2014
Conference article
Open Access
Going beyond research communication and management current practices
Castelli D
This key note presentation discusses the impact of data-driven science in the research "landscape" and describes the functionality of the OpenAIRE infrastructure for research.Project(s): OPENAIREPLUS
Castelli D
This key note presentation discusses the impact of data-driven science in the research "landscape" and describes the functionality of the OpenAIRE infrastructure for research.Project(s): OPENAIREPLUS
See at:
CNR IRIS 
| www.cris2014.org | CNR IRIS 
2014
Conference article
Open Access
Visual media for Cultural Heritage: an opportunity for assessing, finding limitations and enhancing technologies
Scopigno R
Digital technologies are now mature for producing high quality digital replicas of Cultural Heritage (CH) artifacts. The research results produced in the last two decades have shown an impressive evolution and consolidation of the technologies for acquiring high-quality digital 3D models, encompassing both geometry and color (or, better, surface reflectance properties); technologies for the interactive visualisation of complex models and the integration of different media have been also an important subject of research. In this talk, I will present the more recent progresses, focusing on practical solutions which aim at a major impact in real applications. The talk will also try to give a glance into the near future, demonstrating how geometry processing and visualization could become a major instrument in the study and dissemination of our cultural heritage.
Scopigno R
Digital technologies are now mature for producing high quality digital replicas of Cultural Heritage (CH) artifacts. The research results produced in the last two decades have shown an impressive evolution and consolidation of the technologies for acquiring high-quality digital 3D models, encompassing both geometry and color (or, better, surface reflectance properties); technologies for the interactive visualisation of complex models and the integration of different media have been also an important subject of research. In this talk, I will present the more recent progresses, focusing on practical solutions which aim at a major impact in real applications. The talk will also try to give a glance into the near future, demonstrating how geometry processing and visualization could become a major instrument in the study and dissemination of our cultural heritage.
See at:
CNR IRIS | www.cescg.org | CNR IRIS
2014
Conference article
Restricted
Oil spills detection through a marine environment monitoring system
Moroni D, Pieri G, Salvetti O, Tampucci M
The ability to detect and monitor oil spills at sea is becoming more and more important due to the high demand of oil based products and to the increase in maritime traffic density. Remote sensing frameworks have been proved to yield accurate results in the case of major events; nonetheless also medium and micro oil spills are of their own importance, especially in protected areas that deserve special attention. In this paper, we propose a monitoring framework based on the collection of in-situ observations and on their integration with remote sensing in order to fill out existing observational gaps. A risk assessment model is included for providing environmental decision support and for generating alerts in case of potentially dangerous situations. Field operational tests in an area of great environmental interest demonstrate the technical validity of the approach.
Moroni D, Pieri G, Salvetti O, Tampucci M
The ability to detect and monitor oil spills at sea is becoming more and more important due to the high demand of oil based products and to the increase in maritime traffic density. Remote sensing frameworks have been proved to yield accurate results in the case of major events; nonetheless also medium and micro oil spills are of their own importance, especially in protected areas that deserve special attention. In this paper, we propose a monitoring framework based on the collection of in-situ observations and on their integration with remote sensing in order to fill out existing observational gaps. A risk assessment model is included for providing environmental decision support and for generating alerts in case of potentially dangerous situations. Field operational tests in an area of great environmental interest demonstrate the technical validity of the approach.
