Discovering Robust Knowledge from Databases that Change

Many applications of knowledge discovery and data mining such as rule discovery for semantic query optimization, database integration and decision support, require the knowledge to be consistent with the data. However, databases usually change over time and make machine-discovered knowledge inconsistent. Useful knowledge should be robust against database changes so that it is unlikely to become inconsistent after database updates. This paper defines this notion of robustness in the context of relational databases and describes how robustness of first-order Horn-clause rules can be estimated. Experimental results show that our estimation approach can accurately identify robust rules. We also present a rule antecedent pruning algorithm that improves the robustness and applicability of machine discovered rules to demonstrate the usefulness of robustness estimation.     

鲁棒性的汉语人称代词消解

指代消解在自然语言处理中起着越来越重要的作用.许多自然语言处理应用系统都需要高效、鲁棒的指代消解策略.然而,传统的指代消解方法需要用到句法知识、语义知识、上下文知识,甚至领域知识等多级知识,在目前的自然语言处理水平下,要有效获取这些知识是相当困难的.结合汉语的特点,提出了一种弱化语言知识的人称代词消解方法,仅仅用到了单复数特征、性别特征和语法角色特征.该方法主要分为两步,首先,利用这3种特征的简单约束关系,过滤与人称代词特征不一致的词,并形成可能的先行语候选集;然后,使用一个权值算法,计算候选的权值,并将最高权值的候选作为代词最终的先行语.权值算法并不是枚举式地计算每个候选的权值,而会通过动态评测机制,在合适的条件下自动终止计算,因而有效地控制了计算复杂度.此外,该方法不需要对文本进行深层的分析处理,实现起来也很容易.测试结果表明,该方法达到了满意效果.     

Representing membership functions as points in high-dimensionalspaces for fuzzy interpolation and extrapolation

This paper introduces a new approach for fuzzy interpolation and extrapolation of sparse rule base comprising of membership functions with finite number of characteristic points. The approach calls for representing membership functions as points in high-dimensional Cartesian spaces using the locations of their characteristic points as coordinates. Hence, a fuzzy rule base can be viewed as a set of mappings between the antecedent and consequent spaces and the interpolation and extrapolation problem becomes searching for an image in the consequent space upon given an antecedent observation. The present approach divides observations into two groups: 1) observations within the antecedent spanning set contain the same geometric properties as the given antecedents; and 2) observations lying outside the antecedent spanning set contain new geometric properties beyond those of the given rules. Heuristic reasoning must therefore be applied. In this case, a two-step approach with certain flexibility to accommodate additional criteria and design objectives is formulated     

指代消解中语义角色特征的研究

该文实现了一个基于机器学习的指代消解平台,并在此基础上着重研究了语义角色特征对指代消解的影响。该文使用ASSERT^①语义角色标注系统得到语义角色标注信息,然后在原型系统的基础上加入语义角色特征。为了分析语义角色特征对指代消解的影响,该文还分析了语义角色特征和指代链特征以及代词细化特征的结合对系统的影响。通过把先行语和照应语在句子中所作的语义角色特征加入机器学习系统中进行研究,该文发现语义角色特征能够显著提高系统的性能,特别是对代词的消解有很好的效果。在ACE 2003 NWIRE基准语料上的所有类型名词短语的指代消解测试表明,召回率提高了3.4%,F值提高了1.8%。     

Interval Uncertainty-Based Robust Optimization for Convex and Non-Convex Quadratic Programs with Applications in Network Infrastructure Planning

Planning infrastructure networks such as roads, pipelines, waterways, power lines and telecommunication systems, require estimations on the future demand as well as other uncertain factors such as operating costs, degradation rates, or the like. When trying to construct infrastructure that is either optimal from a social welfare or profit perspective (depending on a public or private sector focus), typically researchers treat the uncertainties in the problem by using robust optimization methods. The goal of robust optimization is to find optimal solutions that are relatively insensitive to uncertain factors. This paper presents an efficient and tractable approach for finding robust optimum solutions to linear and, more importantly, quadratic programming problems with interval uncertainty using a worst case analysis. For linear, mixed-integer linear, and mixed-integer problems with quadratic objective and constraint functions, our robust formulations have the same complexity and tractability as their deterministic counterparts. Numerous examples with differing difficulties and complexities, especially with selected ones on network planning/operations problems, have been tested to demonstrate the viability of the proposed approach. The results show that the computational effort of the proposed approach, in terms of the number of function calls, for the robust problems is comparable to or even better than that of deterministic problems in some cases.     

