The internet has been inundated with an ocean of information, and hence, information retrieval systems are failing to provide optimal results to the user. In order to meet the challenge, query expansion techniques have emerged as a game-changer and are improving the results of information retrieval significantly. Of late, semantic query expansion techniques have attracted increased interest among researchers since these techniques offer more pertinent and practical results to the users. These allow the user to retrieve more meaningful and useful information from the web. Currently, few research works provide a comprehensive review on semantic query expansion; usually, they cannot provide a full view on recent advances, diversified data application, and practical challenges. Therefore, it is imperative to go deep in review in order to explain these advances and assist researchers with concrete insights for future development. This article represents the comprehensive review of the query expansion methods, with a particular emphasis on semantic approaches. It overviews the recent frameworks that have been developed within a period of 2015–2024 and reviews the limitations of each approach. Further, it discusses challenges that are inherent in the semantic query expansion field and identifies some future research directions. This article emphasizes that the linguistic approach is the most effective and flexible direction for researchers to follow, while the ontology approach better suits domain-specific search applications. This, in turn, means that development of the ontology field may further open new perspectives for semantic query expansion. Moreover, by employing artificial intelligence (AI) and making most of the query context without relying on user intervention, improvements toward the optimal expanded query can be achieved.

The expanding Arabic user base presents a unique opportunity for researchers to tap into vast online Arabic resources. However, the lack of reliable Arabic word embedding models and the limited availability of Arabic corpora poses significant challenges. This paper addresses these gaps by developing and evaluating Arabic word embedding models trained on diverse Arabic corpora, investigating how varying hyperparameter values impact model performance across different NLP tasks. To train our models, we collected data from three distinct sources: Wikipedia, newspapers, and 32 Arabic books, each selected to capture specific linguistic and contextual features of Arabic. By using advanced techniques such as Word2Vec and FastText, we experimented with different hyperparameter configurations, such as vector size, window size, and training algorithms (CBOW and skip-gram), to analyze their impact on model quality. Our models were evaluated using a range of NLP tasks, including sentiment analysis, similarity tests, and an adapted analogy test designed specifically for Arabic. The findings revealed that both the corpus size and hyperparameter settings had notable effects on performance. For instance, in the analogy test, a larger vocabulary size significantly improved outcomes, with the FastText skip-gram models excelling in accurately solving analogy questions. For sentiment analysis, vocabulary size was critical, while in similarity scoring, the FastText models achieved the highest scores, particularly with smaller window and vector sizes. Overall, our models demonstrated strong performance, achieving 99% and 90% accuracies in sentiment analysis and the analogy test, respectively, along with a similarity score of 8 out of 10. These results underscore the value of our models as a robust tool for Arabic NLP research, addressing a pressing need for high-quality Arabic word embeddings.

Background: Measuring glycated hemoglobin (HbA1c) is essential for assessing long-term glycemic control, yet direct testing remains expensive and underutilized in many large-scale health surveys and resource-constrained settings. This study aims to (i) deliver a highly accurate and interpretable ML model for predicting HbA1c from routinely collected clinical, biochemical, and demographic data, (ii) reduce dependency on extensive laboratory panels by identifying a compact, cost-efficient subset of key predictors, and (iii) establish a transferable, explainable modeling framework applicable across chronic disease biomarkers. Unlike prior HbA1c prediction studies that focus primarily on classification or accuracy-driven models, this work introduces a unified framework for continuous HbA1c regression that jointly integrates cost-oriented feature parsimony, stratified regression validation, and explainability by design. Methods: We aggregated data from the National Health and Nutrition Examination Survey (NHANES) cycles 2007–2020, encompassing 66,148 records and 224 candidate features. We implemented a two-stage feature selection pipeline: Incremental Correlation Selection (ICS) to narrow the variable space, followed by Recursive Feature Elimination with Cross-Validation (RFECV) to isolate the most informative features. Model interpretability was assessed using partial dependence plots and feature importance analysis. Results: The optimal model, LightGBMRegressor with most-frequent imputation, achieved R² = 0.7161, MAE = 0.334, MSE = 0.304, and MAPE = 5.56%, while using only 40 selected features. Interpretability analysis revealed clinically coherent relationships that align with physiological expectations. Discussion: The proposed framework maintains robust predictive performance while substantially reducing the number of required input features, enabling cost-efficient HbA1c estimation together with transparent, physiologically coherent model insights. By consolidating continuous HbA1c prediction, cost-aware feature selection, stratified evaluation, and explainability within a single pipeline are enhanced. Conclusions: This study advances beyond existing approaches and offers a practical blueprint for scalable biomarker estimation in population health and clinical decision-support applications. Its explainable, efficient, and generalizable design positions it as a strong candidate for clinical decision-support and population-health applications.

