信标可控性定义及问题

死锁是资源分配系统中极不希望出现的现象,目前死锁控制的一个重要的方法是信标控制法,信标控制法的基础是信标可控性的定义.对于普通Petri网,已有一个完善的信标可控性定义,而对于一般Petri网,这方面的工作还需改进和完善.近年来,学者们针对一般Petri 网及其子类提出了不少信标可控性定义,但这些定义并不完善,仍有大量的问题亟待解决.首先回顾了文献中的各个信标可控性定义,提出了两个新的信标可控性定义,然后从可控性定义的宽松程度、应用范围以及等价性等方面分析比较了现有的信标可控性定义优缺点.最后给出了今后的研究方向.     

Minimal strict siphons extraction for S3PMR

Abstract

A siphon is an important structure object for deadlock control. Insufficiently marked siphons lead to deadlocks. Deadlock occurs due to inappropriate resource sharing. Hence most of the research focuses on the minimal siphon extraction problem covering a set of places representing resources, which, for general Petri Nets is known to be an NP‐Complete problem. Control places and arcs are often added to the original net to prevent a siphon from becoming insufficiently marked. The number of siphons grows rapidly with the size of the net leading to very complicated control nets. Efficient enumeration of problematic siphons is an urgent research topic. Earlier, we proposed fast algorithms to find all such siphons for both S³PR and S²CPR (System of Synchronized Choice Processes with Resources). However, it was assumed that siphons occur between adjacent processes. This paper removes this assumption and develops an algorithm for S³PMR which is more powerful than S³PR by allowing a state to use more than one resource and than S²CPR by allowing more than one state to use the same resources. Comparisons with previously published work have been made.     

Monitoring Interfaces for Faults

We consider the problem of a module interacting with an external interface (environment) where the interaction is expected to satisfy some system specification Φ. While we have the full implementation details of the module, we are only given a partial external specification for the interface. The interface specification being partial (incomplete) means that the interface displays only a strict subset of the behaviors allowed by the interface specification.Based on the assumption that interface specifications are typically incomplete, we address the question of whether we can tighten the interface specification into a strategy, consistent with the given partial specification, that will guarantee that all possible interactions resulting from possible behaviors of the module will satisfy the system specification Φ. We refer to such a tighter specification as Φ-guaranteeing specification. Rather than verifying whether the interface, which is often an off-the-shelf component, satisfies the tighter specification, the paper proposes a construction of a run-time monitor which continuously checks the existence of a Φ-guaranteeing interface.We view the module and the external interface as players in a 2-player game. The interface has a winning strategy if it can guarantee that no matter what the module does, the overall specification Φ is met. The problem of incomplete specifications is resolved by allowing the interface to follow any strategy consistent with the interface specification. Our approach essentially combines traditional run-time monitoring and static analysis. This allows going beyond the focus of traditional run-time monitoring tools – error detection in the execution trace, towards the focus of the static analysis – bug detection in the programs.     

基于通信的MAS内多Agent自动协商

给出了一个通用的基于联合意图的多Agent系统内部Agent协商模型，详细分析了Agent间的异步通信机制以及基于语言行为学的Agent自动协商语义，并在该协商语义的基础上给出了MAS内部基于联合意图的Agent自动协商通信协议，最后利用通信顺序进程验证了该协议的安全性和活性．     

无冲突Petri网的结构活性判定研究

结构活性作为Petri网的重要结构性质,在Petri网活性判定领域具有较高的研究价值。从Petri网有向回路对结构活性的影响入手,分析与判定无冲突Petri网的结构活性,讨论库所元素及其后置变迁之间是否存在有向回路对Petri网结构活性的影响,研究该类Petri网结构活性判定方法的相关条件与结论,得到无冲突Petri网是满足结构活性的充分必要条件。分析结果表明,该判定方法可在多项式时间内判定无冲突Petri网的结构活性。     

T-组合Petri网的活性和公平性分析

同步合成是研究复杂Ｐｅｔｒｉ网系统性质的有效途径．文中通过引入可引发变迁序偶的概念,研究了Ｔ－组合（同步合成）Ｐｅｔｒｉ网对子网的活性和公平性继承关系,给出了一组Ｔ－组合Ｐｅｔｒｉ网活或公平的充要条件和充分条件．这些结果对网组合同步设计具有重要的指导意义     

基于深度学习和特征融合的人脸活体检测算法

针对目前基于深度学习的活体检测算法大都基于大型卷积神经网络的问题,提出一种基于轻量级网络MobileNetV2和特征融合的活体检测算法。首先,以改进的MobileNetV2为基础网络分别从RGB、HSV、LBP图中提取特征;然后,将得到的特征图堆叠在一起以进行特征层的融合;最后,从融合后的特征图中继续提取特征,并利用Softmax层作出真假人脸的判断。仿真结果显示,所提算法在NUAA数据集上的等错误率（EER）为0.02%,在Siw数据集上的ACER（Average Classification Error Rate）为0.75%,而且测试单张图像仅用时6 ms。实验结果表明：融合不同的信息可以获得更低的错误率,改进的轻量化网络保证了算法的高效性并满足实时性需求。     

增强型灰度图像空间实现虹膜活体检测

目的 虹膜作为一种具有高稳定性与区分性的生物特征,使得虹膜识别在应用场景中十分普及,但很多虹膜识别系统在抵御各类演示攻击时无法保证十足的可靠性,导致虹膜识别在高级安全场景中的应用受限,使得虹膜活体检测成为生物识别技术中亟需解决的问题之一。现有的区分真实与假体虹膜最先进的算法主要依靠在原始灰度空间中提取的虹膜纹理深度特征,但这类特征差异不明显,只能辨别单源假体虹膜。为此,提出一种基于增强型灰度图像空间的虹膜活体检测方法。方法 利用残差网络（ResNet）将原始虹膜图像映射到可分离的灰度图像空间,使真假虹膜特征具有明显的判别性;用预训练LightCNN （light convolational neural networks）-4网络提取新空间中的虹膜纹理特征;设计三元组损失函数与softmax损失函数训练模型实现二分类任务。结果 在两个单源假虹膜数据库上采用闭集检测方式分别取得100%和99.75%的准确率;在多源假虹膜数据库上采用开集检测方式分别取得98.94%和99.06%的准确率。结论 本文方法通过空间映射的方式增强真假虹膜纹理之间清晰度的差异,设计三元组损失函数与softmax损失函数训练模型,既增加正负样本集之间的距离差,又提升模型收敛速度。实验结果表明,基于图像空间的分析与变换可有效解决真实虹膜与各类假体虹膜在原始灰度空间中不易区分的问题,并且使网络能够准确检测未知类型的假体虹膜样本,实现虹膜活体检测的最新性能,进一步提升了虹膜活体检测方法的泛化性。