Search results for "Algorithm"

Online Sparse Collapsed Hybrid Variational-Gibbs Algorithm for Hierarchical Dirichlet Process Topic Models

2017

Topic models for text analysis are most commonly trained using either Gibbs sampling or variational Bayes. Recently, hybrid variational-Gibbs algorithms have been found to combine the best of both worlds. Variational algorithms are fast to converge and more efficient for inference on new documents. Gibbs sampling enables sparse updates since each token is only associated with one topic instead of a distribution over all topics. Additionally, Gibbs sampling is unbiased. Although Gibbs sampling takes longer to converge, it is guaranteed to arrive at the true posterior after infinitely many iterations. By combining the two methods it is possible to reduce the bias of variational methods while …

A Lightweight Network Discovery Algorithm for Resource-constrained IoT Devices

2019

Although quite simple, existing protocols for the IoT suffer from the inflexibility of centralized infrastructures and require several configuration stages. The implementation of these protocols is often prohibitive on resource-constrained devices. In this work, we propose a distributed lightweight implementation of network discovery for simple IoT devices. Our approach is based on the exchange of symbolic executable code among nodes. Based on this abstraction, we propose an algorithm that makes even IoT resource-constrained nodes able to construct the network topology graph incrementally and without any a priori information about device positioning and presence. The minimal set of executab…

A genetic algorithm for combined topology and shape optimisations

2003

A method to find optimal topology and shape of structures is presented. With the first the optimal distribution of an assigned mass is found using an approach based on homogenisation theory, that seeks in which elements of a meshed domain it is present mass; with the second the discontinuous boundaries are smoothed. The problem of the optimal topology search has an ON/OFF nature and has suggested the employment of genetic algorithms. Thus in this paper a genetic algorithm has been developed, which uses as design variables, in the topology optimisation, the relative densities (with respect to effective material density) 0 or 1 of each element of the structure and, in the shape one, the coord…

TWO-LANE TRAFFIC WITH PLACES OF OBSTRUCTION TO TRAFFIC

2004

As the Nagel–Schreckenberg model (NaSch model) became known as a realistic approach to describe traffic flow on single-lane streets, this model was extended to two-lane traffic by several groups. On the base of our two-lane model, we will now investigate the impact of a place of obstruction, e.g., because of road works, on partial fractions, densities and mean velocities.

Traffic fundamentals for A22 Brenner freeway by microsimulation models.

La tesi di dottorato ha avuto come tema lo studio e l’applicazione di un modello di micro-simulazione del traffico in ambito autostradale. Essa si compone di quattro capitoli, con ognuno dei quali si è voluto sintetizzare e descrivere il lavoro di studio e ricerca svolto durante il suddetto corso di Dottorato di Ricerca. L’obiettivo principale del presente lavoro di tesi è stato quello di mettere a punto una metodologia finalizzata all’ottenimento delle relazioni fondamentali di deflusso in ambito autostradale attraverso il software di microsimulazione del traffico Aimsun. Come risulta infatti noto dalla letteratura scientifica, le relazioni fondamentali del deflusso sono utilizzate nel cam…

Capacity-based calculation of passenger car equivalents using traffic simulation at double-lane roundabouts

2018

Abstract Calculation of passenger car equivalents for heavy vehicles represents the starting point for the operational analysis of road facilities and other traffic management applications. This paper introduces a criterion to find the passenger car equivalents that reflect traffic conditions at double-lane roundabouts, where the capacity is typically estimated for each entry lane. Based on the equivalence defined by the proportion of capacity used by vehicles of different classes, the criterion implies a comparison between the capacity that would occur with a traffic demand of passenger cars only and the capacity reached beginning from a demand with a certain percentage of heavy vehicles. …

Estimation of significant solvent concentration ranges and its application to the enhancement of the accuracy of gradient predictions.

2004

Abstract The solvent concentration range actually useful for gradient predictions is significantly narrower than the total range scanned in a gradient run. This range, called “solvent informative range” (SIR), if known with the highest accuracy, allows to predict gradient retention times ( t g ) with minimal error. The small size of the SIR supports the application of the linear solvent strength theory (LSST). Furthermore, LSST allows a closed-form solution to the integral required to predict gradient retention times, which eliminates numerical integration, needed with other retention models. A methodology that calculates the SIR by applying error analysis, and uses it to improve the accura…

Ultimate Order Statistics-Based Prototype Reduction Schemes

2013

Published version of a chapter in the book: AI 2013: Advances in Artificial Intelligence. Also available from the publisher at: http://dx.doi.org/10.1007/978-3-319-03680-9_42 The objective of Prototype Reduction Schemes (PRSs) and Border Identification (BI) algorithms is to reduce the number of training vectors, while simultaneously attempting to guarantee that the classifier built on the reduced design set performs as well, or nearly as well, as the classifier built on the original design set. In this paper, we shall push the limit on the field of PRSs to see if we can obtain a classification accuracy comparable to the optimal, by condensing the information in the data set into a single tr…

Multilayer neural networks: an experimental evaluation of on-line training methods

2004

Artificial neural networks (ANN) are inspired by the structure of biological neural networks and their ability to integrate knowledge and learning. In ANN training, the objective is to minimize the error over the training set. The most popular method for training these networks is back propagation, a gradient descent technique. Other non-linear optimization methods such as conjugate directions set or conjugate gradient have also been used for this purpose. Recently, metaheuristics such as simulated annealing, genetic algorithms or tabu search have been also adapted to this context.There are situations in which the necessary training data are being generated in real time and, an extensive tr…

Learning the structure of HMM's through grammatical inference techniques

2002

A technique is described in which all the components of a hidden Markov model are learnt from training speech data. The structure or topology of the model (i.e. the number of states and the actual transitions) is obtained by means of an error-correcting grammatical inference algorithm (ECGI). This structure is then reduced by using an appropriate state pruning criterion. The statistical parameters that are associated with the obtained topology are estimated from the same training data by means of the standard Baum-Welch algorithm. Experimental results showing the applicability of this technique to speech recognition are presented. >