2014
Journal article
Open Access
Thesaurus: un database per il patrimonio culturale sommerso
La Monica D, Costa S, Pace G, Martinelli M, Salvetti O, Tampucci M, Righi M
Thesaurus Project aims at promoting the knowledge of the underwater cultural heritage, ancient and modern, through the application of several typologies of tools: underwater autonomous vehicles, which will be able to explore the sea bottom in teams communicating with each other; a database, which will be useful to store and manage all the information referring to archaeological or historical objects, shipwrecks and sites. This paper aims to explain the logic structure of the database indicating the particular needs of the research, the different typologies of items which have to be managed (archaeological and historical objects; ancient, medieval or modern shipwrecks; underwater sites; written or figurative sources, etc.), the relation with other similar databases and projects. The main task of this part of Thesaurus is to plan and organize an IT system, which will allow archaeologists to describe information in detail, in order to make an efficient managing and retrieving data system available.Source: ARCHEOLOGIA E CALCOLATORI, vol. 25, pp. 51-69
La Monica D, Costa S, Pace G, Martinelli M, Salvetti O, Tampucci M, Righi M
Thesaurus Project aims at promoting the knowledge of the underwater cultural heritage, ancient and modern, through the application of several typologies of tools: underwater autonomous vehicles, which will be able to explore the sea bottom in teams communicating with each other; a database, which will be useful to store and manage all the information referring to archaeological or historical objects, shipwrecks and sites. This paper aims to explain the logic structure of the database indicating the particular needs of the research, the different typologies of items which have to be managed (archaeological and historical objects; ancient, medieval or modern shipwrecks; underwater sites; written or figurative sources, etc.), the relation with other similar databases and projects. The main task of this part of Thesaurus is to plan and organize an IT system, which will allow archaeologists to describe information in detail, in order to make an efficient managing and retrieving data system available.Source: ARCHEOLOGIA E CALCOLATORI, vol. 25, pp. 51-69
See at:
CNR IRIS | www.progettocaere.rm.cnr.it | CNR IRIS
2014
Other
Restricted
MARINE research infrastructures as big data producers
Castelli D
This presentation discusses how defining appropriate conservation and policy measures for the sustainable exploitation of natural resources in the marine environment requires comprehensive, multi-domain and good quality knowledge on the status of biodiversity and ecosystems and on marine resources exploitation and management.Project(s): IMARINE
Castelli D
This presentation discusses how defining appropriate conservation and policy measures for the sustainable exploitation of natural resources in the marine environment requires comprehensive, multi-domain and good quality knowledge on the status of biodiversity and ecosystems and on marine resources exploitation and management.Project(s): IMARINE
2014
Other
Restricted
SHE - Infrastruttura di comunicazione
Bacco F M, Barsocchi P, Cresci G, Ferro E, Gotta A, Della Maggiore R
Nel presente capitolo viene definita e descritta l'infrastruttura di comunicazione del sistema, nella sua componente fissa e in quella mobile. Verranno descritte le funzionalita? offerte dalla componente fissa e dalla componente mobile della rete; per componente fissa si intendono i nodi statici disponibili in punti della citta? ben definiti, mentre per componente mobile si intendono i nodi in movimento disponibili su veicoli atti al trasporto. La componente fissa e quella mobile dell'infrastruttura di comunicazione sono in grado di dialogare tra loro al fine dello scambio dei dati rilevati dalla sensoristica disponibile nell'ambito di progetto. Un appropriato set di protocolli di rete permettera?, quindi, alla sensoristica fissa di comunicare con se stessa ed alla sensoristica mobile di interfacciarsi con la componente fissa.
Bacco F M, Barsocchi P, Cresci G, Ferro E, Gotta A, Della Maggiore R
Nel presente capitolo viene definita e descritta l'infrastruttura di comunicazione del sistema, nella sua componente fissa e in quella mobile. Verranno descritte le funzionalita? offerte dalla componente fissa e dalla componente mobile della rete; per componente fissa si intendono i nodi statici disponibili in punti della citta? ben definiti, mentre per componente mobile si intendono i nodi in movimento disponibili su veicoli atti al trasporto. La componente fissa e quella mobile dell'infrastruttura di comunicazione sono in grado di dialogare tra loro al fine dello scambio dei dati rilevati dalla sensoristica disponibile nell'ambito di progetto. Un appropriato set di protocolli di rete permettera?, quindi, alla sensoristica fissa di comunicare con se stessa ed alla sensoristica mobile di interfacciarsi con la componente fissa.
