Search Results (74,257)

Background/Objectives: Mild Cognitive Impairment (MCI), a condition between normal aging and dementia, is characterized by cognitive changes that do not significantly affect instrumental activities of daily living. The Memory Support System (MSS), an evidence-based behavioral intervention developed by the Mayo Clinic, has been shown to aid those living with MCI and their support partners in coping with cognitive challenges. However, the MSS has not been offered clinically within the Canadian context. Therefore, we conducted a study assessing the feasibility of the MSS from the perspectives of individuals living with MCI and their support partners. Methods: Participants from an institutional registry of research participants, patients, and support partners at a memory clinic, as well as members of a local Dementia Society, were approached to complete an online or paper version of a survey assessing feasibility dimensions. Responses were compared between and within groups for differences in mean scores and associations between linked binary choice response questions. Results: A total of 77 responses were received; 39 surveys were completed by participants with MCI, and 38 by support partners. Respondents found the MSS to be acceptable and practical. On average, participants thought it would be more difficult to train in using the MSS than support partners. Both groups expressed interest in the intervention. On average, participants with MCI and support partners preferred virtual MSS training to in-person and indicated more interest in participating in training over six weeks as compared to two weeks. Conclusions: Flexibility in duration and format when offering the MSS are important considerations when offering the intervention as part of a clinical program. Future research should evaluate cost-effectiveness (e.g., financial, staff resources, etc.) of the MSS approach if it were to be institutionalized in the Ontario healthcare system. Full article

The present study explores the application of RNNs for the prediction and propagation of flood waves along a section of the Bârsa River, Romania, as a fast alternative to classical hydraulic models, aiming to identify new ways to alert the population. Five neural architectures were analyzed as follows: S-RNN, LSTM, GRU, Bi-LSTM, and Bi-GRU. The input data for the neural networks were derived from 2D hydraulic simulations conducted using HEC-RAS software, which provided the necessary training data for the models. It should be mentioned that the input data for the hydraulic model are synthetic hydrographs, derived from the statistical processing of recorded floods. Performance evaluation was based on standard metrics such as NSE, $R^2$ MSE, and RMSE. The results indicate that all studied networks performed well, with NSE and $R^2$ values close to 1, thus validating their capacity to reproduce complex hydrological dynamics. Overall, all models yielded satisfactory results, making them useful tools particularly the GRU and Bi-GRU architectures, which showed the most balanced behavior, delivering low errors and high stability in predicting peak discharge, water level, and flood wave volume. The GRU and Bi-GRU networks yielded the best performance, with RMSE values below 1.45, MAE under 0.3, and volume errors typically under 3%. On the other hand, LSTM architecture exhibited the most significant instability and errors, especially in estimating the flood wave volume, often having errors exceeding 9% in some sections. The study concludes by identifying several limitations, including the heavy reliance on synthetic data and its local applicability, while also proposing solutions for future analyses, such as the integration of real-world data and the expansion of the methodology to diverse river basins thus providing greater significance to RNN models. The final conclusions highlight that RNNs are powerful tools in flood risk management, contributing to the development of fast and efficient early warning systems for extreme hydrological and meteorological events. Full article

The rapid expansion of peptide libraries and the increasing functional diversity of peptides have highlighted the significance of predicting the multifunctional properties of peptides in bioinformatics research. Although supervised learning methods have made advancements, they typically necessitate substantial amounts of labeled data for yielding accurate prediction. This study presents MvAl-MFP, a multi-label active learning approach that incorporates multiple feature views of peptides. This method takes advantage of the natural properties of multi-view representation for amino acid sequences, meets the requirement of the query-by-committee (QBC) active learning paradigm, and further significantly diminishes the requirement for labeled samples while training high-performing models. First, MvAl-MFP generates nine distinct feature views for a few labeled peptide amino acid sequences by considering various peptide characteristics, including amino acid composition, physicochemical properties, evolutionary information, etc. Then, on each independent view, a multi-label classifier is trained based on the labeled samples. Next, a QBC strategy based on the average entropy of predictions across all trained classifiers is adopted to select a specific number of most valuable unlabeled samples to submit them to human experts for labeling by wet-lab experiments. Finally, the aforementioned procedure is iteratively conducted with a constantly expanding labeled set and updating classifiers until it meets the default stopping criterion. The experiments are conducted on a dataset of multifunctional therapeutic peptides annotated with eight functional labels, including anti-bacterial properties, anti-inflammatory properties, anti-cancer properties, etc. The results clearly demonstrate the superiority of the proposed MvAl-MFP method, as it can rapidly improve prediction performance while only labeling a small number of samples. It provides an effective tool for more precise multifunctional peptide prediction while lowering the cost of wet-lab experiments. Full article

