Abdelfettah SOULTANA

Abdelfettah SOULTANA


Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
14 November 2024 in IEEE Access
Verified
Journal Article
Open access
SBSoukaina Bouhsissin
Soukaina Bouhsissin
NSNawal SAEL
Nawal SAEL
FBFaouzia BENABBOU
Faouzia BENABBOU
ASAbdelfettah SOULTANA
Abdelfettah SOULTANA
AJAyoub Jannani
Ayoub Jannani
The advancement of intelligent transportation systems is crucial for improving road safety and optimizing traffic flow. In this paper, we present SafeSmartDrive, an integrated transportation monitoring system designed to detect and assess critical elements in the driving environment while simultaneously monitoring driver behavior. The system is structured into four key layers: perception, filtering and preparation, detection and classification, and alert. SafeSmartDrive focuses on two primary objectives: (1) detecting and assessing essential traffic elements, including vehicles (buses, cars, motorcycles, trucks, bicycles), traffic signs and lights, pedestrians, animals, infrastructure damage, accident classification, and traffic risk assessment, and (2) evaluating driver behavior across various road types, such as highways, secondary roads, and intersections. Machine learning and deep learning algorithms are employed throughout the system’s components. For traffic element detection, we utilize YOLOv9 in this paper, which outperforms previous versions like YOLOv7 and YOLOv8, achieving a precision of 83.1%. Finally, we present the evaluation of the SafeSmartDrive system’s real-time detection capabilities in a specific scenario in Casablanca. SafeSmartDrive’s comprehensive architecture offers a novel approach to improving road safety through the integration of advanced detection, classification, and risk assessment capabilities.

1 July 2024 in Indonesian Journal of Electrical Engineering and Computer Science
Verified
Journal Article
Open access
PDF file
SBSoukaina Bouhsissin
Soukaina Bouhsissin
NSNawal SAEL
Nawal SAEL
FBFaouzia BENABBOU
Faouzia BENABBOU
ASAbdelfettah SOULTANA
Abdelfettah SOULTANA
Machine learning (ML) techniques empower computers to learn from data and make predictions or decisions in various domains, while preprocessing methods assist in cleaning and transforming data before it can be effectively utilized by ML. Feature selection in ML is a critical process that significantly influences the performance and effectiveness of models. By carefully choosing the most relevant and informative attributes from the dataset, feature selection enhances model accuracy, reduces overfitting, and minimizes computational complexity. In this study, we leverage the UAH-DriveSet dataset to classify driver behavior, employing Filter, embedded, and wrapper methods encompassing 10 distinct feature selection techniques. Through the utilization of diverse ML algorithms, we effectively categorize driver behavior into normal, drowsy, and aggressive classes. The second objective is to employ feature selection techniques to pinpoint the most influential features impacting driver behavior. As a results, random forest emerges as the top-performing classifier, achieving an impressive accuracy of 96.4% and an F1-score of 96.36% using backward feature selection in 7.43 s, while K-nearest neighbour (K-NN) attains an accuracy of 96.29% with forward feature selection in 0.05 s. Following our comprehensive results, we deduce that the primary influential features for studying driver behavior include speed (km/h), course, yaw, impact time, road width, distance to the ahead vehicle, vehicle position, and number of detected vehicles.

31 August 2022 in International Journal of Interactive Mobile Technologies (iJIM)
Verified
Journal Article
Open access
PDF file
ASAbdelfettah SOULTANA
Abdelfettah SOULTANA
FBFaouzia BENABBOU
Faouzia BENABBOU
NSNawal Sael
Nawal Sael
SOSara Ouahabi
Sara Ouahabi
In recent years, a significant increase in road accidents worldwide has been observed. This can partly be due to either driver distraction or fatigue. Therefore, a reliable alerting system that can detect the driver's inattention including fatigue, sleep, and distraction is necessarily required to prevent any potential accidents. The aim of this paper is to conduct a systematic review of literature (SLR) on monitoring driver inattention. In particular, the present study deals with different aspects of prior studies such as the sensors used; the types of data, the feature engineering techniques, the machine-learning techniques applied and their performance along with, the dataset used, etc. anotherFour approaches can be depicted from literature according to indicators they are based on: physiological, physical, driver performance and hybrid approach. We will focus on these different approaches in order to answer different questions, starting with the type of indicators used in the case of distraction or fatigue detection, the different datasets employed, the feature extraction techniques and the machine learning models applied. Furthermore, the study examines the practicality and reliability of each of the four approaches, as well as possible future prospects in the area, and highlights new challenges in the field of driver inattention detection with both forms of fatigue and distraction.

