Search Results (203)

Background/Objectives: Food allergy (FA) is a growing concern in pediatric care, requiring effective avoidance strategies and timely emergency responses. The role of caregivers is central to the daily management of FA. This study aimed to assess parental knowledge, preparedness, and behaviors regarding pediatric FA management, focusing on both prevention and emergency readiness. Methods: A cross-sectional survey was conducted from December 2024 to April 2025 through the SurveyMonkey^® platform, promoted by the Italian Society of Pediatric Allergology and Immunology (SIAIP). The anonymous, structured questionnaire was distributed online and in two Italian university hospitals. A total of 129 fully completed responses from caregivers of children with FA were analyzed. The survey explored self-perceived knowledge, symptom recognition, preventive actions, emergency preparedness, and communication practices. Results: Only 9.3% of parents considered themselves “very informed,” while 54.3% reported limited or no knowledge. Just 16.0% recognized all symptoms of an allergic reaction, and only 24.0% could distinguish mild reactions from anaphylaxis. Notably, 67.4% reported not knowing how to respond to anaphylaxis, and 83.7% did not possess an epinephrine auto-injector. Preventive measures at home were inconsistently applied, and 41.1% took no precautions when eating out. Communication with external caregivers was often informal or absent. Only 33% updated physicians regularly. Conclusions: The findings reveal significant gaps in parental preparedness and highlight critical areas for educational intervention. Enhanced caregiver training, standardized communication protocols, and improved clinical follow-up are essential to strengthen pediatric FA management and safety. Full article

Previous work used machine learning (ML) to estimate past and current alfalfa yields and showed that domain adaptation (DA) with data synthesis shows promise in classifying yields as high, medium, or low. The current work uses similar techniques to forecast future alfalfa yields. A novel technique is proposed for forecasting alfalfa time series data that exploits stationarity and predicts differences in yields rather than the yields themselves. This forecasting technique generally provides more accurate forecasts than the established ARIMA family of forecasters for both univariate and multivariate time series. Furthermore, this ML-based technique is potentially easier to use than the ARIMA family of models. Also, previous work is extended by showing that DA with data synthesis also works well for predicting continuous values, not just for classification. The novel scale-invariant tabular synthesizer (SITS) is proposed, and it is competitive with or superior to other established synthesizers in producing data that trains strong models. This synthesis algorithm leads to R scores over 100% higher than an established synthesizer in this domain, while ML-based forecasters beat the ARIMA family with symmetric mean absolute percent error (sMAPE) scores as low as 12.81%. Finally, ML-based forecasting is combined with DA (ForDA) to create a novel pipeline that improves forecast accuracy with sMAPE scores as low as 9.81%. As alfalfa is crucial to the global food supply, and as climate change creates challenges with managing alfalfa, this work hopes to help address those challenges and contribute to the field of ML. Full article

Background/Objectives: Injury prevention programs (IPPs) are evidence-based interventions that reduce musculoskeletal injuries in youth sports. Despite their proven benefits, the adoption of IPPs by coaches remains limited. This study aimed to evaluate the awareness, usage, and perceptions of IPPs among youth sports coaches in Poland and to identify factors associated with their implementation. Methods: A cross-sectional study was conducted using a web-based survey tailored to youth sports coaches in Poland. Coaches of athletes aged 9–17 were recruited through targeted outreach to clubs and professional networks. The survey assessed IPP awareness, implementation, perceptions, and sources of information. Statistical analyses included chi-square tests, non-parametric comparisons, Firth’s logistic regression, and cluster profiling. Results: Only 54.6% of coaches (59 out of 108) were aware of IPPs, and among them, just 47.5% reported using them. No significant associations were found between IPP use and demographic variables such as gender, sport, or place of residence. Coaches who were aware of IPPs were significantly younger than those who were unaware (p = 0.029). The information source was the strongest predictor of IPP implementation: coaches trained via formal courses were over 20 times more likely to use IPPs compared to those learning from peers (OR = 20.4, p < 0.001). While coaches generally perceived IPPs as beneficial for fitness and recovery, 28.6% expressed doubts about their effectiveness in reducing injury risk. Conclusions: Despite broadly positive beliefs, only 47.5% of coaches who were aware of IPPs reported using them. Formal training significantly enhances the likelihood of adoption. These findings emphasize the need for structured educational efforts and improved dissemination strategies to promote evidence-based injury prevention in youth sports settings. Full article

