Search

Recent advances in sensing, processing, and learning of physiological parameters, make the development of non-invasive health monitoring systems increasingly effective, especially in those situations that need particular attention to the usability of devices and software solutions due to the frailty of the target population. In this context, we developed a sensorized shoe that detects significant features in subjects' gait and monitors variations related to an intervention protocol in people affected by Neuromuscular Disorders (NMDs). This paper outlines the challenges in the field and summarizes the approach used to overcome the technological barriers related to connectivity, deployment, and usability that are typical in a medical setting. The proposed solution adopts the new paradigm offered by Web Bluetooth based on Bluetooth WebSocket. We show the architectural and deployment choices and how this solution can be easily adapted to different devices and scenarios.

With the diffusion of Web and Social Media, automatic user profiling classifiers applied to digital contents have become extremely important in application contexts related to social and forensic studies. In many research papers on this topic, an important part of the work is devoted to a costly manual "feature engineering" phase, where the semantic, syntactic, and often language-dependent features need to be accurately chosen to be relevant for profilation task. Differently from this approach, in this work we propose a Twitter user profiling classifier which exploits deep learning techniques to automatically generate user features being a) optimal for user profilation task, and b) able to fight covariance shift problem due to data distribution differences in training and test sets. In the best configuration found, the built system is able to achieve very interesting accuracy results on both English and Spanish languages, with an average final accuracy of more than 0.83.

Il documento contiene l'analisi dei requisiti del progetto e la definizione dei parametri biometrici/biomeccanici da rilevare, della piattaforma sensoristica necessaria, dell'interfaccia utente e il database per la memorizzazione delle informazioni.

Inspired by biological DNA, we model the behaviour of online users as "Digital DNA" sequences, introducing a strikingly novel, simple, and effective approach to discriminate between genuine and spambot online accounts.

The manual annotation of tweets is an essential task for the training of new algorithms based on those data. Unfortunately, conventional and consolidated automatic annotation systems that already exists are based and trained on documents where text is longer than 140 characters (the maximum length of a tweet) and the grammar is correct. Besides the length, tweets must be treated differently because they have peculiar characteristics, such as the presence of links, abbreviations, hashtags and mentions. To face the challenge of the linguistic annotation of tweets, we have created #tweeTag, a web­tool designed for a specific approach on tweets. The tool is able to annotate tweets in three different ways: (i) global annotation to bring out macro characteristics of the tweet, given context (e.g., if it is related to a certain phenomenon, if it is positive or negative etc.)? (ii) textual annotation to annotate the text of a tweet in order to identify information about the topic or content (e.g., whether describes various types of damage to property and/or people, etc)? (iii) timeline annotation to evaluate the credibility of a specific user through the analysis of its timeline. 1 #tweeTag has been developed in order to make it possible to run multiple annotation campaigns with different purposes in order to meet every need. Results show a usable and effective tool, with great potential for the near future. As this is a web application, #tweeTag could also be implemented as a crowdsourcing system.

The growing popularity of online platforms based on user-generated content is gradually creating a digital world that mirrors the physical world. In the paradigm of crowdsensing, the crowd becomes a distributed network of sensors that allows us to understand real life events at a quasi-real-time rate. The SoS - Social Sensing project (http://socialsensing.eu/) exploits the opportunistic crowdsensing, involving users in the sensing process in a minimal way, for social media emergency management purposes in order to obtain a very fast, but still reliable, detection of emergency dimension to face. First of all we designed and implemented a decision support system for the detection and the damage assessment of earthquakes. Our system exploits the messages shared in real-time on Twitter. For the detection phase, data mining and natural language processing techniques are firstly adopted to select meaningful and comprehensive sets of tweets. We then applied a burst detection algorithm in order to promptly identify outbreaking seismic events. By using georeferenced tweets and reported locality names, a rough epicentral determination is also possible. Results were compared to Italian INGV official reports and show that the system is able to detect, within seconds, events of a magnitude in the region of 3.5 with a precision of 75% and a recall of 81,82%. We then focused our attention on damage assessment phase. We investigated the possibility to exploit social media data to determine earthquake intensity. We designed a set of predictive linear models and evaluated their ability to map the intensity of worldwide earthquakes. The models build on a dataset of almost 5 million tweets exploited to compute our earthquake features, and more than 7,000 globally distributed earthquakes data, acquired in a semi-automatic way from USGS, serving as ground truth. We extracted 45 distinct features falling into four categories: profile, tweet, time and linguistic. We run diagnostic tests and simulations on generated models to assess their significance and avoid overfitting. Overall results show a correlation between the messages shared in social media and intensity estimations based on online survey data (CDI)

The AeroFototeca Nazionale (AFN) of Italian Ministry of Cultural Heritage in Rome maintains an extensive set of aerial photographs that constitute a large archive of memory of the Italian territory from the end of the XIX century to the end of XX century. Together the Institute of Informatics and Telematics of CNR in Pisa have signed an agreement to make the archive accessible via internet by developing a web 2.0 mashup application to display the evolution of the Italian Landscape.

