Explore the vast range of titles available.

This study addresses key challenges in optimizing agricultural industry structures and facilitating intelligent transformation through the application of deep learning algorithms and advanced optimization techniques. An intelligent system for agricultural industry optimization is developed, with convolutional neural networks, recurrent neural networks, Long Short-Term Memory networks, and generative adversarial networks introduced for tasks such as image recognition, time series forecasting, and synthetic data generation. Subsequently, a hybrid optimization method is designed, combining the Genetic Algorithms with particle swarm optimization to improve the model’s global search capability and local convergence speed. The performance of these techniques is rigorously evaluated through extensive experimentation. The results demonstrate that the proposed method outperforms conventional algorithms in regression tasks, particularly in terms of computational efficiency, data processing speed, and model training stability, while also exhibiting high scalability. In crop yield prediction, the proposed method achieves superior performance, as evidenced by reductions in both absolute error and mean squared error, along with attaining the highest R 2 value (0.93). Additionally, in pest and disease detection, the proposed method exceeds other models in accuracy (97.5%), precision (96.8%), recall (97.2%), and F1 score (0.97), underscoring its superior performance in detecting agricultural pests and diseases. The method also significantly surpasses traditional algorithms in crop disease identification accuracy, climate change prediction precision, and the quality of synthetic data generation. This study offers novel technical solutions and decision-making tools for advancing intelligent agriculture.

This study aims to conduct a comprehensive and in-depth analysis of the marketing performance of e-commerce live broadcast platforms based on big data management technology and deep learning. Firstly, by synthesizing large-scale datasets and surveys, the study constructs a series of performance evaluation indicators including user participation, content quality, commodity sales effect, user satisfaction, and platform promotion effect. Secondly, the weight of each indicator is finally determined through the indicator screening of the expert scoring method. Finally, the experimental design and implementation steps such as data collection, experimental environment setting, parameter setting, and performance evaluation are introduced in detail. Through the training and evaluation of the Back Propagation Neural Network (BPNN), each secondary indicator’s adjusted weight value and global ranking are obtained, providing a scientific basis for subsequent management opinions. The research results emphasize the importance of comments and ratings, purchase conversion rate, advertising click-through rate, and other indicators in improving user satisfaction, promoting sales, and effective promotion. Overall, this study provides a clear direction for an e-commerce live broadcast platform to optimize user experience, improve sales performance, and strengthen brand promotion.

This work aims to enhance the accuracy and efficiency of corporate strategic decision-making, particularly in rapidly changing and highly competitive market environments. Traditional strategic decision-making methods rely on managers’ experiential judgment and exhibit limitations when handling complex data and high-frequency market fluctuations. To address this issue, this work proposes a hybrid optimization model combining transformer models and reinforcement learning algorithms, designed to optimize corporate strategic decision-making processes and improve competitiveness. First, relevant studies on strategic decision-making and corporate competitiveness are reviewed, clarifying the potential and advantages of artificial intelligence (AI) in decision support. Second, the hybrid model is developed and trained through steps including data collection and preprocessing, algorithm selection and model construction, as well as model training and validation. Finally, real-world data are applied to evaluate model performance across indicators such as training time, convergence speed, and prediction effectiveness. The results demonstrate that the hybrid model successfully converges within 150 iterations and exhibits substantial advantages over traditional algorithms, particularly in prediction accuracy for market share (92%), profit growth rate (91%), and customer satisfaction (89%). Implementing the model leads to notable improvements in corporate market position, brand influence, and technological innovation capabilities. The work shows that the hybrid model enhances the scientific rigor and accuracy of decision-making. Meanwhile, it strengthens corporate competitiveness and market responsiveness, highlighting the substantial potential of AI technologies in strategic management. This work provides enterprises with an efficient and reliable decision-support tool, facilitating the maintenance of competitive advantages in complex and dynamic market environments.