The expanding Arabic user base presents a unique opportunity for researchers to tap into vast online Arabic resources. However, the lack of reliable Arabic word embedding models and limited availability of Arabic corpora pose significant challenges. This paper aims to address these gaps by conducting an experiment to train word embedding models with Arabic corpora and examine the influence of varying hyperparameter values on different NLP tasks. To gather data for training the models, we collected information from three distinct sources: Wikipedia, newspapers, and 31 Arabic books. Each corpus’s specific impact on the outcomes was analyzed. The experiment involved assessing the models across diverse NLP tasks, including sentiment analysis, similarity tests, and analogy tests. The findings revealed that both the corpus size and hyperparameter values had distinct effects on each test. In the Analogy test, employing a larger vocabulary size positively influenced the outcomes, with Fasttext models using skip-gram approaches performing well in solving Analogy Test questions. For sentiment analysis, we discovered that vocabulary size played a crucial role. In the similarity score test, Fasttext models achieved the highest scores, with lower window sizes and smaller vector sizes leading to better results. Overall, our models performed well, achieving a score of 99%, 90% accuracies for sentiment analysis and Analogy Test, respectively. Moreover, they achieved a similarity score of 8 out of 10. Our findings indicate that our models can serve as a valuable resource for Arabic NLP researchers, equipping them with a robust tool for handling Arabic text.

The integration of AI vision-based sensing and human motion analysis has grown to be a key element of intelligent perception systems, which now allow for automated interpretation of human movement, activity patterns, and complex visual behaviors. However, accurate functional movement assessment from monocular aerial and ground-view videos remains challenging due to low spatial resolution, background clutter, occlusions, and large variations in body posture, limiting the reliability of AI-assisted future healthcare applications. This study presents a multi-level framework that integrates asymmetric deep feature representation with transformer-based architecture and graph-driven optimization for robust vision-based human movement analysis. First, a Heavy Attention Transformer is employed to enhance image quality and emphasize clinically relevant anatomical and motion patterns by suppressing background interference. Panoptic segmentation and Real-Time Detection Transformer V2 are then used for subject localization, followed by skeletal keypoint extraction using YOLOv8. The proposed framework adopts an asymmetric dual-stream feature extraction strategy, where global contextual information is captured through Bag of Visual Words, Video Swin Transformer, Video Masked Autoencoder, and TimeSformer, while local biomechanical motion dynamics are modeled using DiffPose, PoseFormer, and Spatial–Temporal Graph Convolutional Networks. The key contribution lies in the asymmetric feature design that preserves the distinct information structures of visual context and skeletal dynamics. To reduce feature redundancy and select discriminative clinical representations, the Slime Mould Algorithm is utilized as a metaheuristic optimizer. The optimized features are subsequently classified using a Graph Attention Network for automated functional movement assessment. Experimental evaluation on the UAV-Human and UCF-ARG benchmark datasets achieved an accuracy of 82.50% and 78.20%, respectively. The proposed framework illustrates the potential of asymmetry-aware AI-enabled vision sensing to perform strong human movement analysis in complex viewpoints and lays the groundwork for future healthcare-related applications such as remote human movement evaluation and rehabilitation monitoring.