Most vital links and nodes in weighted networks

The n most vital links (or nodes) in a weighted network are those n links (nodes) whose removal from the network results in the greatest increase in shortest distance between two specified nodes. Preliminary results are presented for obtaining these entities.     

Decomposition algorithms for locating minimal cuts in a network

This paper provides decomposition algorithms for locating minimal cuts in a large directed network. The main theorem provides several cases for the algorithms. In the worst case, it is shown that the efficiency of one of the proposed algorithms is of the same order as a no-decomposition algorithm. As in linear programming, the obvious advantage of the proposed decomposition procedure is its ability to potentially handle larger problems than a no-decomposition algorithm.     

Modeling the social obesity epidemic with stochastic networks

In this paper we extend a compartmental model to the case of a homogenous network epidemic model for a study of the dynamics of obese populations. The social epidemic network-based approach developed here uses different algorithms and points of views regarding the simulation of the dynamics of the network. First, Monte Carlo simulations for homogeneous networks using a traditional constant probability transition rates and a mean-field-like approach are presented. We show that these networks evolve towards an approximately stationary state, which coincides with the one obtained by the underlying classical compartmental continuous model. A mean-field-like approach is applied in order to reduce the large computation time required when dealing with large contact networks. We also investigate, using homogenous contact networks, the effect of the realistic assumption that the waiting times between subpopulations follow a gamma distribution instead of the traditional exponential distribution. It is concluded that careful attention must be paid to the distributions assumed for the state periods.     

A Bayesian Networks approach to Operational Risk

A system for Operational Risk management based on the computational paradigm of Bayesian Networks is presented. The algorithm allows the construction of a Bayesian Network targeted for each bank and takes into account in a simple and realistic way the correlations among different processes of the bank. The internal losses are averaged over a variable time horizon, so that the correlations at different times are removed, while the correlations at the same time are kept: the averaged losses are thus suitable to perform the learning of the network topology and parameters; since the main aim is to understand the role of the correlations among the losses, the assessments of domain experts are not used. The algorithm has been validated on synthetic time series. It should be stressed that the proposed algorithm has been thought for the practical implementation in a mid or small sized bank, since it has a small impact on the organizational structure of a bank and requires an investment in human resources which is limited to the computational area.     

Data Envelopment Analysis of multiple response experiments

Taguchi method is the usual strategy in robust design and involves conducting experiments using orthogonal arrays and estimating the combination of factor levels that optimizes a given performance measure, typically a signal-to-noise ratio. The problem is more complex in the case of multiple responses since the combinations of factor levels that optimize the different responses usually differ. In this paper, an Artificial Neural Network, trained with the experiments results, is used to estimate the responses for all factor level combinations. After that, Data Envelopment Analysis (DEA) is used first to select the efficient (i.e. non-dominated) factor level combinations and then for choosing among them the one which leads to a most robust quality loss penalization. Mean Square Deviations of the quality characteristics are used as DEA inputs. Among the advantages of the proposed approach over traditional Taguchi method are the non-parametric, non-linear way of estimating quality loss measures for unobserved factor combinations and the non-parametric character of the performance evaluation of all the factor combinations. The proposed approach is applied to a number of case studies from the literature and compared with existing approaches.     

The human brain,social conformity,and presidential elections

This paper investigates aggregate voting behavior in American presidential elections from 1904 to 1980; the state is unit of analysis. We abandon the traditional assumption that voting is a rational process and instead construct a model to test the power of social conformity over voting decisions. The model, which uses the entropy measure of statistical information theory, allows specific numerical tests of its validity and, additionally, reveals unexpected dynamic patterns in voting behavior. We find four distinct processes related to social conformity that affect voter turnout and the distribution of votes among presidential candidates. A mathematical model for each process is identified and parameters are estimated from election data.     

固定合作规模网络的平均路径长度

本文提出了一种特殊的合作网络,称之为固定合作规模网络．我们重点研究了这类网络的平均路径长度,通过建立微分方程,得到平均路径长度的增加速度近似与网络规模的对数成正比．     

Analysis of Transmission Performance in SUPERPONs

In this work we study how optical amplifiers can deeply improve the performance of the passive optical networks (PONs), permitting a large number of optical network units (ONUs), transmitting at high bit rate. These high-capacity networks are called SUPERPONs, and we show how to achieve a network with 8,192 ONUs with a transmission in the downstream direction up to 10 Gbit/s.     

Dynamic decision making for graphical models applied to oil exploration

We present a framework for sequential decision making in problems described by graphical models. The setting is given by dependent discrete random variables with associated costs or revenues. In our examples, the dependent variables are the potential outcomes (oil, gas or dry) when drilling a petroleum well. The goal is to develop an optimal selection strategy of wells that incorporates a chosen utility function within an approximated dynamic programming scheme. We propose and compare different approximations, from naive and myopic heuristics to more complex look-ahead schemes, and we discuss their computational properties. We apply these strategies to oil exploration over multiple prospects modeled by a directed acyclic graph, and to a reservoir drilling decision problem modeled by a Markov random field. The results show that the suggested strategies clearly improve the naive or myopic constructions used in petroleum industry today. This is useful for decision makers planning petroleum exploration policies.     

Static search games played over graphs and general metric spaces

We define a general game which forms a basis for modelling situations of static search and concealment over regions with spatial structure. The game involves two players, the searching player and the concealing player, and is played over a metric space. Each player simultaneously chooses to deploy at a point in the space; the searching player receiving a payoff of 1 if his opponent lies within a predetermined radius r of his position, the concealing player receiving a payoff of 1 otherwise. The concepts of dominance and equivalence of strategies are examined in the context of this game, before focusing on the more specific case of the game played over a graph. Methods are presented to simplify the analysis of such games, both by means of the iterated elimination of dominated strategies and through consideration of automorphisms of the graph. Lower and upper bounds on the value of the game are presented and optimal mixed strategies are calculated for games played over a particular family of graphs.