2014
Journal article
Open Access
Teilhard de Chardin e Wolfram: modelli di universo computazionale ed emergenza del foglietto interno delle cose
Bolognesi T
The ambitious goal of 'The Human Phenomenon' by Teilhard de Chardin is to describe the Cosmos and its evolution in a way that integrates the outside and the inside of things - the material world and the dimensions of psyche and consciousness - while preserving the character of a scientific investigation. By following the teilhardian steps of Prelife-Life-Though, and by using results that were still largely unknown during Teilhard's lifespan, due, in particular, to Wolfram, Chaitin and Tononi, in this short essay we show that it is possible and useful to try and understand the ultimate fabric of the universe, some phenomena in the biosphere, and the notion of consciousness itself, in terms of the concept of computation, that is, as phenomena emerging from information processing.
Bolognesi T
The ambitious goal of 'The Human Phenomenon' by Teilhard de Chardin is to describe the Cosmos and its evolution in a way that integrates the outside and the inside of things - the material world and the dimensions of psyche and consciousness - while preserving the character of a scientific investigation. By following the teilhardian steps of Prelife-Life-Though, and by using results that were still largely unknown during Teilhard's lifespan, due, in particular, to Wolfram, Chaitin and Tononi, in this short essay we show that it is possible and useful to try and understand the ultimate fabric of the universe, some phenomena in the biosphere, and the notion of consciousness itself, in terms of the concept of computation, that is, as phenomena emerging from information processing.
See at:
CNR IRIS | www.edizionistudium.it | CNR IRIS
2014
Contribution to book
Restricted
Dallo stato di rudere alla realtà virtuale
Pingi P, Siotto E, Callieri M, Ferrara A, Scopigno R
The chapter of the book "La Badia Camaldolese Volterra" reports the results obtained to the knowledge of preservation history of the Abbey church, through a deepening and integration of different knowledge fields. For this purpose, we have been used different data acquisition procedures, which have been specifically chosen to the investigated ancient building. They are supported through the study of historical and architectural features of the structure. This knowledge process was followed by a data processing step in order to manage and visualize the achieved results.DOI: 10.4399/97888548795537
Metrics:
Pingi P, Siotto E, Callieri M, Ferrara A, Scopigno R
The chapter of the book "La Badia Camaldolese Volterra" reports the results obtained to the knowledge of preservation history of the Abbey church, through a deepening and integration of different knowledge fields. For this purpose, we have been used different data acquisition procedures, which have been specifically chosen to the investigated ancient building. They are supported through the study of historical and architectural features of the structure. This knowledge process was followed by a data processing step in order to manage and visualize the achieved results.DOI: 10.4399/97888548795537
Metrics:
See at:
bozze.aracneeditrice.it | CNR IRIS | CNR IRIS
2014
Contribution to book
Restricted
On the Top-k Retrieval Problem for Ontology-Based Access to Databases
Straccia U
The chapter is a succinct summary on the problem of evaluating ranked top-k queries in the context of ontology-based access over relational databases. An ontology layer is used to define the relevant abstract concepts and relations of the application domain, while facts with associated score are stored into a relational database. Queries are conjunctive queries with ranking aggregates and scoring functions. The results of a query may be ranked according to the score and the problem is to find efficiently the top-k ranked query answers.Source: STUDIES IN COMPUTATIONAL INTELLIGENCE (INTERNET), pp. 95-114
DOI: 10.1007/978-3-319-00954-4_5
Metrics:
Straccia U
The chapter is a succinct summary on the problem of evaluating ranked top-k queries in the context of ontology-based access over relational databases. An ontology layer is used to define the relevant abstract concepts and relations of the application domain, while facts with associated score are stored into a relational database. Queries are conjunctive queries with ranking aggregates and scoring functions. The results of a query may be ranked according to the score and the problem is to find efficiently the top-k ranked query answers.Source: STUDIES IN COMPUTATIONAL INTELLIGENCE (INTERNET), pp. 95-114
DOI: 10.1007/978-3-319-00954-4_5
Metrics:
See at:
doi.org | CNR IRIS | CNR IRIS | link.springer.com
2014
Other
Open Access
Logics of space and time
Ciancia V, Latella D, Massink M
