The fraudulent website image is a vital information carrier for telecom fraud.The efficient and precise recognition of fraudulent website images is critical to combating and dealing with fraudulent websites.Current re...The fraudulent website image is a vital information carrier for telecom fraud.The efficient and precise recognition of fraudulent website images is critical to combating and dealing with fraudulent websites.Current research on image recognition of fraudulent websites is mainly carried out at the level of image feature extraction and similarity study,which have such disadvantages as difficulty in obtaining image data,insufficient image analysis,and single identification types.This study develops a model based on the entropy method for image leader decision and Inception-v3 transfer learning to address these disadvantages.The data processing part of the model uses a breadth search crawler to capture the image data.Then,the information in the images is evaluated with the entropy method,image weights are assigned,and the image leader is selected.In model training and prediction,the transfer learning of the Inception-v3 model is introduced into image recognition of fraudulent websites.Using selected image leaders to train the model,multiple types of fraudulent websites are identified with high accuracy.The experiment proves that this model has a superior accuracy in recognizing images on fraudulent websites compared to other current models.展开更多
Objectives: To analyze the documental quality of 389 websites in Portuguese about physical activity, healthy lifestyles and sedentary lifestyles found on the Brazilian version of the general search engine Google. Meth...Objectives: To analyze the documental quality of 389 websites in Portuguese about physical activity, healthy lifestyles and sedentary lifestyles found on the Brazilian version of the general search engine Google. Methods: The documental quality of the 389 websites was estimated based upon the following parameters: 1) a combination of quality criteria from the Health Information Locator (LIS—OPS/BIREME) and those from Chile’s Pontifical Catholic University, organized into 17 variables;2) uniformity of reference criteria (Vancouver);3) association between the presence of authorship and a higher number of the quality criteria being fulfilled. We also studied the ranking of the results presented by Google in addition to attributes connected to the websites’ target audience, the types of content, their sponsors and country of origin. Results: Of the 389 websites studied, 111 links were not active (28.53% CI 95% [24.05 - 33.02]) and none of the websites in the sample met all of the 17 quality variables. Authored websites displayed remarkable differences in quality when compared to those which did not identify their authors. Conclusions: Faced with the issue of the proliferation of websites with questionable quality content, and the fact that the ranking of results interferes directly in the internal evaluation of content relevance, we propose that public-health research institutions cooperate with web-searching developers to improve the website-positioning formula, in which the “identified authorship” criterion should play a major role in the ranking system.展开更多
为实现高超声速飞行器姿态自抗扰控制的参数整定,提出一种模糊Q学习算法。首先,采用强化学习中的Q学习算法来实现姿态自抗扰控制参数的离线闭环快速自适应整定;然后,根据模糊控制的思路,将控制参数划分为不同区域,通过设定奖励,不断更新...为实现高超声速飞行器姿态自抗扰控制的参数整定,提出一种模糊Q学习算法。首先,采用强化学习中的Q学习算法来实现姿态自抗扰控制参数的离线闭环快速自适应整定;然后,根据模糊控制的思路,将控制参数划分为不同区域,通过设定奖励,不断更新Q表;最后,将训练好的Q表用于飞行器的控制。仿真结果表明,相对于传统的线性自抗扰控制(linear active disturbance rejection control,LADRC)和滑模控制,基于Q学习的LADRC省去了人工调试参数的繁琐过程,且仍具有良好的跟踪效果。蒙特卡罗仿真测试结果验证了基于Q学习的LADRC的鲁棒性。展开更多