The ABCD SW (Autistic Behavior & Computer-based Didactic software) project aims to design and develop didactic software for children in the low-functioning autism spectrum, according to the principles of Applied Behavior Analysis (ABA). ABA therapy is based on scientific principles: teaching by discrete levels, errorless interaction, teacher prompting, reinforcement, fading, shaping and analysis of data collected during the educational sessions to monitor the child?s progress. In this paper we describe the ABA didactic software component, illustrating and discussing design choices, showing system architecture and user interfaces, and describing future developments

The creation, customization, and maintenance of knowledgeresources are essential for fostering the full deployment ofLanguage Technologies. The de nition and re nement ofknowledge resources are time- and resource-consuming activities.In this paper we explore how the Wiki paradigmfor online collaborative content editing can be exploited togather massive social contributions from common Web usersin editing knowledge resources. We discuss the WikyotoKnowledge Editor, also calledWikyoto. Wikyoto is a collaborativeWeb environment that enables users with no knowledgeengineering background to edit the multilingual networkof knowledge resources exploited by KYOTO, a crosslingualtext mining system developed in the context of theKYOTO European Project.

Enhancing the development of multilingual resources is of utmost importance for use in computer applications. The need of ever growing resources for effective multilingual content processing has given impulse to a radical change in the perspective of language resource (LR) creation, structuring, exploitation and maintenance. The Web has played a key role in this process: indeed the possibility to access growing amounts of structured and unstructured data as well as the ease of creating and sharing contents between distributed communities of users have strongly affected the methodologies and techniques to bootstrap, enrich and access LRs. From static knowledge bases usually created and maintained by groups of experts and tailored to the specific exploitation contexts, LRs have turned into dynamic repositories of linguistic knowledge. Their content is usually easily accessible over the Web and often exploited aggregated and optimized on-the-fly by on-line information mining services. In this context, the adoption of standardized data formats to facilitate interoperability and data exchange is essential. Moreover, the creation and maintenance of these resources has taken great advantage from the possibility to harvest Web data in order to bootstrap or enrich them. Several new frameworks have been proposed to support access, search, integration and interoperability of "new generation" LRs. Wide distributed communities of Web users are more and more directly or indirectly involved in keeping language resources updated or in extending them. After a brief description of modern LRs, we focus our attention on two essential issues involving them: the need for standard formats that support interoperability in a distributed Web context and the possibility for the Web communities to collaboratively maintain and enrich these resources. In particular, we present the Italian WordNet (IWN) and its exploitation in the context of the KYOTO Project, as a real-world scenario where standardization, interlinking, enrichment as well as collaborative editing are put into practice.

In this paper we introduce the Wikyoto Knowledge Editor, the wiki Web-based environment where the multilingual and multicultural community of KYOTO users interacts to maintain and extend, with respect to their particular domain of interest, the background knowledge resources of the KYOTO system, constituting the Multilingual Knowledge Base. KYOTO is a knowledge-driven system for fact mining from a multilingual collection of information sources concerning a specific domain of interest. Facts are mined from relevant documents that are linguistically and semantically annotated exploiting the Multilingual Knowledge Base, made of several languagespecific WordNets all referred to a common Central Ontology.

Domain portability and adaptation of NLP components and Word Sense Disambiguation systems present new challenges. The difficulties found by supervised systems to adapt might change the way we assess the strengths and weaknesses of supervised and knowledge-based WSD systems. Unfortunately, all existing evaluation datasets for specific domains are lexical-sample corpora. This task presented all-words datasets on the environment domain for WSD in four languages (Chinese, Dutch, English, Italian). 11 teams participated, with supervised and knowledge-based systems, mainly in the English dataset. The results show that in all languages the participants where able to beat the most frequent sense heuristic as estimated from general corpora. The most successful approaches used some sort of supervision in the form of hand-tagged examples from the domain.

This paper reports prototype multilingual query expansion system relying on LMF compliant lexical resources. The system is one of the deliverables of a three-year project aiming at establishing an international standard for language resources which is applicable to Asian languages. Our important contributions to ISO 24613, standard Lexical Markup Framework (LMF) include its robustness to deal with Asian languages, and its applicability to cross-lingual query tasks, as illustrated by the prototype introduced in this paper.

