A maximum self-esteem degree based feedback mechanism for group consensus reaching with the distributed linguistic trust propagation in social network

This paper focuses on consensus reaching process (CRP) under social network in which the trust relationship expressed by linguistic information. A new feedback mechanism in social network group decision making (SN-GDM) is proposed, which mainly consists of the following two aspects: (1) The propagation of distributed linguistic trust is investigated to study trust relation among experts; (2) A maximum self-esteem degree based feedback mechanism is developed to produce personalized advice for reaching higher group consensus. To do so, a novel linguistic trust propagation method is proposed to obtain the complete trust relationship among group. The self-esteem degree is used to define the extent that an individual makes concessions. Then, a maximum self-esteem degree based optimal feedback mechanism is built to produce personalized advice to help inconsistent experts make change of their opinion. Its novelty lies in the establishment of an optimization model with the nonlinear group self-esteem degree function as the objective function while group consensus threshold as the restrictions. Therefore, the inconsistent experts will reach a group consensus with the minimum loss of self-esteem degree, and then, it achieves the optimal balance between individual self-esteem and group consensus. Finally, a ranking process is applied to derive the appropriate consensus solution.     

基于深度学习的文本分类技术研究进展

随着深度学习技术的快速发展,许多研究者尝试利用深度学习来解决文本分类问题,特别是在卷积神经网络和循环神经网络方面,出现了许多新颖且有效的分类方法。对基于深度神经网络的文本分类问题进行分析,介绍卷积神经网络、循环神经网络、注意力机制等方法在文本分类中的应用和发展,分析多种典型分类方法的特点和性能,从准确率和运行时间方面对基础网络结构进行比较,表明深度神经网络较传统机器学习方法在用于文本分类时更具优势,其中卷积神经网络具有优秀的分类性能和泛化能力。在此基础上,指出当前深度文本分类模型存在的不足,并对未来的研究方向进行展望。     

基于自动编码器的深度伪造图像检测方法

基于深度学习的图像伪造方法生成的图像肉眼难辨,一旦该技术被滥用于制作虚假图像和视频,可能会对国家政治、经济、文化造成严重的负面影响,也可能会对社会生活和个人隐私构成威胁。针对上述问题,提出了一种基于自动编码器的深度伪造Deepfake图像检测方法。首先,借助高斯滤波对图像进行预处理,提取高频信息作为模型输入;然后,利用自动编码器对图像进行特征提取,并在编码器中添加注意力机制模块以获取更好的分类效果;最后,通过消融实验证明,采用所提的预处理方法和添加注意力机制模块有助于伪造图像检测。实验结果表明,与ResNet50、Xception以及InceptionV3相比,所提方法在数据集样本量较小且包含的场景丰富时,可以有效检测多种生成方法所伪造的图像,其平均准确率可达97.10%,明显优于对比方法,且其泛化性能也明显优于对比方法。     

基于动态注意力和多角度匹配的答案选择模型

针对当前主流神经网络在处理答案选择任务时无法同时满足句子的充分表示以及句子间信息充分交互的问题,提出了基于动态注意力和多角度匹配（DAMPM）的答案选择模型。首先,调用预训练语言模型的嵌入（ELMo）获得包含简单语义信息的词向量;接着,在注意力层采用过滤机制有效地去除句子中的噪声,从而更好地得到问句和答案句的句子表征;其次,在匹配层同时引入多种匹配策略来完成句子向量之间的信息交互;然后,利用双向长短期记忆（BiLSTM）网络对匹配层输出的句子向量进行拼接;最后,通过分类器来计算拼接向量的相似度大小,从而得到问句和答案句之间的语义关联。在文本检索会议问答（TRECQA）数据集上的实验结果表明,与基于比较聚合框架的基线模型中的动态滑动注意力网络（DCAN）方法相比,DAMPM在平均准确率均值（MAP）和平均倒数排名（MRR）两个性能指标上均提高了1.6个百分点。在维基百科问答（WikiQA）数据集上的实验结果表明,DAMPM相较DCAN在两个性能指标上分别提高了0.7个百分点和0.8个百分点。所提DAMPM相较于基线模型中的方法整体上有更好的性能表现。     