28 December 2023 in Arabian Journal for Science and Engineering
Verified
Journal Article
Closed access
PDF file
ASAbdelfettah SOULTANA
Abdelfettah SOULTANA
FBFaouzia BENABBOU
Faouzia BENABBOU
NSNawal SAEL
Nawal SAEL

1 December 2024 in IAES International Journal of Artificial Intelligence (IJ-AI)
Verified
Journal Article
Open access
PDF file
ASAbdelfettah SOULTANA
Abdelfettah SOULTANA
FBFaouzia BENABBOU
Faouzia BENABBOU
NSNawal SAEL
Nawal SAEL
SBSoukaina Bouhsissin
Soukaina Bouhsissin
Driver inattention has emerged as a critical concern impacting road safety, resulting in an alarming surge in accidents and fatalities. This research introduces a novel system for detecting inattention, structured across six levels: perception, facial feature extraction, tracking driver face, and driver secondary task using pre-trained deep learning models, inattention detection, risk estimation, and alert. The system is based on image processing captured from two strategically positioned cameras that simultaneously capture the driver’s activities while driving and their facial expressions. The second contribution concerns the driver facial features extraction using multi-task cascaded convolutional networks (MTCNN), and it is comparison with the histogram of gradient (HOG)-based frontal face detector, and haar feature based cascade classifier. The algorithms were compared based on their runtime efficiency, robustness in handling varying lighting conditions, and various head movements. The MTCNN achieves high performance, reaching accuracy levels ranging from 96.4% to 99.5% on two datasets including realistic driving scenarios: the DrivFace dataset and, the driver drowsiness dataset. The comparative analysis sheds light on the strengths and weaknesses of each algorithm, providing valuable insights for selecting the most suitable face detection algorithm to use in our system.

1 March 2025 in Indonesian Journal of Electrical Engineering and Computer Science
Verified
Journal Article
Open access
PDF file
ASAbdelfettah SOULTANA
Abdelfettah SOULTANA
FBFaouzia BENABBOU
Faouzia BENABBOU
NSNawal SAEL
Nawal SAEL
SBSoukaina Bohsissin
Soukaina Bohsissin
Recognizing the pivotal importance of monitoring driver inattention in the quest to minimize accidents and enhance safety and security, it is essential to highlight the inherent danger posed by drowsiness-a specific form of inattention that can significantly contribute to accidents. To address this issue, several propositions involving artificial intelligence have been put forth to effectively monitor and identify instances of driver drowsiness. However, challenges persist in the form of real-time processing constraints, the intricate nature of model parameters, and the response time of the model. The proposed methodology focuses on using convolutional neural networks (CNNs) and Residual blocks as robust and effective deep-learning models for the real-time detection of driver drowsiness. The integration of CNNs and Residual blocks enhances the model's precision, striking a well-balanced synergy between computational efficiency and performance. Notably, this approach demonstrated an impressive accuracy of 96.09% along with a recall, f1-score, and precision all at 96% when evaluated on the publicly available eye_dataset. Furthermore, the runtime of the developed model is a mere 70 ms. To further validate the efficiency of our proposed model, we conducted a comparative analysis with various pre-trained residual neural networks, including ResNet152, ResNet50, ResNet50v2, ResNet101, and ResNet101v2.