Search

In the field of Generalized Zero-Shot Learning (GZSL), the challenge lies in learning attribute-based information from seen classes and effectively conveying this knowledge to recognize both seen and unseen categories during the training process. This paper proposes an innovative approach to enhance the generalization ability and efficiency of GZSL models by integrating a Convolutional Block Attention Module (CBAM). The CBAM blends channel-wise and spatial-wise information to emphasize key features, thereby improving the model's discriminative and localization capabilities. Additionally, the method employs a ResNet101 backbone for systematic image feature extraction, enhanced contrastive learning, and a similarity map generator with attribute prototypes. This comprehensive framework aims to achieve robust visual–semantic embedding for classification tasks. The proposed method demonstrates significant improvements in performance metrics in benchmark datasets, showcasing its potential in advancing GZSL applications. [ABSTRACT FROM AUTHOR]

Surface electromyography (sEMG) offers a novel method in human–machine interactions (HMIs) since it is a distinct physiological electrical signal that conceals human movement intention and muscle information. Unfortunately, the nonlinear and non-smooth features of sEMG signals often make joint angle estimation difficult. This paper proposes a joint angle prediction model for the continuous estimation of wrist motion angle changes based on sEMG signals. The proposed model combines a temporal convolutional network (TCN) with a long short-term memory (LSTM) network, where the TCN can sense local information and mine the deeper information of the sEMG signals, while LSTM, with its excellent temporal memory capability, can make up for the lack of the ability of the TCN to capture the long-term dependence of the sEMG signals, resulting in a better prediction. We validated the proposed method in the publicly available Ninapro DB1 dataset by selecting the first eight subjects and picking three types of wrist-dependent movements: wrist flexion (WF), wrist ulnar deviation (WUD), and wrist extension and closed hand (WECH). Finally, the proposed TCN-LSTM model was compared with the TCN and LSTM models. The proposed TCN-LSTM outperformed the TCN and LSTM models in terms of the root mean square error (RMSE) and average coefficient of determination (R2). The TCN-LSTM model achieved an average RMSE of 0.064, representing a 41% reduction compared to the TCN model and a 52% reduction compared to the LSTM model. The TCN-LSTM also achieved an average R2 of 0.93, indicating an 11% improvement over the TCN model and an 18% improvement over the LSTM model. [ABSTRACT FROM AUTHOR]

Modern low‐pressure turbine (LPT) pursues high blade loading to improve its efficiency while the possibility of boundary layer separation on the blades is still a challenging problem. The incidence angle is one of the main factors affecting the flow separation and laminar‐turbulent transition, which is of key importance for the design of LPT. In this work, based on the initial simulation results obtained using the Reynolds‐averaged Navier–Stokes (RANS) method, the flow past a single LPT cascade at three representative incident angles (i = −10°, 0°, +10°) is investigated using large‐eddy simulation (LES) method with approximately 26 million structured grids. The simulations are carried out with Open Source Field Operation and Manipulation (OpenFOAM) for an off‐design low Reynolds number condition Re = 40,000 and Ma = 0.5. The time‐averaged aerodynamic performances and three‐dimensional instantaneous flow characteristics of the LPT cascade are discussed in detail, and the results show that the blade loading and the transverse pressure gradient (TPG) from the pressure side to the suction side of leading edge (LE) increase with increasing incidence angle. At the incidence angle of +10°, the LPT cascade undergoes separation and reattachment from the LE to around 20% Cax on the suction surface, which weakens the separation phenomenon at the rear half of the suction surface and the total pressure loss downstream of the trailing edge (TE). It is worth noting that the RANS method underpredicts the blade boundary layer separation region compared with LES under these extreme conditions. These results may offer off‐design condition data for the future improvement of RANS models or experimental studies. [ABSTRACT FROM AUTHOR]

IN the above article [1], we found the formula (1) is presented incorrectly because of an error in the formula editing process. The correction is as follows: ITR=[log 2 K+Plog 2 P+(1-p)log 2 (1-P/K-1)]×60/T (1).