Cristina Marrocco

• University of Cassino and Southern Lazio

Water monitoring systems continuously working ensure real–time pollutant detection capabilities according to their sensitivity and specificity. It is necessary to balance such features because, although being able to sense several substances is a desired feature, the reduction of false positives is a primary goal a classification system should have...

This paper is the editorial of the virtual special issue (VSI) “Artificial Intelligence for Distributed Smart Systems” (AI4DSS), of which the authors of this paper have been the guest editors. It aims to bring together the work of experts from the fields of artificial intelligence and that of smart sensing. Smart Sensing and, more generally, Smart...

Water pollution caused by human activities poses a serious global threat to human health. Sensor technologies enabling water monitoring are an important tool that can help facing this problem. In this work, we propose an embedded IoT-ready system based on a proprietary sensor technology for the detection and recognition of six water contaminants. T...

This paper presents an end-to-end system to identify writers in medieval manuscripts. The proposed system consists in a three-step model for detection and classification of lines in the manuscript and page writer identification. The first two steps are based on deep neural networks trained with transfer learning techniques and specialized to solve...

In the framework of handwriting recognition, we present a novel GA-based feature selection algorithm in which feature subsets are evaluated by means of a specifically devised separability index. This index measures statistical properties of the feature subset and does not depends on any specific classification scheme. The proposed index represents...

Classifier combination methods have shown their effectiveness in a number of applications. Nonetheless, using simultaneously multiple classifiers may result in some cases in a reduction of the overall performance, since the responses provided by some of the experts may generate consensus on a wrong decision even if other experts provided the correc...

We present a Genetic Algorithm based feature selection approach according to which feature subsets are represented by individuals of an evolving population. Evolution is controlled by a fitness function taking into account statistical properties of the input data in the subspace represented by each individual, and aims to select the smallest featur...

We present a GA–based feature selection algorithm in which feature subsets are evaluated by means of a separability index. This index is based on a filter method, which allows to estimate statistical properties of the data, independently of the classifier used. More specifically, the defined index uses covariance matrices for evaluating how spread...

We propose a new feature selection algorithm for remote sensing image classification. Our approach has been especially devised for applications in which there is a large number of different features that can be potentially selected, implying that the search space is complex and high-dimensional. In this framework, our proposal is that of reformulat...

The aim of our study was to determine the prevalence of genotypic resistance to nucleoside analogues and protease inhibitors before and after 1997, the year of introduction of Highly Active Antiretroviral Therapy (HAART) in Campania (Italy). Forty-eight plasma HIV-RNA positive patients who had not been previously treated for HIV infection (naïve) w...

Few data are available on histological features of chronic hepatitis B (HBV) and C (HCV) virus coinfection. We enrolled 142 consecutive patients with viral chronic hepatitis on their first liver biopsy: 27 HBsAg and anti-HCV positive (case BC group), 57 HBsAg positive and anti-HCV negative (control B group) and 58 anti-HCV positive, HBsAg/anti-HBs/...

To verify whether serial determination of titre of IgM to HCV core protein (HCV IgM) may be useful to distinguish acute hepatitis C (AHC) from reactivation of chronic hepatitis C (r-CHC), we studied 18 consecutive patients with AHC (identified by seroconversion to anti-HCV) and 15 consecutive patients who had been anti-HCV positive for at least one...

To detect HIV antigens in circulating complement fixing immune complexes (ICs) we assessed an ELISA using wells of microtitre plates coated with F(ab)2 anti-C3b and monoclonal antibodies anti-HIV gp120 and anti-HIV p24. We tested 24 anti-HIV positive subjects (Group A), 10 anti-HIV negative subjects at risk of acquiring HIV infection (Group B), 20...

To detect the presence of anti-HIV IgA in HIV infected subjects and in seronegative subjects at risk of infection, we assessed a Western Blot using nitrocellulose strips with HIV separated proteins. We tested at least 2 different serum samples from 9 anti-HIV positive subjects (Group A), 9 anti-HIV negative subjects at risk of infection (Group B) a...

To detect HlV proviral DNA in lymphocytes from subjects at risk of acquiring HIV infection, we assessed a Polymerase Chain Reaction Assay using the SK38 and SK39 primers for the amplification and the SK19 probe for the hybridization. The detection of amplified HIV-DNA was obtained by a new colorimetric method, the DNA enzyme immunoassay (DEIA). The...

The Hepatitis Delta virus infecting humans and chimpanzees is a roundish particle with a chimeric structure: a specific viral genome (HDV RNA) and a specific antigen (HDAg) enclosed in a coat of the surface antigen (HBsAg) of HBV. HDV may be considered a defective virus since a helper virus is required to establish in vivo infection. HBV is the hel...

The diagnosis of HIV infection is generally lead using two different ELISAs to detect specific anti-HIV antibodies, the eventual reactivity must then be confirmed by a Western Blot The antibodies can be detected only 1-6 months after the infection; in fact in the earliest phases neither the antibodies, for their low titre, nor the specific antigens...