Kyoto is a knowledge-driven system for fact mining from a multilingual collection of information sources concerning a specific domain of interest. Facts are mined from relevant documents that are linguistically and semantically annotated exploiting a Multilingual Knowledge Base, made of several language-specific WordNets all referred to a common Central Ontology. In this paper we introduce a core component of KYOTO, the Wikyoto Knoweldge Editor: it is the collaborative Web environment where the multilingual and multicultural community of KYOTO users interacts to maintain and extend, in respect to their particular domain of interest, the background knowledge of KYOTO, constituting the Multilingual Knowledge Base. After an overview of the most relevant examples of collaborative environments to manage knowledge resources, we briefly introduce KYOTO architecture to provide the global context to describe the Wikyoto Knowledge Editor. Thus we focus our attention on the description of the Wikyoto Knowledge Editor, introducing its purpose inside KYOTO, its architecture and its Web-based user interface. By mean of an example, we explain how KYOTO Multilingual Knowledge Base can be browsed and enriched by the Wikyoto Knowledge Editor both thanks to the suggestions provided by the terminology automatically mined from documents in KYOTO and by accessing other external Web resources, like DBpedia. We consider the first working prototype of the Wikyoto Knowledge Editor, implementing a core set of relevant features. In conclusion, we expose our future works summarizing all the features that are planned to be supported in the upcoming versions of the Wikyoto Knolwedge Editor.

We present KAF, the KYOTO Annotation Format. KAF is a layered and extendible linguistic annotation format that is specifically developed to arrive at semantic interoperability. KAF is used in seven languages in several applications throughout the KYOTO (Knowledge Yielding Ontologies for Transition-based Organization) project. The goal of these applications is to derive semantic data from linguistically processed text. Separate annotation layers are defined for each annotation process but these can be combined to arrive at a higher level of semantic representation. This paper gives an outline of KAF and a description of how it is applied in the KYOTO project.

The introduction of XML Markup from the first stages of production of Parliamentary Acts allows to make them easily manageable for further processing, thanks to the definition of some sort of logical structuring for their contents. To make it possible, we need document editors that enable users to effectively markup their texts, without making substantial changes in their usual interaction patterns. We present a Web-based editor of daily Italian Parliamentary Reports: it allows reporters to write parts of Parliamentary Sessions' speeches and easily structure them in accordance to a predefined XML Schema.

In this paper we present LexFlow, a framework for the automatic and cooperative enrichment, integration and exploitation of semantic resources. Borrowing from techniques used in the domain of document workflows, we model the activity of lexicon management as a particular case of workflow instance, where lexical entries move across agents and become dynamically updated. We also give an important exploitation example of the semantic resources managed or built thanks to LexFlow, describing its integration with SemKey, a system for semantic collaborative tagging.

By analysing the current structure and the usage patterns of collaborative tagging systems, we can find out many important aspects which still need to be improved. Problems related to synonymy, polysemy, different lexical forms, mispelling errors or alternate spellings, different levels of precision and different kinds of tag-to-resource association cause inconsistencies and reduce the efficiency of content search and the effectiveness of the tag space structuring and organization. They are mainly caused by the lack of semantic information inclusion in the tagging process. We propose a new way to describe resources: the semantic tagging. It allows user to state semantic assertions: each of them expresses a defined characteristic of a resource associating it with a concept. We present SemKey, a semantic collaborative tagging system, describing its global architecture and functioning along with the most relevant organizational issues faced. We explore the adequacy of the support offered by the entries of Wikipedia and WordNet in order to access to and reference concepts.

Collaborative tagging is a new content sharing and organization trend, mainly diffused over the Web, which has attracted growing attention during the last years. It refers to the process by which many users add metadata in the form of keywords to shared content. Today many different collaborative tagging systems are available on the Web, enabling users to add descriptive keywords to different types of Internet resources (web pages, photos, videos, etc.). The great number of advantages offered by the availability of collaboratively tagged resources in terms of their organization and shared information is also underlined by their growing adoption, also in non-technical communities of users. In spite of this, analyzing the actual structure and usage patterns of collaborative tagging systems, we can discover many important aspects which still need to be improved so as to bring tagging systems to their full potential. In particular, problems related to synonymy, polysemy and plural words represent a great limit, causing inconsistencies among the terms used in the tagging process and thus reducing the efficiency of content search and the effectiveness of the tag space structuring and organization. This kind of problems is mainly caused by the lack of semantic information inclusion in the tagging process. Considering the increasing attention focused on the Semantic Web, we propose a new model of tagging system, based on semantic keywords. We let the users easily define the meaning of their tags, referencing some sort of social ontology. As social ontology we explore the adequacy of the support offered by the entries of Wikipedia and WordNet. Finally we present a tool that allows users to tag in a semantic context, providing an evaluation of the system proposed in comparison with classical tagging tools.