A novel self-constructing Radial Basis Function Neural-Fuzzy System

This paper proposes a novel self-constructing least-Wilcoxon generalized Radial Basis Function Neural-Fuzzy System (LW-GRBFNFS) and its applications to non-linear function approximation and chaos time sequence prediction. In general, the hidden layer parameters of the antecedent part of most traditional RBFNFS are decided in advance and the output weights of the consequent part are evaluated by least square estimation. The hidden layer structure of the RBFNFS is lack of flexibility because the structure is fixed and cannot be adjusted effectively according to the dynamic behavior of the system. Furthermore, the resultant performance of using least square estimation for output weights is often weakened by the noise and outliers.This paper creates a self-constructing scenario for generating antecedent part of RBFNFS with particle swarm optimizer (PSO). For training the consequent part of RBFNFS, instead of traditional least square (LS) estimation, least-Wilcoxon (LW) norm is employed in the proposed approach to do the estimation. As is well known in statistics, the resulting linear function by using the rank-based LW norm approximation to linear function problems is usually robust against (or insensitive to) noises and outliers and therefore increases the accuracy of the output weights of RBFNFS. Several nonlinear functions approximation and chaotic time series prediction problems are used to verify the efficiency of self-constructing LW-GRBFNIS proposed in this paper. The experimental results show that the proposed method not only creates optimal hidden nodes but also effectively mitigates the noise and outliers problems.     

Using robust optimization for distribution and inventory planning for a large pulp producer

Södra Cell is a world leading producer of pulp and has a large distribution network for its pulp products. This network includes production mills in Sweden and Norway, terminals in European harbours and inland locations, and many customers. The company uses several transport modes including long chartered vessels, spot vessels, trains, barges and trucks. The company uses a supplier managed inventory with a large proportion of its customers. This makes the logistic planning including transportation and inventory critical, as Södra Cell has direct responsibility of their customers’ inventories. However, there is still some uncertainty regarding customer demand and Södra Cell has traditionally used a safety stock inventory approach to handle this. In this paper, we introduce a robust optimization approach to handle the uncertainty and to establish a distribution plan, together with related inventory management. With this approach there is no need for explicit safety stock levels. This is instead taken into account directly through the robust solution. In the proposed model, we can use practical characterization and historical information on the uncertainty. An important result with this is that we can avoid solutions that are too conservative and costly as in standard robust models. A large case study from Södra Cell is used to validate the proposed approach against the traditional approach with safety stock. The analysis is based on simulations and it shows that the robust approach is more cost efficient and can be used as a basis in a decision support system.     

指代消解中距离特征的研究

指代消解是自然语言处理中的一个重要问题,包括专有名词、普通名词、代词的指代识别。本文实现了一个基于机器学习的英语名词短语的指代消解平台,通过对原始语料进行命名实体识别和名词短语识别等一系列预处理,选取了多个有效特征及其组合,分别采用最大熵和SVM两种分类算法对名词短语进行分类,在此基础上着重研究了距离特征对指代消解的影响。在传统的基于机器学习的指代消解研究方法中,候选词和先行语的距离被定义为特征,而没有考虑距离在生成训练样例中的作用,本文通过把候选词和先行语的距离作为一个特征加入机器学习算法和作为限制条件用于指代关系候选实例的产生两方面进行详细研究,在MUC-6基准语料库上评测,实验结果表明,合理利用距离特征能够大大提高系统的性能。最终,本文采用最大熵和SVM两种分类器在测试集上分别获得了67.5和68.7的F1值,该结果优于同类型的其他系统。     

Sequential Association Rule Mining with Time Lags

This paper presents MOWCATL, an efficient method for mining frequent association rules from multiple sequential data sets. Our goal is to find patterns in one or more sequences that precede the occurrence of patterns in other sequences. Recent work has highlighted the importance of using constraints to focus the mining process on the association rules relevant to the user. To refine the data mining process, this approach introduces the use of separate antecedent and consequent inclusion constraints, in addition to the traditional frequency and support constraints in sequential data mining. Moreover, separate antecedent and consequent maximum window widths are used to specify the antecedent and consequent patterns that are separated by either a maximal width time lag or a fixed width time lag.Multiple time series drought risk management data are used to show that our approach can be effectively employed in real-life problems. This approach is compared to existing methods to show how they complement each other to discover associations in the drought risk management domain. The experimental results validate the superior performance of our method for efficiently finding relationships between global climatic episodes and local drought conditions. Both the maximal and fixed width time lags are shown to be useful when finding interesting associations.     

