A <Emphasis Type="Italic">k</Emphasis>-norm pruning algorithm for decision tree classifiers based on error rate estimation

Decision trees are well-known and established models for classification and regression. In this paper, we focus on the estimation and the minimization of the misclassification rate of decision tree classifiers. We apply Lidstone’s Law of Succession for the estimation of the class probabilities and error rates. In our work, we take into account not only the expected values of the error rate, which has been the norm in existing research, but also the corresponding reliability (measured by standard deviations) of the error rate. Based on this estimation, we propose an efficient pruning algorithm, called k-norm pruning, that has a clear theoretical interpretation, is easily implemented, and does not require a validation set. Our experiments show that our proposed pruning algorithm produces accurate trees quickly, and compares very favorably with two other well-known pruning algorithms, CCP of CART and EBP of C4.5. Editor: Hendrik Blockeel.     

Uncorrelated discriminant vectors using a kernel method

Uncorrelated discriminant vectors using a kernel method are proposed in this paper. In some sense, kernel uncorrelated discriminant vectors extend Jin's method and then several related theorems are stated. Most importantly, the proposed method can deal with nonlinear problems. Finally, experimental results on handwritten numeral characters show that the proposed method is effective and feasible.     

Thermal problem solution using a surrogate model clustering technique

The thermal problem defined for the validation challenge workshop involves a simple one-dimensional slab geometry with a defined heat flux at the front face, adiabatic conditions at the rear face, and a provided baseline predictive simulation model to be used to simulate the time-dependent heatup of the slab. This paper will discuss a clustering methodology using a surrogate heat transfer algorithm that allows propagation of the uncertainties in the model parameters using a very limited series of full simulations. This clustering methodology can be used when the predictive model to be run is very expensive, and only a few simulation runs are possible. A series of time-dependent statistical comparisons designed to validate the model against experimental data provided in the problem formulation will also be presented, and limitations of the approach discussed. The purpose of this paper is to represent methods of propagation of uncertainty with limited computer runs, validation with uncertain data, and decision-making under uncertainty. The final results of the analysis indicate that the there is approximately 95% confidence that the regulatory criteria under consideration would be failed given the high level of physical data provided.     

Worst‐case execution time analysis for a Java processor

In this paper, we propose a solution for a worst‐case execution time (WCET) analyzable Java system: a combination of a time‐predictable Java processor and a tool that performs WCET analysis at Java bytecode level. We present a Java processor, called JOP, designed for time‐predictable execution of real‐time tasks. The execution time of bytecodes, the instructions of the Java virtual machine, is known to cycle accuracy for JOP. Therefore, JOP simplifies the low‐level WCET analysis. A method cache, which fills whole Java methods into the cache, simplifies cache analysis. The WCET analysis tool is based on integer linear programming. The tool performs the low‐level analysis at the bytecode level and integrates the method cache analysis. An integrated data‐flow analysis performs receiver‐type analysis for dynamic method dispatches and loop‐bound analysis. Furthermore, a model checking approach to WCET analysis is presented where the method cache can be exactly simulated. The combination of the time‐predictable Java processor and the WCET analysis tool is evaluated with standard WCET benchmarks and three real‐time applications. The WCET friendly architecture of JOP and the integrated method cache analysis yield tight WCET bounds. Comparing the exact, but expensive, model checking‐based analysis of the method cache with the static approach demonstrates that the static approximation of the method cache is sufficiently tight for practical purposes. Copyright © 2010 John Wiley & Sons, Ltd.     

Improving surrogate-assisted variable fidelity multi-objective optimization using a clustering algorithm

Surrogate-assisted evolutionary optimization has proved to be effective in reducing optimization time, as surrogates, or meta-models can approximate expensive fitness functions in the optimization run. While this is a successful strategy to improve optimization efficiency, challenges arise when constructing surrogate models in higher dimensional function space, where the trade space between multiple conflicting objectives is increasingly complex. This complexity makes it difficult to ensure the accuracy of the surrogates. In this article, a new surrogate management strategy is presented to address this problem. A k-means clustering algorithm is employed to partition model data into local surrogate models. The variable fidelity optimization scheme proposed in the author's previous work is revised to incorporate this clustering algorithm for surrogate model construction. The applicability of the proposed algorithm is illustrated on six standard test problems. The presented algorithm is also examined in a three-objective stiffened panel optimization design problem to show its superiority in surrogate-assisted multi-objective optimization in higher dimensional objective function space. Performance metrics show that the proposed surrogate handling strategy clearly outperforms the single surrogate strategy as the surrogate size increases.     

