Article Per Year (5 Year)
p-Index From 2020 - 2025
0.778
P-Index
This Author published in this journals
All Journal IAES International Journal of Artificial Intelligence (IJ-AI) Indonesian Journal of Electrical Engineering and Computer Science
Ez-zahout, Abderrahmane
Unknown Affiliation
Computer Science & IT Engineering

Published : 4 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 4 Documents
Search

 1 
Prediction of chronic diseases based on ML packages using spark MLlib Oussous, Aicha; Ez-Zahout, Abderrahmane; Ziti, Soumia
Indonesian Journal of Electrical Engineering and Computer Science Vol 37, No 2: February 2025
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v37.i2.pp1121-1129

Abstract

Heart disease, diabetes, and breast cancer pose significant global health challenges, and effectively addressing these chronic diseases necessitates a coordinated international effort. The integration of machine learning and predictive analytics offers promising solutions for tackling these issues. Our study presents a unified model that utilizes the random forest (RF) algorithm and SparkMLlib to predict these three diseases, testing the model on three distinct datasets and evaluating its performance using scientific metrics, including the receiver operating characteristic (ROC) curve, accuracy, precision, recall, and F1-score. Furthermore, we aim to investigate whether variations in medical data and contextual factors impact the results. The findings indicate that while the model shows strong overall performance, its effectiveness may differ for each disease due to factors such as data characteristics, disease-specific features, model behavior, and various biological and medical considerations; understanding these factors is essential for improving model performance and ensuring its appropriate use in clinical environments.
Reviewing chronic ailments: predicting diseases with a multi-symptom approach Oussous, Aicha; Ez-Zahout, Abderrahmane; Ziti, Soumia
Indonesian Journal of Electrical Engineering and Computer Science Vol 35, No 1: July 2024
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v35.i1.pp418-427

Abstract

The integration of machine learning (ML) techniques is now indispensable in healthcare, especially in addressing the challenges posed by chronic illnesses, which present a significant global health concern due to their unpredictable nature. This study compares ML techniques employed in the diagnosis and treatment of chronic conditions such as diabetes, liver disease, thyroid disease, breast cancer, heart disease, Alzheimer’s disease, and others. Two primary criteria guided the selection of diseases under investigation. Firstly, those extensively studied with ML methods, and secondly, those leveraging ML models to resolve issues or yield promising results. The research concludes that in real-time clinical practice, there is no universally proven method for selecting the optimal course of action due to each method’s unique advantages and disadvantages. While a hybrid technique may exhibit slightly slower speed growth, it holds the potential to enhance the accuracy and performance of a model.
Extracting contextual insights from user reviews for recommender systems: a novel method Madani, Rabie; Ez-Zahout, Abderrahmane; Omary, Fouzia
Indonesian Journal of Electrical Engineering and Computer Science Vol 35, No 1: July 2024
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v35.i1.pp542-550

Abstract

Recommender systems (RS) primarily rely on user feedback as a core foundation for making recommendations. Traditional recommenders predominantly rely on historical data, which often presents challenges due to data scarcity issues. Despite containing a substantial wealth of valuable and comprehensive knowledge, user reviews remain largely overlooked by many existing recommender systems. Within these reviews, there lies an opportunity to extract valuable insights, including user preferences and contextual information, which could be seamlessly integrated into recommender systems to significantly enhance the accuracy of the recommendations they provide. This paper introduces an innovative approach to building context-aware RS, spanning from data extraction to ratings prediction. Our approach revolves around three essential components. The first component involves corpus creation, leveraging Dbpedia as a data source. The second component encompasses a tailored named entity recognition (NER) mechanism for the extraction of contextual data. This NER system harnesses the power of advanced models such as bidirectional encoder representations from transformers (BERT), bidirectional long short term memory (Bi-LSTM), and bidirectional conditional random field (Bi-CRF). The final component introduces a novel variation of factorization machines for the prediction of ratings called contextual factorization machines. Our experimental results showcase robust performance in both the contextual data extraction phase and the ratings prediction phase, surpassing the capabilities of existing state-of-the-art methods. These findings underscore the significant potential of our approach to elevate the quality of recommendations within the realm of context-aware recommender systems.
Impact of batch size on stability in novel re-identification model Idrissi Alami, Mossaab; Ez-zahout, Abderrahmane; Omary, Fouzia
IAES International Journal of Artificial Intelligence (IJ-AI) Vol 14, No 4: August 2025
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijai.v14.i4.pp2724-2733

Abstract

This research introduces ConvReID-Net, a custom convolutional neural network (CNN) developed for person re-identification (Re-ID) focusing on the batch size dynamics and their effect on training stability. The model architecture consists of three convolutional layers, each followed by batch normalization, dropout, and max-pooling layers for regularization and feature extraction. The final layers include flattened and dense layers, optimizing the extracted features for classification. Evaluated over 50 epochs using early stopping, the network was trained on augmented image data to enhance robustness. The study specifically examines the influence of batch size on model performance, with batch size 64 yielding the best balance between validation accuracy (96.68%) and loss (0.1962). Smaller (batch size 32)and larger (batch size 128) configurations resulted in less stable performance, underscoring the importance of selecting an optimal batch size. These findings demonstrate ConvReID-Net’s potential for real-world Re-ID applications, especially in video surveillance systems. Future work will focus on further hyperparameter tuning and model improvements to enhance training efficiency and stability.
Co-Authors Idrissi Alami, Mossaab Madani, Rabie Omary, Fouzia Oussous, Aicha Ziti, Soumia