Search Results (9,936)

Background/Objectives: The current study aims to investigate the rate and the factors associated with mobile screen dependence as a coping mechanism among women residing in Jordan and screened for stress, with a focus on demographics and insomnia. Methods: This cross-sectional study with predefined inclusion criteria used validated tools to assess stress, anxiety, and insomnia. Results: The data analyzed from 431 women showed that 265 (61.5%) were ≤25 years old, 352 (81.7%) received a university education, and 201 (46.6%) were current students. In addition, 207 (48.0%) reported a dependence on mobile screens for coping, 107 (24.8%) reported severe anxiety, and 180 (41.7%) reported severe insomnia. The multivariable regression analysis revealed that mobile screen dependence—as a personal coping choice—was significantly associated with “students” (OR = 1.75, 95% CI = 1.19–2.57, p = 0.004) and “severe insomnia” (OR = 1.07, 95% CI = 1.07–2.32, p = 0.02). Conclusions: We report that a high rate of mobile dependence is associated with students and insomnia. Prompt action should be taken to raise awareness regarding the proper coping mechanisms in this population. Full article

Background: Natural nootropic compounds are evidenced to restore brain function in clinical and older populations and are purported to enhance cognitive abilities in healthy cohorts. This study aimed to provide neurocomputational insight into the discrepancies between the remarkable self-reports and growing interest in nootropics among healthy adults and the inconclusive performance-enhancing effects found in the literature. Methods: Towards this end, we devised a randomised, double-blinded, and placebo-controlled study where participants performed a visual categorisation task prior to and following 60 days of supplementation with a plant-based nootropic, while electroencephalographic (EEG) signals were concurrently captured. Results: We found that although no improvements in choice accuracy or reaction times were observed, the application of multivariate information-theoretic measures to the EEG source space showed broadband increases in similar and complementary interdependencies across brain networks of various spatial scales. These changes not only resulted in localised increases in the redundancy among brain network interactions but also more significant and widespread increases in synergy, especially within the delta frequency band. Conclusions: Our findings suggest that natural nootropics can improve overall brain network cohesion and energetic efficiency, computationally demonstrating the beneficial effects of natural nootropics on brain health. However, these effects could not be related to enhanced rapid perceptual decision-making performance in a healthy adult sample. Future research investigating these specific compounds as cognitive enhancers in healthy populations should focus on complex cognition in deliberative tasks (e.g., creativity, learning) and over longer supplementation durations. Clinical trials registration number: NCT06689644. Full article

This study employs two distinct machine learning (ML) methodologies to investigate the impact of 12 different key climatic variables on wheat production efficiency, a crucial component of the global and Turkish agricultural economy. Neural network (NN) and eXtreme Gradient Boosting (XGBoost) algorithms are utilised to model wheat production performance using climate variable data, including greenhouse gases, from 1990 to 2024. The models incorporate a total of 21 different independent variables, comprising 9 climatic variables (daytime and nighttime total 18 variables) and 3 distinct greenhouse gas variables, considering day and night values separately. Wheat production efficiency analyses indicate that between 2005 and 2024, Turkey’s wheat cultivation area decreased, while production efficiency increased. ML analyses reveal that greenhouse gases are the most influential variables in wheat production. XGBoost identified four different variables associated with wheat production, whereas the neural network determined that five different variables affect wheat production. While the influence of greenhouse gases was observed in both ML models, it was concluded that nighttime humidity, daytime 10 m v-wind, and daytime 2 m temperature may be additional climatic factors that will impact wheat production in the future. This study elucidates the complex relationship between climate change and wheat production in Turkey. The findings emphasise the importance of the potential for predicting wheat yields with the dual influence of climatic factors and informing agricultural producers about such next-generation practices. Full article

