Selection of optimized features for fusion of palm print and finger knuckle‐based person authentication

The impact of digital technology in biometrics is much more efficient at interpreting data than humans, which results in completely replacement of manual identification procedures in forensic science. Because the single modality‐based biometric frameworks limit performance in terms of accuracy and anti‐spoofing capabilities due to the presence of low quality data, therefore, information fusion of more than one biometric characteristic in pursuit of high recognition results can be beneficial. In this article, we present a multimodal biometric system based on information fusion of palm print and finger knuckle traits, which are least associated to any criminal investigation as evidence yet. The proposed multimodal biometric system might be useful to identify the suspects in case of physical beating or kidnapping and establish supportive scientific evidences, when no fingerprint or face information is present in photographs. The first step in our work is data preprocessing, in which region of interest of palm and finger knuckle images have been extracted. To minimize nonuniform illumination effects, we first normalize the detected circular palm or finger knuckle and then apply line ordinal pattern (LOP)‐based encoding scheme for texture enrichment. The nondecimated quaternion wavelet provides denser feature representation at multiple scales and orientations when extracted over proposed LOP encoding and increases the discrimination power of line and ridge features. To best of our knowledge, this first attempt is a combination of backtracking search algorithm and 2D²LDA has been employed to select the dominant palm and knuckle features for classification. The classifiers output for two modalities are combined at unsupervised rank level fusion rule through Borda count method, which shows an increase in performance in terms of recognition and verification, that is, 100% (correct recognition rate), 0.26% (equal error rate), 3.52 (discriminative index), and 1,262 m (speed).     

入侵检测主流技术及发展动态

入侵检测技术是网络安全的主要技术和网络研究的热点,入侵检测方法包括基于数据挖掘、粗糙集、模式识别、支持向量机和人工免疫等主要技术,详细分析了各种检测方法在入侵检测应用中的优缺点。通过回顾研究人员近期的研究成果,提出了该技术的主要发展方向,为进一步研究提供参考。     

非部分嵌套信息结构的LQG动态队决策问题的可解性（II）*

本文讨论非嵌套信息结构的递阶队决策问题和控制均享信息结构的LQG分散控制问题,文中首先证明这两类问题的信息结构都是“部分控制嵌入”的,进而给出最优策略(或控制)存在的充要条件和当此条件成立时最优策略(或控制)的表达式。     

基于扩展染色Petri网的工作流过程模型

尽管已有广泛领域应用,但工作流系统在处理业务流程不确定的和动态的参数规格表时存在局限性。为此,本文提出基于扩展染色petri网的CPWF-net以及定义变迁行为和原子过程作为CPWF-net工作流模式结构的支持。这些工作流模式是从微观上进行处理,并可应用于动态不稳定的与时间和数据相关的环境中。本文通过CPWF-net执行程序检测工作流错误或异常执行状态,评估动态业务流程的整体执行时间,证实所提方法的有效性。     

选择性集成算法分类与比较

选择性集成是当前机器学习领域的研究热点之一。由于选择性集成属于NP"难"问题,人们多利用启发式方法将选择性集成转化为其他问题来求得近似最优解,因为各种算法的出发点和描述角度各不相同,现有的大量选择性集成算法显得繁杂而没有规律。为便于研究人员迅速了解和应用本领域的最新进展,本文根据选择过程中核心策略的特征将选择性集成算法分为四类,即迭代优化法、排名法、分簇法、模式挖掘法;然后利用UCI数据库的20个常用数据集,从预测性能、选择时间、结果集成分类器大小三个方面对这些典型算法进行了实验比较;最后总结了各类方法的优缺点,并展望了选择性集成的未来研究重点。     

战略性新兴产业创新空间格局及影响因素研究——以湖南省为例

应用ArcGIS软件,选取2010年、2016年两个时间节点,用空间核密度、空间自相关、地理探测器等方法,分析了湖南省战略性新兴产业技术创新的空间分布与集聚特征,结果表明:湖南省战略性新兴产业创新活动整体呈现"东北多,西南少"的分布态势,空间集聚分布特征明显,长株潭城市群为空间热点与核心区域;专利数量空间核密度分布存在明显的"区域差异",具体表现为大面积的块状分布和小面积的零星核分布并存;湖南省战略性新兴产业创新空间分布主要受科学研究和技术服务业单位数、人均GDP、固定资产投资、农业机械总动力、消费品零售总额、卫生技术人员数等因素的影响。     

中国熔模精密铸造展望

中国熔模精密铸造近10年来得到较大发展：2001年总产量达到27．4万t，总产约47．8亿元，占世界总产值的8％。需要做的工作：提高产品档次、增加合金种类、扩大企业规模和加强管理水平。     

基于时间序列模式表示的异常检测算法*

提出了一种基于时间序列的模式表示提取时间序列异常值的异常检测算法(PREOV).时间序列的模式表示本身就具有压缩数据、保持时间序列基本形态的功能,并且具有一定的除噪能力.在时间序列模式表示的基础上提取异常值,可以大大提高算法的效率和准确性,达到事半功倍的效果.在本算法中,还使用了一定的剪枝策略,使得算法的时间复杂度进一步降低.该算法计算简单、实现方便、无须训练,可以支持时间序列的动态增长.     

Developing a talent training model related to chemical process safety based on interdisciplinary education in China

While chemical industrial development in China is growing rapidly, the corresponding safety training resources remain inadequate, which may often lead to increased risk of chemical accidents. These accidents are often associated with the negligence of safety management, poor safety hazard awareness, and lack of safety practice. In order to alleviate these prominent risk factors in chemical industries in China, our study develops a talent training model related to chemical process safety. First, we propose an approach for establishing the “talent training model” related to chemical process safety, consisting of three steps: analyzing the current status and existing problems of talent training related to chemical process safety, determining the theoretical basis and training objectives for developing interdisciplinary talents, and designing a new talent training model. Second, we establish a talent training model using the proposed method, which includes a comprehensive curriculum system, a diversified teaching pattern, and a quintuple evaluation method. Furtherly, we determine the expected outcomes of the talent training model. The research results provide an innovative chemical process safety training method that is applicable nationwide, also it works as a reference for other rapidly developing countries in the chemical process industry to improve safety within the chemical industry.     

Mold-filling characteristics of AZ91 magnesium alloy in the low-pressure expendable pattern casting process

The magnesium (Mg) alloy low-pressure expendable pattern casting (EPC) process is a newly developed casting technique combining the advantages of both EPC and low-pressure casting. In this article, metal filling and the effect of the flow quantity of inert gas on the filling rate in the low-pressure EPC process are investigated. The results showed that the molten Mg alloy filled the mold cavity with a convex front laminar flow and the metal-filling rate increased significantly with increasing flow quantity when flow quantity was below a critical value. However, once the flow quantity exceeded a critical value, the filling rate increased slightly. The influence of the flow quantity of inert gas on melt-filling rate reveals that the mold fill is controlled by flow quantity for a lower filling rate, and, subsequently, controlled by the evaporation of polystyrene and the evaporation products for higher metal velocity. Meanwhile, the experimental results showed that the melt-filling rate significantly affected the flow profile, and the filling procedure for the Mg alloy in the low-pressure EPC process. A slower melt-filling rate could lead to misrun defects, whereas a higher filling rate results in folds, blisters, and porosity. The optimized filling rate with Mg alloy casting is 140 to 170 mm/s in low-pressure EPC.