Tungsten ditelluride (WTe 2 ) is a semi-metallic layered transition metal dichalcogenide with a stable distorted 1T phase. The reduced symmetry of this system leads to in-plane anisotropy in various materials properties. We have systemically studied the in-plane anisotropy of Raman modes in few-layer and bulk WTe 2 by angle-dependent and polarized Raman spectroscopy (ADPRS). Ten Raman modes are clearly resolved. Their intensities show periodic variation with sample rotating. We identify the symmetries of the detected modes by quantitatively analyzing the ADPRS results based on the symmetry selection rules. Material absorption effect on the phonon modes with high vibration frequencies is investigated by considering complex Raman tensor elements. We also provide a rapid and nondestructive method to identify the crystallographic orientation of WTe 2 . The crystallographic orientation is further confirmed by the quantitative atomic-resolution force image. Finally, we find that the atomic vibrational tendency and complexity of detected modes are also reflected in the shrinkage degree defined based on ADPRS, which is confirmed by corresponding density functional calculation. Our work provides a deep understanding of the interaction between WTe 2 and light, which will benefit in future studies about the anisotropic physical properties of WTe 2 and other in-plane anisotropic materials.

The recent discovery of a Weyl semimetal in TaAs offers the first Weyl fermion observed in nature and dramatically broadens the classification of topological phases. However, in TaAs it has proven challenging to study the rich transport phenomena arising from emergent Weyl fermions. The series Mo x W 1− x Te 2 are inversion-breaking, layered, tunable semimetals already under study as a promising platform for new electronics and recently proposed to host Type II, or strongly Lorentz-violating, Weyl fermions. Here we report the discovery of a Weyl semimetal in Mo x W 1− x Te 2 at x =25%. We use pump-probe angle-resolved photoemission spectroscopy (pump-probe ARPES) to directly observe a topological Fermi arc above the Fermi level, demonstrating a Weyl semimetal. The excellent agreement with calculation suggests that Mo x W 1− x Te 2 is a Type II Weyl semimetal. We also find that certain Weyl points are at the Fermi level, making Mo x W 1− x Te 2 a promising platform for transport and optics experiments on Weyl semimetals. A Type II Weyl fermion semimetal has been predicted in Mo x W 1− x Te 2 , but it awaits experimental evidence. Here, Belopolski et al . observe a topological Fermi arc in Mo x W 1− x Te 2 , showing it originates from a Type II Weyl fermion and offering a new platform to study novel transport phenomena in Weyl semimetals.

Background The habenula (Hb) is a vital hub for the monoaminergic pathway and plays a crucial role in depression pathophysiology. However, owing to its small size and heterogeneity between individuals, there is no consensus on imaging alterations in the Hb in depression. This study aimed to examine the differences in the Hb between healthy controls (HCs) and patients with first-episode depression (FED) who were not taking any antidepressants, and to assess the value of Hb voxel cluster radiomic features in discriminating patients with FED from HCs. Methods This cross-sectional study included 94 participants (47 HCs and 47 patients with FED) who underwent 3-T magnetic resonance imaging. Differences in the Hb volume and T1 values between the two groups were examined. Correlations among volume, T1 value, depression severity, and age were also examined. Furthermore, a clustering-based radiomics model to differentiate patients with FED from HCs was developed and validated. Results In HCs, the Hb T1 value was positively related to age, whereas that of patients with FED showed no significant correlation. The prediction performance was improved in the clustering-based radiomics model (area under the curve [AUC] = 0.844) compared with the traditional model (AUC = 0.708). Conclusions Our findings imply that the Hb and its internal heterogeneity are imaging markers for depression studies. Trial registration Not applicable.