Rolling bearing vibration signals in rotating machinery exhibit complex nonlinear and multi-scale features with redundant information interference. To address these challenges, this paper presents a multi-scale channel mixing convolutional network (MSCMN) and an enhanced deep residual shrinkage network (eDRSN) for improved feature learning and fault diagnosis accuracy in industrial settings. The MSCMN, applied in the initial and intermediate network layers, extracts multi-scale features from vibration signals, providing detailed information. By incorporating 1 × 1 convolutional blocks, the MSCMN mixes and reduces the feature dimensions, generating attention weights to suppress the interference from redundant information. Due to the high noise and nonlinear nature of industrial vibration signals, traditional linear layer representation is often inadequate. Thus, we propose an eDRSN with a Kolmogorov–Arnold Network–linear layer (KANLinear), which combines linear transformations with B-spline interpolation to capture both linear and nonlinear features, thereby enhancing threshold learning. Experiments on datasets from Case Western Reserve University and our laboratory validated the efficacy of the MSCMN-eDRSN model, which demonstrated improved diagnostic accuracy and robustness under noisy, real-world conditions. Full article

Background/Objectives: Although tolvaptan efficacy in ADPKD has been demonstrated in randomized clinical trials, there is no definitive method for assessing its efficacy in the individual patient in the clinical setting. In this exploratory feasibility study, we report a method to quantify the change in total kidney volume (TKV) growth rate to retrospectively evaluate tolvaptan efficacy for individual patients. Treatment-related changes in estimated glomerular filtration rate (eGFR) are also assessed. Methods: MRI scans covering at least 1 year prior to and during treatment with tolvaptan were performed, with deep learning facilitated kidney segmentation and fitting multiple imaging timepoints to exponential growth in 32 ADPKD patients. Clustering analysis differentiated tolvaptan treatment “responders” and “non-responders” based upon the magnitude of change in TKV growth rate. Differences in rate of eGFR decline, urine osmolality, and other parameters were compared between responders and non-responders. Results: Eighteen (56%) tolvaptan responders (mean age 42 ± 8 years) were identified by k-means clustering, with an absolute reduction in annual TKV growth rate of >2% (mean = −5.1% ± 2.5% per year). Thirteen (44%) non-responders were identified, with <1% absolute reduction in annual TKV growth rate (mean = +2.4% ± 2.7% per year) during tolvaptan treatment. Compared to non-responders, tolvaptan responders had significantly higher mean TKV growth rates prior to tolvaptan treatment (7.1% ± 3.6% per year vs. 3.7% ± 2.4% per year; p = 0.003) and higher median pretreatment spot urine osmolality (Uosm, 393 mOsm/kg vs. 194 mOsm/kg, p = 0.03), confirmed by multivariate analysis. Mean annual rate of eGFR decline was less in responders than in non-responders (−0.25 ± 0.04, CI: [−0.27, −0.23] mL/min/1.73 m² per year vs. −0.40 ± 0.06, CI: [−0.43, −0.37] mL/min/1.73 m² per year, p = 0.036). Conclusions: In this feasibility study designed to assess predictors of tolvaptan treatment efficacy in individual patients with ADPKD, we found that high pretreatment levels of annual TKV growth rate and higher pretreatment spot urine osmolality were associated with a responder phenotype. Full article

Behind human voice production, a complex biological mechanism generates and modulates sound. Recent research has explored machine-learning (ML) techniques to analyze singing-voice characteristics. However, the classification efficiency reported in such research works suggests the possibility of improvement. In addition, there is also scope for further improvement through the application of still under-utilized optimization techniques. Thus, the present article proposes a novel approach that leverages the Differential Evolution (DE) algorithm to optimize hyperparameters within three selected ML models, with the aim of classifying singing-voice registers i.e., chest, mixed, and head registers). To develop the present study, a dataset of 350 audio files encompassing the three aforementioned registers was constructed. Then, the TSFEL Python library was employed to extract 14 pieces of temporal information from the audio signals for subsequent classification by the employed ML models. The obtained findings demonstrated that the Extreme Gradient Boosting model, optimized with DE, achieved an average classification accuracy of 97.60%, thus indicating the efficacy of the proposed approach for singing-voice register classification. Full article