Objective: Intestinal ultrasound (IUS) is increasingly valued as a noninvasive tool for inflammatory bowel disease (IBD) management, offering real-time, radiation-free assessment of bowel wall thickness, vascularity, and complications. While IUS is widely adopted in Europe, data on its use in Turkey is scarce. This study aims to address this gap. Methods: A nationwide, cross-sectional survey was conducted targeting 817 adult and 150 pediatric gastroenterologists in Turkey. The survey included 26 structured questions on demographics, familiarity with and use of IUS, and barriers to implementation. Results: A total of 191 gastroenterologists participated in this survey, with 56% being adult gastroenterologists (n = 107) and 44% pediatric gastroenterologists (n = 84). Regarding whether they participated in IUS training, 73% (n = 140) of the 191 respondents stated they had not received training. There were notable differences in how IUS was utilized among gastroenterologists: 29% (n = 31) of adult gastroenterologists performed IUS independently, compared to just 2% (n = 2) of pediatric gastroenterologists (p < 0.001). In total, 63% (n = 67) of adult gastroenterologists and 46% (n = 39) of pediatric gastroenterologists reported not using IUS. Altogether, 94% (n = 179) emphasized the necessity of educational opportunities, and 86% (n = 165) favored national guidelines. Conclusions: Our findings reveal that the current application of IUS in Turkey fails to correspond with its expected advantages in managing IBD. Limited educational opportunities are a major challenge, emphasizing the necessity for coordinated educational programs and national guidelines. The expanded adoption of the IUS might significantly improve Turkey’s management of IBD. What is known: Intestinal ultrasound (IUS) is a non-invasive, cost-effective, and reliable imaging method increasingly recognized for its utility in diagnosing and monitoring inflammatory bowel disease (IBD). What is new: This is the first national survey assessing the awareness, usage patterns, and barriers to the adoption of IUS among gastroenterologists in Turkey. The study highlights significant gaps in training opportunities while also identifying strategies to promote IUS integration into routine clinical practice. The findings may encourage similar efforts in other regions where IUS remains underutilized, ultimately improving IBD management and patient outcomes globally. Full article

Cotton is the most widely cultivated natural fiber crop worldwide, yet it is highly susceptible to various diseases and pests that significantly compromise both yield and quality. To enable rapid and accurate diagnosis of cotton diseases and pests—thus supporting the development of effective control strategies and facilitating genetic breeding research—we propose a lightweight model, the Resource-efficient Cotton Network (RF-Cott-Net), alongside an open-source image dataset, CCDPHD-11, encompassing 11 disease categories. Built upon the MobileViTv2 backbone, RF-Cott-Net integrates an early exit mechanism and quantization-aware training (QAT) to enhance deployment efficiency without sacrificing accuracy. Experimental results on CCDPHD-11 demonstrate that RF-Cott-Net achieves an accuracy of 98.4%, an F1-score of 98.4%, a precision of 98.5%, and a recall of 98.3%. With only 4.9 M parameters, 310 M FLOPs, an inference time of 3.8 ms, and a storage footprint of just 4.8 MB, RF-Cott-Net delivers outstanding accuracy and real-time performance, making it highly suitable for deployment on agricultural edge devices and providing robust support for in-field automated detection of cotton diseases and pests. Full article

In this paper we describe the processes and challenges involved in the design, implementation, and assessment of a small-scale intervention in four primary schools in Ghana’s Central Region that aimed to enhance learners’ mother tongue and bilingual literacy practices whilst at the same time strengthening their sense of cultural identity. Within the framework of Educational Design Research (EDR), this paper describes the steps that were involved in the development process, from context analysis to the design of a locally developed Fante–English bilingual storybook, as well as the formative evaluation of this prototype. This paper shows how to translate contextual findings into a final product, while sharing with the reader important findings for each phase in the process. Formative evaluation in the form of a teacher workshop, surveys, and classroom observations was used. Results showed that, in the opinion of teachers, Fante–English bilingual books can promote learners’ cultural identity, self-awareness, and a sense of prestige when they speak the language. Not only do the books preserve the Fante language and culture, but they show learners that Fante is just as important as English. A second round of formative evaluation showed that additional teacher manual and training could benefit the outcome of the bilingual method. Full article