We review some literature in the field of spatial logics. The selection of papers we make is intended as an introductory guide in this broad area. In perspective, this review should be expanded in the future and become tailored to the use of spatial reasoning in the context of population models and their ODE / PDE approximations. The application to keep in mind is the analysis of population models where individuals are scattered over a spatial structure. In this context, typically, space is intended to be multi-dimensional, discrete or continuous; it may be useful to think in terms of Euclidean spaces, but also graph-based relational models may be the subject of spatial reasoning. Furthermore, metrics, measures, probabilities and rates may also be part of the requirements of an analysis methodology.Project(s): QUANTICOL
Ciancia V, Latella D, Massink M
We review some literature in the field of spatial logics. The selection of papers we make is intended as an introductory guide in this broad area. In perspective, this review should be expanded in the future and become tailored to the use of spatial reasoning in the context of population models and their ODE / PDE approximations. The application to keep in mind is the analysis of population models where individuals are scattered over a spatial structure. In this context, typically, space is intended to be multi-dimensional, discrete or continuous; it may be useful to think in terms of Euclidean spaces, but also graph-based relational models may be the subject of spatial reasoning. Furthermore, metrics, measures, probabilities and rates may also be part of the requirements of an analysis methodology.Project(s): QUANTICOL
See at:
CNR IRIS | milner.inf.ed.ac.uk | ISTI Repository | CNR IRIS
2014
Journal article
Restricted
Computer graphics in Brazil: a selection of papers from SIBGRAPI 2012
Scopigno R, Dal Sasso Freitas C
Source: COMPUTERS & GRAPHICS, vol. 38 (issue 1), p. 1
DOI: 10.1016/j.cag.2013.11.012
Metrics:
Scopigno R, Dal Sasso Freitas C
Source: COMPUTERS & GRAPHICS, vol. 38 (issue 1), p. 1
DOI: 10.1016/j.cag.2013.11.012
Metrics:
See at:
Computers & Graphics | CNR IRIS | CNR IRIS | www.sciencedirect.com
2014
Other
Open Access
On the effects of low-quality training data on information extraction from clinical reports
Marcheggiani D, Sebastiani F
In the last five years there has been a flurry of work on information extraction from clinical documents, i.e., on algorithms capable of extracting, from the informal and unstructured texts that are generated during everyday clinical practice, mentions of concepts relevant to such practice. Most of this literature is about methods based on supervised learning, i.e., methods for training an information extraction system from manually annotated examples. While a lot of work has been devoted to devising learning methods that generate more and more accurate information extractors, little work (if any) has been devoted to investigating the effect of the quality of training data on the learning process. Low quality in training data sometimes derives from the fact that the person who has annotated the data is different (e.g., more junior) from the one against whose judgment the automatically annotated data must be evaluated. In this paper we test the impact of such data quality issues on the accuracy of information extraction systems oriented to the clinical domain. We do this by comparing the accuracy deriving from training data annotated by the authoritative coder (i.e., the one who has annotated the test data), with the accuracy deriving from training data annotated by a different coder. The results indicate that, although the disagreement between the two coders (as measured on the training set) is substantial, the difference in accuracy is not so. This hints at the fact that current learning technology is robust to the use of training data of suboptimal quality.
Marcheggiani D, Sebastiani F
In the last five years there has been a flurry of work on information extraction from clinical documents, i.e., on algorithms capable of extracting, from the informal and unstructured texts that are generated during everyday clinical practice, mentions of concepts relevant to such practice. Most of this literature is about methods based on supervised learning, i.e., methods for training an information extraction system from manually annotated examples. While a lot of work has been devoted to devising learning methods that generate more and more accurate information extractors, little work (if any) has been devoted to investigating the effect of the quality of training data on the learning process. Low quality in training data sometimes derives from the fact that the person who has annotated the data is different (e.g., more junior) from the one against whose judgment the automatically annotated data must be evaluated. In this paper we test the impact of such data quality issues on the accuracy of information extraction systems oriented to the clinical domain. We do this by comparing the accuracy deriving from training data annotated by the authoritative coder (i.e., the one who has annotated the test data), with the accuracy deriving from training data annotated by a different coder. The results indicate that, although the disagreement between the two coders (as measured on the training set) is substantial, the difference in accuracy is not so. This hints at the fact that current learning technology is robust to the use of training data of suboptimal quality.