Improving stock index forecasts by using a new weighted fuzzy-trend time series method

We propose using new weighted operators in fuzzy time series to forecast the future performance of stock market indices. Based on the chronological sequence of weights associated with the original fuzzy logical relationships, we define both chronological-order and trend-order weights, and incorporate our proposals for the ex-post forecast into the classical modeling approach of fuzzy time series. These modifications for the assignation of weights affect the forecasting process, because we use jumps as technical indicators to predict stock trends, and additionally, they provide a trapezoidal fuzzy number as a forecast of the future performance of the stock index value. Working with trapezoidal fuzzy numbers allows us to analyze both the expected value and the ambiguity of the future behavior of the stock index, using a possibilistic interval-valued mean approach. Therefore, using fuzzy logic more useful information is provided to the decision analyst, which should be appropriate in a financial context. We analyze the effectiveness of our approach with respect to other weighted fuzzy time series methods using trading data sets from the Taiwan Stock Index (TAIEX), the Japanese NIKKEI Index, the German Stock Index (DAX) and the Spanish Stock Index (IBEX35). The comparative results indicate the better accuracy of our procedure for point-wise one-step ahead forecasts.     

Eliminating the effect of freezing frames on user perceptive by using a time interleaving technique

Streaming video over a wireless network faces several challenges such as high packet error rates, bandwidth variations, and delays, which could have negative effects on the video streaming and the viewer will perceive a frozen picture for certain durations due to loss of frames. In this study, we propose a Time Interleaving Robust Streaming (TIRS) technique to significantly reduce the frozen video problem and provide a satisfactory quality for the mobile viewer. This is done by reordering the streaming video frames as groups of even and odd frames. The objective of streaming the video in this way is to avoid the losses of a sequence of neighbouring frames in case of a long sequence interruption. We evaluate our approach by using a user panel and mean opinion score (MOS) measurements; where the users observe three levels of frame losses. The results show that our technique significantly improves the smoothness of the video on the mobile device in the presence of frame losses, while the transmitted data are only increased by almost 9% (due to reduced time locality).     

Predicting economic time series using a nonlinear deterministic technique

In this paper, a deterministic predictive technique is introduced, which is based on the embedding theorem by Takens and the recently developed wavelet networks. Several economic time series are tested by using this technique. As a result, the predicted values correspond quite well with the actual values. It shows that some economic time series are predictable by using a deterministic approach. Furthermore, the effects of using smoothing techniques (e.g., moving average) upon the prediction results are also investigated since there inevitably exists noise in almost all economic time series. Our numerical results show that smoothing like moving average can improve the prediction results for some of our tested time series, and for others predictions without smoothing are even better than with smoothing. This implies that wavelet network is capable of drawing the underlying dynamics directly from noisy economic time series.     

云计算环境下基于代表点增量层次密度聚类的微博事件检测及跟踪

为从微博服务平台产生的大量实时信息中抽取新闻事件,提出了一套完整的云计算环境下的微博事件检测跟踪算法。首先采用新的基于微博转发数和评论数的权值计算方法,将微博文本表示成向量空间模型;再利用基于代表点的增量层次密度聚类(RIHDBSCAN)算法抽取关键词,最终实现新闻事件的检测和跟踪。针对单一节点无法快速高效地处理海量微博数据的问题,将算法部署在云计算平台Hadoop上。通过在新浪微博平台上获取的真实数据进行实验,结果表明,所提出的权值计算方法比     

A method of relational fuzzy clustering based on producing feature vectors using FastMap