Background: Histopathological images are often used to diagnose breast cancer and have shown high accuracy in classifying cancer subtypes. Prediction of gene expression from whole-slide images and spatial transcriptomics data is important for cancer treatment in general and breast cancer in particular. This topic has been a challenge in numerous studies. Method: In this study, we present a deep learning framework called GeNetFormer. We evaluated eight advanced transformer models including EfficientFormer, FasterViT, BEiT v2, and Swin Transformer v2, and tested their performance in predicting gene expression using the STNet dataset. This dataset contains 68 H&E-stained histology images and transcriptomics data from different types of breast cancer. We followed a detailed process to prepare the data, including filtering genes and spots, normalizing stain colors, and creating smaller image patches for training. The models were trained to predict the expression of 250 genes using different image sizes and loss functions. GeNetFormer achieved the best performance using the MSELoss function and a resolution of 256 × 256 while integrating EfficientFormer. Results: It predicted nine out of the top ten genes with a higher Pearson Correlation Coefficient (PCC) compared to the retrained ST-Net method. For cancer biomarker genes such as DDX5 and XBP1, the PCC values were 0.7450 and 0.7203, respectively, outperforming ST-Net, which scored 0.6713 and 0.7320, respectively. In addition, our method gave better predictions for other genes such as FASN (0.7018 vs. 0.6968) and ERBB2 (0.6241 vs. 0.6211). Conclusions: Our results show that GeNetFormer provides improvements over other models such as ST-Net and show how transformer architectures are capable of analyzing spatial transcriptomics data to advance cancer research. Full article

The use of digital patient cases (eCases) is associated with student-perceived improvements in learning. However, novel instructional tools must demonstrate measurable student benefits to justify ongoing use. This research sought to identify the impact of digital patient cases (eCases) on student performance in a PharmD cardiovascular course. Optional eCases for hypertension (HTN), venous thromboembolism (VTE), and acute heart failure (AHF) were incorporated into the course. Performance on the exams and course overall was compared between student cohorts based on eCase use. Aggregated data were analyzed by year. Additional analysis was performed for scores on exam items related to eCase content. From 2020 to 2022, a total of 322/562 students (57.3%) used any eCase. While there were no differences in 2020 and 2021, eCase users in 2022 had significantly higher course (83.6% vs. 79.7%, p = 0.002) and final exam scores (75.0% vs. 67.7%, p < 0.001) compared with non-users. VTE eCase users had higher scores on VTE exam items compared to non-users, but only in 2021. AHF eCase users received higher scores on AHF exam items compared to non-users in 2021 and 2022. Among certain cohorts, student eCase use was associated with improved performance, and the use of certain eCases showed differences in content-specific performance. The eCase is a promising instructional tool that warrants further investigation to determine best design elements for maximal effectiveness. Full article

Accurately partitioning evapotranspiration (ET) of cropland into productive plant transpiration (T) and non-productive soil evaporation (E) is important for improving crop water use efficiency. Many methods, including machine learning methods, have been developed for ET partitioning. However, the applicability of machine learning models in cropland ET partitioning with diverse crop rotations is not clear. In this study, machine learning models are used to predict E, and T is obtained by calculating the difference between ET and E, leading to the derivation of the ratio of transpiration to evapotranspiration (T/ET). We evaluated six machine learning models (i.e., artificial neural networks (ANN), extremely randomized trees (ExtraTrees), gradient boosting decision tree (GBDT), light gradient boosting machine (LightGBM), random forest (RF), and extreme gradient boosting (XGBoost)) on partitioning ET at 16 cropland flux sites during the period from 2000 to 2020. The evaluation results showed that the XGBoost model had the best performance (R = 0.88, RMSE = 6.87 W/m², NSE = 0.77, and MAE = 3.41 W/m²) when considering the meteorological data, ecosystem sensible heat flux, ecosystem respiration, soil water content, and remote sensing vegetation indices as input variables. Due to the unavailability of observed E or T data at the 16 cropland sites, we used three other widely used ET partitioning methods to indirectly validate the accuracy of our ET partitioning results based on XGBoost. The results showed that our T estimation results were highly consistent with their T estimation results (R = 0.83–0.91). Moreover, based on the XGBoost model and the three other ET partitioning methods, we estimated the ratio of transpiration to evapotranspiration (T/ET) for different crops. On average, maize had the highest T/ET of 0.619 ± 0.119, followed by soybean (0.618 ± 0.085), winter wheat (0.614 ± 0.08), and sugar beet (0.611 ± 0.065). Lower T/ET was found for paddy rice (0.505 ± 0.055), winter barley (0.590 ± 0.058), potato (0.540 ± 0.088), and rapeseed (0.522 ± 0.107). These results suggest the machine learning models are easy and applicable for cropland T/ET estimation with different crop rotations and reveal obvious differences in water use among different crops, which is crucial for the sustainability of water resources and improvements in cropland water use efficiency. Full article

