基于自适应投影的指纹模板生成算法

针对现有指纹模板生成算法存在的准确性较低、安全性较差的问题,提出一种基于自适应投影的指纹模板生成算法。该算法将有效细节点对之间的距离垂直投影到自适应圆上,并对投影后的向量进行量化得到比特串。此外,为增强数据的安全性及隐私性,采用异或和随机索引置乱变换对比特串进行处理,最终生成指纹模板。在数据库FVC2002 DB1和DB2中的实验结果表明,该算法相较于对比算法,具有较高的准确性和安全性。     

Multi-instance cancellable biometrics schemes based on generative adversarial network

The main role of cancellable biometric schemes is to protect the privacy of the enrolled users. The protected biometric data are generated by applying a parametrized transformation function to the original biometric data. Although cancellable biometric schemes achieve high security levels, they may degrade the recognition accuracy. One of the mostwidely used approaches to enhance the recognition accuracy in biometric systems is to combine several instances of the same biometric modality. In this paper, two multi-instance cancellable biometric schemes based on iris traits are presented. The iris biometric trait is used in both schemes because of the reliability and stability of iris traits compared to the other biometric traits. A generative adversarial network (GAN) is used as a transformation function for the biometric features. The first scheme is based on a pre-transformation feature-level fusion, where the binary features of multiple instances are concatenated and inputted to the transformation phase. On the other hand, the second scheme is based on a post-transformation feature-level fusion, where each instance is separately inputted to the transformation phase. Experiments conducted on the CASIA Iris-V3-Internal database confirm the high recognition accuracy of the two proposed schemes. Moreover, the security of the proposed schemes is analyzed, and their robustness against two well-known types of attacks is proven.

     

QFT template generation for time-delay plants based on zero-inclusion test

Plant template generation is the key step in applying quantitative feedback theory (QFT) to design robust control for uncertain systems. In this paper we propose a technique for generating plant templates for a class of linear systems with an uncertain time delay and affine parameter perturbations in coefficients. The main contribution lies in presenting a necessary and sufficient condition for the zero inclusion of the value set f(T,Q)={f(τ,q): τT[τ⁻,τ⁺], qQ∏_k=0^m−1[q_k⁻,q_k⁺]}, where f(τ,q)=g(q)+h(q)e^−jτω*, g(q) and h(q) are both complex-valued affine functions of the m-dimensional real vector q, and ω^* is a fixed frequency. Based on this condition, an efficient algorithm which involves, in the worst case, evaluation of m algebraic inequalities and solution of m2^m−1 one-variable quadratic equations, is developed for testing the zero inclusion of the value set f(T,Q). This zero-inclusion test algorithm allows one to utilize a pivoting procedure to generate the outer boundary of a plant template with a prescribed accuracy or resolution. The proposed template generation technique has a linear computational complexity in resolution and is, therefore, more efficient than the parameter gridding and interval methods. A numerical example illustrating the proposed technique and its computational superiority over the interval method is included.     

CBRC: a novel approach for cancelable biometric template generation using random permutation and Chinese Remainder Theorem

Multimedia Tools and Applications - Cancelable Biometrics is a challenging research field in which a cancelable template corresponding to a biometric is generated without affecting the performance....     

A novel rule-centric object oriented approach for document generation

Complex business models in large-scale enterprises deal with voluminous knowledge based on which most decisive official and technical documents are generated. Nowadays, template processors are available for generating such documents. However, the existing template processors are either labor intensive or complicated to suit well-established business model and knowledge repositories in a heterogeneous environment. Hence, a novel generalized adaptable and flexible template processor that utilizes the existing resources without modifying the business model is proposed. The tacit business intelligence defined as rules, knowledge repositories and document structure are the nodal agents of this approach. Further, an XML based Object Query Definition Markup Language for rule definition is newly suggested. The rules are reorganized into hierarchical DAG structured rules using a transformation algorithm and traversed using hybrid traversal. The required output document is represented through a template. Object wrappers act as the communicating agent between diversified datasets and the templates. The proposed architecture is modeled and implemented using set theory. It is experimented in a web-based distributed environment using JAVA and tested using a real world dataset of a large-scale engineering enterprise. The results demonstrate its adaptability and extensibility to any multi-organizational structure.     

A novel parallel implementation of partial distortion search algorithm based on template search

This paper proposes a new early terminating partial distortion search algorithm based on template search in fast motion estimation. Our algorithm accomplishes a parallel implementation technique by considering both the idea of partial distortion search and the advantage of the template search. With this technique, the proposed algorithm achieves a better performance by faster updating the current minimum distortion. The proposed parallel implementation that reduces a large amount of distortion computations between pixels outperforms the standard partial distortion search method by faster rejecting the unlikely candidate blocks. Our algorithm is embedded into the diamond search algorithm, star diamond search algorithm and three-step search algorithm respectively. According to the experiment results, it is proved that about 30% reduction of computational complexity has been obtained compared with the standard partial distortion search. Moreover, there is no degradation of the peak signal-to-noise ratio(PSNR) for motion estimation compared with the embedded block-based template search motion estimation algorithm.     