无人机群目标搜索的主动感知方法

为提升蚁群搜索算法在规模大的栅格环境中对未知目标的搜索效率,提出基于蚁群算法的主动感知搜索框架。该框架通过应用历史环境信息来选择无人机的运动方式,并由无人机运动方式和感知域信息得到新的环境信息,从而实现无人机群的智能自动化搜索功能。新方法计算出一种具有探索偏好的未搜索概率,可使无人机搜索时偏向未搜索程度高的栅格,以此来提高算法的搜索能力。同时,以未搜索概率和信息素作为运动方式决策的依据来建立一种新的运动方式选择机制。该机制不仅考虑了目标可能出现的区域,又可兼顾未知区域,从而可实现无目标先验信息条件下的搜索过程。仿真结果表明,此算法在规模大的栅格环境中,与现有算法相比具有更高的搜索效率,并且得到的目标分布信息将更加全面。     

一种基于并联机构的航天器姿态模拟装置的设计开发

航天器发射升空前进行地面测试和试验是航天器研制过程中的重要环节。文中针对一种基于并联机构的姿态模拟装置的设计开发,从位置分析、速度分析和虚拟样机的建造和仿真分析等方面对3UPS-PU并联机构进行研究,完成姿态模拟装置的设计,为航天器装配、试验和测试设备的设计提供一种新的思路。     

基于MLP和SPSO的机器人行为选择与运动控制方法

针对传统行为选择机制(ASM)不能很好地做出控制决策的问题,提出一种基于多层感知(MLP)前馈神经网络的ASM,并将其应用到移动机器人目标跟踪中。首先,根据具体应用场景预定义多个机器人行为。然后,根据机器人配备的图像和红外传感器获得的目标位置和障碍物信息,通过MLP神经网络从预定义行为中选择出所需执行的行为。另外,为了构造最优的MLP模型,采用一种简化粒子群算法(SPSO)来优化网络权值参数。机器人目标跟踪仿真的结果表明,提出的ASM能够准确选择出合适的行为,实现了控制机器人跟踪目标移动且能够避开各种障碍物。     

Intergranular oxidation of silicon in 20Cr-25Ni niobium-stabilized stainless steel at 1140–1230 K

The kinetics of intergranular oxidation of silicon in a 20Cr-25Ni Nb-stabilized stainless steel are reported, at temperatures in the range 1140–1230 K, in CO₂ at 40 bar pressure. The depth of attack increased parabolically with respect to time, with an activation energy of 335±30 kJ/mol. The mechanism of growth is discussed in terms of classical internal-oxidation theories, and an alternative explanation based on an available-space theory is developed. The internal oxidation rates in a number of different alloys are compared with diffusivities of metals in the base alloy. It is proposed that intergranular oxidation in the 20–25 Nb steel is controlled by the rate of outward diffusion of iron or chromium in the alloy.     

当前网络政治参与中存在的问题与对策

针对我国当前网络政治参与中存在着非法参与行为多、政务信息不公开致使公众政治参与缺乏信息基础、政府对公众网络政治参与的行为与观点缺乏回应等问题,本文提出了采取完善政治参与和网络政治参与的法治化机制,建立健全网络参政相关法规,保障公民网络参政议政权益,规范和打击非法政治参与行为;修改政府信息公开的法律法规,加大政府信息公开力度与规范网络监督机制;建立政府对公民网络政治参与的回应制度,以解决公民网络政治参与的相关问题,推动法治文明.     

Oxidation behavior and mechanism of aluminum oxynitride (AlON) at elevated temperatures

The oxidation behavior and mechanism of aluminum oxynitride (AlON) powder exposed to air at elevated temperatures between 800°C and 1300°C was investigated by X-ray diffractometry (XRD), scanning electron microscope (SEM), electron spin resonance (ESR), nuclear magnetic resonance (NMR), and simultaneous thermogravimetry, differential thermal analysis, and mass spectrometry techniques (TG-DTA-MS). The weight of AlON gradually increases to a maximum value at 1150°C and then decreases with further heating. Meanwhile, AlON powder undergoes chemical changes, as evidenced by lattice expansion, and turns eventually into alumina. ESR spectra reveal the occurrence of lone pair electrons in the oxidized products and the intensity of corresponding resonance signal increases before disappearing with the increase in temperature. Combined with the results of NMR and TG-DTA-MS, the measured data suggest that Al-N in [AlO₃N] tetrahedron and [AlO₅N] octahedron are gradually oxidized into Al-O-N group with lone pair electrons, which causes continuous weight gain and lattice expansion. Further oxidation at higher temperatures results in alumina and N₂.