Browse Articles
Discover research articles across all indexed journals
Remote sensing-based spatiotemporal assessment of agricultural drought and its impact on crop yields in Punjab, Pakistan
Prognostic and immunotherapeutic significance of NCAPD2 in pan-cancer and its role in hepatocellular carcinoma progression via the AKT/GSK-3β signaling pathway
Homocysteine promotes cardiomyocyte hypertrophy through inhibiting β-catenin/ FUNDC1 mediated mitophagy
Using twin data to examine heritable and intrauterine hormonal influences on transgender and gender diverse identities
The interplay of incivility, peer support, and psychological capital in higher education
Cold environment regulates ischemic stroke through modulation of gut microbiota
The influence of serotonergic multilocus genetic variants and parent–child relationship on adolescent creativity
A spherical fuzzy WASPAS approach to prioritize the factors enhancing the effectiveness of physical education classroom teaching
The molecular basis of T cell receptor recognition of citrullinated tenascin-C presented by HLA-DR4
Improved convolutional neural network for precise exercise posture recognition and intelligent health indicator prediction
Abstract This paper presents a novel framework for accurate exercise posture recognition and health indicator prediction based on improved convolutional neural networks. We propose a multi-scale feature fusion architecture incorporating spatiotemporal attention mechanisms to enhance key point detection precision while maintaining computational efficiency. The system achieves superior posture recognition performance with 78.6% mAP and 91.5% PCK@0.5, outperforming state-of-the-art methods while maintaining real-time inference capabilities (27.3 FPS). For health indicator prediction, we develop a CNN-LSTM model with personalized parameter adaptation that accurately forecasts multiple physiological metrics including cardiorespiratory fitness, muscular strength, and metabolic rate, achieving 86.1–92.6% prediction accuracy across diverse health dimensions. Comprehensive evaluations on both self-collected and public datasets demonstrate the system’s robustness across varying exercise types, environmental conditions, and demographic groups. The proposed approach offers significant potential for applications in personal fitness coaching, rehabilitation monitoring, and preventive healthcare by providing automated exercise form evaluation and personalized health insights.
Blockchain-based heterogeneous resource configuration scheme in computing power network
Exploiting spinel manganese oxide decorated with silver nanoparticles as electrodes for supercapacitor application
Eveningness and distinctness of the circadian rhythm in men are related to altered neural responses to gain and loss
Counting the costs of injury and disease to first responders as a result of extreme bushfires
Abstract Extreme bushfires are devastating and costly and are predicted to increase in frequency. This project investigated emergency responders’ (ER) compensable injury/disease costs associated with extreme bushfire periods compared with the general workforce. Workers’ compensation claims data for Victoria, Australia, were sourced for ER and controls (10% of the general workforce) from January 2005 to April 2021 (encompassing two extreme bushfires). Using generalised linear models, claims from ambulance officers, career firefighters, police, and controls were compared across extreme bushfires, other summers, and all other periods. In total, ER made 749/24,008 (3.1%) claims in extreme bushfire periods, compared to 1254/49,484 (2.5%) in the controls. The study group overall (including both ER and the general workforce control group) experienced significantly higher income compensation costs/claims during extreme bushfire periods, with a 31% increase. ER’ costs/claims were highest for mental illness, burns and cancer. After accounting for bushfire impacts on the general workforce, total claims costs were increased by 67% among firefighters in extreme bushfire periods, largely attributable to fatality payments (other non-medical expenses). These results highlight the need for targeted injury prevention for fatal and non-fatal injuries among ERs and measures that address the broader socio-economic impacts on ERs and the general workforce.
Enhancing occluded and standard bird object recognition using fuzzy-based ensembled computer vision approach with convolutional neural network
Abstract Classifying bird species is essential for ecological study and biodiversity protection, currently, conventional approaches are frequently laborious and susceptible to mistakes. Convolutional Neural Networks (CNNs) provide a more reliable option for feature extraction and classification. By combining the top three independently superior CNN architectures for recognizing bird species from the DenseNet and ResNet families into a fuzzy-based ensemble learning framework, this study helps increase classification accuracy, especially for occluded bird objects. The model improves generalization by using 11,352 images collected from the Caltech-UCSD Birds-200-2011 and Birds525 Species-Image Classification datasets, as well as sophisticated augmentation approaches. Our ensemble method adaptively allocates model weights based on feature contributions found using fuzzy logic, in contrast to existing methods that have trouble with obstructed images. Since, every CNN model candidate in the suggested fuzzy-based ensemble learning showed excellent classification performance, the proposed fuzzy-based ensemble approach achieving 98.73% accuracy, a 98.75% F1-score for standard images, and 95.78% accuracy, and a 95.1% F1-score for occluded images, the results indicating performance improvements of 2% for standard and 9% for occluded bird images over the methods used in existing research work. Furthermore, as compared to the individual CNN candidates in the proposed fuzzy-based ensemble, this indicates a 2–5% performance improvement for standard bird images and a 4–7% performance improvement for occluded bird images. Additionally, the reliability and significance of the observed performance increases are verified by statistical validation of the results using p-value and F-statistic testing and 95% Confidence Intervals.