The first stage of organizing objects is to partition them into groups or clusters. The clustering is generally done on individual object data representing the entities such as feature vectors or on object relational data incorporated in a proximity matrix.This paper describes another method for finding a fuzzy membership matrix that provides cluster membership values for all the objects based strictly on the proximity matrix. This is generally referred to as relational data clustering. The fuzzy membership matrix is found by first finding a set of vectors that approximately have the same inter-vector Euclidian distances as the proximities that are provided. These vectors can be of very low dimension such as 5 or less. Fuzzy c-means (FCM) is then applied to these vectors to obtain a fuzzy membership matrix. In addition two-dimensional vectors are also created to provide a visual representation of the proximity matrix. This allows comparison of the result of automatic clustering to visual clustering. The method proposed here is compared to other relational clustering methods including NERFCM, Rouben’s method and Windhams A-P method. Various clustering quality indices are also calculated for doing the comparison using various proximity matrices as input. Simulations show the method to be very effective and no more computationally expensive than other relational data clustering methods. The membership matrices that are produced by the proposed method are less crisp than those produced by NERFCM and more representative of the proximity matrix that is used as input to the clustering process.     

Comments on “single-link characteristics of a mode-seeking clustering algorithm”

The paper refutes the assertion of Shaffer et al.⁽¹⁾ that, in general, the minimum spanning tree algorithm and the mode-seeking clustering algorithm⁽²⁾ yield identical results. An example is given to exhibit the differences of these two algorithms.     

Improving the time efficiency of proving theorems using a learning mechanism

In this paper, we develop a new approach for enhancing the time efficiency of proving theorems by using a learning mechanism. A system is proposed for analyzing a set of theorems and observing those features that often affect the speed at which the theorems are proved. The system uses the learning mechanism for choosing between two well known theorem-provers, namely, Resolution–Refutation (TGTP) and Semantic Trees (HERBY). A three-step process has been implemented. The first step is to prove a set of theorems using the above two theorem provers. A training set of two classes of theorems is thus created. Each class represents those theorems that have been proven in less time using a particular theorem prover. The second step is to train neural networks on both classes of theorems in order to construct an internal representation of the decision boundary between the two classes. In the last step, a voting scheme is invoked in order to combine the decisions of the individual neural networks into a final decision. The results achieved by the system when working on the standard theorems of the Stickel Test Set are shown. Those results confirm the feasibility of our approach to inte-grate a learning mechanism into the process of automated theorem proving.     

A partitional clustering algorithm validated by a clustering tendency index based on graph theory

Applying graph theory to clustering, we propose a partitional clustering method and a clustering tendency index. No initial assumptions about the data set are requested by the method. The number of clusters and the partition that best fits the data set, are selected according to the optimal clustering tendency index value.     

Model falsification using set‐valued observers for a class of discrete‐time dynamic systems: a coprime factorization approach

This article introduces a new method for model falsification using set‐valued observers, which can be applied to a class of discrete linear time‐invariant dynamic systems with time‐varying model uncertainties. In comparison with previous results, the main advantages of this approach are as follows: The computation of the convex hull of the set‐valued estimates of the state can be avoided under certain circumstances; to guarantee convergence of the set‐valued estimates of the state, the required number of previous steps is at most as large as the number of states of the nominal plant; and it provides a straightforward nonconservative method to falsify uncertain models of dynamic systems, including open‐loop unstable plants. The results obtained are illustrated in simulation, emphasizing the advantages and shortcomings of the suggested method. Copyright © 2013 John Wiley & Sons, Ltd.     

Improving volcanic ash cloud detection by a robust satellite technique

Automated and reliable satellite-based techniques are strongly required for volcanic ash cloud detection and tracking. In fact, volcanic ash clouds pose a serious hazard for air traffic and the synoptic (and possibly frequent) coverage offered by satellites can provide exciting opportunities for monitoring activities as well as for risk mitigation purposes.A new, AVHRR-based technique for improved automatic detection of volcanic clouds by means of multi-temporal analysis of historical, long-term satellite records has been recently proposed. The technique basically rests on the Robust AVHRR Techniques (RAT) approach, which is an innovative strategy of satellite data analysis, devoted to a former characterisation of the measured signal, in terms of expected value and natural variability and a further recognition of signal anomalies by an automatic, unsupervised change detection step. In this work, an extension of this method to nighttime observations is presented, by using thermal infrared information coming from AVHRR bands centred approximately at 3.5, 11.0 and 12.0 μm. Results achieved for two recent eruptive events of Mount Etna (occurred in May 2000 and in July 2001) seem to be encouraging, showing clear improvements in terms of ash detection sensitivity as well as in terms of false alarms reduction. The technique performance is also evaluated by comparison with the traditional “split-window” brightness temperature difference method; this exercise revealed a general improvement obtained by the proposed approach, even though some common problems still remain unsolved. The main merits of such an approach are its intrinsic self-adaptability to different environmental/natural/observational conditions and its natural exportability also to different satellite sensors. The results here presented show the benefits of such a technique especially when different observational conditions (time of pass, seasonal period, atmospheric moisture, solar illumination, volcanic cloud composition, satellite angles of view, etc.) are considered.The future prospects, also in terms of possible operational scenarios, coming from the implementation of such an approach on the new generation of satellite sensors (like, for example, SEVIRI aboard Meteosat Second Generation platform) are also discussed.     

