• Publicationsclose
• Research softwareclose
• Other research productsclose
• 2012-2021close
• IT close
• EU close
• IRIS - Università degli Studi di Verona close

We present a novel probabilistic framework that jointly models individuals and groups for tracking. Managing groups is challenging, primarily because of their nonlinear dynamics and complex layout which lead to repeated splitting and merging events. The proposed approach assumes a tight relation of mutual support between the modeling of individuals and groups, promoting the idea that groups are better modeled if individuals are considered and vice versa. This concept is translated in a mathematical model using a decentralized particle filtering framework which deals with a joint individual-group state space. The model factorizes the joint space into two dependent subspaces, where individuals and groups share the knowledge of the joint individual-group distribution. The assignment of people to the different groups (and thus group initialization, split and merge) is implemented by two alternative strategies: using classifiers trained beforehand on statistics of group configurations, and through online learning of a Dirichlet process mixture model, assuming that no training data is available before tracking. These strategies lead to two different methods that can be used on top of any person detector (simulated using the ground truth in our experiments). We provide convincing results on two recent challenging tracking benchmarks.

We present a novel approach to computing Hamming distance and its kernelisation within Topological Quantum Computation. This approach is based on an encoding of two binary strings into a topological Hilbert space, whose inner product yields a natural Hamming distance kernel on the two strings. Kernelisation forges a link with the field of Machine Learning, particularly in relation to binary classifiers such as the Support Vector Machine (SVM). This makes our approach of potential interest to the quantum machine learning community.

Obstructive sleep apnea in children is frequently due to tonsil and adenoid hypertrophy. This study aimed to investigate the relationship between ambulatory clinical parameters and sleep respiratory events in obese children. We carried out a prospective respiratory sleep study between 2013 and 2015. Nails obstruction, tonsils enlargement and palate position were subjectively measured. Italian attention deficit hyperactivity disorder (ADHD) rating scale for parents was also performed. The polygraph study was performed using a portable ambulatory device. Forty-four obese children were consecutively recruited into this study. Mild sleep respiratory disturbance was showed in 31.8 % of patients; 18.2% previously had an adeno (tonsillectomy). In 50% of these obese children, both apnea-hypopnea index and oxygen desaturation index showed polygraph abnormal results. ADHD rating scale for parents scores were positive in 9.1% of patients. We found a high rate of mild sleep respiratory disturbance and ADHD-like symptoms referred by parents. The respiratory disturbance was not totally cured by surgery. Finally, otorhinolaryngology variables were not able to explain mild sleep respiratory disturbance.

Autophagy is involved in different degenerative diseases and it may control epigenetic modifications, metabolic processes, stem cells differentiation as well as apoptosis. Autophagy plays a key role in maintaining the homeostasis of cartilage, the tissue produced by chondrocytes; its impairment has been associated to cartilage dysfunctions such as osteoarthritis (OA). Due to their location in a reduced oxygen context, both differentiating and mature chondrocytes are at risk of premature apoptosis, which can be prevented by autophagy. AutophagomiRNAs, which regulate the autophagic process, have been found differentially expressed in OA. AutophagomiRNAs, as well as other regulatory molecules, may also be useful as therapeutic targets. In this review, we describe and discuss the role of autophagy in OA, focusing mainly on the control of autophagomiRNAs in OA pathogenesis and their potential therapeutic applications.