3,575 research outputs found
Local Hypothesis Testing for Functional Data: Extending False Discovery Rate to the Functional Framework
No full textA topic which is becoming more and more popular in Functional Data Analysis is local inference, i.e., the continuous statistical testing of a null hypothesis along the domain. This can be seen as an extreme case of the multiple comparison problem. During the talk, we will define and discuss the notion of False Discovery Rate (FDR) in the setting of functional data.We will then introduce a new procedure (i.e., a continuous version of the Benjamini-Hochberg procedure) able to control the FDR over the functional domain, describe its properties in terms of control of the Type-I error probability and of consistency. The proposed method will be applied to satellite measurements of Earth temperature with the aim of identifying the regions of the planet where temperature has significantly increased in the last decades
Local inference on functional data based on the control of the family-wise error rate
No full textIn this work we focus on the problem of local inference for functional data. We describe a unified framework for testing hypotheses on functional data in a local perspective. The result of the testing procedures within the unified framework is an adjusted p-value function that can be used to select the areas of the domain responsible for the rejection of the null hypothesis. We discuss how different state of the art inferential procedures fall within the framework, and briefly describe a novel testing procedure with sound theoretical properties
La riqualificazione come strumento per la promozione della sicurezza urbana
No full textIl volume illustra i risultati di una ricerca condotta nell'ambito dell'Osservatorio permanente sulla riqualificazione urbana organizzato dalla Regione Emilia Romagna, dal DAPT dell'Università di Bologna e dal DA dell'Università di Ferrara. Il tema della sicurezza viene analizzato come un aspetto essenziale dei programmi complessi di riqualificazione. Viene posto particolare attenzione alle problematiche dello spazio pubblico, spesso trascurato dagli strumenti di pianificazione e da un approccio ricorrente alla progettazione urbana che tende a privilegiare l'edificato
Parallel Flow Evaluation and Preconditioning of Gradient Eigensolvers
No full textDeveloping parallel codes
for computing the nonlinear
flow in multiaquifer porous systems is an important task both for
improving model efficiency
and for performing large real-life simulations.
When
highly compressible multiaquifer systems are considered,
the flow inside some layers
is governed by nonlinear equations.
An effective Finite Element (FE)
procedure for solving these equations was developed,
relying upon the partition of the
solution procedure into layer-wise steps.
Such procedure was implemented and tested
on a multi--processor computer.
A satisfactory degree of parallelization was achieved when computing
the flow in a
realistic nonlinear multiaquifer system.
While studying numerical models, we analyzed the topic of computing
a small number of the
leftmost eigenpairs in the generalized problem Ax=l Bx,
where A and B are large, sparse,
symmetric positive definite FE matrices, arising from the
numrical integration of our models.
The eigenpairs are needed both for evaluating relevant characteristics
of our systems, and for developing parallel PDE solvers.
Our optimization method for evaluating
a number of the smallest eigenpairs, called DACG
(Deflation-Accelerated Conjugate Gradient), was parallelized.
When effectively preconditioned,
the efficiency of DACG well compares with that of
established packages.
Some approximate inverse preconditioners,
as accelerators for our parallel DACG, were studied.
