Search Results (4,717)

Landslides are destructive geological hazards, making accurate landslide susceptibility assessment essential for disaster prevention and mitigation. However, existing studies often lack scientific rigor in negative sample construction and have unclear model applicability. This study focuses on Ya’an City, Sichuan Province, China, and proposes an innovative approach to negative sample construction using Geographically Weighted Regression (GWR), which is then integrated with Tabular Network (TabNet), a deep learning architecture tailored to structured tabular data, to assess landslide susceptibility. The performance of TabNet is compared against Random Forest, Light Gradient Boosting Machine, deep neural networks, and Residual Networks. The experimental results indicate that (1) the GWR-based sampling strategy substantially improves model performance across all tested models; (2) TabNet trained using the GWR-based negative samples achieves superior performance over all other evaluated models, with an average AUC of 0.9828, exhibiting both high accuracy and interpretability; and (3) elevation, land cover, and annual Normalized Difference Vegetation Index are identified as dominant predictors through TabNet’s feature importance analysis. The results demonstrate that combining GWR and TabNet substantially enhances landslide susceptibility modeling by improving both accuracy and interpretability, establishing a more scientifically grounded approach to negative sample construction, and providing an interpretable, high-performing modeling framework for geological hazard risk assessment. Full article

How do humans analyze the sentiments embedded in text? When attempting to analyze a text, humans construct a “scene” in their minds through imagination based on the text, generating a vague image. They then synthesize the text and the mental image to derive the final analysis result. However, current sentiment analysis models lack such imagination; they can only analyze based on existing information in the text, which limits their classification accuracy. To address this issue, we propose the SceEmoNet model. This model endows text classification models with imagination through Stable diffusion, enabling the model to generate corresponding visual scenes from input text, thus introducing a new modality of visual information. We then use the Contrastive Language-Image Pre-training (CLIP) model, a multimodal feature extraction model, to extract aligned features from different modalities, preventing significant feature differences caused by data heterogeneity. Finally, we fuse information from different modalities using late fusion to obtain the final classification result. Experiments on six datasets with different classification tasks show improvements of 9.57%, 3.87%, 3.63%, 3.14%, 0.77%, and 0.28%, respectively. Additionally, we set up experiments to deeply analyze the model’s advantages and limitations, providing a new technical path for follow-up research. Full article

Effective earthquake early warning (EEW) is essential for disaster prevention in the built environment, enabling a rapid structural response, system shutdown, and occupant evacuation to mitigate damage and casualties. However, most current EEW systems lack rigorous reliability analyses of their predictive outcomes, limiting their effectiveness in real-world scenarios—especially for on-site warnings, where data are limited and time is critical. To address these challenges, we propose a Bayesian neural network (BNN) framework based on Stein variational gradient descent (SVGD). By performing Bayesian inference, we estimate the posterior distribution of the parameters, thus outputting a reliability analysis of the prediction results. In addition, we incorporate a continual learning mechanism based on elastic weight consolidation, allowing the system to adapt quickly without full retraining. Our experiments demonstrate that our SVGD-BNN model significantly outperforms traditional peak displacement (Pd)-based approaches. In a 3 s time window, the Pearson correlation coefficient R increases by 9.2% and the residual standard deviation $SD$ decreases by 24.4% compared to a variational inference (VI)-based BNN. Furthermore, the prediction variance generated by the model can effectively reflect the uncertainty of the prediction results. The continual learning strategy reduces the training time by 133–194 s, enhancing the system’s responsiveness. These features make the proposed framework a promising tool for real-time, reliable, and adaptive EEW—supporting disaster-resilient building design and operation. Full article

