithm. We then employed five machine learning algorithms: decision tree, random forest, support vector machine, K-nearest neighbors, and gradient boosting. We compared the hyperparameter optimization of these algorithms using four metaheuristic techniques: gray wolf optimization, particle swarm optimization, genetic algorithm, and artificial bee colony. The models' effectiveness was evaluated using multiple metrics, such as accuracy, recall, precision, F1-score, and area under the receiver operating characteristic curve. Our findings indicate that the random forest optimized by the genetic algorithm achieved the best performance, with an accuracy of 97.39% and an F1-score of 97.35%. This study highlights the effectiveness of balancing and metaheuristics techniques in optimizing machine learning models for stroke forecasting.


  • Open Access

    Enhancing hypertension prediction: a hybrid machine learning optimization approach

    by Abd Allah Aouragh, Mohamed Bahaj, Fouad Toufik

    Early identification of hypertension is crucial to prevent its serious complications, which can lead to devastating health effects by threatening lifestyle quality and significantly increasing premature mortality. This study aims to evaluate the effectiveness of machine learning techniques in predicting the presence of hypertension from an unbalanced dataset consisting of 4,363 records and 35 features. To balance the dataset, we employed the synthetic minority over-sampling technique (SMOTE) algorithm. In addition, to select the most relevant features, we used ant colony optimization. Next, we applied various algorithms, including logistic regression (LR), K-nearest neighbors (KNNs), support vector machine (SVM), extra trees (ETs), and AdaBoost (AB). We also evaluated the optimization of hyperparameters using two methods: Bayesian optimization (BO) and particle swarm optimization (PSO). The results reveal that the combination of AB with BO demonstrated superior performance, with an accuracy of 97.60%, a recall of 98.93%, and a precision of 98.59%. This research emphasizes the potential of machine learning techniques for anticipating hypertension and highlights the importance of optimization techniques in improving predictive models’ performance.

  • Open Access

    Advancing breast cancer prediction: machine learning, data balancing, and ant colony optimization

    by Abd Allah Aouragh, Mohamed Bahaj, Fouad Toufik

    Breast cancer constitutes a significant threat to women's health worldwide. The World Health Organization (WHO) reports around 2.3 million new cases each year, making this disease the primary reason for cancer-related fatalities among women. In light of this alarming situation, developing innovative tools for early detection and optimal treatment is imperative, as it directly addresses the pressing need to enhance our capabilities in the quest to overcome breast cancer. This study fits in with this approach, introducing a comparative assessment of multiple machine learning algorithms and integrating data preprocessing, data balancing and feature selection techniques. The studied Coimbra dataset, composed of 116 records and including 10 medical characteristics, exhibited promising performance in all classification metrics, reaching an accuracy of 89.74%, and an area under the receiver operating characteristic curve (AUC-ROC) of 89.68%. These findings highlight the significant potential of our approaches to improve breast cancer treatment and detection systems, providing health practitioners with more efficient resources.


  • Open Access

    Integration of ontology with machine learning to predict the presence of covid-19 based on symptoms

    by Hakim El Massari, Noreddine Gherabi, Sajida Mhammedi, Hamza Ghandi, Fatima Qanouni, Mohamed Bahaj

    Coronavirus (covid 19) is one of the most dangerous viruses that have spread all over the world. With the increasing number of cases infected with the coronavirus, it has become necessary to address this epidemic by all available means. Detection of the covid-19 is currently one of the world's most difficult challenges. Data science and machine learning (ML), for example, can aid in the battle against this pandemic. Furthermore, various research published in this direction proves that ML techniques can identify illness and viral infections more precisely, allowing patients' diseases to be detected at an earlier stage. In this paper, we will present how ontologies can aid in predicting the presence of covid-19 based on symptoms. The integration of ontology and ML is achieved by implementing rules of the decision tree algorithm into ontology reasoner. In addition, we compared the outcomes with various ML classifications used to make predictions. The findings are assessed using performance measures generated from the confusion matrix, such as F-measure, accuracy, precision, and recall. The ontology surpassed all ML algorithms with high accuracy value of 97.4%, according to the results.


  • Semantic integration of traditional and heterogeneous data sources (UML, XML and RDB) in OWL2 triplestore

    by Oussama El Hajjamy, Hajar Khallouki, Larbi Alaoui, Mohamed Bahaj

    With the success of the internet and the expansion of the amount of data in the web, the exchange of information from various heterogeneous and classical data sources becomes a critical need. In this context, researchers must propose integration solutions that allow applications to simultaneously access several data sources. In this perspective, we propose a semi-automatic integration approach of classical data sources via a global schema located in database management systems of RDF or OWL data, called triplestore. Our contribution is subdivided into three axes: 1) an automatic mapping solution that converts classical data sources such as UML, XML and RDB to local ontologies based on OWL2 language; 2) an alignment system of local ontologies based on syntactic, semantic and structural similarity measurement techniques in order to increase the probability of having real correspondences and real differences; 3) a fusion system of pre-existing local ontologies into a global ontology based on the alignment found in the previous step.


  • Lean Methods from Manufacturing to Health Care Amelioration

    by Soukayna Belkadi, Ilias Cherti, Mohamed Bahaj

  • The Storage of Data from TXML document into Temporal Object Relational Database

    by Soumiya Ain El Hayat, Mohamed Bahaj

    Extensible markup language (XML) is nowadays one of the most important standards for web information management and complex data representation. Massive Data is still treated, tagged and stored in XML Document. Yet, the most methods for processing XML Data have its difficulties due to the construction of schema-centric and semi-structured information resources of the major portion of existing XML data. Therefore, a huge amount of data treated, transferred and stored using Temporal Database system. There is a need for integrated methods that deal with for the storage of data from XML document into a temporal database. In this paper, we present the results of a research study concerning the migration of structured XML document including temporal data features into Object-Relational database according to the management varying time Data. First, we propose a data Model based on tree graph for tracking historical data in an XML Document for summarizing and indexing temporal XML documents. To achieve this, we constructing an effective index using Dewey Key with additional information structure. In our approach, we develop our own XML storage document and Build the temporal Database system according To object Relational Database concepts. In the next, we will develop our TORDB design scheme in order to simplify the migration of data from XML files into Object relational database implemented with varying time features. In addition, an algorithm is implemented for validating our solution and show that our mapping strategy is feasible and efficient.