Enhancing the development of multilingual lexicons is of foremost importance for intercultural collaboration to take place, as multilingual lexicons are the cornerstone of several multilingual applications. However, the development and maintenance of large-scale, robust multilingual dictionaries is a tantalizing task. In this paper we present a tool, based on a web service architecture, enabling semi-automatic generation of bilingual lexicons through linking of distributed monolingual lexical resources. In addition to lexicon development, the architecture also allows enrichment of monolingual source lexicons through exploitation of the semantic information encoded in corresponding entries. In the paper we describe our case study applied to the Italian and Chinese wordnets, and we illustrate how the architecture can be extended to access distributed multilingual WordNets over the Internet, paving the way to exploitation in a cross-lingual framework of the wealth of information built over the last decade.

Summary of the research activities involved in the development of a XML Schema for Brazilian Legislative atcs

In this paper we present an application fostering the integration and interoperability of computational lexicons, focusing on the particular case of mutual linking and cross-lingual enrichment of two wordnets, ItalWordNet and Sinica-BOW lexicons. This is intended as a case-study investingating the needs and requirements of semi-automatic integration and interoperability of lexical resources.

This demo presents LeXFlow, a workflow management system for cross-fertilization of computational lexicons. Borrowing from techniques used in the domain of document workflows, we model the activity of lexicon management as a set of workflow types, where lexical entries move across agents in the process of being dynamically updated. A prototype of LeXFlow has been implemented with extensive use of XML technologies (XSLT, XPath, XForms, SVG)and open-source tools (Cocoon, Tomcat, MySQL). LeXFlow is a web-based application that enables the cooperative and distributed management of computational lexicons.

Creare una presentazione significa mettere in sequenza i propri pensieri per presentarli in modo facilmente comprensibile. Questa operazione non proprio banale, che ha visto lo studio di psicologi, esperti della comunicazione, studiosi di interfaccia uomo macchina, ha una risposta: PowerPoint. La maggior parte delle presentazioni, anche quelle fatte da persone appartenenti al mondo scientifico, sono realizzate con questo strumento perché consente in modo semplice e rapido la creazione di effetti multimediali gradevoli e accattivanti Inoltre il tool è facilmente reperibile in quanto presente nel pacchetto MS Office (molto diffuso) ed il formato delle slide ppt è ormai uno standard de facto e spesso viene richiesto come formato con cui fornire le proprie presentazioni.

I sistemi di workflow coordinano tutte le operazioni che riguardano l'elaborazione e la trasmissione dei documenti, specificando le attività ed i ruoli di tutti gli appartenenti al processo di lavoro. Un document workflow segue un documento durante tutto il suo ciclo di vita, fornendo un'azione di controllo costante per la sua compilazione. Nello studio presentato si cerca di far luce sulle varie problematiche che sorgono quando si descrivono iter documentali. A tale proposito viene definito un modello concettuale che permette di descrivere in maniera dettagliata un iter documentale e tutte le attività che si possono effettuare sul documento. Per sviluppare il modello si è scelto di adottare la tecnologia XML, sia per strutturare i documenti che tutte le informazioni relative al flusso. Come agente si è intesa una qualsiasi entità, sia umana che software, capace di interagire con il documento, mentre con flusso di documenti si è inteso tutti i possibili percorsi che il documento stesso segue nel suo ciclo di vita, passando da un agente all'altro. Il flusso documentale viene descritto tramite un linguaggio dichiarativo attraverso l'elencazione di tutti gli agenti che partecipano al flusso, specificando tutte le operazioni che ogni agente può svolgere sull'istanza del documento. I documenti elaborati dai vari agenti hanno una struttura definita da uno schema XML e sono accompagnati per tutto il loro ciclo di vita da altri documenti, che contengono informazioni sul flusso, sui vincoli e sulla visualizzazione dei dati. Una particolare enfasi è data ai problemi relativi alla fusione di due o più documenti compilati da molteplici agenti in maniera concorrente. Per quanto concerne la progettazione di un sistema di gestione di workflow documentali, sono due le soluzioni architetturali analizzate: quella centralizzata e quella distribuita. Al fine di rappresentare graficamente i documenti da elaborare si utilizza il browser XSmiles, in grado di visualizzare documenti Xhtml con all'interno moduli XForms. Adoperando tecniche innovative, come XML-Signature, sono stati presi in esame tutti gli aspetti legati alla firma dei documenti modificati dagli agenti.