Generative AI tools such as ChatGPT are reshaping educational practice, yet first-year teacher-education students often lack the prompt-engineering skills and confidence required to use them responsibly. This pilot study examined whether a concise three-session clinic on prompt engineering could simultaneously boost AI literacy and reduce technology anxiety in prospective teachers. Forty-five freshmen in a Peruvian teacher-education program completed validated Spanish versions of a 12-item AI-literacy scale and a 12-item technology-anxiety scale one week before and after the intervention; normality-checked pre–post differences were analysed with paired-samples t-tests, Cohen’s d, and Pearson correlations. AI literacy rose by 0.70 ± 0.46 points (t (44) = −6.10, p < 0.001, d = 0.91), while technology anxiety fell by 0.58 ± 0.52 points (t (44) = −3.82, p = 0.001, d = 0.56); individual gains were inversely correlated (r = −0.46, p = 0.002). These findings suggest that integrating micro-level prompt-engineering clinics in the first semester can help future teachers engage critically and comfortably with generative AI and guide curriculum designers in updating teacher-training programs. Full article

The knowledge tracing method based on deep learning is used to assess learners’ cognitive states, laying the foundation for personalized education. However, deep learning methods are inefficient when processing long-term series data and are prone to overfitting. To improve the accuracy of cognitive state prediction, we design a Multi-layer Attention Self-supervised Knowledge Tracing Method (MASKT) using self-supervised learning and the Transformer method. In the pre-training stage, MASKT uses a random forest method to filter out positive and negative correlation feature embeddings; then, it reuses noise-processed restoration tasks to extract more learnable features and enhance the learning ability of the model. The Transformer in MASKT not only solves the problem of long-term dependencies between input and output using an attention mechanism, but also has parallel computing capabilities that can effectively improve the learning efficiency of the prediction model. Finally, a multidimensional attention mechanism is integrated into cross-attention to further optimize prediction performance. The experimental results show that, compared with various knowledge tracing models on multiple datasets, MASKT’s prediction performance remains 2 percentage points higher. Compared with the multidimensional attention mechanism of graph neural networks, MASKT’s time efficiency is shortened by nearly 30%. Due to the improvement in prediction accuracy and performance, this method has broad application prospects in the field of cognitive diagnosis in intelligent education. Full article

Accurate streamflow forecasting at fine temporal and spatial scales is essential to manage the diverse hydrological behaviors of individual catchments, particularly in rapidly responding mountainous regions. This study compares three forecasting models ARIMAX, LSTM, and HEC-HMS applied to the Posina River basin in northern Italy, using 13 years of hourly hydrological data. While recent literature promotes multi-basin LSTM training for generalization, we show that a well-configured single-basin LSTM, combined with a rolling forecast strategy, can achieve comparable accuracy under high-frequency, data-constrained conditions. The physically based HEC-HMS model, calibrated for continuous simulation, provides robust peak flow prediction but requires extensive parameter tuning. ARIMAX captures baseflows but underestimates sharp hydrological events. Evaluation through NSE, KGE, and MAE shows that both LSTM and HEC-HMS outperform ARIMAX, with LSTM offering a compelling balance between accuracy and ease of implementation. This study enhances our understanding of streamflow model behavior in small basins and demonstrates that LSTM networks, despite their simplified configuration, can be reliable tools for flood forecasting in localized Alpine catchments, where physical modeling is resource-intensive and regional data for multi-basin training are often unavailable. Full article

