基于图嵌入与拓扑结构信息的蛋白质复合物识别算法

蛋白质复合物是细胞结构和生化机制的研究基础,如何准确识别蛋白质复合物成为近年来的研究热点。针对传统算法根据结构信息对蛋白质复合物进行搜索存在敏感度和F-measure低的问题,以及现有监督学习算法根据人为构造特征进行蛋白质复合物识别存在特征构造不能较好地反映图的真实信息等不足,提出了graph2vec-SVM识别算法。将蛋白质复合物看作稠密子图并考虑子图模块度大小,利用graph2vec将图信息转换为向量,并进一步采用SVM分类器对蛋白质复合物进行识别,提高了蛋白质复合物识别的敏感度和F-measure。该算法分别与目前流行的4种非监督学习算法(ClusterOne、CMC、HC-PIN和COACH)和3种监督学习算法(SCI-BN、SCI-SVM和RM)进行比较,在精准度、敏感度和F-measure 3项指标上都显示出了良好的性能。     

基于情境学习的射孔仿真培训系统应用研究

由于传统的仿真培训中只能通过鼠标的点击与键盘进行交互,存在着现场感缺乏以及用户体验不足等缺点,针对油田射孔岗位仿真培训中的交互问题,提出了应用情境学习理论结合体感交互技术的仿真培训系统。通过将Unity与体感交互技术结合,学习者可以运用手势与姿势来实现与仿真培训系统的交互操作。结合应用这一技术可以使得学习者能够在更逼真的虚拟学习环境中尽情的体会和学习,满足学习者的体验和参与需求,可以有效促进学习者从具体的感知经验上升到抽象的知识概念,为教学培训的顺利开展创设有利的条件。     

双流网络信息交互机制下的微表情识别

针对深度学习的方法用于微表情识别时微表情识别的实验数据库非常稀缺,导致神经网络在学习的过程中知识获取有限而难以提高精度及泛化能力的问题,提出基于双流网络信息交互的微表情识别方法.通过改进的深度互学习策略引导图像序列不同模态之间的交互训练,提高网络的识别率.方法基于RGB图像序列建立主体网络,基于光流建立辅助网络;在训练阶段,通过设计互学习损失中的有监督学习损失和拟态损失,优化训练过程,使得每一种模态都能学习正确地预测训练样本的真实标识,同时能与其他模态的预测相匹配;在测试阶段,由于互学习机制增强了RGB分支的判别能力,因此可对光流分支进行剪裁,在保证精度的前提下提高识别速度.在CASME,CASMEⅡ和SMIC数据库上的实验结果表明,该方法有效地提高了识别精度,整体性能优于已有方法.     

The mass,fake news,and cognition security

The widespread fake news in social networks is posing threats to social stability, economic development, and political democracy, etc. Numerous studies have explored the effective detection approaches of online fake news, while few works study the intrinsic propagation and cognition mechanisms of fake news. Since the development of cognitive science paves a promising way for the prevention of fake news, we present a new research area called Cognition Security (CogSec), which studies the potential impacts of fake news on human cognition, ranging from misperception, untrusted knowledge acquisition, targeted opinion/attitude formation, to biased decision making, and investigates the effective ways for fake news debunking. CogSec is a multidisciplinary research field that leverages the knowledge from social science, psychology, cognition science, neuroscience, AI and computer science. We first propose related definitions to characterize CogSec and review the literature history. We further investigate the key research challenges and techniques of CogSec, including humancontent cognition mechanism, social influence and opinion diffusion, fake news detection, and malicious bot detection. Finally, we summarize the open issues and future research directions, such as the cognition mechanism of fake news, influence maximization of fact-checking information, early detection of fake news, fast refutation of fake news, and so on.     