See at:
ISTI Repository | CNR IRIS | CNR IRIS
2014
Book
Restricted
Compressed data structures for strings. On searching and extracting strings from compressed textual data
Venturini R
Data compression is mandatory to manage massive datasets, indexing is fundamental to query them. However, their goals appear as counterposed: the former aims at minimizing data redundancies, whereas the latter augments the dataset with auxiliary information to speed up the query resolution. In this monograph we introduce solutions that overcome this dichotomy. We start by presenting the use of optimization techniques to improve the compression of classical data compression algorithms, then we move to the design of compressed data structures providing fast random access or efficient pattern matching queries on the compressed dataset. These theoretical studies are supported by experimental evidences of their impact in practical scenarios.Source: ATLANTIS STUDIES IN COMPUTING
DOI: 10.2991/978-94-6239-033-1
Metrics:
Venturini R
Data compression is mandatory to manage massive datasets, indexing is fundamental to query them. However, their goals appear as counterposed: the former aims at minimizing data redundancies, whereas the latter augments the dataset with auxiliary information to speed up the query resolution. In this monograph we introduce solutions that overcome this dichotomy. We start by presenting the use of optimization techniques to improve the compression of classical data compression algorithms, then we move to the design of compressed data structures providing fast random access or efficient pattern matching queries on the compressed dataset. These theoretical studies are supported by experimental evidences of their impact in practical scenarios.Source: ATLANTIS STUDIES IN COMPUTING
DOI: 10.2991/978-94-6239-033-1
Metrics:
See at:
doi.org | CNR IRIS | CNR IRIS | link.springer.com
2014
Journal article
Open Access
An experimental characterization of reservoir computing in ambient assisted living applications
Bacciu D, Barsocchi P, Chessa S, Gallicchio C, Micheli A
In this paper, we present an introduction and critical experimental evaluation of a reservoir computing (RC) approach for ambient assisted living (AAL) applica- tions. Such an empirical analysis jointly addresses the issues of efficiency, by analyzing different system config- urations toward the embedding into computationally con- strained wireless sensor devices, and of efficacy, by analyzing the predictive performance on real-world appli- cations. First, the approach is assessed on a validation scheme where training, validation and test data are sampled in homogeneous ambient conditions, i.e., from the same set of rooms. Then, it is introduced an external test set involving a new setting, i.e., a novel ambient, which was not available in the first phase of model training and vali- dation. The specific test-bed considered in the paper allows us to investigate the capability of the RC approach to discriminate among user movement trajectories from received signal strength indicator sensor signals. This capability can be exploited in various AAL applications targeted at learning user indoor habits, such as in the roposed indoor movement forecasting task. Such a joint analysis of the efficiency/efficacy trade-off provides novel insight in the concrete successful exploitation of RC for AAL tasks and for their distributed implementation into wireless sensor networks.Source: NEURAL COMPUTING & APPLICATIONS, vol. 24 (issue 6), pp. 1451-1464
DOI: 10.1007/s00521-013-1364-4
Project(s): RUBICON
Metrics:
Bacciu D, Barsocchi P, Chessa S, Gallicchio C, Micheli A
In this paper, we present an introduction and critical experimental evaluation of a reservoir computing (RC) approach for ambient assisted living (AAL) applica- tions. Such an empirical analysis jointly addresses the issues of efficiency, by analyzing different system config- urations toward the embedding into computationally con- strained wireless sensor devices, and of efficacy, by analyzing the predictive performance on real-world appli- cations. First, the approach is assessed on a validation scheme where training, validation and test data are sampled in homogeneous ambient conditions, i.e., from the same set of rooms. Then, it is introduced an external test set involving a new setting, i.e., a novel