Electricity theft remains a pressing challenge in modern smart grid systems, leading to significant economic losses and compromised grid stability. This paper presents a sensor-driven framework for electricity theft detection that leverages data collected from smart meter sensors, key components in smart grid monitoring infrastructure. The proposed approach combines prototype learning and meta-level ensemble learning to develop a scalable and accurate detection model, capable of identifying zero-day attacks that are not present in the training data. Smart meter data is compressed using Principal Component Analysis (PCA) and K-means clustering to extract representative consumption patterns, i.e., prototypes, achieving a 92% reduction in dataset size while preserving critical anomaly-relevant features. These prototypes are then used to train base-level one-class classifiers, specifically the One-Class Support Vector Machine (OCSVM) and the Gaussian Mixture Model (GMM). The outputs of these classifiers are normalized and fused in a meta-OCSVM layer, which learns decision boundaries in the transformed score space. Experimental results using the Irish CER Smart Metering Project (SMP) dataset show that the proposed sensor-based detection framework achieves superior performance, with an accuracy of 88.45% and a false alarm rate of just 13.85%, while reducing training time by over 75%. By efficiently processing high-frequency smart meter sensor data, this model contributes to developing real-time and energy-efficient anomaly detection systems in smart grid environments. Full article

Remaining useful life (RUL) prediction of cutting tools plays an important role in modern manufacturing because it provides the criterion used in decisions to replace worn cutting tools just in time so that machining deficiency and unnecessary costs will be restrained. However, the performance of existing deep learning algorithms is limited due to the smaller quantity and low quality of labeled training datasets, because it is costly and time-consuming to build such datasets. A large amount of unlabeled data in practical machining processes is underutilized. To solve this issue, an unlabeled-data-enhanced tool RUL prediction method is proposed to make full use of the abundant accessible unlabeled data. This paper proposes a novel and effective method for utilizing unlabeled data. This paper defines a custom criterion and loss function to train on unlabeled data, thereby utilizing the valuable information contained in these unlabeled data for tool RUL prediction. The physical rule that tool wear increases with the increasing number of cuts is employed to learn knowledge crucial for tool RUL prediction from unlabeled data. Model parameters trained on unlabeled data contain this knowledge. This paper then transfers the parameters through transfer learning to another model based on labeled data for tool RUL prediction, thus completing unlabeled data enhancement. Since multiple sensors are frequently used to simultaneously collect cutting data, this paper uses a graph neural network (GNN) for multi-sensor data fusion, extracting more useful information from the data to improve unlabeled data enhancement. Through multiple sets of comparative experiments and validation, the proposed method effectively enhances the accuracy and generalization capability of the RUL prediction model for cutting tools by utilizing unlabeled data. Full article

This paper proposes a tree-based regression model for hybrid channel estimation in wireless sensor networks (WSNs) in generalized frequency division multiplexing (GFDM) over both visible light communication (VLC) and radio frequency (RF) links. The hybrid channel incorporates both additive white Gaussian noise (AWGN) and Rayleigh fading to mimic realistic environments. Traditional estimators, such as MMSE and LMMSE, often underperform in such heterogeneous and nonlinear conditions due to their analytical rigidity. To overcome these limitations, we introduce a data-driven approach using a decision tree regressor trained on 18,000 signal samples across 36 SNR levels. Simulation results show that support vector machine (SVM) achieved 91.34% accuracy and a BER of 0.0866 at 10 dB, as well as 96.77% accuracy with a BER of 0.0323 at 30 dB. Random forest achieved 91.01% accuracy and a BER of 0.0899 at 10 dB, as well as 97.88% accuracy with a BER of 0.0212 at 30 dB. The proposed tree model attained 90.83% and 97.63% accuracy with BERs of 0.0917 and 0.0237, respectively, at the corresponding SNR values. The distinguishing advantage of the tree model lies in its inference efficiency. It completes predictions on the test dataset in just 45.53 s, making it over three times faster than random forest (140.09 s) and more than four times faster than SVM (189.35 s). This significant reduction in inference time makes the proposed tree model particularly well suited for real-time and resource-constrained WSN scenarios, where fast and efficient estimation is often more critical than marginal gains in accuracy. The results also highlight a trade-off, where the tree model provides sub-optimal predictive performance while significantly reducing computational overhead, making it an attractive choice for low-power and latency-sensitive wireless systems. Full article