Their performance and their
potential in performing parallel computations were analyzed
The usefulness of prognostic inflammatory and nutritional index (pini) in hemodialysis population
No full textBackground: Protein-Energy Wasting and inflammation are the principal risk factors of haemodialysis complications. Aim: We evaluated the reliability of a simple and non expensive test, Prognostic Inflammatory and Nutritional Index (PINI), for regular screening of maintenance hemodialysis (MHD) patients in order to detect early the onset of inflammation and malnutrition. Methods and Results: 121 adult patients on maintenance dialysis were followed up for 32 months and screened every 6 months for PINI, calculated as alpha1-Acid Glycoprotein (AG) x C-Reactive Protein (CRP)/Albumin x Transthyretin. PINI score ≤1 was considered normal. Patients were stratified according to their PINI score: 86 patients (71.66%) had a normal score, whereas 35 (28.33%) had PINI>1. The latter had also higher CRP levels, despite no clinical evidence of inflammation was found at the time of enrolment. Survival in patients with normal PINI was similar to patients with normal CRP, while in patients with abnormal PINI it was significantly lower than in patients with low serum albumin (p<0.05) or elevated CRP (p<0.05). After follow-up, all survived MHD patients with PINI>1 had at least 1 cardiovascular event vs. 2.5% of patients with PINI<1. Conclusion: the assessment of PINI can reliably identify MHD patients at higher risk of mortality and morbidity, even in absence of overt Malnutrition Inflammation Complex Syndrome (MICS). This simple test appears to be more sensitive and specific of the single components, and not expensive, so that it could be routinely used to individuate patients with sub-clinical inflammation and/or malnutrition
The DMLPG meshless technique for Poisson problems
No full textMeshless Local Petrov Galerkin (MLPG) techniques are pure mesh-less methods nowadays used to solve a large class of Partial Di erential Equations. Recently, the Direct MLPG (DMLPG) techniques have been proposed. They are based upon the Generalized Least Square Method. DMLPG technique alleviates some difficulties found in MLPG, such as tricky numerical integration. In this article we report our expansion of DMLPG techniques to 3D Poisson problems. We also compare MLPG vs DMLPG performances
Predicting and improving smart mobility: a robust model-based approach to the BikeMi BSS = Prevedere e migliorare la mobilita smart: un approccio robusto di classificazione applicato a BikeMi
No full textI sistemi di Bike Sharing giocano un ruolo centrale nella mobilita sosteni- ` bile, uno dei sei pilastri che indentificano una Smart City. Motivati da un set di dati disponibile online, questo lavoro presenta l’utilizzo di due modelli di classificazione robusta per prevedere il manifestarsi di situazioni in cui una bike station sia piena e/o vuota, cos`ı creando perdita di domanda ed insoddisfazione nei clienti. Esperimenti di classificazione sulle stazioni BikeMi nel centro di Milano evidenziano l’efficacia dei metodi proposti.Bike Sharing Systems play a central role in what is identified to be one of the six pillars of a Smart City: smart mobility. Motivated by a freely available dataset, we discuss the employment of two robust model-based classifiers for pre- dicting the occurrence of situations in which a bike station is either empty or full, thus possibly creating demand loss and customer dissatisfaction. Experiments on BikeMi stations located in the central area of Milan are provided to underline the benefits of the proposed methods
First report of a polychelid lobster (Crustacea: Decapoda: Coleiidae) from the Early Cretaceous of Italy
No full textWe report Coleia appenninica n. sp. (Coleiidae Van Straelen, 1925) discovered inside a concretion from Calderino, Northern Apennines (Bologna, Emilia Romagna, N Italy). In this area, blocks and rare concretions are present from the Lower and Upper Cretaceous, coming from the washing away of clays of the “Argille Varicolori del Samoggia unit” (AVS). The discovery of this species is exceptional not only for the rarity of fossils inside these blocks, but also because it extends the stratigraphical range for the genus to, at least, the Early Cretaceous. Coleia appenninica n. sp. represents the third unambiguous record of a Cretaceous polychelid decapod in the Tethyans realm
Cervantes in Italia: Contributo a un saggio bibliografico sul cervantismo italiano (con un'appendice sulle trasposizioni musicali)
No full textBibliografia che sottolinea e rivaluta l'esistenza del cervantismo italian
MESHLESS TECHNIQUES FOR ANISOTROPIC DIFFUSION
No full textMeshless Local Petrov Galerkin (MLPG) methods are pure meshless techniques for solving Partial Differential Equations. They have been successfully used for solving many real-life problems. Their efficiency is downgraded by the requirement of performing numerical multi-dimensional integration of tricky, non-polynomial factors. Recently, Direct MLPG (DMLPG) methods have been proposed. DMLPG techniques require lower computational costs with respect to their MLPG counterparts. The DMLPG accuracy has been initially ana- lyzed in few papers, but its performance is quite unexplored. In this paper, we perform numerical comparisons between MLPG and DMLPG accuracy and efficiency in solving anisotropic diffusion problems. In particular, we set different boundary conditions, in order to check if and when MLPG and/or DMLPG suffer locking effects
- …