ambient, which was not available in the first phase of model training and vali- dation. The specific test-bed considered in the paper allows us to investigate the capability of the RC approach to discriminate among user movement trajectories from received signal strength indicator sensor signals. This capability can be exploited in various AAL applications targeted at learning user indoor habits, such as in the roposed indoor movement forecasting task. Such a joint analysis of the efficiency/efficacy trade-off provides novel insight in the concrete successful exploitation of RC for AAL tasks and for their distributed implementation into wireless sensor networks.Source: NEURAL COMPUTING & APPLICATIONS, vol. 24 (issue 6), pp. 1451-1464
DOI: 10.1007/s00521-013-1364-4
Project(s): RUBICON
Metrics:
See at:
Neural Computing and Applications | Neural Computing and Applications | CNR IRIS | CNR IRIS | CNR IRIS | link.springer.com
2014
Journal article
Open Access
The D4Science research-oriented social networking facilities
Assante M, Candela L, Castelli D, Pagano P
Modern science calls for innovative practices to facilitate research collaborations spanning institutions, disciplines, and countries. Paradigms such as cloud computing and social computing represent a new opportunity for individuals with scant resources, to participate in science. The D4Science.org Hybrid Data Infrastructure combines these two paradigms with Virtual Research Environments in order to offer a large array of collaboration-oriented facilities as-a-Service.Source: ERCIM NEWS, vol. 96
Project(s): IMARINE
Assante M, Candela L, Castelli D, Pagano P
Modern science calls for innovative practices to facilitate research collaborations spanning institutions, disciplines, and countries. Paradigms such as cloud computing and social computing represent a new opportunity for individuals with scant resources, to participate in science. The D4Science.org Hybrid Data Infrastructure combines these two paradigms with Virtual Research Environments in order to offer a large array of collaboration-oriented facilities as-a-Service.Source: ERCIM NEWS, vol. 96
Project(s): IMARINE
See at:
ercim-news.ercim.eu | CNR IRIS | CNR IRIS
2014
Journal article
Restricted
Task model-driven realization of interactive application functionality through services
Kritikos K., Plexousakis D., Paternò F.
The Service-Oriented Computing (SOC) paradigm is currently being adopted by many developers, as it promises the construction of applications through reuse of existing Web Services (WSs). However, current SOC tools produce applications that interact with users in a limited way. This limitation is overcome by model-based Human-Computer Interaction (HCI) approaches that support the development of applications whose functionality is realized with WSs and whose User Interface (UI) is adapted to the user's context. Typically, such approaches do not consider various functional issues, such as the applications' semantics and their syntactic robustness in terms of the WSs selected to implement their functionality and the automation of the service discovery and selection processes. To this end, we propose a model-driven design method for interactive service-based applications that is able to consider the functional issues and their implications for the UI. This method is realized by a semiautomatic environment that can be integrated into current model-based HCI tools to complete the development of interactive service front-ends. The proposed method takes as input an HCI task model, which includes the user's view of the interactive system, and produces a concrete service model that describes how existing services can be combined to realize the application's functionality. To achieve its goal, our method first transforms system tasks into semantic service queries by mapping the task objects onto domain ontology concepts; then it sends each resulting query to a semantic service engine so as to discover the corresponding services. In the end, only one service from those associated with a system task is selected, through the execution of a novel service concretization algorithm that ensures message compatibility between the selected services.Source: ACM TRANSACTIONS ON INTERACTIVE INTELLIGENT SYSTEMS, vol. 3 (issue 5), pp. 25-31
DOI: 10.1145/2559979
Metrics:
Kritikos K., Plexousakis D., Paternò F.