The brain age gap (BAG), the divergence of an individual’s neurobiologically predicted brain age from their chronological age, is a key indicator of brain health. While BAG can be derived from diverse brain metrics, its interpretation often polarizes between early-life trait influences and current state-dependent factors like cognitive decline. Here, we propose an integrative framework that moves beyond single summary statistics by considering the full distribution of brain metrics across regions or time. We distinguish between a neural system’s “baseline” (typical values, e.g., mean) and its “capacity” (extreme values, e.g., maximum) within these distributions. To test this, we analyzed resting-state magnetoencephalography (MEG) from the Cam-CAN adult cohort, focusing on cross-frequency coupling (CFC) within functional MRI-defined networks. We derived network-specific CFC baseline (mean) and capacity (maximum) measures. Separate brain age prediction models were trained for each measure. The resulting BAGs (baseline-BAG and capacity-BAG) for each network were then correlated with cognitive performance on a picture priming task. Both baseline-BAG and capacity-BAG profiles showed associations with cognitive scores, with younger predicted brain age correlating with better performance. However, capacity-BAG exhibited more conclusive relationships, suggesting that metrics reflecting a neural system’s peak operational ability (capacity) may better capture an individual’s current cognitive state. These findings indicate that brain age models emphasizing neural capacity, rather than just baseline activity, could offer a more sensitive lens for understanding the state-dependent aspects of brain ageing. Full article

Modernizing and mechanizing agriculture are vital to increasing productivity and meeting the growing global food demand. Timely harvesting decisions, traditionally based on farmers’ experience, are crucial for crop management. This study introduces the Brinjal Harvesting Decision System (BHDS), an automated, real-time framework designed to optimize harvesting decisions using a portable, low-power edge computing device. Unlike conventional object detection models, which require substantial pre-training and curated datasets, the BHDS integrates automated data acquisition and dynamic image quality assessment, enabling effective operation with minimal data input. Tested on diverse farm layouts, the BHDS achieved 95.53% accuracy in data collection and captured quality images within an average of 3 s, reducing both time and energy for dataset creation. The brinjal detection algorithm employs pixel-based methods, including background elimination, K-means clustering, and symmetry testing for precise identification. Implemented on a portable edge device and tested in actual farmland, the system demonstrated 79% segmentation accuracy, 87.48% detection precision, and an F1-score of 87.53%, with an average detection time of 3.5 s. The prediction algorithm identifies ready-to-harvest brinjals with 89.80% accuracy in just 0.029 s. Moreover, the system’s low energy consumption, operating for over 7 h on a 10,000 mAh power bank, demonstrates its practicality for agricultural edge applications. The BHDS provides an efficient, cost-effective solution for automating harvesting decisions, minimizing manual data processing, reducing computational overhead, and maintaining high precision and operational efficiency. Full article

Speech recognition approaches typically fall into three categories: audio, visual, and audio–visual. Visual speech recognition, or lip reading, is the most difficult because visual cues are ambiguous and data is scarce. To address these challenges, we present a new multi-task audio–visual speech recognition, or MultiAVSR, framework for training a model on all three types of speech recognition simultaneously primarily to improve visual speech recognition. Unlike prior works which use separate models or complex semi-supervision, our framework employs a supervised multi-task hybrid Connectionist Temporal Classification/Attention loss cutting training exaFLOPs to just 18% of that required by semi-supervised multitask models. MultiAVSR achieves state-of-the-art visual speech recognition word error rate of 21.0% on the LRS3-TED dataset. Furthermore, it exhibits robust generalization capabilities, achieving a remarkable 44.7% word error rate on the WildVSR dataset. Our framework also demonstrates reduced dependency on external language models, which is critical for real-time visual speech recognition. For the audio and audio–visual tasks, our framework improves the robustness under various noisy environments with average relative word error rate improvements of 16% and 31%, respectively. These improvements across the three tasks illustrate the robust results our supervised multi-task speech recognition framework enables. Full article

