Michel Ianotto

Scaling of Distributed Multi-simulations on Multi-core Clusters

DACCOSIM is a multi-simulation environment for continuous time systems, relying on FMI standard, making easy the design of a multi-simulation graph, and specially developed for multi-core PC clusters, in order to achieve speedup and size up. However, the distribution of the simulation graph remains complex and is still the responsibility of the simulation developer. This paper introduces DACCOSIM parallel and distributed architecture, and our strategies to achieve efficient multi-simulation graph distribution on multi-core clusters. Some performance experiments on two clusters, running up to 81 simulation components (FMU) and using up to 16 multi-core computing nodes, are shown. Performances measured on our faster cluster exhibit a good scalability, but some limitations of current DACCOSIM implementation are discussed.

Simulation of the grounding process in spoken dialog systems with Bayesian networks

User simulation has become an important trend of research in the field of spoken dialog systems because collecting and annotating real man-machine interactions with users is often expensive and time consuming. Yet, such data are generally required for designing and assessing efficient dialog systems. The general problem of user simulation is thus to produce as many as necessary natural, various and consistent interactions from as few data as possible. In this paper, is proposed a user simulation method based on Bayesian Networks (BN) that is able to produce consistent interactions in terms of user goal and dialog history but also to simulate the grounding process that often appears in human-human interactions. The BN is trained on a database of 1234 human-machine dialogs in the TownInfo domain (a tourist information application). Experiments with a state-of-the-art dialog system (REALL-DUDE/DIPPER/OAA) have been realized and promising results are presented.

Adaptive Prediction of Steel Hardness on Hot Strip Mill Using Neural Networks and K-Means Classifier

Abstract The hardness prediction system we describe in this paper is part of a force model adaptation strategy for hot strip mill. Prediction is performed using a neural network just before the finisher set-up. The training database is automatically actualized in order to adapt the neural networks. The actualization algorithm, based on k-means classifier, is designed to keep information about rare products and track the process and products evolutions as quickly as possible. The last part of the paper shows the performance of this on line system on the Dunkirk hot strip mill. Installation on other hot strip mills is planned for 2004.