This study evaluates the mapping accuracy between textile stretch sensor data and surface electromyography (sEMG) signals using Multilayer Perceptron (MLP), Convolutional Neural Network (CNN), and Residual Network (ResNet) models. Data from the forearm, biceps brachii, and triceps brachii were analyzed using Root Mean Square Error (RMSE) and R² as performance metrics. ResNet achieved the lowest RMSE (e.g., 0.1285 for biceps brachii) and highest R² (0.8372), outperforming CNN (RMSE: 0.1455; R²: 0.7639) and MLP (RMSE: 0.1789; R²: 0.6722). The residual learning framework of ResNet effectively handles nonlinear patterns and noise, enabling more accurate predictions even for low-variability datasets like the triceps brachii. CNN showed moderate improvement over MLP by learning temporal features but struggled with low-variability datasets. MLP, as the baseline model, demonstrated the highest RMSE and lowest R², highlighting its limitations in capturing complex relationships. These results suggest the potential reliability of ResNet for mapping textile stretch sensor data to sEMG signals, showing promising performance within the scope of this study. Future research could explore broader applications across different sensor configurations and activities to further validate these findings. Full article

With the increasing demand for road defect detection, existing deep learning methods have made significant progress in terms of accuracy and speed. However, challenges remain, such as insufficient detection precision for detection precision for road defect recognition and issues of missed or false detections in complex backgrounds. These issues reduce detection reliability and hinder real-world deployment. To address these challenges, this paper proposes an improved YOLOv8-based model, RepGD-YOLOV8W. First, it replaces the C2f module in the GD mechanism with the improved C2f module based on RepViTBlock to construct the Rep-GD module. This improvement not only maintains high detection accuracy but also significantly enhances computational efficiency. Subsequently, the Rep-GD module was used to replace the traditional neck part of the model, thereby improving multi-scale feature fusion, particularly for detecting small targets (e.g., cracks) and large targets (e.g., potholes) in complex backgrounds. Additionally, the introduction of the Wise-IoU loss function further optimized the bounding box regression task, enhancing the model’s stability and generalization. Experimental results demonstrate that the improved REPGD-YOLOV8W model achieved a 2.4% increase in mAP50 on the RDD2022 dataset. Compared with other mainstream methods, this model exhibits greater robustness and flexibility in handling road defects of various scales. Full article

This paper summarizes the findings and main conclusions from the first presentation of the module “CETD23: Cómo entrenar a tu dragón: la inteligencia artificial generativa como herramienta para mejorar el aprendizaje en entornos online e híbridos”. This is an optional module accredited through the ECTS (European Credit Transfer System) and delivered as part of the “Plan de Formación de Docencia y Personal Investigador 2021–2025” of the Universidad de Las Palmas de Gran Canaria (ULPGC). The Plan de Formación is a development programme offered by Spanish universities to new and existing teaching staff, aimed at improving the quality of their teaching practises in line with Aneca’s Docencia regulations (like the PGCERT and PGCAPT programmes in the UK). The aim of module CETD23 is to explore the use of Generative AI (GenAI) to enhance learning and teaching and to build the AI literacy of ULPGC’s teaching staff. The module received high student satisfaction, with an average score of 4.84 on the Likert Scale, and achieved a 100% completion rate for the final summative project. The final conclusions highlight the need for universities to establish reglamentos (policies and guidance) on how to use GenAI to enhance learning and assessment, as well as to involve students as equal partners in the design and assessment of methods that use AI. Full article