China is one of the countries severely affected by earthquakes, making precise and timely identification of earthquake precursors essential for reducing casualties and property damage. A novel method is proposed that combines a rock acoustic emission (AE) detection technique with deep learning methods to facilitate real-time monitoring and advance earthquake precursor detection. The AE equipment and seismometers were installed in a granite tunnel 150 m deep in the mountains of eastern Guangdong, China, allowing for the collection of experimental data on the correlation between rock AE and seismic activity. The deep learning model uses features from rock AE time series, including AE events, rate, frequency, and amplitude, as inputs, and estimates the likelihood of seismic events as the output. Precursor features are extracted to create the AE and seismic dataset, and three deep learning models are trained using neural networks, with validation and testing. The results show that after 1000 training cycles, the deep learning model achieves an accuracy of 98.7% on the validation set. On the test set, it reaches a recognition accuracy of 97.6%, with a recall rate of 99.6% and an F₁ score of 0.975. Additionally, it successfully identified the two biggest seismic events during the monitoring period, confirming its effectiveness in practical applications. Compared to traditional analysis methods, the deep learning model can automatically process and analyse recorded massive AE data, enabling real-time monitoring of seismic events and timely earthquake warning in the future. This study serves as a valuable reference for earthquake disaster prevention and intelligent early warning. Full article

This study is the first to systematically integrate supervised machine learning (decision tree) and association rule mining techniques to analyze accident data from the Taipei Metro system, conducting a large-scale data-driven investigation into both passenger injury and train malfunction events. The research demonstrates strong novelty and practical contributions. In the passenger injury analysis, a dataset of 3331 cases was examined, from which two highly explanatory rules were extracted: (i) elderly passengers (aged > 61) involved in station incidents are more likely to suffer moderate to severe injuries; and (ii) younger passengers (aged ≤ 61) involved in escalator incidents during off-peak hours are also at higher risk of severe injury. This is the first study to quantitatively reveal the interactive effect of age and time of use on injury severity. In the train malfunction analysis, 1157 incidents with delays exceeding five minutes were analyzed. The study identified high-risk condition combinations—such as those involving rolling stock, power supply, communication, and signaling systems—associated with specific seasons and time periods (e.g., a lift value of 4.0 for power system failures during clear mornings from 06:00–12:00, and 3.27 for communication failures during summer evenings from 18:00–24:00). These findings were further cross-validated with maintenance records to uncover underlying causes, including brake system failures, cable aging, and automatic train operation (ATO) module malfunctions. Targeted preventive maintenance recommendations were proposed. Additionally, the study highlighted existing gaps in the completeness and consistency of maintenance records, recommending improvements in documentation standards and data auditing mechanisms. Overall, this research presents a new paradigm for intelligent metro system maintenance and safety prediction, offering substantial potential for broader adoption and practical application. Full article

Sarcopenia is a progressive age-related musculoskeletal disorder characterized by loss of muscle mass, strength, and physical performance, contributing to functional decline and increased risk of disability. Emerging evidence suggests that vitamin D (Vit D) plays a pivotal role in skeletal muscle physiology beyond its classical functions in bone metabolism. This review aims to critically analyze the relationship between serum Vit D levels and sarcopenia in older adults, focusing on pathophysiological mechanisms, diagnostic criteria, clinical evidence, and preventive strategies. An integrative narrative review of observational studies, randomized controlled trials, and meta-analyses published in the last decade was conducted. The analysis incorporated international diagnostic criteria for sarcopenia (EWGSOP2, AWGS, FNIH, IWGS), current guidelines for Vit D sufficiency, and molecular mechanisms related to Vit D receptor (VDR) signaling in muscle tissue. Low serum 25-hydroxyvitamin D levels are consistently associated with decreased muscle strength, reduced physical performance, and increased prevalence of sarcopenia. Although interventional trials using Vit D supplementation report variable results, benefits are more evident in individuals with baseline deficiency and when combined with protein intake and resistance training. Mechanistically, Vit D influences muscle health via genomic and non-genomic pathways, regulating calcium homeostasis, mitochondrial function, oxidative stress, and inflammatory signaling. Vit D deficiency represents a modifiable risk factor for sarcopenia and functional impairment in older adults. While current evidence supports its role in muscular health, future high-quality trials are needed to establish optimal serum thresholds and dosing strategies for prevention and treatment. An individualized, multimodal approach involving supplementation, exercise, and nutritional optimization appears most promising. Full article

