Mining diversity on social media networks

The fast development of multimedia technology and increasing availability of network bandwidth has given rise to an abundance of network data as a result of all the ever-booming social media and social websites in recent years, e.g., Flickr, Youtube, MySpace, Facebook, etc. Social network analysis has therefore become a critical problem attracting enthusiasm from both academia and industry. However, an important measure that captures a participant’s diversity in the network has been largely neglected in previous studies. Namely, diversity characterizes how diverse a given node connects with its peers. In this paper, we give a comprehensive study of this concept. We first lay out two criteria that capture the semantic meaning of diversity, and then propose a compliant definition which is simple enough to embed the idea. Based on the approach, we can measure not only a user’s sociality and interest diversity but also a social media’s user diversity. An efficient top-k diversity ranking algorithm is developed for computation on dynamic networks. Experiments on both synthetic and real social media datasets give interesting results, where individual nodes identified with high diversities are intuitive.     

Rate-smoothed schedule with tolerable data dropping for video coding stream

Most algorithms of smoothing schedule compute the required bit rate of video transmission to satisfy all the transmitted data. In this paper, our proposed tolerable data dropping algorithm can adjust transmitting data to fit available bit rate. MPEG-4 with fine grained scalability (FGS) can support partial data dropping to adapt to available bandwidth network. The algorithm is based on the minimum variance bandwidth allocation (MVBA) algorithm proposed by Salehi et al. to compute the bit rate such that still ensuring that the buffer never underflows and overflows for MPEG-4 FGS streams under the limited bandwidth resource. We prove that our proposed algorithm, named MVBADP, is smoother than the MVBA algorithm. The experimental results show the peak rate, the number of rate changes, and the ratio of total dropping data, and the PSNR for four test sequences with different content characteristics. They are varied by buffer sizes and tolerable dropping ratios. We found that the MVBADP algorithm can reduce the peak rate and the number of changes when the transmitted data are dropped by tolerable dropping ratio, especially on the video sequences with the high motion and complex texture characteristic and larger size change of the consecutive frame.     

Generalized extreme learning machine acting on a metric space

Functional data learning is an extension of traditional data learning, that is, learning the data chosen from the Euclidean space ${\mathbb{R}^{n}}$ to a metric space. This paper focuses on the functional data learning with generalized single-hidden layer feedforward neural networks (GSLFNs) acting on some metric spaces. In addition, three learning algorithms, named Hilbert parallel overrelaxation backpropagation (H-PORBP) algorithm, ν-generalized support vector regression (ν-GSVR) and generalized extreme learning machine (G-ELM) are proposed to train the GSLFNs acting on some metric spaces. The experimental results on some metric spaces indicate that GELM with additive/RBF hidden-nodes has a faster learning speed, a better accuracy, and a better stability than HPORBP algorithm and ν-GSVR for training the functional data. The idea of GELM can be used to extend those improved extreme learning machines (ELMs) that act on the Euclidean space ${\mathbb{R}^{n}, }$ such as online sequential ELM, incremental ELM, pruning ELM and so on, to some metric spaces.     

MicroPort: A general simulation platform for seaport container terminals

Seaport container terminals are essential nodes in sea cargo transportation networks. As such, the operational efficiency of container terminals in handling containers passing through them plays a critical role in a globalized world economy. Many models and algorithms have been developed to address various decision problems in container terminals to help improve operational efficiency. These decision support tools are usually used separately for specific purposes. However, the problems they are trying to tackle are often interrelated. Therefore, in this regard, an evaluation tool which can capture as many operational conditions as possible for different decision problems is necessary. This paper introduces a general simulation platform, named MicroPort, which aims to provide an integrated and flexible modeling system for evaluating the operational capability and efficiency of different designs of seaport container terminals. The software structure of MicroPort comprises three programming layers: (1) the Functions layer; (2) the Applications layer; and (3) the Extensions layer. Different layers are bound by Application Programming Interfaces (APIs). Basic functions built in the Functions layer support the Applications layer in which major operation processes can be modeled by an agent-based method. External modules and decision support tools in the Extensions layer then use APIs to adjust the system to produce suitable simulation models for specific purposes.     