Background: Dietary advice for Paralympic athletes (PAs) with a spinal cord injury (PAs-SCI) requires particular attention and has been widely studied. However, currently, no particular attention has been addressed to nutritional guidelines for athletes with an amputation (PAs-AMP). This study aimed at filling up this gap, at least partially, and compared veteran PAs-SCI with PAs-AMP. Methods: A sample of 25 male PAs (12 with SCI and 13 with AMP), recruited during two training camps, was submitted to the following questionnaires: allergy questionnaire for athletes (AQUA), Nordic Musculoskeletal Questionnaire (NMQ), Starvation Symptom Inventory (SSI), neurogenic bowel dysfunction (NBD), orthorexia (ORTO-15/ORTO-7), alcohol use disorders identification test (AUDIT), and Mediterranean diet adherence (MDS). The PAs were also submitted to the following measurements: dietary Oxygen Radical Absorbance Capacity (ORAC) and intakes, body composition, handgrip strength (HGS), basal energy expenditure (BEE), peak oxygen uptake (VO_2peak), peak power, peak heart rate (HR), post-exercise ketosis, and antioxidant response after a cardiopulmonary exercise test (CPET) to voluntary fatigue. Results: Compared to PAs-AMP, PAs-SCI had higher NBD and lower VO_2peak (p < 0.05), peak power, peak HR, peak lactate, phase angle (PhA) of the dominant leg (p < 0.05), and ORTO15 (p < 0.05). The latter was related to NBD (r = −0.453), MDS (r = −0.638), and ORAC (r = −0.529), whereas ORTO7 correlated with PhA of the dominant leg (r = 0.485). Significant differences between PAs-AMP and PAs-SCI were not found in the antioxidant response, glucose, and ketone levels after CPET, nor in dietary intake, AUDIT, AQUA, NMQ, SSI, BEE, HGS, and FM%. Conclusions: The present study showed that PAs-SCI and PAs-AMP display similar characteristics in relation to lifestyle, energy intake, basal energy expenditure, and metabolic response to CPET. Based on both the similarities with PAs-SCI and the consequences of the limb deficiency impairment, PAs-AMP and PAs-SCI require personalized nutritional advice. Full article

Rapid data growth in large systems has introduced significant challenges in real-time monitoring and analysis. One of these challenges is detecting anomalies in time series data with high-dimensional inputs that contain complex inter-correlations between them. In addition, the lack of labeled data leads to the use of unsupervised learning that relies on daily system data to train models, which can contain noise that affects feature extraction. To address these challenges, we propose PCA-AAE, a novel anomaly detection model for time series data using an Adversarial Autoencoder integrated with Principal Component Analysis (PCA). PCA contributes to analyzing the latent space by transforming it into uncorrelated components to extract important features and reduce noise within the latent space. We tested the integration of PCA into the model’s phases and studied its efficiency in each phase. The tests show that the best practice is to apply PCA to the latent code during the adversarial training phase of the AAE model. We used two public datasets, the SWaT and SMAP datasets, to compare our model with state-of-the-art models. The results indicate that our model achieves an average F1 score of 0.90, which is competitive with state-of-the-art models, and an average of 58.5% faster detection speed compared to similar state-of-the-art models. This makes PCA-AAE a candidate solution to enhance real-time anomaly detection in high-dimensional datasets. Full article

