Loading [MathJax]/extensions/TeX/noErrors.js
  • 基于用户偏好优化模型的推荐算法研究

    Subjects: Computer Science >> Integration Theory of Computer Science submitted time 2018-10-11 Cooperative journals: 《计算机应用研究》

    Abstract: Traditional personalized recommendation algorithm generally suffers from the problem of data sparseness, which affects the accuracy of recommendation. The Slope one algorithm is simple and efficient, but the algorithm is only based on the user - project score matrix to analyze the data, ignoring the type characteristics of the project and the user's preference for the type of the project. In order to solve the above problems, the LR-Slope one algorithm is proposed. Firstly, the user's preference matrix is constructed based on user project score matrix and project type information. Secondly, the weight of each type is calculated by linear regression model and optimized by random gradient descending algorithm. Finally, the score is predicted combined by Slope one, and the scoring matrix is filled, which improves the quality of recommendation. Experimental results show that the proposed algorithm improves the accuracy of recommendation and alleviates data sparseness effectively.

  • 紫茎泽兰叶片水浸液对蚕豆的化感效应

    Subjects: Biology >> Botany >> Applied botany submitted time 2018-09-07 Cooperative journals: 《广西植物》

    Abstract: Exotic invasive plants can alter ecosystem and displace the native plants by releasing allelochemicals to the surrounding environment by means of leaching, natural volatilization, root exudation and plant litter decomposition. In this study, Vicia faba seeds were treated with different concentrations of Eupatorium adenophorum leaf aqueous extracts. The effects of Eupatorium adenophorum leaf aqueous extracts on the micronucleus, chromosome aberration, apoptosis, chlorophyll and N content and photosynthetic physiological characteristics of Vicia faba were studied in this paper. The results were as follows: (1) the treatment of Eupatorium adenophorum leaf aqueous extracts significantly inhibited the root tip elongation and cell mitosis of Vicia faba, and induced chromosome aberration and cell micronucleus in the root tip cells of V. faba. With the increasing concentration of leaf water extracts, mitosis index significantly decreased and micronucleus rate of root tip cells significantly increased. In addition, the treatment of high concentration leaf aqueous extracts significantly affects apoptosis and necrosis of V . faba root tip cells. (2) the content of chlorophyll and N in leaves of V . faba decreased significantly, and the maximum net photosynthetic rate and biomass of V. faba seedlings were significantly decreased. In conclusion, Eupatorium adenophorum leaf aqueous extracts may cause the oxidative damage oftheroottipofViciafabaand theelongationoftheroot tip,andtheinhibitoryeffect ofleafwater extract shows a certain dose effect.At the same time, the damage and inhibition effect of Eupatorium adenophorum leaf aqueous extracts on the root tip of Vicia faba may affect the uptake of nitrogen, and thus have a significant negative effect on the photosynthetic physiological performance and biomass accumulation of broad bean seedlings. The results reveal the mechanism of Eupatorium adenophorum leaf aqueous extracts, and promote the understandingpotentialimpactofexoticinvasiveplantsonagriculturalproduction.

  • Opportunities and challenges in monitoring cultivated land red line in big data era

    Subjects: Statistics >> Social Statistics submitted time 2024-03-27 Cooperative journals: 《中国科学院院刊》

    Abstract: The demographic reality of a large population and limited land resources in China necessitates the implementation of the world’s most stringent cultivated land protection system. Effective, timely, and accurate monitoring of the status of cultivated land protection red line is essential to ensuring cultivated land protection and food security. The development of cutting-edge technologies such as remote sensing big data, cloud computing, and artificial intelligence has provided new opportunities for cultivated land control and monitoring. This article systematically elaborates on the current research status and challenges in the field of cultivated land protection redline control and monitoring, including the establishment of the monitoring object system, the availability of remote sensing data, the accuracy, and timeliness of monitoring results, and other related issues. It introduces advanced technologies and prospects for big data technology in cultivated land redline monitoring and proposes innovative technical solutions for cultivated land redline monitoring. The article also discusses the challenges faced in achieving this paradigm shift in research and provides corresponding recommendations on the connotations of cultivated land protection, delineation of basic land units, and the construction of monitoring networks for implementing national land spatial planning.