Explore the vast range of titles available.

Poorly maintained roads can cause lethal automobile accidents in various ways. Thus, detecting and reporting damaged parts of roads is one of the most crucial road maintenance tasks, and it is vital to identify the type and severity of the damage to help fix it as soon as possible. Several researchers have used computer vision and detection algorithms to detect and classify road damages, including cracking, distortion, and disintegration. Providing automatic road damage detection methods can help municipalities save time and effort and speed up maintenance operations. This study proposes a method to classify road damage and its severity based on CNN and trained on a newly curated dataset collected from Saudi roads. Hence, this study also presents a dataset with labeled classes, which are cracks, potholes, depressions, and shoving. The dataset was collected in collaboration with maintenance employees in the municipality of Rabigh Governorate using a smartphone device and reviewed by experts. In addition, several deep learning algorithms were implemented and evaluated using the proposed dataset. The study found that the proposed custom CNN (RoadNet) has higher accuracy than pre-trained models.

Intercropping regimes enhance the efficiency of land use and ecological sustainability but present serious problems to automated disease analysis since the overlapping canopy and the similarity of symptoms in crop species are visually indistinguishable. This work presents an explainable artificial intelligence (XAI)-based hyperspectral analysis on leaf disease in intercropping systems. The framework combines the spectral-spatial feature generators that utilize transformers including vision transformer (ViT), Swin transformer, pyramid vision transformer (PVT), and detection transformer (DETR) to identify nuanced biochemical and structural changes in crop combinations for maize-soybean and pea-cucumber. In order to reduce spectral redundancy and high dimensionality, an enhanced greedy political optimization (EGPO) algorithm is used as a wrapper-based feature selection strategy. A capsule spatial shift neural network (CSSNet) is used to predict the classification of diseases. Explainable AI methods, such as Local Interpretable Model-agnostic Explanations (LIME) and SHapley Additive exPlanations (SHAP) feature attribution analysis and gradient-weighted class activation mapping (Grad-CAM) visualization of disease-relevant regions, provide model transparency. The DETR + EGPO + CSSNet framework is tested on the conventional feature selection methods. The results or findings on publicly available hyperspectral datasets on intercropping show an average recall of 99.998% with high region consistency (Dice score: 99.997%) of activation maps and expert-marked disease regions. These findings affirm that the proposed framework is highly accurate, stable, and interpretable to identify subtle and overlapping disease in leaves in a complex system of intercropping.

Accurate assessment of transformer insulating paper is vital for reliable operation and optimal transformer management, with the Degree of Polymerization (DP) serving as a primary indicator of insulation health. Direct DP measurement is often impractical, prompting this study to explore machine learning models for predicting DP using 2-Furfuraldehyde (2-FAL), a cellulose degradation byproduct measurable in transformer oil. This approach classifies insulation into four categories—Fresh (DP: 700–1200), Lightly Aged (DP: 450–700), Moderately Aged (DP: 250–450), and Worstly Aged (DP < 250)—based on DP values, offering a streamlined alternative to conventional multi-gas diagnostic methods. Supervised machine learning algorithms were developed using IEEE C57.104-2019 standard data, employing regression (Linear Regression, Polynomial Regression, Random Forest Regressor) to predict continuous DP and classification (Logistic Regression, Support Vector Machine with RBF kernel, Random Forest Classifier) to categorize insulation condition. Model performance was evaluated using regression metrics (Mean Squared Error, Mean Absolute Error, R² Score) and classification metrics (accuracy, precision, recall, F1-score). The Random Forest Regressor (R²: 0.894) and Classifier (accuracy: 0.925) demonstrated superior performance, enabling precise, non-invasive DP estimation and condition assessment. These findings highlight the efficacy of 2-FAL-based machine learning models for transformer health monitoring, facilitating predictive maintenance and enhancing operational reliability.

Deep learning has made great progress in many fields. One of the most important fields is the medical field, where we can classify images, detect objects and so on. More specifically, deep learning algorithms entered the field of single-cell classification and revolutionized this field, by classifying the components of the cell and identifying the location of the proteins in it. Due to the presence of large numbers of cells in the human body of different types and sizes, it was difficult to carry out analysis of cells and detection of components using traditional methods, which indicated a research gap that was filled with the introduction of deep learning in this field. We used the Human Atlas dataset which contains 87,224 images of single cells. We applied three novel deep learning algorithms, which are CSPNet, BoTNet, and ResNet. The results of the algorithms were promising in terms of accuracy: 95%, 93%, and 91%, respectively.

