IRIS - Res&Arch Institutional Research Information System - Research & Archive

Ricerche applicate. Progetto e realizzazione di una rete di centri di comunità per i territori a maggior rischio sismico

Classification of lung nodules on CT via pseudo-colour images and deep features from pre-trained convolutional networks

Developing accurate methods for differentiating benign vs. malignant pulmonary nodules on CT is crucial for the correct management of patients referred for suspicious lung cancer. In this context deep learning by convolutional neural networks (CNN) has been gaining ground as an alternative to conventional methods based on feature engineering, although the use of CNN is often hampered by the lack of sufficiently large datasets for training. Herein we explore the effectiveness of deep features ...

On 1-Bend Upward Point-Set Embeddings of st-Digraphs

We study the upward point-set embeddability of digraphs on one-sided convex point sets with at most 1 bend per edge. We provide an algorithm to compute a 1-bend upward point-set embedding of outerplanar st-digraphs on arbitrary one-sided convex point sets. We complement this result by proving that for every n≥18 there exists a 2-outerplanar st-digraph G with n vertices and a one-sided convex point set S so that G does not admit a 1-bend upward point-set embedding on S.

La spontaneità malata. Follia e patologia nella filosofia di Félix Ravaisson

In Ravaisson's philosophy, the concept of spontaneity refers to the first, basic and organic form of improvisation. Nature consists indeed of a rational law of development named habit, that regulates all movements, summarizing the external impulsions and the internal penchants in the form of spontaneous activity. However the insertion of spontaneity in nature determines the appearance of unpredictability and negativity in life's productions, as organic and psychical pathologies. Ravaisson wil...