Domenico Soldo

Dialogue-oriented interface for linguistic human-computer interaction: A chat-based application

This work presents a prototype conversational system enabling human-computer interaction by using natural language expression. As an enhancement to well-known conversational agents like chatbots, in the proposed setting, human-machine dialogue is intended as a query/answer monotonic process aimed at minimizing semantic ambiguity within communication and delivering the required service. When user queries are ambiguous, hence semantically distant from the set of possible recognized interpretations, the system instantiates a dialogue with the user. In this case, the system provides suggestions on how to reformulate the query until a valid form is reached; this feed-back makes the dialogue-oriented interaction process resemble an ordinary chat (in the very restricted domain of system services) but with a machine interlocutor. The popularity of the chat as a synchronous communication instrument lets our proposal be suitable for a great variety of applications.

A semantic lexicon-based approach for sense disambiguation and its WWW application

This work proposes a basic framework for resolving sense disambiguation through the use of Semantic Lexicon, a machine readable dictionary managing both word senses and lexico-semantic relations. More specifically, polysemous ambiguity characterizing Web documents is discussed. The adopted Semantic Lexicon is WordNet, a lexical knowledge-base of English words widely adopted in many research studies referring to knowledge discovery. The proposed approach extends recent works on knowledge discovery by focusing on the sense disambiguation aspect. By exploiting the structure of WordNet database, lexico-semantic features are used to resolve the inherent sense ambiguity of written text with particular reference to HTML resources. The obtained results may be extended to generic hypertextual repositories as well. Experiments show that polysemy reduction can be used to hint about the meaning of specific senses in given contexts.

Semantic Lexicon-Based Multi-agent System for Web Resources Markup

A hierarchical multi-agent system that exploits one (or more) Semantic Lexicon for performing semantic markup of Web resources is presented. Semantic Lexicon is considered here as a golden ontology defining taxonomical relations among concepts such as hypernymy, meronymy, holonymy and so forth. The system attempts to annotate Web resources according to the available taxonomical relations using simple annotation schemes. The system is completely autonomous if the chosen golden ontology is provided by linguistic experts as it happens for WordNet. The proposed conceptual architecture has been applied to real-world scenarios for test purposes, obtaining promising results.

Online wastewater monitoring system using solid state sensor

Water and wastewater monitoring management is a task of paramount importance for the environmental control operations in the framework of the Adaptive Water Management policies enforced by the current EU legislation. Water resources management, on one side, and efficient water/wastewater treatment and control operations, on the other, must be carried-out timely and synergistically for best results. It is well known that conventional field sampling operations condition significantly data reliability from both qualitative and quantitative aspects. To overcome this problem, speditive field analysis, carried-out by the use of low-cost devices with solid-state gas sensors (e-nose), may offer a solution to the sampling, transport and deferred laboratory operations. The proposed devices do not require consumable and may be easily connected to data acquisition network.

M-DUST: An innovative low-cost smart PM sensor

In this work, we present M-DUST, a novel low-cost and real-time smart monitoring sensor for Particulate Matter (PM) emission measurement. It is based on the Tyndall scattering process to count particle concentration about solid aerosol (e.g., smoke, dust, etc.). A comparison on different methods to evaluate particle concentration has been discussed. A mechanical filter is used to select the particulate matter with the appropriate cut-off aerodynamic diameter. The presented device is an intelligent sensor thanks to its features, such as: ability to make self-diagnosis, self-adaptation and transparency to communication interface. Tests are carried out in the Italian city of Taranto.

On designing task-oriented intelligent interfaces: an e-mail based design framework

This paper presents a design framework for building intelligent interfaces using e-mails to dialogue with human users in task-oriented settings. In particular, the proposed approach is pursued from the pattern matching standpoint. Human-computer interaction (HCI) is faced as a classification process where the input data is represented by the user query written in natural language and the output is represented by the most likely classes of system services with a certain degree of match. In case of partial matching, the system instantiates a dialogue with the human user, attempting to disambiguate the meaning of the written text in the context of system services. A case study is reported and preliminary results are commented.