A novel virtual sample generation method based on Gaussian distribution

Traditional machine learning algorithms are not with satisfying generalization ability on noisy, imbalanced, and small sample training set. In this work, a novel virtual sample generation (VSG) method based on Gaussian distribution is proposed. Firstly, the method determines the mean and the standard error of Gaussian distribution. Then, virtual samples can be generated by such Gaussian distribution. Finally, a new training set is constructed by adding the virtual samples to the original training set. This work has shown that training on the new training set is equivalent to a form of regularization regarding small sample problems, or cost-sensitive learning regarding imbalanced sample problems. Experiments show that given a suitable number of virtual sample replicates, the generalization ability of the classifiers on the new training sets can be better than that on the original training sets.     

An interactive approach to template generation in quantitative feedback theory methodology

The calculation of templates associated with plant uncertainty at some frequencies is one of the first steps in the design of robust controllers using the quantitative feedback theory (QFT) methodology. If the QFT designer does not calculate the templates correctly, the design will be unnecessarily conservative, or even erroneous. This paper describes the main features of Template Interactive Generator (TIG), a new, free software tool that calculates the templates of plants with special parameter dependences, such as interval plants and plants with affine parametric uncertainty. The paper also includes two examples that illustrate the ease of use and the high level of interactivity of TIG. Copyright © 2008 John Wiley and Sons Asia Pte Ltd and Chinese Automatic Control Society     

基于数据分类的领域自适应新算法

一般的机器学习都假设训练数据与测试数据分布相同,而领域自适应算法则是在不同数据分布条件下进行知识传递和学习,在数据挖掘、数据校正、数据预测等领域有着广泛的应用。支持向量机SVM的主要思想是针对二分类问题,在高维空间寻找一个最优分类超平面,以保证最小的分类错误率。CCMEB理论由Tsang I提出的,是一种改进了核向量机CVM的最小包含球算法,在大样本数据集处理上有着较快的速度。而CCMEB理论同样适用于二分类的SVM数据集。将SVM理论、CCMEB理论与概率分布理论相结合,提出了一种全新的基于数据分类的领域自适应算法CCMEB SVMDA,该算法通过计算各自分类数据组的包含球球心,能够有效地对不同领域数据进行整体校正和相似度识别,具有较好的便捷性和自适应性。在UCI数据、文本分类等数据上对该算法进行了验证,取得了较好的效果。     

CCRNet: a novel data-driven approach to improve cross-domain Iris recognition

In spite of the prominence and robustness of iris recognition systems, iris images acquisition using heterogeneous cameras/sensors, is the prime concern in deploying them for wide-scale applications. The textural qualities of iris samples (images) captured through distinct sensors substantially differ due to the differences in illumination and the underlying hardware that yields intra-class variation within the iris dataset. This paper examines three miscellaneous configurations of convolution and residual blocks to improve cross-domain iris recognition. Further, the finest architecture amongst three is identified by the Friedman test, where the statistical differences in proposed architectures are identified based on the outcomes of Nemeny and Bonferroni-Dunn tests. The quantitative performances of these architectures are perceived on several experiments simulated on two iris datasets; ND-CrossSensor-Iris-2013 and ND-iris-0405. The finest model is referred to as “Collaborative Convolutional Residual Network (CCRNet)” and is further examined on several experiments prepared in similar and cross-domains. Results depict that least two error rates reported by CCRNet are 1.06% and 1.21% that enhances the benchmark for the state of the arts. This is due to fast convergence and rapid weights updation achieved from convolution and residual connections, respectively. It helps in recognizing the micro-patterns existing within the iris region and results in better feature discrimination among large numbers of iris subjects.

     

基于深度学习的无人机识别算法研究

无人机的广泛运用,在给人们带来便利的同时,也引发了不良影响。比如,无人机飞入禁飞区引发安全问题,由于不正当的使用侵犯公民的隐私等,因此需要构建一个无人机警察系统,对无人机实施监控,遏制乱飞现象。采用传统的识别方法,灵活性不足,精度也不够高。为此提出一种基于深度学习的无人机识别算法,通过训练一个基于卷积神经网络(CNNs)的学习网络,得出一个高效的识别模型,实现无人机和非无人机间的分类。模型的测试结果表明,该方法具有较高的识别率。     

A novel multi-focus image fusion approach based on image decomposition

Multi-focus image fusion is an effective technique to integrate the relevant information from a set of images with the same scene, into a comprehensive image. The fused image would be more informative than any of the source images. In this paper, a novel fusion scheme based on image cartoon-texture decomposition is proposed. Multi-focus source images are decomposed into cartoon content and texture content by an improved iterative re-weighted decomposition algorithm. It can achieve rapid convergence and naturally approximates the morphological structure components. The proper fusion rules are constructed to fuse the cartoon content and the texture content, respectively. Finally, the fused cartoon and texture components are combined to obtain the all-in-focus image. This fusion processing can preserve morphological structure information from source images and performs few artifacts or additional noise. Our experimental results have clearly shown that the proposed algorithm outperforms many state-of-the-art methods, in terms of visual and quantitative evaluations.     