Racket sports are very popular not only in professional sports but also among recreational players. As a result, their impact on the field of education has grown significantly in recent years. Table tennis (TT) offers significant advantages in terms of skill acquisition and health improvement. Nevertheless, its application within physical education (PE) curricula remains undetermined. The aim of this systematic review was to analyze the use of TT as educational content in the subject of PE in primary school. The PRISMA 2020 methodology was used to conduct the systematic review. Six databases (ERIC, Pubmed, ScienceDirect, Scopus, Sport Discus, and Web of Science) were used during the search process. The search cutoff date was December 31, 2024. After applying the eligibility criteria, 3595 articles were found. Only seven studies were selected for the final analysis and the data included 1526 students from primary school. The results indicate that TT is rarely used in primary education during PE classes. Research indicates interest among teachers and students in playing it during PE. Furthermore, due to the benefits, motivation, and interest this sport generates, educational experiences have been developed, such as roundtable discussions, table top tennis, balloon TT, and TT triathlon. A lack of materials, facilities, and teacher training for teaching this sport is notable. The teaching experiences analyzed in this review confirm that TT is a highly versatile and interesting sport as a subject matter in school PE. The use of TT allows for innovative, comprehensive, and inclusive PE, thanks to the sport’s multiple possibilities. Given its adaptability and low entry barrier, TT could serve as an effective tool for increasing children’s physical activity levels, improving motor skills, and fostering social–emotional development. However further research is needed to quantify its impact on health outcomes such as cardiovascular fitness or obesity prevention. Full article

In high-dynamic bipedal locomotion control, robotic systems are often constrained by motor torque limitations, particularly during explosive tasks such as jumping. One of the key challenges in reinforcement learning lies in bridging the sim-to-real gap, which mainly stems from both inaccuracies in simulation models and the limitations of motor torque output, ultimately leading to the failure of deploying learned policies in real-world systems. Traditional RL methods usually focus on peak torque limits but ignore that motor torque changes with speed. By only limiting peak torque, they prevent the torque from adjusting dynamically based on velocity, which can reduce the system’s efficiency and performance in high-speed tasks. To address these issues, this paper proposes a reinforcement learning jump-control framework tailored for tendon-driven bipedal robots, which integrates dynamic torque boundary constraints and torque error-compensation modeling. First, we developed a torque transmission coefficient model based on the tendon-driven mechanism, taking into account tendon elasticity and motor-control errors, which significantly improves the modeling accuracy. Building on this, we derived a dynamic joint torque limit that adapts to joint velocity, and designed a torque-aware reward function within the reinforcement learning environment, aimed at encouraging the policy to implicitly learn and comply with physical constraints during training, effectively bridging the gap between simulation and real-world performance. Hardware experimental results demonstrate that the proposed method effectively satisfies actuator safety limits while achieving more efficient and stable jumping behavior. This work provides a general and scalable modeling and control framework for learning high-dynamic bipedal motion under complex physical constraints. Full article

This study aimed to compare isometric strength, range of motion (RoM), and strength ratios of shoulder internal and external rotators between female volleyball and hand ball players Twenty-five volleyball players (age = 21.8 ± 4.8 years, height = 178.5 ± 7.1 cm, mass = 69.3 ± 7.7 kg) and twenty-four handball players (age = 19.5 ± 2.9 years, height = 169.7 ± 6.4 cm, mass = 67.6 ± 8.4 kg), all competing in the Slovenian 1st national league, participated. Maximal isometric strength and passive RoM of internal and external rotation were measured bilaterally using a handheld dynamometer and goniometer, respectively. A significant group × side interaction was observed for internal rotation RoM (F = 5.41; p = 0.024; η² = 0.10), with volleyball players showing lower RoM on the dominant side (p = 0.001; d = 0.89), but this was not the case for handball players (p = 0.304). External rotation strength also showed a significant interaction (F = 9.34; p = 0.004; η² = 0.17); volleyball players were stronger in the non-dominant arm (p = 0.033), while handball players were stronger in the dominant arm (p = 0.041). The external-to-internal rotation strength ratio was significantly lower on the dominant side in volleyball players compared to handball players (p = 0.047; d = 0.59). Findings suggest sport-specific adaptations and asymmetries in shoulder function, emphasizing the need for sport-specific and individually tailored injury prevention strategies. Volleyball players, in particular, may benefit from targeted strengthening of external rotators and flexibility training to address imbalances. Full article

