Article
29 December 2025
The Al-Farahidi Expert Systems Journal (FESJ) is an international, open-access publication established in 2024, dedicated to advancing research in expert systems and related computational fields. As a premier platform, FESJ focuses on cutting-edge developments in artificial intelligence, machine learning, decision-support systems, and their diverse applications across industries. The journal employs a rigorous double-blind peer review process and publishes two issues per volume annually, ensuring high-quality contributions from researchers worldwide. FESJ exclusively accepts manuscripts in English, reinforcing its commitment to global scholarly communication. As an open-access journal, it guarantees free accessibility to its content for researchers, academics, and professionals, fostering widespread knowledge dissemination. The journal prioritizes research that highlights advancements, challenges, and future directions in expert systems and their integration with real-world applications. It welcomes original research articles, comprehensive reviews, and concise communication pieces. With an efficient editorial workflow, FESJ ensures an average turnaround of 55 days from submission to acceptance, enabling the timely publication of impactful findings that contribute to the growing field of expert systems.
See the Aims and Scope for a complete coverage of the journal.
Current Issue
Volume 1, Issue 2 (2025)View issue
Featured Content
- Article29 December 2025
Deep Learning Approaches for Fatigue Detection: A Traditional Review of Models, Datasets, and Applications
Fatigue is an important factor affecting human safety, effectiveness and health in various industries, but it still is a challenge to accurately detect it. Recent advances in deep learning fuel the emergence of vision-based, physiology-based, and hybrid fatigue detection systems with better accuracy and real-time monitoring. We cover work up until 2025 and perform a meta-analysis of recent models, datasets, and methodologies. Face- and appearance-based—building system upon facial expression, eye closure, and head pose information—is highly effective but sensitive to image variation caused by illumination change (lighting condition change) or occlusions. Physiological systems based on EEG, ECG and HRV approaches are more sensitive to subtle fatigue markers but lack practicality in natural environment due to their intrusiveness. Hybrid models fusing multimodal data sources can achieve better accuracy (often more than 92%) and robustness, while at a sufficient computational cost and use of resources. Challenges identified include small and non-diverse datasets, dependence on simulated environments, as well as unaddressed ethical implications of continuous monitoring. Huge practical dataset, non-invasion sensing techniques and privacy-preserving methods under the data governance norms are necessary to address these issues. The findings of this work provide a guided path toward scalable, valid and ethically responsible deep learning fatigue prediction systems.
Current Articles
Most Popular Articles
- Article29 December 2025
Advancements in Intelligent Systems for Industrial Management: Enhancing Efficiency and Automation
The modern industrial management is quite dependent on intelligent systems that promote intensifying automation and general efficiency in different industries. With the introduction of advanced technologies in form of AI, machine learning, CPS and IoT these systems move the industrial functionality to a great extent. By combining, such technologies have the ability to quickly interpret data, detect the need for maintenance early in the line and make informed decisions, which produce highly optimized manufacturing processes. Automation has automated the process, reducing costs considerably, producing more, and maintaining high standards. Development of industry 4.0 has been a major tool in coordinating the merge of smart technologies to satisfy the efficiency in conversation between machines, software, and man. The adoption of intelligent systems has helped in increasing operational flexibility, reducing the downtime, and increased commitment to sustainability. Similar benefits have materialized in areas such as manufacturing, pharmaceuticals and logistics within which intelligent systems integration results in reduced cycle times and better inventory control and safer operations. However, the increased application of these technologies is limited by such issues as lack of compatibility of legacy systems, organizational factors, and lack of competent personnel. As predictable, it is critical to get over these hurdles to actualize the potential of intelligent systems and promote sustainable industrial efficiency. With the advancement of technology, role of intelligent systems to play in the development of industrial management policies, moving the industry towards sustainability and supporting global market success will increase. - Article29 December 2025
Analysis of Exhaust Gases from Marine Propulsion Plants Using Diffraction-Based Analytical Methods
This research deals with one of the most important environmental security issues of energy production media and equipment used in the marine field, primarily marine diesel engines used to propel ships. Initially, information was collected regarding the specific standards for the quantities and components of harmful substances emitted with the exhaust gases from marine Diesel and Gase Turbin engines. Then, modern methods for monitoring exhaust gases were reviewed, which depend on the diffraction analysis of the stream of materials present in these gases and the gas transmitters used for this purpose. The method presented in this research depends on determining the components of the gas mixture based on the linear equivalence hypothesis adopted in the thermal diagrams and applying this hypothesis in the device that was designed, which is a device for analyzing exhaust gases emitted by marine diesel engines using sensors that depend on semiconductor technology. This report includes the initial and structural drawings of the designed device, description of its basic components, test results of the device, and method of calibrating and adjusting the thermal diagrams. To solve the mathematical problems during the collection and processing of data, the method of the system of equations with decreasing degrees and the method of linear programming were used, which allows to verify the accuracy of the sequence of the algorithm for solving the problem. The algorithm of the device’s operation is also included, with some test examples for determining the components of the gas mixture emitted by marine Diesel and Gase Turbin engines. - Article29 December 2025