A novel approach for process mining based on event types

Despite the omnipresence of event logs in transactional information systems (cf. WFM, ERP, CRM, SCM, and B2B systems), historic information is rarely used to analyze the underlying processes. Process mining aims at improving this by providing techniques and tools for discovering process, control, data, organizational, and social structures from event logs, i.e., the basic idea of process mining is to diagnose business processes by mining event logs for knowledge. Given its potential and challenges it is no surprise that recently process mining has become a vivid research area. In this paper, a novel approach for process mining based on two event types, i.e., START and COMPLETE, is proposed. Information about the start and completion of tasks can be used to explicitly detect parallelism. The algorithm presented in this paper overcomes some of the limitations of existing algorithms such as the α-algorithm (e.g., short-loops) and therefore enhances the applicability of process mining.

A novel clock generation algorithm for system-on-chip based on least common multiple

Due to increase in the number of Intellectual Property (IP) cores, clock generation in current day System-on-Chips (SoCs) is facing a crisis. The conventional method of using a dedicated Phase Locked Loop (PLL) to generate the clock for each IP core is becoming inefficient in terms of power and cost. We propose an algorithm based on Least Common Multiple (LCM) to minimize the number of PLLs required to generate the clocks for the IP cores in a SoC. This is done by finding an Optimum Operating Frequency (OOF) for each IP core within 10% below the maximum operating frequency of the core. The OOF is chosen such that the LCM of the OOF of all the IP cores is minimized. Simulated annealing is used to find the LCM. This LCM is the crucial high frequency from which maximum number of clocks can be derived by clock dividers.     

A novel intrusion detection system based on feature generation with visualization strategy

In this paper, a four-angle-star based visualized feature generation approach, FASVFG, is proposed to evaluate the distance between samples in a 5-class classification problem. Based on the four angle star image, numerical features are generated for network visit data from KDDcup99, and an efficient intrusion detection system with less features is proposed. The FASVFG-based classifier achieves a high generalization accuracy of 94.3555% in validation experiment, and the average Mathews correlation coefficient reaches 0.8858.     

基于场景及规则获取模板的知识获取方法

产生式规则作为知识库系统进行推理的常用的、可读性好的知识表示形式,在构建知识库系统时有极大的优越性.提出一种基于场景及规则获取模板的知识获取方法,并以某高分子复合材料的加工专家为知识获取对象.该方法通过分析、记录领域专家进行设计的过程、解决问题的过程和动作,将领域问题按层次细化为一系列子问题,并在子问题场景下结合场景模型及知识获取模板来获取规则性知识.采用该方法可以辅助领域专家在明晰领域知识结构的基础上,逐步挖掘领域中细粒度的规则性知识.     

A novel approach to feature selection based on analysis of classregions

This paper presents a novel approach to feature selection based on analysis of class regions which are generated by a fuzzy classifier. A measure for feature evaluation is proposed and is defined as the exception ratio. The exception ratio represents the degree of overlaps in the class regions, in other words, the degree of having exceptions inside of fuzzy rules generated by the fuzzy classifier. It is shown that for a given set of features, a subset of features that has the lowest sum of the exception ratios has the tendency to contain the most relevant features, compared to the other subsets with the same number of features. An algorithm is then proposed that performs elimination of irrelevant features. Given a set of remaining features, the algorithm eliminates the next feature, the elimination of which minimizes the sum of the exception ratios. Next, a terminating criterion is given. Based on this criterion, the proposed algorithm terminates when a significant increase in the sum of the exception ratios occurs due to the next elimination. Experiments show that the proposed algorithm performs well in eliminating irrelevant features while constraining the increase in recognition error rates for unknown data of the classifiers in use.     

A novel approach for ANFIS modelling based on full factorial design

Adaptive neural network based fuzzy inference system (ANFIS) is an intelligent neuro-fuzzy technique used for modelling and control of ill-defined and uncertain systems. ANFIS is based on the input–output data pairs of the system under consideration. The size of the input–output data set is very crucial when the data available is very less and the generation of data is a costly affair. Under such circumstances, optimization in the number of data used for learning is of prime concern. In this paper, we have proposed an ANFIS based system modelling where the number of data pairs employed for training is minimized by application of an engineering statistical technique called full factorial design. Our proposed method is experimentally validated by applying it to the benchmark Box and Jenkins gas furnace data and a data set collected from a thermal power plant of the North Eastern Electric Power Corporation (NEEPCO) Limited. By employing our proposed method the number of data required for learning in the ANFIS network could be significantly reduced and thereby computation time as well as computation complexity is remarkably reduced. The results obtained by applying our proposed method are compared with those obtained by using conventional ANFIS network. It was found that our model compares favourably well with conventional ANFIS model.