Composite bipolar plates (BPs) hinder their application in proton exchange membrane fuel cells (PEMFC) because of their poor conductivity and mechanical properties. Nanofillers can effectively solve this problem but often have a limited effect due to their easy agglomeration. In this work, a continuous mesh carboxylated multi-walled carbon nanotube (MWCNT) coating on the surface of graphite was synthesized by chemical vapor deposition (CVD) and carboxylation modification, and the composite BPs were prepared by molding using prepared reticulated carboxylated MWCNTs, expanded graphite, and resin. By optimizing the carboxylation treatment time and the content of the nano-filler, the composite BPs had the best performance at a 15 min carboxylation treatment time and 2.4% filler content. The planar conductivity reached up to 243.52 S/cm, while the flexural strength increased to 61.9 MPa. The thermal conductivity and hydrophobicity were improved compared with the conventional graphite/resin composite BPs, and good corrosion resistance has been demonstrated under the PEMFC operating environment. This work provides a novel nanofiller modification paradigm for PBs.

The cost effectiveness of using exogenous phosphorus to remediate heavy metals in soil, which would alter the structure of the soil microbial community, had been widely acknowledged. In the present study, phospholipid fatty acid (PLFA) technology was taken as the breakthrough point, and rhizosphere soil microorganisms in different growth stages (jointing stage and maturity stage) of Minghui 86 (MH) and Yangdao No.6 (YD) rice were taken as the research objects. As revealed by the results, the rhizosphere soil microorganisms of MH and YD had distinct sensitivities to exogenous phosphorus and had a certain inhibitory effect on MH and YD enhancement. The sensitivity of rice root soil microorganisms to exogenous phosphorus also varied in different growth stages of rice. Bacteria were the dominant microorganism in the soil microbial community of rice roots, and the gain of exogenous phosphorus had a certain impact on the structure of the two soil microbial communities. Through analysis of the microbial community characteristics of MH rice and YD soil after adding exogenous phosphorus, further understanding was attained with respect to the effect of exogenous phosphorus on the microbial community characteristics of rice rhizosphere soil and the impact thereof on ecological functions.

The recently discovered two-dimensional (2D) semimetal 1 T´-MoTe 2 exhibits colossal magnetoresistance and superconductivity, driving a strong research interest in the material’s quantum phenomena. Unlike the typical hexagonal structure found in many 2D materials, the 1 T´-MoTe 2 lattice has strong in-plane anisotropy. A full understanding of the anisotropy is necessary for the fabrication of future devices which may exploit these quantum and topological properties, yet a detailed study of the material’s anisotropy is currently lacking. While angle resolved Raman spectroscopy has been used to study anisotropic 2D materials, such as black phosphorus, there has been no in-depth study of the Raman dependence of 1 T´-MoTe 2 on different layer numbers and excitation energies. Here, our angle resolved Raman spectroscopy shows intricate Raman anisotropy dependences of 1 T´-MoTe 2 on polarization, flake thickness (from single layer to bulk), photon, and phonon energies. Using a Paczek approximation, the anisotropic Raman response can be captured in a classical framework. Quantum mechanically, first-principle calculations and group theory reveal that the anisotropic electron-photon and electron-phonon interactions are nontrivial in the observed responses. This study is a crucial step to enable potential applications of 1 T´-MoTe 2 in novel electronic and optoelectronic devices where the anisotropic properties might be utilized for increased functionality and performance.

The rapid advancement of generative artificial intelligence has led to its widespread application in social interactions and internet behavior research. Sentiment analysis of social media data has emerged as a critical tool for understanding consumer behavior and market trends. This study focuses on the new energy vehicle market, employing generative artificial intelligence and the bidirectional encoder representations from transformers model to extract key topics and perform sentiment analysis on social media data. Based on these key topics, a consumer purchase intention influence model is developed. Experimental and survey findings indicate that, in the new energy vehicle market, 57.8% of sentiment related to vehicle performance is positive, 68.3% of sentiment concerning energy consumption is neutral, and comfort receives the highest proportion of negative feedback (17.2%), suggesting that consumer expectations regarding comfort remain largely unmet.