Large Language Models (LLMs) have advanced rapidly, driving major progress in Natural Language Processing (NLP) tasks. However, this advancement has also raised significant concerns about its potential misuse, particularly in academic and research contexts, such as the production of unoriginal or fabricated content. To address this challenge, we propose a robust approach for detecting artificial intelligence (AI)-generated text that emphasizes a deep understanding of linguistic context. Our methodology leverages cutting-edge language models, specifically Distilled Bidirectional Encoder Representations from Transformers (DistilBERT) and Cross-lingual Language Model-Robustly Optimized BERT Pretraining Approach (XLM-RoBERTa), to extract deep semantic features from text. These features capture intricate linguistic nuances, including contextual cues, stylistic patterns, and semantic relationships, which are critical for accurately differentiating human-written text from machine-generated text (MGT). We employ the Extreme Gradient Boosting (XGBoost) algorithm to enhance classification accuracy, a powerful machine learning technique renowned for its efficiency and predictive capability. We evaluated the proposed approach on two extensive English datasets, Daigt-V4 and LLM-Detect AI-Generated Text, extracting features primarily from the uppermost transformer layers that capture high-level semantic information. Similarly, for multilingual evaluation using XLM-RoBERTa on the Urdu Human and AI Text (UHAT) dataset, we applied a layer-weighting mechanism that combines representations from all transformer layers. This mechanism assigns trainable weights to each layer’s output, enabling the model to balance low-level syntactic and high-level semantic patterns, thereby enhancing cross-lingual robustness. Our experiments showed that DistilBERT performed well in comparison with XLM-RoBERTa by an average of 2% on the Daigt-V4 dataset. Specifically, XLM-RoBERTa achieved 94% accuracy, while DistilBERT reached 96% accuracy on the same dataset. On the LLM-Detect AI-Generated Text dataset, both models achieved 99% accuracy. In contrast, on the UHAT dataset, the model achieved a promising accuracy of 85%, demonstrating the effectiveness of the layer-weighting mechanism in handling cross-lingual challenges.

The proposed Architecture will provide the processing and analysis essential to accurate and reliable detection of brain tumors from MRI, for timely diagnosis and evidence-based decisions. Medical imaging now routinely enters clinical assessment; the thrust is shifting toward attaining high performance within open and governed systems to enable deployment in real-world healthcare applications. This paper proposes a two-stage deep learning framework: first, DeepLabV3 for segmentation to demarcate candidate tumor regions, and then CNN to classify whether a tumor exists. The different components employ pre-trained models through transfer learning and fine-tuning. The DeepLabV3 and CNN architectures are used, together with metric computation modules. This approach will be tested on BraTS MRI data. For efficient model training, optimizers such as SGD, RMSprop, and Adam can be employed. The classification performance could be achieved with a high value of 99.31% using an ADAM optimizer in the proposed architecture. Besides, both the precision and recall are very high, indicating good generalization and stable performance. Moreover, segmenting before classification provides more reliable detection compared to using a single-stage model. These results indicate that feature learning guided by segmentation enhances tumor detection with a binary classifier, while remaining interpretable and robust. This makes the framework much more transparent and easy to audit, suitable for use in cloud-enabled, secure, and IoT-enabled clinical environments. It therefore proposes a two-layer deep learning architecture that effectively incorporates precise tumor localization into explicit binary tumor detection. Beyond this, the work focuses on practical clinical applicability, robust data governance, and deployment-ready systems rather than diagnosing subtypes of tumors.

Different computational models for generating analogies of the form \"A is to B as C is to D\" have been proposed over the past 35 years. However, analogy generation is a challenging problem that requires further research. In this article, we present a new approach for generating analogies in Multiple Choice Question (MCQ) format that can be used for students' assessment. We propose to use existing high-quality ontologies as a source for mining analogies to avoid the classic problem of hand-coding concepts in previous methods. We also describe the characteristics of a good analogy question and report on experiments carried out to evaluate the new approach. (Contains 3 tables and 1 figure.) [This paper was published in the ALT-C 2012 Conference Proceedings.]

Abnormal behavior detection in dense crowd, during the Hajj pilgrimage is vital to public security. Existing approaches face challenges due to factors like occlusions, illumination variations, and uniform attire. This research introduces the Crowd Anomaly Detection Framework (CADF), an improved YOLOv8-based model, integrating Soft-NMS to improve detection accuracy under complex conditions. CADF extensively evaluated on the Hajjv2 dataset, delivering an AUC of 88.27%, a 13.09% improvement over YOLOv2 and 12.19% over YOLOv5, with an Accuracy of 91.6%. To validate its generalizability, the framework is also tested on UCSD and ShanghaiTech datasets. Comparisons with state-of-the-art models, including VGG19 and EfficientDet, demonstrated CADF’s superiority in accuracy, AUC, precision, recall, and mAP metrics. By addressing the unique challenges of Hajj crowd and achieving strong performance across diverse datasets, CADF highlights its potential for real-time crowd anomaly detection, contributing to enhanced safety in large-scale public gatherings and aligning with Sustainable Development Goals 3 and 11.

Educational data mining (EDM) uses data mining techniques to analyze huge amounts of student data in the educa-tional environments. The main purpose of EDM is to analyze and solve educational issues and, consequently, improve educational processes. With the emergence of EDM applications in the educational environments, several techniques have been identified to implement these applications. This paper reviews the relevant studies in EDM including datasets and techniques used in those studies and identifies the most effective techniques. The most prevalent applications include predicting student performance, detecting undesirable student behaviors, grouping students and student modeling. These applications aim to help decision makers in the educational institutions to understand student situations, improve students’ performance, identify learning priorities for different groups of students and develop learning process. The prediction accuracy is selected as the evaluation criteria for the effectiveness of educational data mining techniques. The results show that Bayesian Network and Random Forest are the most effective techniques for predicting student performance, Social Network Analysis is the best technique for detecting undesirable student behaviors, Clustering and Social Network Analysis are the most effective techniques for grouping students and student modeling, respectively. This study recommends conducting more comprehensive and extended studies to evaluate the effectiveness of EDM techniques with an extended evaluation criteria.