Protein interaction networks: centrality,modularity, dynamics,and applications

In the post-genomic era, proteomics has achieved significant theoretical and practical advances with the development of high-throughput technologies. Especially the rapid accumulation of protein-protein interactions (PPIs) provides a foundation for constructing protein interaction networks (PINs), which can furnish a new perspective for understanding cellular organizations, processes, and functions at network level. In this paper, we present a comprehensive survey on three main characteristics of PINs: centrality, modularity, and dynamics. 1) Different centrality measures, which are used to calculate the importance of proteins, are summarized based on the structural characteristics of PINs or on the basis of its integrated biological information; 2) Different modularity definitions and various clustering algorithms for predicting protein complexes or identifying functional modules are introduced; 3) The dynamics of proteins, PPIs and sub-networks are discussed, respectively. Finally, the main applications of PINs in the complex diseases are reviewed, and the challenges and future research directions are also discussed.     

Self-excited vibration problems of maglev vehicle-bridge interaction system

The self-excited vibration problems of maglev vehicle-bridge interaction system were addressed, which greatly degrades the stability of the levitation control, decreases the ride comfort, and restricts the cost of the whole system. Firstly, the coupled model containing the quintessential parts was built, and the mechanism of self-excited vibration was explained in terms of energy transmission from levitation system to bridge. Then, the influences of the parameters of the widely used integral-type proportion and derivation（PD） controller and the delay of signals on the stability of the interaction system were analyzed. The result shows that the integral-type PD control is a nonoptimal approach to solve the self-excited vibration completely. Furthermore, the differential-type PD controller can guarantee the passivity of levitation system at full band. However, the differentiation of levitation gap should be filtered by a low-pass filter due to noise of gap differentiation. The analysis indicates that a well tuned low-pass filter can still keep the coupled system stable.     

移动平台三维花卉植物触摸反馈可视化模拟

移动平台上高交互感的三维花卉植物可视化已成为植物研究、园艺设计等领域的重要需求,但现有植物运动形变方法还不能根据触摸力度对整株花卉植物或单一叶片的受力进行不同的形变过程模拟。为此,提出一种改进的三维花卉植物触摸反馈可视化模拟方法。根据植物整株交互需求或单一叶片受力情况,研究不同方式的触摸反馈模拟方法。在模拟触摸反馈时,整株受力应用动力学原理,抽象为杆件模型并计算形变结果。单一叶片受力时,根据触摸屏获取数据,并结合叶脉骨架旋转模型算法,模拟不同力度触摸造成的叶片形变,过程中无需手动输入参数。仿真结果表明,该方法应用于移动平台后,帧速率稳定,具有较高的真实感。     

基于软件的环境量化模型

在一些特殊领域中需要建立一定的实验环境对软件性能进行测试,因此实验环境与实际环境之间的近似程度对软件的性能起到关键作用。为建立环境之间的近似度量,在进程代数理论基础上,根据软件与环境的交互程度,利用拓扑度量和论域理论中的偏序关系,建立实验环境之间近似程度的量化模型。根据软件与环境之间的部分交互,建立实验环境之间近似程度的度量模型。通过实例对度量模型进行说明,并证明度量模型的代数性质。     

救援机器人远程监控平台的设计与实现

以救援机器人为研究背景,详细介绍了远程监控平台的设计方案和系统架构,包括硬件结构、底层软件和上层应用软件的设计和实现。该救援机器人通过便携式操控箱实现远程监控,具有人机交互友好、操作灵活、携带方便等特点。实践结果表明,该平台能很好地实现机器人远程操控和传感器信息的传输,有助于机器人在灾难环境中更好地开展探测和搜救工作。     

PR状态方程二元相互作用参数的拟合及对柴油中氢气溶解度的预测

通过Aspen Hysys模拟计算了温度(323~623)K和压力(4~10)MPa条件下,氢气在0~#柴油、直馏柴油、催化柴油和焦化柴油中的溶解度。计算结果对比实验数据,得到氢气在4种柴油中溶解度的平均误差分别为17.49%、11.48%、20.09%和14.00%。因二元相互作用参数与柴油性质以及温度之间存在着一定的关联,为了得到更加准确的溶解度数据,提出了计算PR状态方程中二元相互作用参数的关联式,并用Matlab进行关联式参数的拟合和氢气溶解度的计算,得到溶解度数据的平均误差分别为8.12%、7.51%、5.73%和6.10%,有效地提高了数据的准确性。因此,提出的二元相互作用参数的计算关联式可以为更加准确地预测氢气在柴油中的溶解度提供有效的方法。