Abdellatif BEKKAR

Dr. Abdellatif BEKKAR

University Hassan II-Casablanca, Faculty of Science and Techniques, Mohammedia, Casablanca-Settat, Morocco
orcid
Ph.D Researcher | AI & Data Science for Smart Cities & Envir...

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
22 December 2021 in Journal of Big Data
Verified
Journal Article
Open access
PDF file
Abdellatif BEKKARAbdellatif BEKKAR
Abdellatif BEKKAR
BHBadr Hssina
Badr Hssina
SDSAMIRA Douzi
SAMIRA Douzi
KDKhadija Douzi
Khadija Douzi
Over the past few decades, due to human activities, industrialization, and urbanization, air pollution has become a life-threatening factor in many countries around the world. Among air pollutants, Particulate Matter with a diameter of less than $$2.5 \mu m$$ 2.5 μ m ( $$PM_{2.5}$$ P M 2.5 ) is a serious health problem. It causes various illnesses such as respiratory tract and cardiovascular diseases. Hence, it is necessary to accurately predict the $$PM_{2.5}$$ P M 2.5 concentrations in order to prevent the citizens from the dangerous impact of air pollution beforehand. The variation of $$PM_{2.5}$$ P M 2.5 depends on a variety of factors, such as meteorology and the concentration of other pollutants in urban areas. In this paper, we implemented a deep learning solution to predict the hourly forecast of $$PM_{2.5}$$ P M 2.5 concentration in Beijing, China, based on CNN-LSTM, with a spatial-temporal feature by combining historical data of pollutants, meteorological data, and $$PM_{2.5}$$ P M 2.5 concentration in the adjacent stations. We examined the difference in performances among Deep learning algorithms such as LSTM, Bi-LSTM, GRU, Bi-GRU, CNN, and a hybrid CNN-LSTM model. Experimental results indicate that our method “hybrid CNN-LSTM multivariate” enables more accurate predictions than all the listed traditional models and performs better in predictive performance.

22 August 2024 in PLOS ONE
Verified
Journal Article
Open access
PDF file
Abdellatif BEKKARAbdellatif BEKKAR
Abdellatif BEKKAR
BHBadr Hssina
Badr Hssina
NANajib Abekiri
Najib Abekiri
SDSAMIRA Douzi
SAMIRA Douzi
KDKhadija Douzi
Khadija Douzi
Urbanization and industrialization have led to a significant increase in air pollution, posing a severe environmental and public health threat. Accurate forecasting of air quality is crucial for policymakers to implement effective interventions. This study presents a novel AIoT platform specifically designed for PM2.5 monitoring in Southwestern Morocco. The platform utilizes low-cost sensors to collect air quality data, transmitted via WiFi/3G for analysis and prediction on a central server. We focused on identifying optimal features for PM2.5 prediction using Minimum Redundancy Maximum Relevance (mRMR) and LightGBM Recursive Feature Elimination (LightGBM-RFE) techniques. Furthermore, Bayesian optimization was employed to fine-tune hyperparameters of popular machine learning models for the most accurate PM2.5 concentration forecasts. Model performance was evaluated using Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and the coefficient of determination (R2). Our results demonstrate that the LightGBM model achieved superior performance in PM2.5 prediction, with a significant reduction in RMSE compared to other evaluated models. This study highlights the potential of AIoT platforms coupled with advanced feature selection and hyperparameter optimization for effective air quality monitoring and forecasting.

1 July 2024 in International Journal of Computing and Digital Systems
Verified
Journal Article
Closed access
PDF file
AEAbdellah Ait Elouli
Abdellah Ait Elouli
ECEl Mehdi Cherrat
El Mehdi Cherrat
HOHassan Ouahi
Hassan Ouahi
Abdellatif BEKKARAbdellatif BEKKAR
Abdellatif BEKKAR

3 March 2022
Verified
Conference Paper
Closed access
Abdellatif BEKKARAbdellatif BEKKAR
Abdellatif BEKKAR
BHBadr Hssina
Badr Hssina
SDSamira Douzi
Samira Douzi
KDKhadija Douzi
Khadija Douzi
Forecasting air pollution is crucial as it not only affects the physical health of people but also provides guidance for pollution control. Particulate Matter with a diameter of less than $2.5\mu m$ (PM 2.5 ) is one of the major contributors to air pollution which can cause acute and chronic effects on human health. Forecasting PM 2.5 involves various meteorological factors as well as the influence of historical data. Therefore, the prediction of the surface PM 2.5 concentration is of great importance for the protection of human health. This study uses machine learning models, namely Decision Tree (DT), Random Forest (RF), and Gradient Boosting Regressor (GBR) to predict PM 2.5 hourly scale concentrations, using meteorological data and PM 2.5 concentrations from adjacent stations. The dataset was collected in the city of Beijing in China as a study region. The experiments have shown that the gradient boosting regressor model achieves higher predictive precision than the other models proposed for estimating hourly PM 2.5 concentrations with an $R^{2}$ value varying between 0.9 and 0.97. This work offers a promising and affordable approach to robustly predict PM 2.5 concentrations.

16 June 2024 in International Journal of Information Technology
Verified
Journal Article
Closed access
PDF file
AAAit Elouli Abdellah
Ait Elouli Abdellah
HOHassan Ouahi
Hassan Ouahi
ECEl mehdi Cherrat
El mehdi Cherrat
Abdellatif BEKKARAbdellatif BEKKAR
Abdellatif BEKKAR

22 November 2023
Verified
Conference Paper
Closed access
Abdellatif BEKKARAbdellatif BEKKAR
Abdellatif BEKKAR
BHBadr Hssina
Badr Hssina
SDSamira Douzi
Samira Douzi
KDKhadija Douzi
Khadija Douzi
Ozone is a major air pollutant that can cause respiratory problems and other health risks. It is formed when pollutants from cars, power plants, and other sources react in the presence of sunlight. Morocco is particularly vulnerable to ozone pollution due to its hot, dry climate. In recent years, there has been a growing interest in using machine learning to predict ozone pollution. Transformers are a type of neural network that have been shown to be effective in a variety of natural language processing tasks, and they have recently been applied to the problem of ozone prediction. In this paper, we present a transformer-based model for predicting ozone in Morocco. We use a dataset of historical ozone measurements and weather data to train our model. Our model is able to predict ozone with high accuracy, and it can be used to improve ozone management in Morocco.