Background/Objective: Nursing and non-nursing students experience high stress levels, making them susceptible to mental health issues. This study compared stress, anxiety, and depression between these two groups after 2 years of the COVID-19 pandemic. Additionally, it explored the relationship between perceived helplessness, self-efficacy, and symptoms of mental stress and strain resulting from challenging internship conditions for nursing students. Methods: This cross-sectional study included 154 nursing students (mean age = 22.43 years) and 291 non-nursing students (mean age = 27.7 years). Data were collected using the Depression Anxiety Stress Scales (DASS-21), Perceived Stress Scale-10 (PSS-10), and a questionnaire on mental stress and strain. Results: Nursing students reported significantly higher scores in the DASS-21 subscales depression (ηp² = 0.016) and anxiety (ηp² = 0.037), and global stress (PSS-10; ηp² = 0.029) compared to non-nursing students, but no significant difference on the DASS-21 Stress subscale. The observed group differences in the present study may be partially attributed to group differences in demographic factors. Helplessness correlated strongly with nearly all scales of mental stress and strain during internships (all p’s < 0.001), while self-efficacy showed a strong negative correlation with non-occupational difficulties, health impairment, and emotional problems (all p’s < 0.001). Conclusions: Nursing students experience elevated depression, anxiety, and perceived stress levels compared to non-nursing students. Stronger feelings of helplessness and lower confidence in their ability to overcome challenges were strongly correlated with mental stress and strain during clinical training. Targeted interventions such as cognitive behavioral training and stress management should be integrated into nursing curricula to enhance resilience and coping strategies. Full article

The presence of Internet of Things (IoT) devices in modern working and living environments is growing rapidly. The data collected in such environments enable us to model users’ behaviour and consequently identify and authenticate them. However, these data may contain information about the user’s current activity, emotional state, or other aspects that are not relevant for authentication. In this work, we employ adversarial deep learning techniques to remove privacy-revealing information from the data while keeping the authentication performance levels almost intact. Furthermore, we develop and apply various techniques to offload the computationally weak edge devices that are part of the machine learning pipeline at training and inference time. Our experiments, conducted on two multimodal IoT datasets, show that P²ESA can be efficiently deployed and trained, and with user identification rates of between 75.85% and 93.31% (c.f. 6.67% baseline), can represent a promising support solution for authentication, while simultaneously fully obfuscating sensitive information. Full article

Multimodal knowledge graphs have recently been successfully applied to tasks such as those relating to information retrieval, question and answer, and recommender systems. In this study, we propose a dual-path fine-tuning mechanism technique with a low-rank adapter and an embedded cueing layer, aiming to improve the generalization and accuracy of the model in analogical reasoning tasks. The low-rank fine-tuning (LoRA) technique with rank-stable scaling factor is used to fine-tune the MKGformer model, and a cue-embedding layer is innovatively added to the input layer, which enables the model to better grasp the scale of the relationship between entities according to the dynamic cue vectors during the fine-tuning process and ensures that the model achieves the best results during training. The experimental results show that the R-MKG model improves several evaluation indexes by more than 20%, which is significantly better than the traditional DoRA and FA-LoRA methods. This research provides technical support for multimodal knowledge graph analogical reasoning. We hope that our work will bring benefits and inspire future research. Full article

With increasing life expectancy, the number of older people living with comorbid diabetes and frailty is increasing. The development of frailty accelerates diabetes-related adverse outcomes. Frailty is a multidimensional syndrome with physical, mental and social aspects which is associated with increased risk of hypoglycaemia, dementia and hospitalisation. Therefore, regular screening for all aspects of frailty should be an integrated part of the care plans of older people with diabetes. In addition, every effort should be made for prevention, which includes adequate nutrition combined with regular resistance exercise training. In already frail older people with diabetes, metabolic targets should be relaxed and hypoglycaemic agents should be of low hypoglycaemic risk potential. Furthermore, the metabolic phenotype of frailty should be considered when choosing hypoglycaemic agents and determining targets. With increasing severity of frailty, proactive chronological plans of de-escalation, palliation and end-of-life care should be considered. These plans should be undertaken in a shared decision-making manner which involves patients and their families. This ensures that patients’ views, wishes and preferences are in the heart of these plans. Full article