Coastal erosion is a critical environmental challenge in the Upper Gulf of Thailand, driven by both natural processes and human activities. This study analyzes 35 years (1988–2023) of shoreline changes using geoinformatics, machine learning algorithms (Random Forest, Support Vector Machine, Maximum Likelihood, Minimum Distance), and the Digital Shoreline Analysis System (DSAS). The results show that the Random Forest algorithm, utilizing spectral bands and indices (NDVI, NDWI, MNDWI, SAVI), achieved the highest classification accuracy (98.17%) and a Kappa coefficient of 0.9432, enabling reliable delineation of land and water boundaries. The extracted annual shorelines were validated with high accuracy, yielding RMSE values of 13.59 m (2018) and 8.90 m (2023). The DSAS analysis identified significant spatial and temporal variations in shoreline erosion and accretion. Between 1988 and 2006, the most intense erosion occurred in regions 4 and 5, influenced by sea-level rise, strong monsoonal currents, and human activities. However, from 2006 to 2018, erosion rates declined significantly, attributed to coastal protection structures and mangrove restoration. The period 2018–2023 exhibited a combination of erosion and accretion, reflecting dynamic sediment transport processes and the impact of coastal management measures. Over time, erosion rates declined due to the implementation of protective structures (e.g., bamboo fences, rock revetments) and the natural expansion of mangrove forests. However, localized erosion remains persistent in low-lying, vulnerable areas, exacerbated by tidal forces, rising sea levels, and seasonal monsoons. Anthropogenic activities, including urban development, mangrove deforestation, and aquaculture expansion, continue to destabilize shorelines. The findings underscore the importance of sustainable coastal management strategies, such as mangrove restoration, soft engineering coastal protection, and integrated land-use planning. This study demonstrates the effectiveness of combining machine learning and geoinformatics for shoreline monitoring and provides valuable insights for coastal erosion mitigation and enhancing coastal resilience in the Upper Gulf of Thailand. Full article

Soybean stands out for being the most economically important oilseed in the world. Remote sensing techniques and precision agriculture are being analyzed through research in different agricultural regions as a technological system aiming at productivity and possible low-cost reduction. Machine learning (ML) methods, together with the advent of demand for remotely piloted aircraft available on the market in the recent decade, have been conducive to remote sensing data processes. The objective of this work was to evaluate the best ML and input configurations in the classification of agronomic variables in different phenological stages. The spectral variables were obtained in three phenological stages of soybean genotypes: V8 (at 45 days after emergence—DAE), R1 (60 DAE), and R5 (80 DAE). A Sensefly eBee fixed-wing RPA equipped with the Parrot Sequoia multispectral sensor coupled to the RGB sensor was used. The Sequoia multispectral sensor with an RGB sensor acquired reflectance at wavelengths of blue (450 nm), green (550 nm), red (660 nm), near-infrared (735 nm), and infrared (790 nm). The following were used to evaluate the agronomic traits: days to maturity, number of branches, productivity, plant height, height of the first pod insertion and diameter of the main stem. The random forest (RF) model showed greater accuracy with data collected in the R5 stage, whose accuracies were close to 56 for the percentage of correct classifications (CC), close to 0.2 for Kappa, and above 0.55 for the F-score. Logistic regression (RL) and support vector machine (SVM) models showed better performance in the early reproductive stage R1, with accuracies above 55 for CC, close to 0.1 for Kappa, and close to 0.4 for the F-score. J48 performed better with data from the V8 stage, with accuracies above 50 for CC and close to 0.4 for the F-score. This reinforces that the use of different specific spectra for each model can enhance accuracy, optimizing the choice of model according to the phenological stage of the plants. Full article

Driven by polymer processing–property data, machine learning (ML) presents an efficient paradigm in predicting the stress–strain curve. However, it is generally challenged by (i) the deficiency of training data, (ii) the one-to-many issue of processing–property relationship (i.e., aleatoric uncertainty), and (iii) the unawareness of model uncertainty (i.e., epistemic uncertainty). Here, leveraging a Bayesian neural network (BNN) and a recently proposed dual-architected model for curve prediction, we introduce a dual Bayesian model that enables accurate prediction of the stress–strain curve while distinguishing between aleatoric and epistemic uncertainty at each processing condition. The model is trained using a Taguchi array dataset that minimizes the data size while maximizing the representativeness of 27 samples in a 4D processing parameter space, significantly reducing data requirements. By incorporating hidden layers and output-distribution layers, the model quantifies both aleatoric and epistemic uncertainty, aligning with experimental data fluctuations, and provides a 95% confidence interval for stress–strain predictions at each processing condition. Overall, this study establishes an uncertainty-aware framework for curve property prediction with reliable, modest uncertainty at a small data size, thus balancing data minimization and uncertainty quantification. Full article