- Paolo Avesani; Anna Perini,Sistemi informativi territoriali e applicazioni verticali,In questo documento si presenta una breve rassegna di due categorie di prodotti software: un primo insieme che comprende gli strumenti per la realizzazione di sistem informativi territoriali, un secondo insieme che contempla le applicazioini verticali per supportare le attività di prevenzione in materia di protezione civile. Tale rassegna è mirata a guidare la scelta del software più idoneo a realizzare un sistema informativo per la gestione dei piano di emergenza comunale per il rischio idrogeologico, sistema che è in corso di progettazione presso il dipartimento di protezione civile della Provincia Autonoma di Trento,
- C. Casotto,Un algoritmo distribuito per l'interrogazione di basi di dati federate,
- Chiara Ghidini,A Semantics for Contextual Reasoning: Theory and Two Relevant Applications,Since McCarthy`s Turing Award speech, in 1971, the notion of context has been used in Artificial Intelligence to localize reasoning, in the sense that intelligent agents reasoning depends on the situation agents are embedded in, and on their cognitive state. A typical example is McCarthy`s above theory, in which, depending on context, the `same` theory, describing a blocks world, can be represented in two different ways with a different degree of generality. The emphasis on the role of context in localizing reasoning does not mean that there is no relation between reasoning performed in different contexts. In many applications of contexts, e.g. reasoning about beliefs, reasoning about viewpoints, integration of heterogeneous information, and multiagent systems, reasoning may involve many interacting contexts. Therefore a certain form of compatibility must exist between facts described in different contexts. This thesis aims at defining a semantics for contextual reasoning, called Local Models Semantics, that formalizes the role of context in localizing reasoning and the relations (compatibilities) among different contexts. Additionally we use tis semantics to formalize two relevant applications, that is, reasoning about beliefs and the integration of heterogeneous information in a federated database. By developing the theory of Local Models Semantics we pursue two objectives. First we aim to illustrate the intuitions underlying the use of context in reasoning. In addition we define a formal semantics for contextual reasoning which formalizes these intuitions. These objectives are accomplished by giving the basic definitions of model, satisfiability, and logical consequence. By applying Local Models Semantics to reasoning about beliefs we intend to provide evidence that our semantics provides enough modularity and flexibility to formalize agents with various introspective reasoning capabilities. Finally, by applying Local Models Semantics to the integration of information coming from heterogeneous databases, we intend to show that a precise formal semantics of a federation of databases can be defined by considering each database in the federation as a context and interactions between different databases as relations between contexts,
- Edmondo Trentin; Marco Gori,A Survey of Hibrid ANN/HMM Models for Automatic Speech Recognition,In spite of the advances accomplished throughout the last decades by a number of research teams, Automatic Speech Recognition (ASR) is still a challenging and difficult task. In particular, recognition systems based on hidden Markov models (HMMs) are effective under many circumstances, but do suffer from some major limitations that limit applicability of ASR technology in real-world environments. Attempts were made to overcome these limitations with the adoption of Artificial Neural Networks (ANN) as an alternative paradigm for ASR, but ANN were unsuccessful in dealing with long time-sequences of speech signals. Between the end of the Eighties and the beginning or the Nineties, some researchers began exploring a new research area, by combining HMMs and ANNs within a single, hybrid architecture. The goal in hybrid systems for ASR is to take advantage from the properties of both HMMs and ANNs, improving flexibility, hardware implementability and recognition performance. A variety of different architectures and novel training algorithms have been proposed in literature. This paper reviews a number of significant hybrid models for ASR. Early attempts to emulate HMMs by ANNs are briefly described. Them we focus on ANNs to estimate posterior probabilities of the states of an HMM and on 'global' optimization, where a single, overall training criterion is defined over the HMM and the ANNs, Connectionist Vector Quantization for discrete HMMs, and other more recent approaches are also reviewed, It is pointed out that, in addition to their theoretical interest, hybrid systems have been allowing for tangible improvements in recognition performance over the standard HMMs in difficult and significant benchmark tasks,
- Marco Aste; Massimo Boninsegna; M. Della Torre,Finding Perspective Projection and Stereo Localization mappings for a Multi-Camera System,This paper investigates the problem of finding the perspective projection and the stereo localization transforms for a binocular imaging system with long baseline. Neural techniques are used to estimate the geometrical mappings from a set of associations between points spread in the 3D space and their corresponding image projections. Aim of this work is to explore how neural networks can deal with acquisition noise and optical distorsions without considering complex camera models. Three techniques are experimentally compared: one based on the simple pin-hole camera model, a second purely based on neural function approximation, and a third which uses neural networks only to account for the deviations of the actual data from the pin-hole model predictions. Experiments have been performed on real data collected by a four-camera system placed in a laboratory room. Performance has been measured in terms of Euclidean distance between actual targets and estimated outputs on a validation and a test set. The results show the effectiveness of the neural approach and validate the combined use of pin-hole model and neural nets to a large extent. The generalization ability of the neural architectures has been finally investigated on a empirical basis,
- Roldano Cattoni; Alessandra Potrich,Bayesian Belief Networks: Introduction and Learning,Bayesian Belief Networks are graph-based representations of probability distributions. In the last decade they became popular for modeling and using uncertain knowledge in many and different contexts. In this paper an introduction to the framework and a review of the main issues related to learning Bayesian Belif Networks are presented. The first part focuses on the definition of the framework: the mathematical and representational properties are described and discussed as well as Belief Networks from data, a topic which received much attention recently. A large amount of works, approaches and methodologies proposed in the literature is surveyed,
- Francesco Ricci; Paolo Avesani,Workshop Italiano sul Ragionamento basato su Casi,
- Lorenzo Potrich,Metodi visivi per la caratterizzazione automatica del moto di bolle di aria in acqua,
- Alessandro Cimatti; Roberto Sebastiani,Servizi forniti dagli strati Safety Layer e Connection Manager,Obiettivo del presente documento è fornire una (proposta preliminare di) descrizione dei servizi forniti agli applicativi dagli strati Connection Manager (CM) e Safety Layer (SL), come perzialmente descritto nei documenti (1) e (3). Tale proposta è risultante della riunione in Ansaldo del 08-05-98 tra Ansaldo e Irst,
- Alessandro Cimatti; Roberto Sebastiani,Specifica formale dei protocolli Safety Layer e Connection Manager,Il presente documento descrive una specifica formale del protocollo di comunicazione tra applicativi in sicurezza basato su ridondanza. Il protocollo è stato suddiviso in due livelli separati, il Safety Layer (SL), come parzialmente descritto nei documenti (1) e (3), ed il Connection Manager (CM). Il S: e il CM sono stati specificati formalmente in SDL, e sono state applicate tecniche di validazione basate su simulazione esaustiva (model checking) attraverso il tool ObjectGEODE Nel presente documento vengono descritti i servizi forniti da tali livelli, e viene descritta la specifica formale delle macchine a stati che realizzano i livelli CM e SL. i dettagli del codice SDL sono descritti nel documento (6).,