Blast-induced airblast poses a significant environmental and operational issue for surface mining, affecting safety, regulatory adherence, and the well-being of surrounding communities. Despite advancements in machine learning methods for predicting airblast, present studies neglect essential geomechanical characteristics, specifically rock mass strength (RMS), which is vital for energy transmission and pressure-wave attenuation. This paper presents a capuchin search algorithm-optimized multilayer perceptron (CapSA-MLP) that incorporates RMS, hole depth (HD), maximum charge per delay (MCPD), monitoring distance (D), total explosive mass (TEM), and number of holes (NH). Blast datasets from a granite quarry were utilized to train and test the model in comparison to benchmark approaches, such as particle swarm optimized artificial neural network (PSO-ANN), multivariate regression analysis (MVRA), and the United States Bureau of Mines (USBM) equation. CapSA-MLP outperformed PSO-ANN (RMSE = 1.120, R² = 0.904 compared to RMSE = 1.284, R² = 0.846), whereas MVRA and USBM exhibited lower accuracy. Sensitivity analysis indicated RMS as the main input factor. This study is the first to use CapSA-MLP with RMS for airblast prediction. The findings illustrate the significance of metaheuristic optimization in developing adaptable, generalizable models for various rock types, thereby improving blast design and environmental management in mining activities. Full article

Teledermatology relies on digital transfer of dermatological images, but compression and resolution differences compromise diagnostic quality. Image enhancement techniques are crucial to compensate for these differences and improve quality for both clinical assessment and AI-based analysis. We developed a customized image degradation pipeline simulating common artifacts in dermatological images, including blur, noise, downsampling, and compression. This synthetic degradation approach enabled effective training of DermaSR-GAN, a super-resolution generative adversarial network tailored for dermoscopic images. The model was trained on 30,000 high-quality ISIC images and evaluated on three independent datasets (ISIC Test, Novara Dermoscopic, PH²) using structural similarity and no-reference quality metrics. DermaSR-GAN achieved statistically significant improvements in quality scores across all datasets, with up to 23% enhancement in perceptual quality metrics (MANIQA). The model preserved diagnostic details while doubling resolution and surpassed existing approaches, including traditional interpolation methods and state-of-the-art deep learning techniques. Integration with downstream classification systems demonstrated up to 14.6% improvement in class-specific accuracy for keratosis-like lesions compared to original images. Synthetic degradation represents a promising approach for training effective super-resolution models in medical imaging, with significant potential for enhancing teledermatology applications and computer-aided diagnosis systems. Full article

Background/Objectives: The aim of this systematic review was to compare the effectiveness of virtual reality (VR)-based training with conventional exercise programs in improving functional outcomes related to fall risk among older adults with various health conditions. Methods: The review was conducted in accordance with the PRISMA 2020 guidelines and registered in PROSPERO (registration number CRD42022345678). The databases Scopus, PubMed, Web of Science, and EBSCO were searched up to 31 March 2025. Randomized controlled trials (RCTs) were included if they involved participants aged ≥60 years, a VR intervention lasting ≥6 weeks, and a control group performing traditional exercises or receiving usual care. Methodological quality was assessed using the PEDro scale, and a narrative synthesis was performed across four outcome domains: balance, mobility, cognitive function, and fall risk. Results: Seven RCTs were included in the analysis (totaling 664 participants). VR training was found to be at least as effective as conventional exercise in improving balance (e.g., Berg Balance Scale) and mobility (e.g., Timed Up and Go), with some studies showing superior effects of VR. One RCT demonstrated that combining VR with balance exercises (MIX) yielded the greatest improvements in muscle strength and physical performance. Additionally, two studies reported cognitive benefits (e.g., MoCA) and a 42% reduction in fall incidence within six months following VR intervention. The methodological quality of the included studies was moderate to high (PEDro score 5–9/10). Conclusions: VR-based training represents a safe and engaging supplement to geriatric rehabilitation, effectively improving balance, mobility, and, in selected cases, cognitive function, while also reducing fall risk. Full article