A5016716189- Soil Geostatistics and Mapping
- Geochemistry and Geologic Mapping
- Morphological variations and asymmetry
- Bayesian Methods and Mixture Models
- Statistical Methods and Inference
- Spatial and Panel Data Analysis
- Data-Driven Disease Surveillance
- Economic theories and models
- Game Theory and Applications
- Stochastic processes and statistical mechanics
- Human Mobility and Location-Based Analysis
- Cerebrovascular and Carotid Artery Diseases
- Intracranial Aneurysms: Treatment and Complications
- Mineral Processing and Grinding
- Gene expression and cancer classification
- Advanced Statistical Process Monitoring
- Data Management and Algorithms
- Bioinformatics and Genomic Networks
- Statistical Methods in Clinical Trials
- Cardiovascular Health and Disease Prevention
- Advanced Clustering Algorithms Research
- Fault Detection and Control Systems
- Stochastic processes and financial applications
- Blind Source Separation Techniques
- Optimal Experimental Design Methods
Politecnico di Milano
2016-2025
Human Technopole
2018-2023
Siemens (Italy)
2014
Fondazione Politecnico di Milano
2014
Medical Solutions
2014
Ospedale Maggiore
2014
Azienda Socio Sanitaria Territoriale Grande Ospedale Metropolitano Niguarda
2014
Mylan (South Africa)
2010-2013
Mario Negri Institute for Pharmacological Research
2009
Bocconi University
2004
We address the problem of predicting spatially dependent functional data belonging to a Hilbert space, with Functional Data Analysis approach. Having defined new global measures spatial variability for random processes, we derive Universal Kriging predictor data. Consistently established theoretical results, develop two-step procedure georeferenced data: first model selection and estimation mean (drift), then prediction on basis identified model. The proposed methodology is applied daily...
This pilot study is a product of the AneuRisk Project, scientific program that aims at evaluating role vascular geometry and hemodynamics in pathogenesis cerebral aneurysms. By means functional data analyses, we explore dataset to highlight relations between geometric features internal carotid artery, expressed by its radius profile centerline curvature, aneurysm location. After introducing new similarity index for data, eliminate ancillary variability vessel curvature profiles through an...
A framework is developed for inference concerning the covariance operator of a functional random process, where itself an object interest statistical analysis. Distances comparing positive-definite matrices are either extended or shown to be inapplicable data. In particular, infinite-dimensional analogue Procrustes size-and-shape distance developed. Convergence finite-dimensional approximations metrics also shown. For inference, Fréchet estimator both and average introduced. permutation...
The advance of sensor and information technologies is leading to data-rich industrial environments, where large amounts data are potentially available. This study focuses on applications image used more for quality inspection statistical process monitoring. In many cases interest, acquired images consist several similar features that randomly distributed within a given region. Examples pores in parts obtained via casting or additive manufacturing, voids metal foams light-weight components,...
Summary We deal with the problem of efficiently estimating a three-dimensional curve and its derivatives, starting from discrete noisy observation curve. This is now arising in many applicative contexts, thanks to advent devices that provide images measures, such as scanners medical diagnostics. Our research, particular, stems need for accurate estimation curvature an artery, image reconstructions angiographies. has emerged within AneuRisk project, scientific endeavour which aims investigate...
We propose an innovative method for the accurate estimation of surfaces and spatial fields when prior knowledge phenomenon under study is available. The included in model derives from physics, physiology, or mechanics problem at hand, formalized terms a partial differential equation governing behavior, as well conditions that has to satisfy boundary domain. proposed models exploit advanced scientific computing techniques specifically make use finite element method. estimators have penalized...
ABSTRACT The paper arises from the experience of Applied Stochastic Models in Business and Industry which has seen, over years, more contributions related to Machine Learning rather than what was intended as a stochastic model. very notion model (e.g., Gaussian process or Dynamic Linear Model) can be subject change: What is Deep Neural Network if not model? presents views, supported by examples, distinguished researchers field business industrial statistics. They are discussing only whether...
AbstractThe quality characteristics in manufacturing processes are often represented terms of spatially- or time-ordered data, called "profiles", which characterized by amplitude and phase variability. In this context, curve registration plays a key role, as it allows separating the two kinds between-profiles variability reducing any undesired inflation natural mainstream literature, warping functions not generally considered monitoring process, even though may cause significant information...
Abstract We address the problem of stochastic simulation soil particle‐size curves (PSCs) in heterogeneous aquifer systems. Unlike traditional approaches that focus solely on a few selected features PSCs (e.g., quantiles), our approach considers entire and can optionally include conditioning available data. rely prior work to model as cumulative distribution functions interpret their density functional compositions. thus approximate latter through an expansion over appropriate basis...
Abstract We employ mobile network data referred to the area of Lombardy in Italy investigate alternative touristic behaviours, such as same-day visits and overnight stays Italy. show that larger availability tourism accommodations, cultural natural endowments are relevant factors explaining stays. Conversely, temporary entertainment transportation facilities increase municipalities attractiveness for visits. The results also highlight a trade-off capability being attractive connection both...
Abstract Cervical neoplastic lesions are associated with infection by high-risk human papilloma viruses (HPVs). HPV-16 and HPV-18 the most common genotypes. It has been proposed that development of HPV-16-positive cervical is impaired CD4+ T cell immunity against early Ags. The aim study was to evaluate whether this impairment also applies HPV-18. We investigated presence quality anti-HPV-18 E6 responses in blood 37 consecutive patients high-grade lesions, 25 normal donors, 20 cord bloods....
We describe the AneuRisk65 data, obtained from image reconstruction of three-dimensional cerebral angiographies. This dataset was collected for study aneurysmal pathology, within AneuRisk Project. It includes geometrical reconstructions one main vessels, Inner Carotid Artery, described in terms vessel centreline and radius profile. briefly illustrate data derivation processing, explaining various aspects that are interest this applied problem, while also discussing peculiarities critical...