The Service-Oriented Computing (SOC) paradigm is currently being adopted by many developers, as it promises the construction of applications through reuse of existing Web Services (WSs). However, current SOC tools produce applications that interact with users in a limited way. This limitation is overcome by model-based Human-Computer Interaction (HCI) approaches that support the development of applications whose functionality is realized with WSs and whose User Interface (UI) is adapted to the user's context. Typically, such approaches do not consider various functional issues, such as the applications' semantics and their syntactic robustness in terms of the WSs selected to implement their functionality and the automation of the service discovery and selection processes. To this end, we propose a model-driven design method for interactive service-based applications that is able to consider the functional issues and their implications for the UI. This method is realized by a semiautomatic environment that can be integrated into current model-based HCI tools to complete the development of interactive service front-ends. The proposed method takes as input an HCI task model, which includes the user's view of the interactive system, and produces a concrete service model that describes how existing services can be combined to realize the application's functionality. To achieve its goal, our method first transforms system tasks into semantic service queries by mapping the task objects onto domain ontology concepts; then it sends each resulting query to a semantic service engine so as to discover the corresponding services. In the end, only one service from those associated with a system task is selected, through the execution of a novel service concretization algorithm that ensures message compatibility between the selected services.Source: ACM TRANSACTIONS ON INTERACTIVE INTELLIGENT SYSTEMS, vol. 3 (issue 5), pp. 25-31
DOI: 10.1145/2559979
Metrics:
See at:
dl.acm.org | ACM Transactions on Interactive Intelligent Systems | CNR IRIS | CNR IRIS
2014
Journal article
Open Access
Feature selection for ordinal text classification
Baccianella S, Esuli A, Sebastiani F
Ordinal classification (also known as ordinal regression) is a supervised learning task that consists of estimating the rating of a data item on a fixed, discrete rating scale. This problem is receiving increased attention from the sentiment analysis and opinion mining community due to the importance of automatically rating large amounts of product review data in digital form. As in other supervised learning tasks such as binary or multiclass classification, feature selection is often needed in order to improve efficiency and avoid overfitting. However, although feature selection has been extensively studied for other classification tasks, it has not for ordinal classification. In this letter, we present six novel feature selection methods that we have specifically devised for ordinal classification and test them on two data sets of product review data against three methods previously known from the literature, using two learning algorithms from the support vector regression tradition. The experimental results show that all six proposed metrics largely outperform all three baseline techniques (and are more stable than these others by an order of magnitude), on both data sets and for both learning algorithms.Source: NEURAL COMPUTATION, vol. 26 (issue 3), pp. 557-591
DOI: 10.1162/neco_a_00558
Metrics:
Baccianella S, Esuli A, Sebastiani F
Ordinal classification (also known as ordinal regression) is a supervised learning task that consists of estimating the rating of a data item on a fixed, discrete rating scale. This problem is receiving increased attention from the sentiment analysis and opinion mining community due to the importance of automatically rating large amounts of product review data in digital form. As in other supervised learning tasks such as binary or multiclass classification, feature selection is often needed in order to improve efficiency and avoid overfitting. However, although feature selection has been extensively studied for other classification tasks, it has not for ordinal classification. In this letter, we present six novel feature selection methods that we have specifically devised for ordinal classification and test them on two data sets of product review data against three methods previously known from the literature, using two learning algorithms from the support vector regression tradition. The experimental results show that all six proposed metrics largely outperform all three baseline techniques (and are more stable than these others by an order of magnitude), on both data sets and for both learning algorithms.Source: NEURAL COMPUTATION, vol. 26 (issue 3), pp. 557-591
DOI: 10.1162/neco_a_00558
Metrics:
See at:
Neural Computation | Neural Computation | CNR IRIS | CNR IRIS | www.mitpressjournals.org
2014
Book
Restricted
Introduction to special issue on interacting with the past
Hachet M, Dellepiane M
The current special issue joins together such examples of fascinating works dedicated to interaction with cultural heritage covering a wide range of possible examples.Source: ACM JOURNAL ON COMPUTING AND CULTURAL HERITAGE
DOI: 10.1145/2635671
Metrics:
Hachet M, Dellepiane M
The current special issue joins together such examples of fascinating works dedicated to interaction with cultural heritage covering a wide range of possible examples.Source: ACM JOURNAL ON COMPUTING AND CULTURAL HERITAGE
DOI: 10.1145/2635671
Metrics:
See at:
dl.acm.org | Journal on Computing and Cultural Heritage | CNR IRIS | CNR IRIS
2014
Conference article
Open Access
GreyGuide. Poster presentation
Biagioni S, Farace D
Welcome to the GreyGuide, a repository of good practices and resources in grey literature. The GreyGuide seeks to capture proposed as well as published practices dealing with the supply and demand sides of grey literature. This is a collaborative project involving GreyNet International and ISTI-CNR. The launch of the GreyGuide Repository took place in December 2013 at the Fifteenth International Conference on Grey Literature. Since then, the acquisition of both proposed and published good practices are underway. The GreyGuide is currently still in a developmental stage and is influenced by changes that have taken place in GreyNet's new infrastructure commencing in January 2014. GreyNet is currently in the process of migrating web-based content to the GreyGuide and in effect, the GreyGuide will come to serve as GreyNet's web access portal. Poster presented during the GL16 Conference, Library of Congress, Washinghton DC, USA.