How the Coherent Detector Works in Spread Spectrum Signals
This research investigates the detection of direct sequence spread spectrum (DSSS) signals, comparing the performance of a traditional energy detector with that of a cross-correlation detector. While energy detectors are widely used, they suffer from reduced sensitivity at low signal-to-noise ratios (SNR) and require accurate noise power estimation. In contrast, the cross-correlation detector utilizes the processing gain of DSSS signals to achieve higher detection accuracy without needing prior noise estimation. Using MATLAB simulations, Receiver Operating Characteristic (ROC) curves were generated for both detectors. Results show that the cross-correlation detector achieves up to 30% higher probability of detection (PD) at a false alarm probability (PFA) of 0.1 and SNR = –11 dB compared to the energy detector. This demonstrates the cross-correlation detector’s robustness and suitability for reliable DSSS signal detection in noisy environments. - Article29 December 2025
ASASy: A Sentiment Analysis Corpus of Syrian Dialect Facebook Posts
A massive amount of textual data is shared each day through the different social media platforms. Analyzing this data to understand the sentiment of users (positive, negative, natural) about various topics and products is a challenging task when it comes to analyze Arabic text due to the morphological diversity and complex grammatical structure of this language, and is more challenging when analyzing social media text with the great diversity in writing style and dialects. Due to the lack of Arabic resources for Sentiment Analysis and the increasing need to create dialectical resources. In this paper, we present a Syrian dialectical Arabic dataset consists of 20k Facebook comment that are manually annotated for three classes positive, negative and natural. We used finetuned AraBERT as our baseline to evaluate our corpus. Also, compared its performance with many traditional machine learning classifiers, LSTM and MARBERT models. The experimental results show that the finetuned AraBERT outperformed all the other algorithms with f1-score of 81%. - Article29 December 2025
Artificial Intelligence in Credit Risk Assessment: Towards More Accurate and Efficient Financial Decision-Making
Credit risk assessment for customers represents one of the core foundations that support the stability of the financial system and promote sustainable economic growth. It plays a crucial role in guiding financing decisions within financial institutions by enabling the evaluation of customers’ ability to assume and manage financial risk. This capability enhances the efficiency of resource allocation and contributes to achieving a balanced approach between economic development and institutional financial safety. However, the process of credit risk assessment is inherently complex due to the interplay of numerous factors, including customers’ financial indicators and behavioral attributes. This complexity necessitates the use of advanced analytical tools that can process large volumes of financial and historical credit data with high precision, thereby facilitating more informed and reliable credit decisions. In this regard, artificial intelligence (AI) has emerged as a transformative tool, demonstrating high effectiveness in improving the accuracy of credit risk evaluation. AI’s ability to swiftly analyses vast and complex datasets significantly enhances decision-making processes while reducing the probability of human error. This research proposes the development of a comprehensive scientific model based on AI techniques for assessing customer credit risk. Specifically, the LightGBM algorithm was applied, yielding an accuracy rate of 92%, while a deep neural network model achieved an accuracy of 87%. These findings illustrate the substantial potential of AI in enhancing credit risk management mechanisms and reinforcing the financial resilience of institutions. The study further underscores the importance of adopting advanced technological solutions to address contemporary financial challenges and to support the pursuit of long-term economic sustainability. - Article29 December 2025
Evaluating Vision Transformers in End-to-End Steering Angle and Speed prediction of Autonomous Vehicles Using Monocular Camera Video Input on Highways
End-to-end autonomous driving systems have recently gained significant interest due to the rapid advancement of deep learning algorithms. This progress has enabled the development of intelligent agents that can drive vehicles like or potentially better than humans in some scenarios. This study investigates using Vision Transformers (ViTs) in end-to-end autonomous driving systems to predict vehicle steering angle and speed through behavior cloning. The paper suggests two models: a single-head ViT-MLP architecture that jointly predicts steering angle and speed and a multi-head model designed with two separate heads: one for steering angle prediction and the other for speed prediction. The models were trained on the Comma 2K19 dataset, which includes 33 hours of highway driving. The results indicated that the single-head model outperformed the multi-head architecture and previous methods, achieving an average MAE of 0.198. Although the model demonstrates strong performance in stable conditions, such as lane-keeping, its efficacy decreases during sudden maneuvers, such as overtaking, and in challenging lighting and weather conditions. These findings emphasize the potential of ViTs for creating cost-effective highway autonomous systems but also point out the necessity for improved robustness through sensor fusion or additional training features.