Dependence tree structure estimation via copula

We propose an approach for dependence tree structure learning via copula. A nonparametric algorithm for copula estimation is presented. Then a Chow-Liu like method based on dependence measure via copula is proposed to estimate maximum spanning bivariate copula associated with bivariate dependence relations. The main advantage of the approach is that learning with empirical copula focuses on dependence relations among random variables, without the need to know the properties of individual variables as well as without the requirement to specify parametric family of entire underlying distribution for individual variables. Experiments on two real-application data sets show the effectiveness of the proposed method.     

Optimal Performance in Tracking Stochastic Signal Under Disturbance Rejection

The analysis method of optimal tracking performance is proposed for multiple‐input multiple‐output (MIMO) linear time‐invariant (LTI) systems under disturbance rejection. An H₂ criterion of the error signal between the output of the plant and the reference signal is used as a measure for the tracking performance. Spectral factorization is applied to obtain the optimal solution of the system tracking error. The explicit expressions are derived for this minimal tracking error with respect to random reference signals under disturbance rejection. It is shown that the nonminimum phase zeros, the zero direction, the unstable poles, the pole direction of a given plant, statistical characteristics of the reference input signal, and disturbance signal have a negative effect on a feedback system's ability to reduce the system error with disturbance rejection. The results show that the optimal tracking performance will further be damaged because of disturbance rejection. Some typical examples are given to illustrate the theoretical results.     

Stabilization of impulsive hybrid systems using quantized input and output feedback

In this paper, we consider the feedback stabilization of impulsive control systems with quantized input and output signals. To study the problem, the notions of quasi‐invariant sets and attracting sets for impulsive systems with quantization are introduced first, and then applied to the control design. Hybrid quantized control schemes are proposed to stabilize the considered impulsive linear or nonlinear systems via either input or output feedback. Mathematical analysis and numerical simulations are given to show the principle and effectiveness of the proposed designs. Copyright © 2011 John Wiley and Sons Asia Pte Ltd and Chinese Automatic Control Society     

A Polynomial Algorithm for Computing Elementary Siphons in a Class of Petri Nets

A set of elementary siphons plays a key role in the development of deadlock prevention policies for automated manufacturing systems. This paper addresses the computation problem for elementary siphons in a subclass of Petri nets which are basic systems of simple sequential processes with resources (BS³PR) and can model many automated manufacturing systems. An algorithm for enumerating elementary siphons is established by the one‐to‐one relationship between maximal perfect resource‐transition circuits (MPCs) and strict minimal siphons. A set of MPCs is first computed, followed by a set of elementary siphons in a BS³PR. The presented algorithm is proved to have polynomial‐time complexity. An example is used to illustrate the algorithm.     

A new admissibility condition of discrete-time singular systems with time-varying delays

This paper gives a novel delay-dependent admissibility condition of discrete-time singular systems with time-varying delays. For convenience, the time-varying delay is assumed to be the sum of delay lower bound and the integral multiples of a constant delay. Specially, if the constant delay is of unit length, the delay is an interval-like time-varying delay. The proposed admissibility condition is presented and expressed in terms of linear matrix inequality (LMI) by Lyapunov approach. Generally, the uncertainty of time-varying delay would lead to conservatism. In this paper, this critical issue is tackled by accurately estimating the time-varying delay. Consequently, the proposed admissibility condition is less conservative than the existing results, which is demonstrated by a numerical example.     

Financial distress prediction using support vector machines: Ensemble vs. individual

Financial distress prediction (FDP) is of great importance to both inner and outside parts of companies. Though lots of literatures have given comprehensive analysis on single classifier FDP method, ensemble method for FDP just emerged in recent years and needs to be further studied. Support vector machine (SVM) shows promising performance in FDP when compared with other single classifier methods. The contribution of this paper is to propose a new FDP method based on SVM ensemble, whose candidate single classifiers are trained by SVM algorithms with different kernel functions on different feature subsets of one initial dataset. SVM kernels such as linear, polynomial, RBF and sigmoid, and the filter feature selection/extraction methods of stepwise multi discriminant analysis (MDA), stepwise logistic regression (logit), and principal component analysis (PCA) are applied. The algorithm for selecting SVM ensemble's base classifiers from candidate ones is designed by considering both individual performance and diversity analysis. Weighted majority voting based on base classifiers’ cross validation accuracy on training dataset is used as the combination mechanism. Experimental results indicate that SVM ensemble is significantly superior to individual SVM classifier when the number of base classifiers in SVM ensemble is properly set. Besides, it also shows that RBF SVM based on features selected by stepwise MDA is a good choice for FDP when individual SVM classifier is applied.