Hand gesture recognition (HGR) heavily relies on high-quality annotated datasets. However, annotating hand landmarks in video sequences is a time-intensive challenge. In this work, we introduce IPN HandS, an enhanced version of our IPN Hand dataset, which now includes approximately 700,000 hand skeleton annotations and corrected gesture boundaries. To generate these annotations efficiently, we propose a novel annotation tool that combines automatic detection, inter-frame interpolation, copy–paste capabilities, and manual refinement. This tool significantly reduces annotation time from 70 min to just 27 min per video, allowing for the scalable and precise annotation of large datasets. We validate the advantages of the IPN HandS dataset by training a lightweight LSTM-based model using these annotations and comparing its performance against models trained with annotations from the widely used MediaPipe hand pose estimators. Our model achieves an accuracy that is 12% higher than the MediaPipe Hands model and 8% higher than the MediaPipe Holistic model. These results underscore the importance of annotation quality in training generalization and overall recognition performance. Both the IPN HandS dataset and the annotation tool will be released to support reproducible research and future work in HGR and related fields. Full article

In forest operations, traditional ergonomic studies have been carried out by assessing body posture manually, but such assessments may suffer in terms of efficiency and reliability. Advancements in machine learning provided the opportunity to overcome many of the limitations of the manual approach. This study evaluated the intra- and inter-reliability of postural assessments in manual and motor-manual forest operations using the Ovako Working Posture Analysing System (OWAS)—which is one of the most used methods in forest operations ergonomics—by considering the predictions of a deep learning model as reference data and the rating inputs of three raters done in two replicates, over 100 images. The results indicated moderate to almost perfect intra-rater agreement (Cohen’s kappa = 0.48–1.00) and slight to substantial agreement (Cohen’s kappa = 0.02–0.64) among human raters. Inter-rater agreement between pairwise human-model datasets ranged from poor to fair (Cohen’s kappa = −0.03–0.34) and from fair to moderate when integrating all the human ratings with those of the model (Fleiss’ kappa = 0.28–0.49). The deep learning (DL) model highly outperformed human raters in assessment speed, requiring just one second per image, which, on average, was 19 to 53 times faster compared to human ratings. These findings highlight the efficiency and potential of integrating DL algorithms into OWAS assessments, offering a rapid and resource-efficient alternative while maintaining comparable reliability. However, challenges remain regarding subjective interpretations of complex postures. Future research should focus on refining algorithm parameters, enhancing human rater training, and expanding annotated datasets to improve alignment between model outputs and human assessments, advancing postural assessments in forest operations. Full article

The physical inactivity of adolescents and their sedentary lifestyle with profuse usage of screens has been a growing issue for the last few years. In contrast, there is some evidence that videogame-based exercising improves cognitive abilities and psychological well-being during growth and maturation. Therefore, there is a need for the wider exploration of innovation tools in physical education (PE) and extracurricular activities for schoolchildren. The aim of this study was to determine the change in psychological well-being and cognitive skills of adolescents when exercising is supplemented with videogame-based activity. The short-term physical activity (PA) program, initiated by in-service PE teachers (n = 3), involved 13–15-year-old adolescents (n = 63, of them 20 were boys) from one of biggest cities in Lithuania. The research subjects were participants of extracurricular exercise groups on a regular basis, attending their respective three-times-a-week sessions for 1 month. The first intervention group engaged in a 60 min functional training program (FT group, n = 31). The second group had 30 min of FT followed by 30 min of video-based dance class (FT + Just Dance group, n = 32). The Trail-Making test (part A and B), the Visual Digit Span test, and the Stroop test were performed to investigate students’ cognitive abilities. In addition, the WHO-5 questionnaire was used to analyse the respondents’ psychological well-being. When comparing pre- and post-intervention results, no changes were observed in the psychological state, visual–executive skills, and short-term visual memory in both groups. Reaction time improved significantly in both groups (p < 0.05). The working memory significantly improved in the FT + Just Dance group (p < 0.05). The implementation of videogame-based training, Just Dance, improved adolescents’ working memory, but had no effect on subjectively perceived psychological well-being. Full article