A Multi Agent System Modelling an Intelligent Transport System

Nowadays, the globalization is one of the most significant phenomena of contemporary life. There are many debates about the real meaning of the globalization, its roots, effects and future. Among the most important aspects of the globalization is surely the global transportation system. In this framework it is clear how the availability of an advanced integrated transportation system, for moving goods and people as quickly as possible all around the world, is a crucial requirement that cannot be ignored in any case, but actually accomplished in the best way possible. In (Frank and Engelke, 2000) there is a remarkable work of review highlighting the steady interaction between transportation systems and human activities and how the former ones have a strong impact on the organization of the built environment. These ideas give explanation for the increasing interest that the scientific community has shown in the field of the transportation systems. The recent improvements in ICT allow for the implementation of novel and pervasive systems. Indeed, in these days a wide spread of the Global Position System (GPS) and communication technologies (e.g. GSM, GPRS and UMTS network) has led to the implementation of interesting Intelligent Transportation System (ITS). These systems try to improve the optimization of many transportation system aspects such as vehicles, loads, routes and (overall) safety just by using these new technologies. Route planning is an optimization problem that has been studied extensively in the past decades. Dijkstra’s algorithm (Dijkstra, 1959) is the most well-known algorithm for determining the shortest path from one location to all other locations in a road network. Moreover it is noteworthy to mention other significant shortest path algorithms e, such as the Bellman-Ford algorithm (Bellman, 1958; Ford Jr. and Fulkerson, 1962), the D’Esopo-Pape algorithm (Pape, 1974), etc. An overview in this regard is given by (Bertsekas, 1998). One of the biggest problems of these algorithms is the huge dimension of the solution space. This fact led the researchers to use parallel computing (Delle Donne et al., 1995) and/or to propose new heuristic methods often based on artificial intelligence techniques (Suzuki et al., 1995; Pellazar, 1998).

Electronic nose for evaluating water use in beer production

This paper is focused on the results of the research project simBART. Particular attention is paid on a method for water evaluation in beer production sector. This process, under investigation, can be targeted to small and not industrialised enterprises as well as to those home brewing productions. Experimental analyses are conducted by means of VPeN, a vapour phase e-nose based on a specific sensor array. Six kinds of Italian mineral water and one type of demineralised water were taken into account in order to carry out the related tests. A comparison among signatures produced by the analysed methodology in function of each sample was realized just to produce the classification of those kinds of water, which resulted to be the most appropriate ones for specific beer production.

Social isolation monitoring system via AI approach

H2020 policy objectives are mainly oriented to social inclusion, in this regard, particular attention is given to better public services for seniors. Due to the high costs of hospitalization, the home care as well as specialized training should be preferable both for reducing public expenditure and improving the physical and psychological well-being of elderly people. In this paper an ICT tool for elderly people (or peoples with psychic, sensory, neuromotor and disabilities) is presented. Aim of this tool is to form a bridge between senior citizen and new technologies, thus overcoming the well-known rejection of “technology with unknown implications”. At the same time the presented tool is suitable to identify variations of the senior ability while doing specific actions just for by evaluating a social isolation parameter.

Dialogue disambiguation in Living Labs experience the Puglia Tremor system

The Living Lab idea was conceived by William Mitchell at MIT and since 2006 also Europe Union has been joining the living lab experience. In August 2011, the Regional Government of Apulia included Living Labs and Pre-commercial public procurement in their existing Operational Program of European Regional Development Fund. Hereinafter the project called “Puglia Tremor” is presented by focusing the attention on web based dialogue among living labs actors. This project represents one possible answer to the regional call and a proposal to future experience and further development of best practices. An innovative text disambiguation system is presented in order to overcome the well-known gap in human-computer interaction. Thanks to the proposed system the unskilled-user and public operators will be able to communicate using a web 2.0 approach.