Search

General Electric Company (GE) partnered with Norfolk Southern Railroad (NS) to create and implement an optimization algorithm-based software system that dispatches thousands of trains in real time, increases their average speed, and allows NS to realize annual savings in the hundreds of millions of dollars. NS handles a range of rail traffic that includes intermodal, automobile transport, manifest freight, and passenger, all with unique priorities and scheduling requirements. Previously, dispatching for each geographic area was managed manually from regional dispatch centers and did not encompass a view of the entire rail network. The algorithm that we developed incorporates data about the properties of the rail networks (e.g., track layout, speed restrictions, height and weight restrictions), data about the trains (e.g., schedules, operating costs, train characteristics), and additional activities associated with train dispatching, such as crew changes and inspections. In doing so, we created a novel system to manage all train dispatching, increased the average speed of trains by two miles per hour, and decreased operating costs, while significantly improving schedule adherence and crew expirations. Every mile-per-hour increase in average speed translates to $200 million savings in capital and operational expenses annually for NS. GE is currently implementing this system at two other railroads and is gaining additional important benefits from the project. Keywords: train dispatch * movement planner * meet-pass planner * computer-aided dispatching * autorouter * train scheduling, Introduction Each of the seven major railroads in North America (called the Class I railroads) owns between 20,000 and 50,000 miles of track and runs approximately 1,000 to 2,500 trains [...]

A novel grid-stitching algorithm has been developed for generating Cartesian-like grids for viscous flow calculations. A grid is generated by recursive division of Cartesian cells. Unlike the conventional Cartesian-mesh calculations that involve unit aspect ratio cells, stretching is used to get the high aspect ratio cells and smooth grid near the body. The grid data are collected in an unstructured format. This novel approach, along with an unstructured mesh-based flow solver (HIFUN-2D, developed in-house), has been successfully used for numerical simulations. This grid is successfully used for Euler and laminar flow computations. Partial success has been achieved for turbulent flow simulations. DOI: 10.2514/1.27854

We apply random graph modeling methodology to analyze bipartite consumer-product graphs that represent sales transactions to better understand consumer purchase behavior in e-commerce settings. Based on two real-world e-commerce data sets, we found that such graphs demonstrate topological features that deviate significantly from theoretical predictions based on standard random graph models. In particular, we observed consistently larger-than-expected average path lengths and a greater-than-expected tendency to cluster. Such deviations suggest that the consumers' product choices are not random even with the consumer and product attributes hidden. Our findings provide justification for a large family of collaborative filtering-based recommendation algorithms that make product recommendations based only on previous sales transactions. By analyzing the simulated consumer-product graphs generated by models that embed two representative recommendation algorithms, we found that these recommendation algorithm-induced graphs generally provided a better match with the real-world consumer-product graphs than purely random graphs. However, consistent deviations in topological features remained. These findings motivated the development of a new recommendation algorithm based on graph partitioning, which aims to achieve high clustering coefficients similar to those observed in the real-world e-commerce data sets. We show empirically that this algorithm significantly outperforms representative collaborative filtering algorithms in situations where the observed clustering coefficients of the consumer-product graphs are sufficiently larger than can be accounted for by these standard algorithms. Key words: random graph theory; consumer-purchase behavior; topological features; recommender systems; collaborative filtering, 1. Introduction The past few years we have witnessed dramatic growth in research using random graph theory to study complex systems in a wide variety of scientific, engineering, and social [...]

To link to full-text access for this article, visit this link: http://dx.doi.org/10.1016/j.ejor.2005.03.062 Byline: Hanene Azzag (a), Gilles Venturini (a), Antoine Oliver (a), Christiane Guinot (a)(b) Keywords: Metaheuristics; Internet; Evolutionary computation; Artificial ants; Multi-agent systems Abstract: In this paper is presented a new model for data clustering, which is inspired from the self-assembly behavior of real ants. Real ants can build complex structures by connecting themselves to each others. It is shown is this paper that this behavior can be used to build a hierarchical tree-structured partitioning of the data according to the similarities between those data. Several algorithms have been detailed using this model (called AntTree): deterministic or stochastic algorithms that may use or not global or local thresholds. Those algorithms have been evaluated using artificial and real databases. Our algorithms obtain competitive results when compared to the Kmeans, to ANTCLASS, and to Ascending Hierarchical Clustering. AntTree has been applied to three real world applications: the analysis of human healthy skin, the on-line mining of web sites usage, and the automatic construction of portal sites. Author Affiliation: (a) Laboratoire d'Informatique, Ecole Polytechnique de l'Universite de Tours, 64 avenue Jean Portalis, 37200 Tours, France (b) CE.R.I.E.S., 20, Rue Victor Noir, 92521 Neuilly-sur-Seine, Cedex, France Article History: Received 6 April 2004; Accepted 23 March 2005

Based on the stator-flux-oriented electromechanical model of a doubly fed induction machine (DFIM), this paper presents two different approaches to wind farm modeling. Particularly, the overall control system of the DFIM is modeled in detail, so that tuning equations that allow adjusting the parameters of its proportional-integral (PI) compensators straightforwardly are provided. In addition to validating the wind generator model proposed, experimental tests carried out on a 660-kW doubly fed induction generator (DFIG) prove that such a control system makes it possible to govern separately its stator-side or net active and reactive powers. The two wind farm models proposed, which are assumed to be made up of DFIM type generators exclusively, are mainly devised to assist the design and test of closed-loop control algorithms for the wind farm total power factor. They generally imply significantly different computational loads, so that the second may be regarded as a simplified version of the first one. The net active and reactive power performances of both wind farm models are finally compared via simulation, which allows identifying the stronger and weaker points associated to each model. Index Terms--Active power, doubly fed induction generators (DFIGs), pole assignment, reactive power, simplified model, vector control, wind farms, wind power generation.