Fast convergence of inviscid fluid dynamic design problems

A new procedure for robust and efficient design optimization of inviscid flow problems has been developed and implemented on a wide variety of test problems. The methodology involves the use of an accurate flow solver to calculate the objective function and an approximate, dissipative flow solver, which is used only in the solution of the discrete quasi-time-dependent adjoint problem. The resulting design sensitivities are very robust even in the presence of noise or other non-smoothness associated with objective functions in many high-speed flow problems. The design problem is solved using what we term progressive optimization, whereby a sequence of a partially converged flow solution, followed by a partially converged adjoint solution followed by an optimization step is performed. This procedure is performed using a sequence of progressively finer grids for the solution of the flow field, while only using coarser grids for the adjoint equation solution.This approach has been tested on numerous inverse and direct (constrained) design problems involving two- and three-dimensional transonic nozzles and airfoils as well as supersonic blunt bodies. The methodology is shown to be robust and highly efficient, with a converged design optimization produced in no more than the amount of computational work to perform from 0.5 to 2.5 fine-mesh flow analyses.     

Robust stability analysis with cycling-based LPTV scaling. Part II: its properties under the use of FIR separators

This paper is concerned with robust stability analysis of discrete-time linear periodically time-varying (LPTV) systems using the cycling-based LPTV scaling approach. It consists of applying the separator-type robust stability theorem through the cycling-based treatment of such systems, where this paper aims at revealing fundamental properties of this approach when we confine ourselves to what we call finite impulse response (FIR) separators as a theoretically and numerically very tractable class of separators. Specifically, we clarify such properties of the cycling-based LPTV scaling approach using FIR separators that cannot readily be seen under the treatment of general class of separators. This is accomplished by comparing it with another approach, called lifting-based LPTV scaling using FIR separators, through the framework of representing the associated robust stability conditions with infinite matrices. More precisely, this leads us to clarifying the fundamental relationships between the cycling-based and lifting-based approaches under the use of FIR separators. We also provide a numerical example demonstrating the fundamental relationships clarified in this paper.     

Robust clustering by pruning outliers

In many applications of C-means clustering, the given data set often contains noisy points. These noisy points will affect the resulting clusters, especially if they are far away from the data points. In this paper, we develop a pruning approach for robust C-means clustering. This approach identifies and prunes the outliers based on the sizes and shapes of the clusters so that the resulting clusters are least affected by the outliers. The pruning approach is general, and it can improve the robustness of many existing C-means clustering methods. In particular, we apply the pruning approach to improve the robustness of hard C-means clustering, fuzzy C-means clustering, and deterministic-annealing C-means clustering. As a result, we obtain three clustering algorithms that are the robust versions of the existing ones. In addition, we integrate the pruning approach with the fuzzy approach and the possibilistic approach to design two new algorithms for robust C-means clustering. The numerical results demonstrate that the pruning approach can achieve good robustness.     

Semi-dense and robust image registration by shift adapted weighted aggregation and variational completion

This work presents a novel approach for both stereo and optical flow that deals with large displacements, depth/motion discontinuities and occlusions. The proposed method comprises two main steps. First, a novel local stereo matching algorithm is presented, whose main novelty relies in the block-matching aggregation step. We adopt an adaptive support weights approach in which the weight distribution favors pixels that share the same displacement with the reference one. State-of-the-art methods make the weight function depend only on image features. On the contrary, the proposed weight function depends additionally on the tested shift, by giving more importance to those pixels in the block-matching with smaller cost, as these are supposed to have the tested displacement. Moreover, the method is embedded into a pyramidal procedure to locally limit the search range, which helps to reduce ambiguities in the matching process and saves computational time. Second, the non-dense local estimation is filtered and interpolated by means of a new variational formulation making use of intermediate scale estimates of the local procedure. This permits to keep the fine details estimated at full resolution while being robust to noise and untextured areas using estimates at coarser scales. The introduced variational formulation as well as the block-matching algorithm are robust to illumination changes. We test our algorithm for both stereo and optical flow public datasets showing competitive results.     

