Marcello Castellano
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Marcello Castellano has a total of 49 co-authors. Here are the top co-authors by number of shared publications:
Giuseppe Mastronardi
3 shared publications- Roberto Bellotti
Dipartimento Interateneo di Fisica, Università degli Studi di Bari Aldo Moro, 70125 Bari, Italy
3 shared publications Vito Dicensi
2 shared publicationsA. Lauria
1 shared publicationA. Preite Martinez
1 shared publicationA. Schenone
1 shared publication
Latest Publications
- Open Access
- 1 April 2010
- Published by IntechOpen
Geodesic Distances and Hidden Markov Models for the 3D Face Recognition
- 1 April 2010
- Published by IntechOpen
Open AccessGeodesic Distances and Hidden Markov Models for the 3D Face Recognition
- Open Access
- 16 June 2009
- Published by Springer Nature in BMC Bioinformatics
- Vol. 10 (S6) , S23
A bioinformatics knowledge discovery in text application for grid computing
A fundamental activity in biomedical research is Knowledge Discovery which has the ability to search through large amounts of biomedical information such as documents and data. High performance computational infrastructures, such as Grid technologies, are emerging as a possible infrastructure to tackle the intensive use of Information and Communication resources in life science. The goal of this work was to develop a software middleware solution in order to exploit the many knowledge discovery applications on scalable and distributed computing systems to achieve intensive use of ICT resources.
- 16 June 2009
- Published by Springer Nature in BMC Bioinformatics
- Vol. 10 (S6) , S23
Open AccessA bioinformatics knowledge discovery in text application for grid computing
A fundamental activity in biomedical research is Knowledge Discovery which has the ability to search through large amounts of biomedical information such as documents and data. High performance computational infrastructures, such as Grid technologies, are emerging as a possible infrastructure to tackle the intensive use of Information and Communication resources in life science. The goal of this work was to develop a software middleware solution in order to exploit the many knowledge discovery applications on scalable and distributed computing systems to achieve intensive use of ICT resources.
- Open Access
- 1 December 2007
- Published by International Academy Publishing (IAP) in Journal of Software
- Vol. 2 (6) , 30-41
A Decision Support System base line Flexible Architecture to Intrusion Detection
Becoming more competitive and more effective in the current scenes of Business and Public Administration, the organizations must be able to approach easily and quickly to the information on the customers and the external conditions of market. In other words it means to head at the improvement of the Decision Support Systems. Decision Support System is concerned with developing systems aimed at helping decision makers solve problems and make decisions. In this paper, we refer to a decision support system based on flexible architecture able to discover the knowledge in a distributed and heterogeneous multi-organization environment. The system architecture has been designed according to the Service Oriented Architecture and Model View Controller design pattern. Moreover it is based on a mining engine whose purpose is to generate and to use suitable e-services for knowledge by driving the user through various stages of the Knowledge Discovery process. An Intrusion Detection application is also described.
- 1 December 2007
- Published by International Academy Publishing (IAP) in Journal of Software
- Vol. 2 (6) , 30-41
Open AccessA Decision Support System base line Flexible Architecture to Intrusion Detection
Becoming more competitive and more effective in the current scenes of Business and Public Administration, the organizations must be able to approach easily and quickly to the information on the customers and the external conditions of market. In other words it means to head at the improvement of the Decision Support Systems. Decision Support System is concerned with developing systems aimed at helping decision makers solve problems and make decisions. In this paper, we refer to a decision support system based on flexible architecture able to discover the knowledge in a distributed and heterogeneous multi-organization environment. The system architecture has been designed according to the Service Oriented Architecture and Model View Controller design pattern. Moreover it is based on a mining engine whose purpose is to generate and to use suitable e-services for knowledge by driving the user through various stages of the Knowledge Discovery process. An Intrusion Detection application is also described.
