This paper presents an'elitist approach' for extracting au tomat-ically well-realized speech sounds with high confidence. Th e elitist approach uses a speech recognition system based on H id-den Markov Models (HMM). The HMM are trained on speech sounds which are systematically well-detected in an iterat ive procedure. The results show that, by using the HMM models defined in the training phase, the speech recognizer detects reliably specific speech sounds with a small rate of errors.

We consider the problem of on-line prediction of real-valued labels, assumed bounded in absolute value by a known constant, of new objects from known labeled objects. The prediction algorithm's performance is measured by the squared deviation of the predictions from the actual labels. No stochastic assumptions are made about the way the labels and objects are generated. Instead, we are given a benchmark class of prediction rules some of which are hoped to produce good predictions. We show that for a wide range of infinite-dimensional benchmark classes one can construct a prediction algorithm whose cumulative loss over the first N examples does not exceed the cumulative loss of any prediction rule in the class plus O(sqrt(N)); the main differences from the known results are that we do not impose any upper bound on the norm of the considered prediction rules and that we achieve an optimal leading term in the excess loss of our algorithm. If the benchmark class is "universal" (dense in the class of continuous functions on each compact set), this provides an on-line non-stochastic analogue of universally consistent prediction in non-parametric statistics. We use two proof techniques: one is based on the Aggregating Algorithm and the other on the recently developed method of defensive forecasting.

Research on integrated neural-symbolic systems has made si gnificant progress in the recent past. In particular the understanding of ways t o deal with symbolic knowledge within connectionist systems (also cal led artificial neural networks) has reached a critical mass which enables the c ommunity to strive for applicable implementations and use cases. Recen t work has covered a great variety of logics used in artificial intelligenc e and provides a multitude of techniques for dealing with them within the con text of artificial neural networks. Already in the pioneering days of computational models of ne ural cognition, the question was raised how symbolic knowledge can be r epresented and dealt with within neural networks. The landmark paper [M cCulloch and Pitts, 1943] provides fundamental insights how propositional logic can be processed using simple artificial neural networks. Within the following decades, however, the topic did not receive much attention as research in artifi cial intelligence initially focused on purely symbolic approaches. The power of machine learning using artificial neural networking was not recogni zed until the 80s, when in particular the backpropagation algorithm [Rumelha rt et al., 1986] made connectionist learning feasible and applicable in pra ctice. These advances indicated a breakthrough in machine learnin g which quickly led to industrial-strength applications in areas s uch as image analysis, speech and pattern recognition, investment analysis, engine monitoring, fault diagnosis, etc. During a training process from raw dat a, artificial neural networks acquire expert knowledge about the problem dom ain, and the ability to generalize this knowledge to similar but previou sly unencountered situations in a way which often surpasses the abilities of hu man experts.

Evolutionary computing (EC) is an exciting development in Computer Science. It amounts to building, applying and studying algorithms based on the Darwinian principles of natural selection. In this paper we briefly introduce the main concepts behind evolutionary computing. We present the main components all evolutionary algorithms (EA), sketch the differences between different types of EAs and survey application areas ranging from optimization, modeling and simulation to entertainment.

This paper presents an artificial evolution-based method for stereo image analysis and its application to real-time obstacle detection and avoidance for a mobile robot. It uses the Parisian approach, which consists here in splitting the representation of the robot's environment into a large number of simple primitives, the "flies", which are evolved following a biologically inspired scheme and give a fast, low-cost solution to the obstacle detection problem in mobile robotics.

The aim of our study is to detect balance disorders and a tendency towards the falls in the elderly, knowing gait parameters. In this paper we present a new tool for gait analysis based on markerless human motion capture, from camera feeds. The system introduced here, recovers the 3D positions of several key points of the human body while walking. Foreground segmentation, an articulated body model and particle filtering are basic elements of our approach. No dynamic model is used thus this system can be described as generic and simple to implement. A modified particle filtering algorithm, which we call Interval Particle Filtering, is used to reorganise and search through the model's configurations search space in a deterministic optimal way. This algorithm was able to perform human movement tracking with success. Results from the treatment of a single cam feeds are shown and compared to results obtained using a marker based human motion capture system.

Automobile has become the dominant transport mode in the world in the last century. In order to meet a continuously growing demand for transport, one solution is to change the control approach for vehicle to full driving automation, which removes the driver from the control loop to improve efficiency and reduce accidents. Recent work shows that there are several realistic paths towards this deployment : driving assistance on passenger cars, automated commercial vehicles on dedicated infrastructures, and new forms of urban transport (car-sharing and cybercars). Cybercars have already been put into operation in Europe, and it seems that this approach could lead the way towards full automation on most urban, and later interurban infrastructures. The European project CyberCars has brought many improvements in the technology needed to operate cybercars over the last three years. A new, larger European project is now being prepared to carry this work further in order to meet more ambitious objectives in terms of safety and efficiency. This paper will present past and present technologies and will focus on the future developments.

This report describes a new version of the OntoSpec methodology for ontology building. Defined by the LaRIA Knowledge Engineering Team (University of Picardie Jules Verne, Amiens, France), OntoSpec aims at helping builders to model ontological knowledge (upstream of formal representation). The methodology relies on a set of rigorously-defined modelling primitives and principles. Its application leads to the elaboration of a semi-informal ontology, which is independent of knowledge representation languages. We recently enriched the OntoSpec methodology by endowing it with a new resource, the DOLCE top-level ontology defined at the LOA (IST-CNR, Trento, Italy). The goal of this integration is to provide modellers with additional help in structuring application ontologies, while maintaining independence vis-à-vis formal representation languages. In this report, we first provide an overview of the OntoSpec methodology's general principles and then describe the DOLCE re-engineering process. A complete version of DOLCE-OS (i.e. a specification of DOLCE in the semi-informal OntoSpec language) is presented in an appendix.

Extraction of association rules is widely used as a data mining method. However, one of the limit of this approach comes from the large number of extracted rules and the difficulty for a human expert to deal with the totality of these rules. We propose to solve this problem by structuring the set of rules into hierarchy. The expert can then therefore explore the rules, access from one rule to another one more general when we raise up in the hierarchy, and in other hand, or a more specific rules. Rules are structured at two levels. The global level aims at building a hierarchy from the set of rules extracted. Thus we define a first type of rule-subsomption relying on Galois lattices. The second level consists in a local and more detailed analysis of each rule. It generate for a given rule a set of generalization rules structured into a local hierarchy. This leads to the definition of a second type of subsomption. This subsomption comes from inductive logic programming and integrates a terminological model.

Preference queries are relational algebra or SQL queries that contain occurrences of the winnow operator ("find the most preferred tuples in a given relation"). Such queries are parameterized by specific preference relations. Semantic optimization techniques make use of integrity constraints holding in the database. In the context of semantic optimization of preference queries, we identify two fundamental properties: containment of preference relations relative to integrity constraints and satisfaction of order axioms relative to integrity constraints. We show numerous applications of those notions to preference query evaluation and optimization. As integrity constraints, we consider constraint-generating dependencies, a class generalizing functional dependencies. We demonstrate that the problems of containment and satisfaction of order axioms can be captured as specific instances of constraint-generating dependency entailment. This makes it possible to formulate necessary and sufficient conditions for the applicability of our techniques as constraint validity problems. We characterize the computational complexity of such problems.