Description: Over the last decades, the advancements in microelectronic technologies allowed for the embedding of complex digital sensors in several systems, ranging from home appliances to health tracking devices and industrial plant machinery. The resulting systems are, in general, quite complex, given the possible heterogeneity of their components and the non-trivial ways in which sensors may interact. In critical domains, formal methods have been employed to ensure the correct behaviour of a system. However, a complete specification of all the properties that have to be guaranteed turns out to be often out of reach, due to the inherent complexity of the system and of its interactions with the environment in which it operates. To overcome these limitations, some approaches that complement formal verification with model-based testing and monitoring have been recently proposed. In this project, we investigate the opportunity of pairing monitoring with machine learning techniques in order to improve its ability of detecting critical system behaviours.

Partner representatives: 

Dr. Federico Pittino

Description: Obstructive sleep apnea syndrome (OSAS) is a breathing disorder characterized by episodes of obstruction of the upper airways during sleep, resulting in phasic reductions of blood oxygen saturation. The gold-standard for diagnosing OSAS is polysomnography, a relatively resource- and cost-intensive exam. Stroke is defined as an acute-onset neurological deficit lasting at least 24 hours, due to either ischemic or hemorragic damage to the brain. Patients with acute stroke undergo a 24-to-48-hour continuous monitoring of vital signs, including EKG, photoplethysmography for blood oxygen saturation and blood pressure. OSAS is a known risk factor for ischemic stroke; moreover, untreated OSAS in the acute phase of stroke treatment is related to a worse rehabilitation outcome. Unfortunately, the high incidence of acute stroke excludes the possibility for every patient with acute stroke to undergo a polysomnography. Thus, a simple and low-cost alternative screening method is definitely needed in order to detect OSAS. The aim of our project is to develop a model to predict the presence of OSAS based exclusively on data extracted from continuous monitoring of vital signs, which cannot currently be done by the medical staff.

Partner representatives: 

Dr. Gian Luigi Gigli

Description: Aim of the project is the study of spatial trajectories, both regarding their modelling and analysis. The management of trajectories for mobile devices is an emerging challenge, together with the problem of repeating patterns from the same device and between different devices. The addition of a notion of trajectory (path) arises from the observation that devices do not move randomly, and many of them typically perform some recurrent journey. Such a notion will allow one to explicitly use information arising from the sequence of known positions from a device. Moreover, rather than restricting the attention to the behaviour of a single device, some kind of  devices mass behaviour may be identified.

Partner representatives: 

Dr. Chris Marshall, Dr. Andrea Dalla Torre

Description: The ever more accurate search of deep analysis in customer data is really appealing to che companies and it is a really strong technological trend nowadays. Speech analytics is an extremely powerful methodology for gaining insights from unstructured data coming both from customer conversations and from human agents in a contact center. Among the several benefits speech analytics can deliver, training and performance improvement of human agents is an important driver for a better customer experience. In this project, a speech analytics process for an Italian contact center, that deals with call registrations extracted from inbound or outbound flows is developed.

Partner representatives: 

MSc. Enrico Marzano