Search Results (5)

Physical fatigue significantly impacts safety and performance across industrial, athletic, and medical domains, yet its detection remains challenging due to individual variability and limited generalizability of existing methods. This study introduces a multimodal fatigue detection system integrating surface electromyography (sEMG) and inertial measurement unit (IMU) signals, processed through a hybrid convolutional neural network–long short-term memory–attention (CNN-LSTM-Attention) model. Fatigue was induced in 35 healthy participants via step-up-and-down exercises, with gait data collected during natural walking before and after fatigue. The model leverages sEMG from the gastrocnemius lateralis and IMU-derived jerk signals from the tibialis anterior and rectus femoris to classify fatigue states. Evaluated using leave-one-subject-out cross-validation (LOSOCV), the system achieved an accuracy of 87.94% with bilateral EMG signals and a balanced recall of 87.94% for fatigued states using a combined IMU-EMG approach. These results highlight the system’s robustness for personalized fatigue monitoring, surpassing traditional subject-dependent methods by addressing inter-individual differences. Full article

The accurate extraction of buildings from remote sensing images is crucial in fields such as 3D urban planning, disaster detection, and military reconnaissance. In recent years, models based on Transformer have performed well in global information processing and contextual relationship modeling, but suffer from high computational costs and insufficient ability to capture local information. In contrast, convolutional neural networks (CNNs) are very effective in extracting local features, but have a limited ability to process global information. In this paper, an asymmetric network (CTANet), which combines the advantages of CNN and Transformer, is proposed to achieve efficient extraction of buildings. Specifically, CTANet employs ConvNeXt as an encoder to extract features and combines it with an efficient bilateral hybrid attention transformer (BHAFormer) which is designed as a decoder. The BHAFormer establishes global dependencies from both texture edge features and background information perspectives to extract buildings more accurately while maintaining a low computational cost. Additionally, the multiscale mixed attention mechanism module (MSM-AMM) is introduced to learn the multiscale semantic information and channel representations of the encoder features to reduce noise interference and compensate for the loss of information in the downsampling process. Experimental results show that the proposed model achieves the best F1-score (86.7%, 95.74%, and 90.52%) and IoU (76.52%, 91.84%, and 82.68%) compared to other state-of-the-art methods on the Massachusetts building dataset, the WHU building dataset, and the Inria aerial image labeling dataset. Full article

Accurate iris segmentation is a crucial preprocessing stage for computer-aided ophthalmic disease diagnosis. The quality of iris images taken under different camera sensors varies greatly, and thus accurate segmentation of heterogeneous iris databases is a huge challenge. At present, network architectures based on convolutional neural networks (CNNs) have been widely applied in iris segmentation tasks. However, due to the limited kernel size of convolution layers, iris segmentation networks based on CNNs cannot learn global and long-term semantic information interactions well, and this will bring challenges to accurately segmenting the iris region. Inspired by the success of vision transformer (VIT) and swin transformer (Swin T), a hybrid deep learning approach is proposed to segment heterogeneous iris images. Specifically, we first proposed a bilateral segmentation backbone network that combines the benefits of Swin T with CNNs. Then, a multiscale feature information extraction module (MFIEM) is proposed to extract multiscale spatial information at a more granular level. Finally, a channel attention mechanism module (CAMM) is used in this paper to enhance the discriminability of the iris region. Experimental results on a multisource heterogeneous iris database show that our network has a significant performance advantage compared with some state-of-the-art (SOTA) iris segmentation networks. Full article

Background and objective: Type of physical activity may influence morphological and muscular asymmetries in the young population. However, less is known about the size of this effect when comparing various sports. The aim of this study was to identify the degree of bilateral asymmetry (BA) and the level of unilateral ratio (UR) between isokinetic strength of knee extensors (KE) and flexors (KF) among athletes of three different types of predominant locomotion in various sports (symmetric, asymmetric and hybrid). Material and methods: The analyzed group consisted of young elite athletes (n = 50). The maximum peak muscle torque of the KE and KF in both the dominant (DL) and non-dominant (NL) lower limb during concentric muscle contraction at an angular velocity of 60°·s⁻¹ was measured with an isokinetic dynamometer. Results: Data analysis showed a significant effect of the main factor (the type of sport) on the level of monitored variables (p = 0.004). The type of sport revealed a significant difference in the bilateral ratio (p = 0.01). The group of symmetric and hybrid sports achieved lower values (p = 0.01) of BA in their lower limb muscles than those who played asymmetric sports. The hybrid sports group achieved higher UR values (p = 0.01) in both lower limbs. Conclusions: The results indicate that sports with predominantly symmetrical, asymmetrical, and hybrid types of locomotion affected the size of the BA, as well as the UR between KE and KF in both legs in young athletes. We recommend paying attention to regular KE and KF strength diagnostics in young athletes and optimizing individual compensatory exercises if a higher ratio of strength asymmetry is discovered. Full article

The energy embodied in construction services consumed by industrial sectors used to increase capacities has led to massive energy-related carbon emissions (ERCE). From the perspective of consumer responsibility, ERCE embodied in construction services is driven by technological changes and the increases in final demand of various sectors, including final consumption, fixed assets investment, and net export. However, little attention has been paid to decomposing sectoral responsibilities from this perspective. To fill this research gap, we propose a dynamic hybrid input–output model combined with structural decomposition analysis (DHI/O-SDA model). We introduce DHI/O modeling into the estimation of ERCE embodied in construction services from the perspective of consumer responsibility and introduce SDA into DHI/O models to improve the resolution of the estimate. Taking China as a case study, we verified the DHI/O-SDA model and present the bilateral relationships among sectoral responsibilities for ERCE embodied in construction services. A major finding is that the “Other Tertiary Industry” sector is most responsible for ERCE embodied in construction services and strongly influences other sectors. Therefore, controlling the final demand increase of the service industry will be the most effective policy to reduce the ERCE embodied in construction services. Full article