Biagioni S, Farace D
Welcome to the GreyGuide, a repository of good practices and resources in grey literature. The GreyGuide seeks to capture proposed as well as published practices dealing with the supply and demand sides of grey literature. This is a collaborative project involving GreyNet International and ISTI-CNR. The launch of the GreyGuide Repository took place in December 2013 at the Fifteenth International Conference on Grey Literature. Since then, the acquisition of both proposed and published good practices are underway. The GreyGuide is currently still in a developmental stage and is influenced by changes that have taken place in GreyNet's new infrastructure commencing in January 2014. GreyNet is currently in the process of migrating web-based content to the GreyGuide and in effect, the GreyGuide will come to serve as GreyNet's web access portal. Poster presented during the GL16 Conference, Library of Congress, Washinghton DC, USA.
See at:
greyguide.isti.cnr.it | CNR IRIS | CNR IRIS | CNR IRIS
2014
Journal article
Restricted
From commercial documents to system requirements: an approach for the engineering of novel CBTC solutions
Ferrari A, Spagnolo Go, Menabeni S, Martelli G
Communications-based train control (CBTC) systems are the new frontier of automated train control and operation. Currently developed CBTC platforms are actually very complex systems including several functionalities, and every installed system, developed by a different company, varies in extent, scope, number, and even names of the implemented functionalities. International standards have emerged, but they remain at a quite abstract level, mostly setting terminology. This paper presents the results of an experience in defining a global model of CBTC, by mixing semi-formal modelling and product line engineering. The effort has been based on an in-depth market analysis, not limiting to particular aspects but considering as far as possible the whole picture. The paper also describes a methodology to derive novel CBTC products from the global model, and to define system requirements for the individual CBTC components. To this end, the proposed methodology employs scenario-based requirements elicitation aided with rapid prototyping. To enhance the quality of the requirements, these are written in a constrained natural language (CNL), and evaluated with natural language processing (NLP) techniques. The final goal is to go toward a formal representation of the requirements for CBTC systems. The overall approach is discussed, and the current experience with the implementation of the method is presented. In particular, we show how the presented methodology has been used in practice to derive a novel CBTC architecture.Source: INTERNATIONAL JOURNAL ON SOFTWARE TOOLS FOR TECHNOLOGY TRANSFER (PRINT), pp. 1-21
DOI: 10.1007/s10009-013-0298-6
Metrics:
Ferrari A, Spagnolo Go, Menabeni S, Martelli G
Communications-based train control (CBTC) systems are the new frontier of automated train control and operation. Currently developed CBTC platforms are actually very complex systems including several functionalities, and every installed system, developed by a different company, varies in extent, scope, number, and even names of the implemented functionalities. International standards have emerged, but they remain at a quite abstract level, mostly setting terminology. This paper presents the results of an experience in defining a global model of CBTC, by mixing semi-formal modelling and product line engineering. The effort has been based on an in-depth market analysis, not limiting to particular aspects but considering as far as possible the whole picture. The paper also describes a methodology to derive novel CBTC products from the global model, and to define system requirements for the individual CBTC components. To this end, the proposed methodology employs scenario-based requirements elicitation aided with rapid prototyping. To enhance the quality of the requirements, these are written in a constrained natural language (CNL), and evaluated with natural language processing (NLP) techniques. The final goal is to go toward a formal representation of the requirements for CBTC systems. The overall approach is discussed, and the current experience with the implementation of the method is presented. In particular, we show how the presented methodology has been used in practice to derive a novel CBTC architecture.Source: INTERNATIONAL JOURNAL ON SOFTWARE TOOLS FOR TECHNOLOGY TRANSFER (PRINT), pp. 1-21
DOI: 10.1007/s10009-013-0298-6
Metrics:
See at:
International Journal on Software Tools for Technology Transfer | CNR IRIS | CNR IRIS | link.springer.com