Asphalt roads play a vital role in land transportation systems, significantly contributing to the growth and development of economies and societies. However, over time, the quality of these roads deteriorates due to aging and the cumulative effects of wear and tear, leading to various pavement and road issues such as potholes, cracks, and damaged sidewalks. This paper aims to develop a deep learning model, specifically leveraging the YOLOv8 object detection framework, to detect and classify road infrastructure problems using images captured from unmanned aerial vehicles (UAVs). The model processes a series of road images from the Roboflow dataset and was trained on Google Colab, utilizing advanced machine learning techniques to analyze the images and accurately identify road damage. Subsequently, the model was evaluated using metrics such as accuracy, recall, precision, and F1-score. The results demonstrated that the model is both efficient and reliable. The model achieved high performance, with an F1-score of 94 %, precision of 93 %, and recall of 95 %, which indicates its effectiveness in identifying various road defects. By detecting and locating issues such as potholes, cracks, and sidewalk damage, this model offers a promising solution for maintaining road infrastructure, supporting smart transportation systems, enhancing road safety, and helping reduce hazards and accidents.

Criminals, including terrorists, may use Twitter to communicate and share their ideologies. They often employ multiple accounts for anonymity. While the other accounts hide their identities and use it for different purposes (e.g., communication with unknown criminals), they use one to write tweets revealing their beliefs and spreading evil thoughts (e.g., racism and bullying). Since these multiple accounts will not have the same contents, stakeholders cannot rely on the contents to detect various accounts belonging to the same person. Using stylometric features may help to detect these accounts as they depend on the writing style of a person rather than the content of the words and their meaning. In this article, we build a model and use stylometric features that differ from the state-of-the-art, such as n-gram for part-of-speech tag, frequency of repeated characters, number of emojis, and more. These features distinguish our approach from existing methods. We evaluated different machine and deep learning classifiers to make comparisons. Our results highlight the effectiveness of our feature set, achieving a remarkable accuracy of 96%. Additionally, our findings indicate that machine learning classifiers exhibit superiority over their deep learning counterparts in the context of this study. Furthermore, we developed a comprehensive dashboard that offers users an in-depth analysis of different Twitter accounts and ranks their similarities. The dashboard serves as a valuable tool for gaining insights into the relationships and similarities among the analyzed Twitter accounts.

Historical documents contain great information for scientific and literary research. Many documents suffer from degradation, especially on initial pages, making identifica- tion difficult when no attribution exists.Arabic historical documents have two challenges: Complexity of the script and poor physical condition. We address the problem of identity loss in Arabic historical documents by presenting a deep learning-based approach. We used a subset of the WAHD dataset comprising 16,491 images: known authors 60% and unknown authors 40%.Data augmentation was applied to enhance diversity. The data was split into 70% for training, 10% testing, and 20% validation. We implemented two models:The first, Deep Writer, is a deep convolutional neural network with a dual-path architecture, consisting of multiple convolutional, pooling, and fully con- nected layers. The second, Half Deep Writer, a similar structure but uses a single pipeline. We experimented different learning rates and found 0.0001 and 0.0002 gave optimal results. Model performance was evaluated using precision, recall, and F1-score to handle class imbalance. The Deep Writer model achieved 92.28% accuracy and an F1-score of 81.16%, while the Half Deep Writer model achieved 92.10% accuracy and an F1-score of 81.63% at a learning rate of 0.0002.

Global energetic transition necessitates efficient and clean combustion technologies for alternative fuels. Biogas (primarily CH₄ and CO₂) and syngas (primarily H₂ and CO) are promising renewable and low-carbon energy carriers. Sustainable energy transition requires improved fuel combustion while minimizing pollutant emissions, especially nitrogen oxides (NOx). This calls for an inclusive understanding of emissions formation, complex flame dynamics, and combustion behavior, particularly in turbulent regimes. Presently, a comprehensive analysis of turbulent, non-premixed biogas-syngas mixtures, integrating fuel composition, turbulence, and injection velocity, is lacking. This present paper addresses this gap through developing a novel approach that integrates high-fidelity Computational Fluid Dynamics with an Artificial Intelligence. Through systematic evaluation of turbulence models, the SST k-ω model is the most effective in capturing the flame structure and species distribution. Using the validated model, the impact of CH₄ and H₂ molar fractions on flame structure (temperature, thickness, key radicals) and NOx emissions is studied. Subsequently, investigating the fuel injection velocity influence on combustion characteristics. Finally, develop and validate a robust AI-based predictive model using a Multi-Adaptive Neuro Fuzzy System for combustion species as a fast and accurate optimization tool. The influence of fuel composition was examined, showing that an increase in the H₂ fraction in the syngas raises the flame temperature but reduces NOx emissions under certain conditions. Conversely, the addition of CH₄ increases both temperature and NOx. The injection velocity also influences flame structure and emissions.

Robotic grinding quality remains difficult to guarantee due to the inherent flexibility and high vibration of industrial robots, which leads to compromised surface finishes. Current industrial practices rely heavily on subjective manual expertise and inefficient trial-and-error procedures. This study was motivated by the critical lack of predictive classification frameworks specifically tailored for automated grinding parameters in aluminum machining. A comprehensive dataset consisting of 350 experimental points from aluminum workpieces was analyzed across seven primary settings: height, force, time, diameter, grinding, press, and speed. The methodology employed Multiple Linear Regression (MLR) as a baseline, followed by tree-based ensemble methods, specifically Random Forest (RF) and Extreme Gradient Boosting (XGBoost), to categorize surface quality and capture complex nonlinear interactions. Statistical analysis confirmed that Height, Force, and Diameter were the most significant predictors for quality classification. While the linear model exhibited low explanatory power with an R ² ≈ 0.105, both RF and XGBoost models achieved classification accuracies of approximately 75%. This study contributes a robust predictive foundation for autonomous robotic deployment by quantifying the interplay of operational variables. The identification of Path Geometry (height) and Contact Mechanics (force) as dominant factors offers an essential framework for replacing time-consuming manual corrections with proactive, data-driven quality control.