传统的拓扑优化算法均基于灵敏度分析的方式求解,如渐进结构优化法(Evolutionary Structural Optimization, ESO)和变密度法(Solid Isotropic Material with Penalization, SIMP)等,灵敏度分析依赖于严谨的数学模型,结果可信度高,但面...传统的拓扑优化算法均基于灵敏度分析的方式求解,如渐进结构优化法(Evolutionary Structural Optimization, ESO)和变密度法(Solid Isotropic Material with Penalization, SIMP)等,灵敏度分析依赖于严谨的数学模型,结果可信度高,但面对不同的结构和约束条件都需要反复重新推导单元灵敏度,对使用人员的数学能力有较高要求,而且也导致了收敛速度慢、迭代步数多的问题。针对现有优化方法中存在的缺陷,结合强化学习Q学习理论和元胞自动机原理,提出一种新的拓扑优化方法:Q学习-元胞法(Q-learning-Cellular Automaton, QCA),尝试为工程构件的优化设计提供一种新思路。这种方法以有限元单元作为元胞,将所有元胞的智能行为集成为一个Q-learning智能体。训练过程中,各个元胞首先完成对自身环境的感知,然后调用智能体进行决策并通过环境交互得到反馈,智能体也借此得到大量数据来学习更新,整个过程不涉及数学模型推导,通过智能体和元胞的不断探索即可完成优化。在此基础上,探讨元胞的选择及其邻域和状态的描述方式,针对元胞的动作空间及收益函数进行比选,进而编制相关拓扑优化软件。优化算例表明,QCA方法优化后的拓扑构型与传统优化方法的构型基本一致,迭代步数较SIMP法降低了64%,且柔顺度更低。Q学习-元胞法在结构拓扑优化中具备良好的可行性,计算效率高且具有迁移优化能力,在结构拓扑优化领域极具潜力。展开更多
基金supported by the National Social Science Fund of China(23BGL272)。
文摘The fraudulent website image is a vital information carrier for telecom fraud.The efficient and precise recognition of fraudulent website images is critical to combating and dealing with fraudulent websites.Current research on image recognition of fraudulent websites is mainly carried out at the level of image feature extraction and similarity study,which have such disadvantages as difficulty in obtaining image data,insufficient image analysis,and single identification types.This study develops a model based on the entropy method for image leader decision and Inception-v3 transfer learning to address these disadvantages.The data processing part of the model uses a breadth search crawler to capture the image data.Then,the information in the images is evaluated with the entropy method,image weights are assigned,and the image leader is selected.In model training and prediction,the transfer learning of the Inception-v3 model is introduced into image recognition of fraudulent websites.Using selected image leaders to train the model,multiple types of fraudulent websites are identified with high accuracy.The experiment proves that this model has a superior accuracy in recognizing images on fraudulent websites compared to other current models.
文摘Objectives: To analyze the documental quality of 389 websites in Portuguese about physical activity, healthy lifestyles and sedentary lifestyles found on the Brazilian version of the general search engine Google. Methods: The documental quality of the 389 websites was estimated based upon the following parameters: 1) a combination of quality criteria from the Health Information Locator (LIS—OPS/BIREME) and those from Chile’s Pontifical Catholic University, organized into 17 variables;2) uniformity of reference criteria (Vancouver);3) association between the presence of authorship and a higher number of the quality criteria being fulfilled. We also studied the ranking of the results presented by Google in addition to attributes connected to the websites’ target audience, the types of content, their sponsors and country of origin. Results: Of the 389 websites studied, 111 links were not active (28.53% CI 95% [24.05 - 33.02]) and none of the websites in the sample met all of the 17 quality variables. Authored websites displayed remarkable differences in quality when compared to those which did not identify their authors. Conclusions: Faced with the issue of the proliferation of websites with questionable quality content, and the fact that the ranking of results interferes directly in the internal evaluation of content relevance, we propose that public-health research institutions cooperate with web-searching developers to improve the website-positioning formula, in which the “identified authorship” criterion should play a major role in the ranking system.
文摘为实现高超声速飞行器姿态自抗扰控制的参数整定,提出一种模糊Q学习算法。首先,采用强化学习中的Q学习算法来实现姿态自抗扰控制参数的离线闭环快速自适应整定;然后,根据模糊控制的思路,将控制参数划分为不同区域,通过设定奖励,不断更新Q表;最后,将训练好的Q表用于飞行器的控制。仿真结果表明,相对于传统的线性自抗扰控制(linear active disturbance rejection control,LADRC)和滑模控制,基于Q学习的LADRC省去了人工调试参数的繁琐过程,且仍具有良好的跟踪效果。蒙特卡罗仿真测试结果验证了基于Q学习的LADRC的鲁棒性。