Improving the generalization performance of RBF neural networks using a linear regression technique

In this paper we present a method for improving the generalization performance of a radial basis function (RBF) neural network. The method uses a statistical linear regression technique which is based on the orthogonal least squares (OLS) algorithm. We first discuss a modified way to determine the center and width of the hidden layer neurons. Then, substituting a QR algorithm for the traditional Gram–Schmidt algorithm, we find the connected weight of the hidden layer neurons. Cross-validation is utilized to determine the stop training criterion. The generalization performance of the network is further improved using a bootstrap technique. Finally, the solution method is used to solve a simulation and a real problem. The results demonstrate the improved generalization performance of our algorithm over the existing methods.     

Improving PDP picture quality by means of a motion-dependent equalizing-pulse technique

Abstract— When moving images are displayed on color plasma displays, motional artifacts such as dynamic false contours with disturbances of gray scales and colors are often observed. Reduction of the disturbances is essential to achieve PDPs with acceptable picture quality for TV use. The moving-picture quality can be improved to some extent by using an equalizing-pulse technique which augments or suppresses light-emission to compensate for the lack or surplus from the original signal. The disturbances, however, become significant as the speed of motion increases. In order to reduce the disturbances, the equalizing pulses are weighted according to the speed and direction of motion. The improvement can be enhanced further by combining the technique with a modified-binary-coded light-emission-period scheme. Disturbance is thus reduced by 82 dB. The technique is applicable to images moving at any speed in any direction. It can also be used for any pixel arrangement and any light-emission scheme.     

Derivation of optimal input parameters for minimizing execution time of matrix-based computations on a GPU

As GPUs are continually being utilized as coprocessors, the demand for optimally utilizing them for various computations continues to grow. The goal of this work is to derive input parameters which yield the minimum execution time for matrix-based computations executing on a GPU. Input parameters are defined as the dimensions of the grid and blocks assigned for execution on the GPU. Since input parameters inadequately represent the executional behavior of the GPU, execution metrics are formulated as functions of the input parameters to represent the behavior. The execution metrics are architecture independent and are utilized to derive optimal input parameters, which are input parameters that yield the minimum execution time. Optimal input parameters are derived for the following matrix-based computations: matrix–vector multiplication (Mv), matrix–matrix multiplication (MM), and convolution. The derivation allows for selection of optimal input parameters without executing code. Results, for all matrix-based computations and sizes tested, show that utilizing the derived optimal input parameters often yields the minimum execution time, and, at worst, execution time within 13.6% of the minimum.     

Testing protocols in Internet of Things by a formal passive technique

In recent years, Extensible Messaging and Presence Protocol （XMPP） is gaining momentum in Internet of Things （IoT）. It has been widely used in chatting, message exchanging and unique addressing. As a matter of course, it raises an interesting issue： how to formally test the conformance and performance of XMPP in IoT environment. While conformance testing of communicating protocols is a functional test that verifies whether the behaviors of the protocol satisfy defined requirements, performance testing is a qualitative and quantitative test that aims at checking whether the performance requirements of the protocol are satisfied under certain conditions. In this paper, we present a logic-based passive testing approach that can test both the conformance and the performance of XMPP protocol through real execution traces and formally specified properties. To evaluate and assess our methodology, we present a developed prototype and the experiments with a set of XMPP properties. Finally, the relevant verdicts and conclusions are provided.