Background: Retinal diseases are becoming an important public health issue, with early diagnosis and timely intervention playing a key role in preventing vision loss. Optical coherence tomography (OCT) remains the leading non-invasive imaging technique for identifying retinal conditions. However, distinguishing between diabetic macular edema (DME) and macular edema resulting from retinal vein occlusion (RVO) can be particularly challenging, especially for clinicians without specialized training in retinal disorders, as both conditions manifest through increased retinal thickness. Due to the limited research exploring the application of deep learning methods, particularly for RVO detection using OCT scans, this study proposes a novel diagnostic approach based on stacked convolutional neural networks. This architecture aims to enhance classification accuracy by integrating multiple neural network layers, enabling more robust feature extraction and improved differentiation between retinal pathologies. Methods: The VGG-16, VGG-19, and ResNet50 models were fine-tuned using the Kermany dataset to classify the OCT images and afterwards were trained using a private OCT dataset. Four stacked models were then developed using these models: a model using the VGG-16 and VGG-19 networks, a model using the VGG-16 and ResNet50 networks, a model using the VGG-19 and ResNet50 models, and finally a model using all three networks. The performance metrics of the model includes accuracy, precision, recall, $F_2$-score, and area under of the receiver operating characteristic curve (AUROC). Results: The stacked neural network using all three models achieved the best results, having an accuracy of 90.7%, precision of 99.2%, a recall of 90.7%, and an $F_2$-score of 92.3%. Conclusions: This study presents a novel method for distinguishing retinal disease by using stacked neural networks. This research aims to provide a reliable tool for ophthalmologists to improve diagnosis accuracy and speed. Full article

A reliable prediction of the remaining useful life of critical electronic components, such as insulated gate bipolar transistors, is necessary for preventing failures in many industrial applications. Recently, diverse machine-learning techniques have been used for this task. However, they are generally focused on capturing the temporal dependencies or on representing the probabilistic nature of the degradation of the device. This work proposes a neural network architecture that combines long short-term memory and mixture density networks to address both targets simultaneously when modeling the remaining useful life. The proposed model was trained and evaluated using a real dataset of insulated gate bipolar transistors, demonstrating a high capacity for predicting the remaining useful life of the validation devices. The proposed model outperformed the other algorithms considered in the study in terms of root mean squared error and coefficient of determination. In general terms, an average reduction of at least 18% of the root mean squared error was obtained when compared with the second-best model among those considered in this work, but in some specific cases, the root mean squared error during the prediction of remaining useful life decreased up to 21%. In addition to the high performance obtained, the characteristics of the network output also facilitated the creation of confidence intervals, which are more informative than solely exact values for decision-making. Full article

Introduction: Despite the key role of healthcare workers (HCWs) in tuberculosis (TB) prevention and control, there is a lack of regional data on their knowledge, attitudes, and practices (KAPs) regarding the disease in Atlantic Canada. Objectives: To assess the KAPs of HCWs and identify targets for educational interventions to enhance TB care and control. Methods: A cross-sectional study was conducted among HCWs in Atlantic Canada aged $\ge$19 years from October 2023 to February 2024. Participants were recruited via multiple channels such as social media, collegiate email lists, and snowball sampling. Survey data were collected using an online platform and analyzed using IBM SPSS Statistics v29. KAPs were assessed using Likert-type scales and internal consistency was evaluated using Cronbach’s alpha. Results: A total of 157 HCWs participated in this study (age range: 19 to 69 years); most were women (n = 145, 92%), born in Canada (n = 134, 85.4%), with nearly three-quarters (n = 115, 73.2%) who had never lived outside of Canada. Study participants demonstrated moderately high knowledge (M = 29.32, SD = 3.25) and positive attitudes (M = 3.87, SD = 0.37) towards TB and strong practices (M = 4.24, SD = 0.69) in TB care; however, gaps were identified in HCW abilities to recognize less common TB symptoms (e.g., rash and nausea), as well as inconsistent practices in ventilation and pre-treatment initiation. Internal consistency analysis indicated suboptimal reliability across all three KAP domains, with Cronbach’s alpha values falling below 0.7, thwarting further planned analyses. Conclusions: This study found overall moderate-to-strong TB-related KAPs among HCWs in Atlantic Canada; however, critical gaps in knowledge and practice were noted. This new information can now guide future educational initiatives and targeted training to enhance TB preparedness and ensure equitable care for patients in the region. Full article

