A path-based approach for web page retrieval

Use of links to enhance page ranking has been widely studied. The underlying assumption is that links convey recommendations. Although this technique has been used successfully in global web search, it produces poor results for website search, because the majority of the links in a website are used to organize information and convey no recommendations. By distinguishing these two kinds of links, respectively for recommendation and information organization, this paper describes a path-based method for web page ranking. We define the Hierarchical Navigation Path (HNP) as a new resource for improving web search. HNP is composed of multi-step navigation information in visitors’ website browsing. It provides indications of the content of the destination page. We first classify the links inside a website. Then, the links for web page organization are exploited to construct the HNPs for each page. Finally, the PathRank algorithm is described for web page retrieval. The experiments show that our approach results in significant improvements over existing solutions.     

Kriging-based convex subspace single linkage method with path-based clustering technique for approximation-based global optimization

This paper proposes an improved approach of the Kriging-based Convex Subspace Single Linkage Method (KCSSL method), which was reported as one of approximation-based global optimization methods. The KCSSL method consists of a convex subspace clustering procedure and a local optimization procedure. For the clustering procedure, previously, the cell-based clustering technique was employed. However, this approach will involve a huge number of convexity estimations in case of a higher dimensional problem. This will cause a very high computational cost, therefore, a path-based clustering procedure is newly developed. At first, a procedure for the convexity estimation with the Kriging method is introduced. Next, outline and detailed procedure of the proposed path-based clustering technique are explained. Also, the proposed method is applied to solving some approximate optimization problems. From the numerical results, validity and effectiveness of the proposed method are discussed.     

On-line sensitivity analysis of Markov chains

Discrete-event systems modeled as continuous-time Markov processes and characterized by some integer-valued parameter are considered. The problem addressed is that of estimating performance sensitivities with respect to this parameter by directly observing a single sample path of the system. The approach is based on transforming the nominal Markov chain into a reduced augmented chain, the stationary-state probabilities which can be easily combined to obtain stationary-state probability sensitivities with respect to the given parameter. Under certain conditions, the reduced augmented chain state transitions are observable with respect to the state transitions of the system itself, and no knowledge of the nominal Markov-chain state of the transition rates is required. Applications for some queueing systems are included. The approach incorporates estimation of unknown transition rates when needed and is extended to real-valued parameters     

Hand-based single sample biometrics recognition

Currently, single sample biometrics recognition (SSBR) has emerged as one of the major research contents. It may lead to bad recognition result. To solve this problem, we present a novel approach by fusing two kinds of hand-based biometrics, i.e., palmprint and middle finger. We obtain their discriminant features by combining statistical information and structural information of each modal which are extracted using locality preserving projection (LPP) based on wavelet transform (WT). In order to reduce the influence of affine transform, we utilize mean filtering to enhance the robustness of structural information to improve the discriminant ability of palmprint high-frequency sub-bands. The two types of features are then fused at score level for the final hand-based SSBR. The experiments on the hand image database that contains 1,000 samples from 100 individuals show that the proposed feature extraction and fusion methods lead to promising performance.     

A sensitivity formula for risk-sensitive cost and the actor–critic algorithm

We propose for risk sensitive control of finite Markov chains a counterpart of the popular ‘actor–critic’ algorithm for classical Markov decision processes. The algorithm is based on a ‘sensitivity formula’ for the risk sensitive cost and is shown to converge with probability one to the desired solution. The proof technique is an adaptation of the ordinary differential equations approach for the analysis of two time-scale stochastic approximation algorithms.     

基于压缩感知的单样本人脸识别

提出一种基于压缩感知的单样本人脸识别方法,通过局部邻域嵌入非线性降维和稀疏系数的方法产生冗余样本,则新样本包含了多种姿态和多种表情。将所有的新样本作为训练样本,运用改进后的稀疏表征分类算法进行人脸图像的识别。在单样本情况下,基于ORL人脸库和FERET人脸库的实验证明,该方法比原稀疏表征方法在识别率上分别提高了15.53%和7.67%。与RSRC、SSRC、DMMA、I-DMMA等方法相比,该方法同样具有良好的识别性能。     

Contract analysis: A performance measures and profit evaluation within two-echelon supply chains

Coordination is regarded as key in managing dependencies between distinctive members of a supply chain through the benefits of coordination mechanisms. Such coordination mechanisms are contracts, implemented to increase total supply chain profit, reduce costs and share risk among supply chain members. However, by contract implementation the retailer is constrained in his purchase by bearing the entire risk of holding the inventory (wholesale price contract) or by limited risk allocated to the supplier (buyback, revenue sharing and quantity flexibility contracts). By implementing an advanced purchase system the risk of inventory is fairly divided between the supplier and the retailer. In order to observe inventory implications on the supply chain bottom line, this article is directed towards the evaluation of performance measures and supply chain profit behavior under buyback, revenue sharing, quantity flexibility and advanced purchase discount contracts versus no coordination and wholesale price systems.     

Boosting quantum annealer performance via sample persistence

We propose a novel method for reducing the number of variables in quadratic unconstrained binary optimization problems, using a quantum annealer (or any sampler) to fix the value of a large portion of the variables to values that have a high probability of being optimal. The resulting problems are usually much easier for the quantum annealer to solve, due to their being smaller and consisting of disconnected components. This approach significantly increases the success rate and number of observations of the best known energy value in samples obtained from the quantum annealer, when compared with calling the quantum annealer without using it, even when using fewer annealing cycles. Use of the method results in a considerable improvement in success metrics even for problems with high-precision couplers and biases, which are more challenging for the quantum annealer to solve. The results are further enhanced by applying the method iteratively and combining it with classical pre-processing. We present results for both Chimera graph-structured problems and embedded problems from a real-world application.     

