Federico Alberto Pozzi

Learn More
The automatic detection of sarcasm and irony in user generated contents is one of the most challenging task of Natural Language Processing. In this paper we address this problem by introducing Bayesian Model Averaging (BMA), an ensemble approach to take into account several classifiers according to their reliabilities and their marginal probability(More)
Background:Hepatocellular carcinoma (HCC) is a highly vascularised and poor-prognosis tumour. NGR-hTNF is a vascular-targeting agent consisting of human tumour necrosis factor-alpha fused to the tumour-homing peptide NGR, which is able to selectively bind an aminopeptidase N overexpressed on tumour blood vessels.Methods:Twenty-seven patients with(More)
Platelet activation and platelet-derived growth factor (PDGF) play a pivotal role in the pathogenesis of atherosclerosis. Evidence has been accumulating that in the evolution of chronic arterial obstructive disease (CAOD) platelets are also crucially important. The aim of the present study was, therefore, to assess plasma levels of PDGF in patients with(More)
The introduction of KRAS testing as a diagnostic tool to select patients for epidermal growth factor receptor (EGFR)-targeted cetuximab- or panitumumab-based therapies for metastatic colorectal cancer is widely regarded as a key advance in the field of personalized cancer medicine. Oncologists are now facing emerging issues in the treatment of metastatic(More)
BACKGROUND The renin-angiotensin system (RAS) plays a role in the pathogenesis of ARDS, Angiotensin II (Ang-II) contributing to the pathogenesis of inflammation and fibrogenesis. Angiotensin-(1-7) (Ang-(1-7)) may antagonize the effects of Ang-II. This study was aimed at evaluating the potential for Ang-(1-7) to reduce injury, inflammation and fibrosis in an(More)
Online social networking communities usually exhibit complex collective behaviors. Since emotions play a relevant role in human decision making, understanding how online networks drive human mood states become a task of considerable interest. One of the most relevant task in Sentiment Analysis is Polarity Classification, aimed at classifying the sentiment(More)
We present an extended modeling for MOSFETs that time-dependently predicts the spontaneous photon emission due to hot carriers. Such very faint luminescence waveforms (less than one photon for every 10<sup>6</sup> switching events) can be measured by means of high-sensitivity single-photon detectors, where time jitter is lower than 30 ps. Thanks to the(More)