Search

Dependency parsing aims to analyze the syntactic structure of sentences from the perspective of linguistics.Existing studies suggest that combining such graph-like data with graph convolutional network(GCN) can help model better understand the text semantics.However,when dealing with dependency syntactic information as adjacency matrix,these methods ignore the types of syntactic dependency tags and the word semantics related to the tags,which makes the model unable to capture the deep emotional features.To solve the preceding problem,this paper proposes a Chinese short text sentiment analysis model CDSI(context and dependency syntactic information).This model can use BiLSTM(bidirectional long short-term memory) network to extract the context semantics of the text.Moreover,a dependency-aware embedding representation method is introduced to mine the contribution weights of different dependent paths to the sentiment classification task based on the syntactic structure.Then the GCN is used to model the context and dependent syntactic information at the same time,so as to strengthen the emotional features in the text representation.Based on SWB,NLPCC2014 and SMP2020-EWEC datasets,experimental results show that CDSI can effectively integrate the semantic and structural information in sentences,which achieves good results in both the Chinese short text sentiment binary classification and multi-classification tasks.

Chatter, a type of self-excited vibration, deteriorates surface quality and reduces tool life and machining efficiency. Chatter detection serves as an effective approach to achieve stable cutting. To address the low accuracy in chatter detection caused by the limitations of both one-dimensional temporal and two-dimensional image modal information, this study proposes a multi-modal denoised data-driven milling chatter detection method using an optimized hybrid neural network architecture. A data denoising model combining Complementary Ensemble Empirical Mode Decomposition (CEEMD) and Singular Value Decomposition (SVD) is established. The Ivy algorithm is employed to optimize the hyperparameters of CEEMD-SVD. Multi-modal data features of different machining states are then obtained using time–frequency domain methods and Markov transition field methods. Sensitivity analysis of time–frequency domain features is conducted using Pearson correlation coefficient analysis. A hybrid neural network model (DBMA) for chatter detection is constructed by integrating dual-scale parallel convolutional neural networks, bidirectional gated recurrent units, and multi-head attention mechanisms. The Ivy algorithm is utilized to optimize the hyperparameters of DBMA. The t-SNE algorithm is employed to visualize features extracted from different network layers of the chatter detection model. Results demonstrate that effective denoising of machining signals and the use of multi-modal data can significantly improve the accuracy of state detection. Compared with other methods, the proposed model exhibits superior stability and robustness. [ABSTRACT FROM AUTHOR]

Based on density functional theory calculations, this study analyzed the gas-sensing performance of Ti3C2Tx (T=O, F, OH) monolayers modified with precious metal atoms (Ag and Au) for HCHO and C6H6 gas molecules. Firstly, stable structures of Ag- and Au-single-atom doped Ti3C2Tx (T=O, F, OH) surfaces were constructed and then HCHO and C6H6 gas molecules were set to approach the modified structures at different initial positions. The most stable adsorption structure was selected for further analysis of the adsorption energy, adsorption distance, charge transfer, charge deformation density, total density of states, and partial density of states. The results show that the Ag and Au modifications improved the adsorption performance of Ti3C2O2 for HCHO and C6H6. In comparison, the effect of the Au modification was better than that of Ag. For Ti3C2F2, the Ag and Au doping modifications did not significantly change the adsorption effects for HCHO and C6H6. However, the Ag and Au doping modifications decreased the adsorption of Ti3C2(OH)2 for HCHO, while there was no significant change in the gas adsorption for C6H6. The above results serve as a theoretical foundation for the design of new sensors for HCHO and C6H6. [ABSTRACT FROM AUTHOR]

Elastic yarns are the key component of high-performance compression garments. However, it remains a challenge to fabricate anti-fatigue yarns with high mechanical force and long elongation for generating compression garments with prolonged wear. In this paper, we report the development of anti-fatigue double-wrapped yarns with excellent mechanical properties by wrapping high-denier Spandex with nylon filaments in opposite twists. In particular, high-denier (560 D) Spandex as the core was untwisted, which can maximally reduce the interaction between the core and wrapping filaments, enabling high elongation of double-wrapped yarns. In addition, we chose 70 D nylon filaments with a tensile force of 3.87 ± 0.09 N as the wrapping materials to provide sufficient force for double-wrapped yarns. Notably, opposite twists were induced for the inner and outer wrapping filaments to achieve a balanced stable yarn structure. By systematically optimizing manufacturing parameters, including inner wrapping density, outer wrapping density, take-up ratio, and drafting ratio, we obtained double-wrapped yarn with excellent tensile stress (32.59 ± 0.82 MPa) and tensile strain (357.28% ± 9.10%). Notably, the stress decay rate of optimized yarns was only 12.0% ± 2.2%. In addition, the optimized yarn was used as the weft-lining yarn for generating weft-lined fabrics. The elastic recovery rate of the obtained fabric was decreased by only 2.6% after five cyclic stretches, much lower than the control fabric. Our design of anti-fatigue double-wrapped yarns could be widely used for fabricating high-performance compression garments. [ABSTRACT FROM AUTHOR]