基于单样本的手掌静脉识别方法

针对单样本手掌静脉识别率较低的问题,研究了一种结合手掌静脉2DPCA特征和分区LBP特征的识别方法。利用图像重采样和奇异值扰动方法生成虚拟样本,利用2DPCA从生成的虚拟样本图像上提取静脉特征进行识别;利用LBP从原单样本手掌静脉提取分区特征进行识别;利用决策层融合方法将以上两种方法进行融合。在Poly U手掌静脉库上的实验表明,该方法能有效地解决手掌静脉的单样本识别问题。     

Mathematical formula identification and performance evaluation in PDF documents

An important initial step of mathematical formula recognition is to correctly identify the location of formulae within documents. Previous work in this area has traditionally focused on image-based documents; however, given the prevalence and popularity of the PDF format for dissemination, alternatives to image-based approaches are increasingly being explored. In this paper, we investigate the use of both machine learning techniques and heuristic rules to locate the boundaries of both isolated and embedded formulae within documents, based upon data extracted directly from PDF files. We propose four new features along with preprocessing and post-processing techniques for isolated formula identification. Furthermore, we compare, analyse and extensively tune nine state-of-the-art learning algorithms for a comprehensive evaluation of our proposed methods. The evaluation is carried out over a ground-truth dataset, which we have made publicly available, together with an application adaptable fine-grained evaluation metric. Our experimental results demonstrate that the overall accuracies of isolated and embedded formula identification are increased by 11.52 and 10.65 %, compared with our previously proposed formula identification approach.     

Illumination robust single sample face recognition based on ESRC

Multimedia Tools and Applications - The extended sparse representation classifier (ESRC) is one of the state-of-the-art solutions for single sample face recognition, but it performs...     

A single performance characteristic for the evaluation of seeker tracking algorithms

This paper presents a single numerical performance characteristic for the evaluation of seeker tracking algorithms. It concentrates on ship IR seeker tracking algorithms. Assessing the threat from guided missiles needs a sound evaluation of their performance. The main goal is to introduce a characteristic which is able to assess the threat for ships depending on various scenario parameters. It is shown that for these applications such a single characteristic is sufficient. In order to achieve this five popular tracking algorithms are used. Synthetic IR image sequences are generated to simulate a large set of attack approaches and assemble sufficient statistics on the behavior of the algorithms. The introduced characteristic can also be used for investigations on algorithms themselves, e.g. for sensitivity analyses and parameter optimization of a single algorithm, and for comparison of different algorithms.     

Portfolio performance sensitivity for various asset-pricing kernels

This paper examines the sensitivity of various measures of portfolio performance to the choice of the benchmark model using the asset-pricing kernel methodology. It derives the appropriate estimation frameworks that are suitable to perform evaluations of fixed-weight and dynamic portfolio strategies. Various asset-pricing kernel-based benchmark models are tested using a comprehensive sample of Canadian equity mutual funds over the period, 1989–1999. The performance statistics and inferences are sensitive to the choice of the kernel-based benchmark model and to the choice of liquidity as an alternative sorting variable for forming the passive benchmark portfolios. However, they are robust to the removal of ex post index mimickers and somewhat less robust to the presence of nonlinearities in the structure of the pricing kernel. Since conditioning has a more pronounced impact on absolute than on relative performance inferences, this supports the common industry practice of comparing the performance of funds against each other.     

Semi-Markov decision problems and performance sensitivity analysis

Recent research indicates that Markov decision processes (MDPs) can be viewed from a sensitivity point of view; and the perturbation analysis (PA), MDPs, and reinforcement learning (RL) are three closely related areas in optimization of discrete-event dynamic systems that can be modeled as Markov processes. The goal of this paper is two-fold. First, we develop the PA theory for semi-Markov processes (SMPs); and then we extend the aforementioned results about the relation among PA, MDP, and RL to SMPs. In particular, we show that performance sensitivity formulas and policy iteration algorithms of semi-Markov decision processes can be derived based on the performance potential and realization matrix. Both the long-run average and discounted-cost problems are considered. This approach provides a unified framework for both problems, and the long-run average problem corresponds to the discounted factor being zero. The results indicate that performance sensitivities and optimization depend only on first-order statistics. Single sample path-based implementations are discussed.     

Fast single sample face recognition based on sparse representation classification

Multimedia Tools and Applications - The extended sparse representation classification (ESRC) is one of the benchmark classification algorithms in the field of single sample face recognition (SSFR)....     

Facebook use and academic performance among college students: A mixed-methods study with a multi-ethnic sample

This paper uses a mixed-methods approach to examine the relation between online academic disclosure and academic performance. A multi-ethnic sample of college students (N = 261; male = 66; female = 195; M age ≈ 22 years) responded to open-ended questions about their Facebook use. Thematic analysis revealed that over 14% of the Facebook wall posts/status updates (N = 714) contained academic themes; positive states were more frequent than negative and neutral states and students with lower GPAs expressed negative states more often. A path analysis suggested that academic performance may determine college students’ Facebook use, rather than the reverse. Implications for student support services are discussed.     

Generalized sample hold functions-frequency domain analysis ofrobustness, sensitivity, and intersample difficulties

Over the past 5 years, there has been substantial interest in the use of generalized sample hold functions for control. In this correspondence, the authors use a tool, which is novel in this context, namely, amplitude modulation theory. The authors employ this tool to analyze the quantitative and qualitative features of the intersample behavior in a frequency domain setting. This offers new theoretical and practical insights into the method. The authors' conclusion is that the perceived benefits come at substantial cost which makes its practical use questionable