- 1 June 2007
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 21591547,p. 63-67
Neural Techniques to Improve the Formative Evaluation Procedure in Intelligent Tutoring Systems
Nowadays a special attention is paid to the quality of teaching valued in terms of efficacy of students' knowledge at the exit of its formative period. This efficacy depends both on the quality of formative iter and on the way formative activities are planned in a single teaching. Not since a lot of time has re-emerged the importance of tutoring as ad hoc regulator in student's learning process. Taking care of a student means design both of diagnostic instruments and of suitable formative interventions. That is the moment in which having the diagnosis to be preceded by a survey of performance indicators becomes important the study of measuring system models to be applied to each student. Intelligent tutoring systems (ITS), are any computer system with the ability to adopt pedagogical activities to individual student needs providing customized instruction and feedback. A correct and effective use of such system is obtained through a careful planning of formative deficit diagnostic measuring. In this paper we propose a model of formative evaluation procedure based on the use of neural techniques qualified to improve its accuracy.
- 1 June 2007
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 21591547,p. 63-67
Neural Techniques to Improve the Formative Evaluation Procedure in Intelligent Tutoring Systems
Nowadays a special attention is paid to the quality of teaching valued in terms of efficacy of students' knowledge at the exit of its formative period. This efficacy depends both on the quality of formative iter and on the way formative activities are planned in a single teaching. Not since a lot of time has re-emerged the importance of tutoring as ad hoc regulator in student's learning process. Taking care of a student means design both of diagnostic instruments and of suitable formative interventions. That is the moment in which having the diagnosis to be preceded by a survey of performance indicators becomes important the study of measuring system models to be applied to each student. Intelligent tutoring systems (ITS), are any computer system with the ability to adopt pedagogical activities to individual student needs providing customized instruction and feedback. A correct and effective use of such system is obtained through a careful planning of formative deficit diagnostic measuring. In this paper we propose a model of formative evaluation procedure based on the use of neural techniques qualified to improve its accuracy.
- 31 March 2007
- Published by Elsevier in Future Generation Computer Systems
- Vol. 23 (3) , 475-484
Distributed medical images analysis on a Grid infrastructure
- 31 March 2007
- Published by Elsevier in Future Generation Computer Systems
- Vol. 23 (3) , 475-484
Distributed medical images analysis on a Grid infrastructure
- 17 April 1995
- Published by SPIE-Intl Soc Optical Eng
- Vol. 2492, 1153-1162
Signal/background classification in a cosmic ray space experiment by a modular neural system
In the cosmic ray space experiments, the separation of the signal from background is a hard task. Due to the well-known critical conditions that characterize this class of experiments, some changes of the detector performances can be observed during the data taking. As a consequence, differences between the test and real data are found as systematic errors in the classification phase. In this paper, a modular classification system based on neural networks is proposed for the signal/background discrimination task in cosmic ray space experiments, without a priori knowledge of the discriminating feature distributions. The system is composed by two neural modules. The first one is a self organizing map (SOM) that both clusters the real data space in suitable classes of similarity and builds a prototype for each of them; a skilled inspection of the prototypes defines the signal and background. The second one, a multi layer perceptron (MLP) with a single hidden layer, adapts the classification model based on training/test data to the real experimental conditions. The MLP synaptic weights adaptive formation takes into account the labelled real data set as defined in the first system-phase. The modular neural system has been applied in the context of TRAMP-Si experiment, performed on the NASA Balloon-Borne Magnet Facility, for the positron/proton discrimination.
- 17 April 1995
- Published by SPIE-Intl Soc Optical Eng
- Vol. 2492, 1153-1162
Signal/background classification in a cosmic ray space experiment by a modular neural system
In the cosmic ray space experiments, the separation of the signal from background is a hard task. Due to the well-known critical conditions that characterize this class of experiments, some changes of the detector performances can be observed during the data taking. As a consequence, differences between the test and real data are found as systematic errors in the classification phase. In this paper, a modular classification system based on neural networks is proposed for the signal/background discrimination task in cosmic ray space experiments, without a priori knowledge of the discriminating feature distributions. The system is composed by two neural modules. The first one is a self organizing map (SOM) that both clusters the real data space in suitable classes of similarity and builds a prototype for each of them; a skilled inspection of the prototypes defines the signal and background. The second one, a multi layer perceptron (MLP) with a single hidden layer, adapts the classification model based on training/test data to the real experimental conditions. The MLP synaptic weights adaptive formation takes into account the labelled real data set as defined in the first system-phase. The modular neural system has been applied in the context of TRAMP-Si experiment, performed on the NASA Balloon-Borne Magnet Facility, for the positron/proton discrimination.