In this paper, an adaptive self-tuning speed control for a permanent-magnet synchronous motor (PMSM) drive with dead time is proposed. Firstly, to equivalently place the dead time element outside the closed-loop speed control, a dead time compensator (DTC), based on the Smith predictor and a self-tuning proportional-integral model-following controller (ST-PI-MFC) is proposed. The model-following error is used to adaptively update the gains of the ST-PI-MFC via the affine projection algorithm (APA). Secondly, a disturbance observer, based on the time delay control (TDC) approach is used for torque feed forward control. The system's model is greatly simplified when the disturbance observer is combined with the motor. Relying on the simplified model, a natural adaptive observer is used to estimate the motor speed. Unknown motor parameters are estimated by minimizing the state estimation error using an iterative gradient algorithm offered by the affine projection. The estimated parameters are used to update the gains of the integral-proportional (IP) servo loop controller, the disturbance observer and the Smith model. The validity and usefulness of the proposed control scheme are verified through simulation and experimental results. Index Terms--Adaptive control, dead time, permanent-magnet synchronous motor.

Monitoring of water consumption in irrigation systems has become increasingly important for water managers in the actual trend of integrated water management. Low spatial resolution (LSR) satellite remote sensing has already proven the capacity of monitoring evapotranspiration (ETa) over large areas at high temporal frequencies, by which monitoring for large irrigation systems can be satisfied. However, smaller pixel size is still required for more local management while keeping the return period within a few days. High spatial resolution (HSR) satellite imagery is indeed available for calculation of ETa and has already been used in many studies. However, its practical return period is a major drawback to its implementation for monitoring irrigation systems. This paper is perusing into the use of genetic algorithms to assimilate parameters of an agrohydrological model called soil-water-air-plant for each of the pixels of HSR images contained into one single pixel of an LSR multitemporal image. The methodology developed and experimented here is trying to take advantage of the spatial content of HSR images and the temporal content of LSR images by fusing them by the process of data assimilation. Index Terms--Data assimilation, data fusion, evapotranspiration (ETa), genetic algorithm (GA), soil-water-air-plant (SWAP) model.

This paper introduces a semisupervised classification method that exploits both labeled and unlabeled samples for addressing ill-posed problems with support vector machines (SVMs). The method is based on recent developments in statistical learning theory concerning transductive inference and in particular transductive SVMs (TSVMs). TSVMs exploit specific iterative algorithms which gradually search a reliable separating hyperplane (in the kernel space) with a transductive process that incorporates both labeled and unlabeled samples in the training phase. Based on an analysis of the properties of the TSVMs presented in the literature, a novel modified TSVM classifier designed for addressing ill-posed remote-sensing problems is proposed. In particular, the proposed technique: 1) is based on a novel transductive procedure that exploits a weighting strategy for unlabeled patterns, based on a time-dependent criterion; 2) is able to mitigate the effects of suboptimal model selection (which is unavoidable in the presence of small-size training sets); and 3) can address multiclass cases. Experimental results confirm the effectiveness of the proposed method on a set of ill-posed remote-sensing classification problems representing different operative conditions. Index Terms--Ill-posed problems, labeled and unlabeled patterns, machine learning, remote sensing, semisupervised classification, support vector machines (SVMs), transductive inference.

This paper presents a nonrigid two-dimensional/three-dimensional (2-D/3-D) registration framework and its phantom validation for subject-specific bronchoscope simulation. The method exploits the recent development of five degrees-of-freedom miniaturized catheter tip electromagnetic trackers such that the position and orientation of the bronchoscope can be accurately determined. This allows the effective recovery of unknown camera rotation and airway deformation, which is modelled by an active shape model (ASM). ASM captures the intrinsic variability of the tracheo-bronchiai tree during breathing and it is specific to the class of motion it represents. The method reduces the number of parameters that control the deformation, and thus greatly simplifies the optimisation procedure. Subsequently, pq-based registration is performed to recover both the camera pose and parameters of the ASM. Detailed assessment of the algorithm is performed on a deformable airway phantom, with the ground truth data being provided by an additional six degrees-of-freedom electromagnetic (EM) tracker to monitor the level of simulated respiratory motion. Index Terms--Nonrigid two-dimensional/three-dimensional (2-D/3-D) registration, respiratory motion, simulation, virtual bronchoscopy, virtual endoscope.