745 research outputs found
Autism Spectrum Disorder Identification from Visual Exploration of Images
No full textAutism Spectrum Disorder (ASD) affects 1 in 77 children in Italy, but the diagnostic process is slow and costly. As autistic individuals exhibit different gaze patterns from healthy controls in visual exploration of images and semantic interpretation, these are promising biomarkers to exploit in diagnosis. This study aims at developing a model to assist in the diagnosis of ASD using gaze data when static images are presented to the subjects. We first propose a set of features, each one motivated by psychological studies and findings. Then we apply a feature selection mechanism based on Boruta algorithm with SHAP values. Finally we use CatBoost to perform binary classification, and a strategy to optimize model hyperparameters using a multivariate Tree Parzen Estimator. We validated our model on the popular Saliency4ASD dataset, outperforming state of the art models tested with the same protocol by more than 3% in accuracy. We also provide an in-depth analysis of the feature importance and we show how these results are in line with the psychological literature
Evaluating the Group Detection Performance: The GRODE Metrics
No full textThe detection of groups of individuals is attracting the attention of many researchers in diverse fields, from automated surveillance to human-computer interaction, with a growing number of approaches published every year. Unexpectedly, the evaluation metrics for this problem are not consolidated, with some measures inherited from different fields, other designed specifically for a particular approach, thus lacking in generalization and making the comparisons between different approaches difficult. Moreover, most of the existent metrics are scarcely expressive, addressing groups as atomic entities, ignoring that they may have different cardinalities, and that group detection approaches may fail in capturing the exact number of individuals that compose it. This paper fills this gap presenting the GROup DEtection (GRODE) metrics, which formally define precision and recall on the groups, including the group cardinality as a variable. This gives the possibility to investigate aspects never considered so far, such as the tendency of a method of over- or under-segmenting, or of better dealing with specific group cardinalities. The GRODE metrics have been evaluated first on controlled scenarios, where the differences with alternative metrics are evident, as well as on public datasets, providing a fresh-new panorama of the state-of-the-art
The GRODE Metrics
No full textThe detection of groups of individuals is attracting the attention of many researchers in diverse fields, from surveillance to social robotics, with a growing number of approaches published every year. Unexpectedly, the evaluation metrics for this problem are not consolidated, with some measures being inherited from the people detection field, others come from clustering or were designed specifically for a particular approach, thus lacking in generalization and making the comparisons hard to be carried out. Moreover, the existent metrics are scarcely expressive, ignoring, for example, the fact that groups have different cardinalities, and that, obviously, larger groups are harder to find. This work fills this gap by presenting the GROup DEtection (GRODE) metrics, which formally define precision and recall on the groups, including the group cardinality as a variable. This gives the possibility to investigate aspects never considered so far, such as the tendency of a method of over- or undersegmenting groups, or of better dealing with specific group cardinalities. The GRODE metrics have been applied to all the publicly available approaches of group detection, on several datasets, discovering interesting strengths and pitfalls so far neglected from the state-of-the-art metrics
The GRODE metrics: Exploring the performance of group detection approaches
No full textThe detection of groups of people is attracting the attention of many researchers in diverse fields, with a growing number of approaches published each year; despite this, the evaluation metrics are not consolidated, with some measures inherited from the people detection fields, other ones designed specifically for a particular approach, generating a set of not comparable figure of merits. Moreover, existent methods of analysis are scarcely expressive, for example ignoring the fact that groups have different cardinalities, and that obviously larger groups are harder to find. This paper fills this gap presenting GRODE, a suite of measures of accuracy which defines precision and recall on the groups, including the group cardinality as variable. This gives the possibility to investigate aspects never considered so far, such as the tendency of a method of over- or under-segmenting groups, or of better dealing with specific group cardinalities. The metrics have been applied to all the publicly available approaches of group detection, discovering interesting strength and pitfalls of the current literature, and promoting further research in the fiel
Bioenergies in East Africa between challenges and opportunities
No full textThis book is the offspring of the Energy_Agro-Food Synergies in Africa: New Educational Models for Universities, a project co-funded by the EU within the EDULINK II, the ACP-EU Cooperation Programme in Higher Education. The Energy_Agro-Food Project arose from the need to face two crucial issues for the future of East Africa: first, the nexus that links bioenergy and the agro-food sectors with the role that these could have in the socio-economic development of the region; and, second, the capacity of African Universities to fulfill the demand for qualified professionals on the labour market. The present publication represents an outstanding output of the project: it embodies all efforts of researchers to extend the University's capacity to open dialogue with the society as a whole. In particular, this book is designed as teaching material for the African Partner Universities in Ethiopia, Kenya, and Tanzania, thus it is a source of information that supports students' academic understanding, growth, and specialization
La transazione fiscale, onere e opportunità
No full textIl lavoro analizza la mancata ricomprensione dei tributi locali nell'ambito della transazione fiscale
A Liouville theorem for a class of superlinear elliptic equations on cones
No full textWe give sufficient conditions for non-existence of positive solutions of the equation Δu + a(x)u + b(x)up = 0 on a cone of Rn We further analyze the existence of positive solutions in the radial, subcritical case, and show that under suitable conditions on the coefficients, every radial solution whose value in 0 is sufficiently large must vanish. 2000 Mathematics Subject Classification: Primary: 35J60 Secondary: 35B05, 35R45
Indagine Sperimentale sulla Duttilità dei Setti di Controvento in Scala Reale Sottoposti a Carichi Ciclici
No full textIl lavoro affronta lo studio della duttilità dei setti di controvento antisismici in calcestruzzo armato. Il comportamento dei setti nel campo di spostamenti oltre il limite elastico pone ancora dei problemi, in particolare dovuti all’incertezza relativa alla loro duttilità. Recenti lavori sperimentali hanno infatti messo in evidenza il rischio di una crisi per taglio alla base dei setti che può penalizzare fortemente la loro capacità di spostamento. Nel presente lavoro sono riportati i risultati più significativi di una prova sperimentale, a scala reale, su un setto di controvento dimensionato per un edificio di cinque piani, sottoposto a carichi orizzontali ciclici. Nel lavoro sperimentale il problema della limitata duttilità flessionale dovuta al taglio è stato risolto adottando armature di grosso diametro uniformemente distribuite lungo l’intera sezione. Il setto di indagine ha raggiunto una duttilità in termini di spostamento superiore a sei, con un drift massimo del 2,5%, senza decadimento di resistenza e senza significativi fenomeni di scorrimento nella zona critica di base. La prova ha permesso di valutare l’estensione della regione a comportamento plastico e di dare indicazioni sulla lunghezza della cerniera plastica equivalente. Accanto ai risultati sperimentali sono riportate alcune semplici formulazioni analitiche che, avvalorate dal confronto con i dati sperimentali, possono costituire un primo riferimento per la valutazione delle caratteristiche necessarie per le verifiche sismiche, quali la capacità di spostamento, la duttilità e la resistenza ultima del setto rispetto a quella di inizio di snervamento
- …
