A social interaction system based on cloud computing for mobile video telephony

As the use of smartphones become popular,people heavily depend on smartphone applications to deal with their social activities.For this reason,traditional message texting between mobile applications does not fulfill the versatile requirements of social networking.Many mobile applications use multimodality to deliver multimedia messages including sticker,voice and photo message,video call,and snap movie to enhance the communicative capability.However,without face-to-face interaction,people may fail to detect the other side’s non-verbal social behavior such as fine-grain facial expressions,body movements,or hand gesture.During social interaction,non-verbal behavior conveys information about the involved individuals and help the speakers express their social emotion in an implicit way.It is so important for real-world face-to-face interaction but is often blocked on the mobile telephony.To cope with this problem,we propose an afective computing model to assist the representation of social emotion and then help the progress of social interaction on the mobile telephony.In this model,for the purpose of real-time afective analysis,we delegate the computing loading to the cloud side service and enhance the system’s scalability and availability.The result of this experiment approves the feasibility of our system design for the applications of social intelligent.Also,the system provides a research framework of the social intelligent system on the mobile telephony.     

Differentially private data fusion and deep learning Framework for Cyber–Physical–Social Systems: State-of-the-art and perspectives

The modern technological advancement influences the growth of the cyber–physical system and cyber–social system to a more advanced computing system cyber–physical–social system (CPSS). Therefore, CPSS leads the data science revolution by promoting tri-space information resource from a single space. The establishment of CPSSs increases the related privacy concerns. To provide privacy on CPSSs data, various privacy-preserving schemes have been introduced in the recent past. However, technological advancement in CPSSs requires the modifications of previous techniques to suit its dynamics. Meanwhile, differential privacy has emerged as an effective method to safeguard CPSSs data privacy. To completely comprehend the state-of-the-art developments and learn the field’s research directions, this article provides a comprehensive review of differentially private data fusion and deep learning in CPSSs. Additionally, we present a novel differentially private data fusion and deep learning Framework for Cyber–Physical–Social Systems , and various future research directions for CPSSs.     

圆锯片的有限元模态分析

针对金属冷热锯机锯片在锯切轧件过程中出现的振动问题 ,利用 MSC/ NASTRAN有限元软件 ,计算分析了各种参数对锯片模态的影响。从而为锯片的设计及其制造工艺的确定提供了可靠的参考依据 ,为最终解决生产中的实际问题发挥了重要作用     

Ni-Cr-Fe-Si-B合金涂层及铝青铜基体熔合区组织的研究

采用钨极氩弧焊方法在铝青铜基体上施焊了Ni—Cr-Fe-Si—B合金涂层，并运用金相显微镜、扫描电子显微镜及能谱分析了喷涂层、熔合区及热影响区的组织形貌和成分分布。结果表明，喷焊时，在涂层与基体界面两侧各组元均发生了明显的扩散，Cu、Ni组元间可相互取代，基体融合区组织的基本组成仍为α (α γ2)，但同时也形成了Cu2FeAl7、NiAl3等新相，且融合区组织细小，涂层与基体间为冶金态结合。     

规划专题影像地图的概念重构与视觉融合设计

针对空间规划领域中专题影像地图的制图应用,对影像地图的分类体系、规划专题影像的制图框架及其中影像的功能角色等进行概念重构,并提出以"矢量与栅格、基础与专题"等关系的处理为核心,以色彩配置、符号构形、构图整饰为主体,以视觉变量协调为关键的视觉融合设计策略;示例证明能够有效指导对规划方案概念的系统表达。     

基于经济的网格资源调度算法研究

网格使构建虚拟组织,在全世界范围内共享资源成为现实.但是,在网格环境下的资源管理和调度是一项相当复杂的工作,这主要是由于资源分布在世界各地,隶属于不同的组织,各个资源拥有者都有不同的使用和访问策略、开销模型、不断变化的负载和可用性.为了满足网格计算环境中资源调度的复杂需要,可以将现实世界中的经济原理和模型应用到网格环境下的任务调度中,并据此提出了几种经济资源调度算法.     

两级数据融合算法在木材干燥过程中的应用

本文提出了一种基于RBF神经网络和证据理论的两级数据融合方法。利用RBF神经网络实现特征层数据融合,建立基本信任分配函数,具有最佳一致逼近特性,同时解决了D-S证据理论确定基本信任分配函数困难的问题。基于D-S证据理论的传感器故障诊断方法的研究,可有效地判断工业现场传感器的工作状态。实验结果表明该方法可正确定位并准确分离出木材含水率检测系统中失效传感器。     

数据融合技术在废弃弹药分类中的应用

为了对废弃弹药进行分类并安全处理,提出了基于数据融合技术的超声波检测弹体内部成份方法.应用超声检测仪采集大量弹体内部成份样本数据,运用数据融合技术建立神经网络融合模型,对超声波的首波、幅值、频率、增益等特征进行融和处理,从而判断弹药的种类.实验结果表明,该方法准确可靠,具有较高的推广应用价值.     

一种基于模糊密度动态调节的融合目标识别方法

针对工程应用的需要,给出一种根据实时动态数据确定模糊密度调节系数的方法,并建立了基于模糊密度动态调节的融合目标识别算法.最后通过仿真实验给出了各种模糊积分用于目标融合识别时的识别结果,验证了所提出方法的有效性.     

基于脸部和步态特征融合的身份识别

提出了一种将脸部和步态特征相结合,应用于智能监控系统进行远距离视频流中身份识别的新方法.该方法首先分别采用隐马尔可夫模型(HMM)和Fisherfaces方法进行步态和脸部的识别,之后将这两个分类器得到的结果进行匹配级的融合.对从不同方向采集的31个人的视频序列进行分析实验,结果表明将脸部和步态特征相结合进行身份识别具有很好的鲁棒性,其识别性能也优于只采用脸部或步态单一特征的识别方法.