Search

[Purpose/Significance] The construction of the "the Belt and Road Initiative" as a major national regional development strategy with an emphasis on technological innovation and talent as the core in the new era, has brought new opportunities for the development of entrepreneurship and innovation education and talent training in universities. [Method/Process] Based on the current domestic and foreign research status of the cultivation of innovation and entrepreneurship capabilities of college students, this paper puts forward 34 kinds of abilities that college students are supposed to have in innovation and entrepreneurship under the background of the "the Belt and Road Initiative". A questionnaire survey on its importance, current ability, the expectations of the status quo and development was held and an in-depth discussion was followed. Through correlation analysis, the necessity of these abilities in three research areas is demonstrated. [Results/Conclusions] Through correlation analysis, the necessity of these abilities in the three aspects of research is demonstrated, so as to expand the effective path of cultivating the innovation and entrepreneurship ability of college students under the background of "the Belt and Road Initiative", and to realize the high-quality and conjunctive development of mass entrepreneurship and innovation education.

Summary: Existing research on recommender systems primarily focuses on improving a single objective, such as prediction accuracy, often ignoring other crucial aspects of recommendation performance such as temporal factor, user satisfaction, and acceptance. To solve this problem, we proposed an explicable recommendation model using many‐objective optimization and a time‐assisted knowledge graph, which utilizes user interaction times within the graph to prioritize recommending recently frequently visited items and is further optimized using a many‐objective optimization algorithm. In this model, the temporal weight of user actions at different times is first determined through a time decay function. Additionally, if a user clicks on the same item again, the current action's temporal weight is set to one. This strategy prioritizes recent user actions and frequently visited items, reflecting current interests and preferences better. Next, the created knowledge graph is used to create a list of potential recommendations. Embedding methods obtain the vectors for entities and relations in the path. These vectors, combined with the temporal weight of actions, quantify the explainability of user recommendations. Optimizing the rest of the recommendation performance with many objective algorithms while focusing on the user's recent frequent visits to the item. Finally, the outcomes of the research study indicate that, compared to other explicable recommended methods, our model, considering temporal factor, improved average accuracy by 11%, diversity by 1%, and explainability by 21% in the Useraction1 data set. Results in other data sets also indicate that the proposed model maintains accuracy, diversity, and novelty while enhancing explainability. [ABSTRACT FROM AUTHOR]

Hyperspectral Image (HSI) classification based on deep learning has been an attractive area in recent years. However, as a kind of data-driven algorithm, the deep learning method usually requires numerous computational resources and high-quality labelled datasets, while the expenditures of high-performance computing and data annotation are expensive. In this paper, to reduce the dependence on massive calculation and labelled samples, we propose a deep Double-Channel dense network (DDCD) for Hyperspectral Image Classification. Specifically, we design a 3D Double-Channel dense layer to capture the local and global features of the input. And we propose a Linear Attention Mechanism that is approximate to dot-product attention with much less memory and computational costs. The number of parameters and the consumptions of calculation are observably less than contrapositive deep learning methods, which means DDCD owns simpler architecture and higher efficiency. A series of quantitative experiences on 6 widely used hyperspectral datasets show that the proposed DDCD obtains state-of-the-art performance, even though when the absence of labelled samples is severe.

In this article, the ABAQUS finite element software is used to simulate the bond behavior of the steel bar in salt–frost-damaged recycled coarse aggregate concrete, and the influence of the steel bar diameter and the concrete cover thickness on the bond strength is investigated. The result shows that the calculated bond–slip curve is in good agreement with the experimental bond–slip curve; the mean value of the ratio of the calculation results of ultimate bond strength to the experiment results of ultimate bond strength is 1.035, the standard deviation is 0.0165, and the coefficient of variation is 0.0159, which proves that the calculation results of the ultimate bond strength are in good agreement with the experimental results; with the increase of steel bar diameter and the concrete cover thickness, the ultimate bonding strength of RAC and steel increases; the calculation formulas for the ultimate bond strength of specimens with different steel bar diameters (concrete cover thickness) after different salt–frost cycles are obtained.