Hybridization of fuzzy GBML approaches for pattern classification problems

We propose a hybrid algorithm of two fuzzy genetics-based machine learning approaches (i.e., Michigan and Pittsburgh) for designing fuzzy rule-based classification systems. First, we examine the search ability of each approach to efficiently find fuzzy rule-based systems with high classification accuracy. It is clearly demonstrated that each approach has its own advantages and disadvantages. Next, we combine these two approaches into a single hybrid algorithm. Our hybrid algorithm is based on the Pittsburgh approach where a set of fuzzy rules is handled as an individual. Genetic operations for generating new fuzzy rules in the Michigan approach are utilized as a kind of heuristic mutation for partially modifying each rule set. Then, we compare our hybrid algorithm with the Michigan and Pittsburgh approaches. Experimental results show that our hybrid algorithm has higher search ability. The necessity of a heuristic specification method of antecedent fuzzy sets is also demonstrated by computational experiments on high-dimensional problems. Finally, we examine the generalization ability of fuzzy rule-based classification systems designed by our hybrid algorithm.     

不确定非线性网络化系统的鲁棒H_∞控制

用T-S(Takagi-Sugeno)模糊方法研究了带有参数不确定的非线性网络化系统的鲁棒控制.首先,考虑到诱导时延和数据丢包等网络因素的影响,基于事件驱动的保持器的更新序列建立闭环反馈系统的采样模型,并将其转化为状态中附加两个时滞变量的连续T-S模糊系统.然后,利用时滞系统方法,分析不确定闭环模糊系统的鲁棒H∞性能,并设计相应的鲁棒H∞模糊控制器.最后,仿真例子表明了方法的有效性.     

Robust stability analysis with cycling-based LPTV scaling: part I. Fundamental results on its relationship with lifting-based LPTV scaling

This paper is concerned with robust stability analysis of discrete-time linear periodically time-varying (LPTV) systems using the cycling-based LPTV scaling approach. To study the properties of this approach in comparison with the lifting-based LPTV scaling approach, we consider exploiting the framework of representing the associated robust stability conditions with infinite matrices. Since it serves as a common framework for comparing the two different LPTV scaling approaches, it provides us with new insights into the relationship between the cycling-based and lifting-based scaling approaches. In particular, we derive fundamental results that enable us to reduce the comparison, with respect to conservativeness in robust stability analysis, of the two scaling approaches with restricted and tractable classes of separators to a modified comparison of the associated classes of what we call infinite-dimensional separators arising in the above infinite matrix framework.     

Branching Strategy Selection Approach Based on Vivification Ratio

The two most effective branching strategies LRB and VSIDS perform differently on different types of instances. Generally, LRB is more effective on crafted instances, while VSIDS is more effective on application ones. However, distinguishing the types of instances is difficult. To overcome this drawback, we propose a branching strategy selection approach based on the vivification ratio. This approach uses the LRB branching strategy more to solve the instances with a very low vivification ratio. We tested the instances from the main track of SAT competitions in recent years. The results show that the proposed approach is robust and it significantly increases the number of solved instances. It is worth mentioning that, with the help of our approach, the solver Maple_CM can solve additional 16 instances for the benchmark from the 2020 SAT competition.     

Service co-creation in social media: An extension of the theory of planned behavior

Social media have become a major channel through which consumers interact with firms and other consumers. This paper examines the factors that drive consumers to co-create in social media and proposes a theoretical model that extends the theory of planned behavior to include perceived usefulness as a key antecedent of consumer attitudes toward co-creation in social media. The model was tested using responses from 743 Chinese consumers. Results of structural equation modeling confirmed that perceived usefulness was an antecedent of consumer attitudes toward co-creation in social media. The relationship between perceived usefulness and customer attitudes toward co-creation was moderated by the level of consumer involvement, and that relationship was found to be more salient for a high rather than a low level of consumer involvement. Practical and theoretical implications are given.     

A Particle Filtering and DSmT Based Approach for Conflict Resolving in case of Target Tracking with Multiple Cues

In this paper, we propose an efficient and robust method for multiple targets tracking in cluttered scenes using multiple cues. Our approach combines the use of Monte Carlo sequential filtering for tracking and Dezert-Smarandache theory (DSmT) to integrate the information provided by the different cues. The use of DSmT provides the necessary framework to quantify and overcome the conflict that might appear between the cues due to the occlusion. Our tracking approach is tested with color and location cues on a cluttered scene where multiple targets are involved in partial or total occlusion.     

Robust Robot Localization by Sensors with Different Degree of Accuracy

In this paper the robust robot localization problem with respect to uncertainties on environment features is formulated in a stochastic setting, and an Extended Kalman Filtering (EKF) approach is proposed for the integration of odometric, gyroscopic, and sonar measures. As gyroscopic readings are much more reliable than the other ones, the localization algorithm gives rise to a nearly singular EKF. This problem is dealt with by defining a reduced order nonsingular EKF. The robust solution has been implemented and tested on a powered wheelchair.