Increasing automation and the rapidly growing use of robots in industrial as well as social areas result in a greater need for research regarding collaboration between humans and robots. Key factors for a safe and successful combination of human and robot abilities include acceptance and trust in the robot. In order to prevent physical and psychological harm to humans, reducing these negative emotions and increasing trust and acceptance are essential. One way to achieve this is through the use of virtual training methods and environments. However, current research scarcely covers this approach. Therefore, this research focusses on an experimental approach to investigate emotional and psychophysiological (ECG, EDA) reactions while performing a collaborative assembly task (screwing) with an industrial robot in a real and a virtual setting, respectively. The study sample consisted of 46 participants (23 female) with an age range from 20 to 58 years. The results of the analyzed subjective and objective psychophysiological (cardiovascular and electrodermal responses) measures provide more information regarding the suitability of virtual trainings for human–robot collaboration. Differences in task complexity were measurable in both virtual and real environments. Furthermore, gender differences were also shown. Full article

Background: Extremely premature neonates are at increased risk for respiratory complications, often resulting in recurrent hospitalizations during early childhood. Early identification of preterm infants at highest risk of respiratory hospitalizations could enable targeted preventive interventions. While clinical and demographic factors offer some prognostic value, integrating transcriptomic data may improve predictive accuracy. Objective: To determine whether early-life gene expression profiles can predict respiratory-related hospitalizations within the first four years of life in extremely preterm neonates. Methods: We conducted a retrospective cohort study of 58 neonates born at <32 weeks’ gestational age, using publicly available transcriptomic data from peripheral blood samples collected on days 5, 14, and 28 of life. Random forest models were trained to predict unplanned respiratory readmissions. Model performance was evaluated using sensitivity, specificity, positive predictive value, negative predictive value, and area under the receiver operating characteristic curve (AUC). Results: All three models, built using transcriptomic data from days 5, 14, and 28, demonstrated strong predictive performance (AUC = 0.90), though confidence intervals were wide due to small sample size. We identified 31 genes and eight biological pathways that were differentially expressed between preterm neonates with and without subsequent respiratory readmissions. Conclusions: Transcriptomic data from the neonatal period, combined with machine learning, accurately predicted respiratory-related rehospitalizations in extremely preterm neonates. The identified gene signatures offer insight into early biological disruptions that may predispose preterm neonates to chronic respiratory morbidity. Validation in larger, diverse cohorts is needed to support clinical translation. Full article

Marine pollution from plastic pellets, small granules used as a raw material for plastic production, is a growing environmental problem with grave consequences for marine ecosystems, biodiversity, and human health. This form of primary microplastic is increasingly becoming the focus of environmental policies, owing to its frequent release into the marine environment during handling, storage, and marine transportation, all of which play a crucial role in global trade. The aim of this paper is to contribute to the ongoing discussions by highlighting the environmental risks associated with plastic pellets, which are recognized as a significant source of microplastics in the marine environment. It will also explore how targeted education and awareness-raising within the maritime sector can serve as key tools to address this environmental challenge. The study is based on a survey conducted among seafarers and maritime students to raise their awareness and assess their knowledge of the issue. Given their operational role in ensuring safe and responsible shipping, seafarers and maritime students are in a key position to prevent the release of plastic pellets into the marine environment through increased awareness and initiative-taking practices. The results show that awareness is moderate, but there is a significant lack of knowledge, particularly in relation to the environmental impact and regulatory aspects of plastic pellet pollution. These results underline the need for improved education and training in this area, especially among future and active maritime professionals. Full article