Projects

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.

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.

Temporal information plays a very important role in many analysis tasks, and can be encoded in at least two different ways. It can be modeled by discrete sequences of events as, for example, in the business intelligence domain, with the aim of tracking the evolution of customer behaviors over time. Alternatively, it can be represented by time series, as in the stock market to characterize price histories. In some analysis tasks, temporal information is complemented by other kinds of data, which may be represented by static attributes, e.g., categorical or numerical ones. In order to deal with such heterogenous datasets, we developed J48SS, a novel decision tree inducer capable of natively mixing static (i.e., numerical and categorical), sequential, and time series data for classification purposes. The novel algorithm is based on the popular C4.5 decision tree learner, and it relies on the concepts of frequent pattern extraction and time series shapelet generation. The model is capable of providing competitive classification performances, while generating highly interpretable models and effectively reducing the data preparation effort. 

Computerized data management is playing an ever more increasing important role in Public Administration. Government agencies are now heavily dependent on the use of information and communications technology, in a certain sense,  we can say that the data (digital information) are currently the `money 'of public administration. In every nation, the information managed by the public administration in general is a significant component of the overall information economy and knowledge. The data of the public administration are the foundation on which rely the decision-making process of public management itself. Originally, data and information were kept in paper form, with the following obvious problems: making difficult to find possible inconsistency between multiple copies of the same data and the need for a large space to keep the archives. Thanks to the advent of information technology has been possible to solve some of these problems. In particular, thanks to digital data, the employment problem of space is less and data retrieval is almost instantly done. That said, poor implementation of the computer system may cause problems (for example, problems of consistency or integrity of the data). For such reasons it is of fundamental importance, to provide automated methods for systematically accessing to the management  of the available right information,  making it more accessible and transparent  to the citizens.

The data managed by public authorities have a significant space component. Careful management of space data increases the efficiency of the services provided and allows you to extract new information of interest from existing ones through appropriate spatial analysis. For example, addresses have clearly a spatial component, which is fundamental for many activities. The delivery of mail to the management of emergencies; Furthermore, the house number can be associated to information Identifyng to provide a placement of the subjects on the territory useful for statistical purposes,. Between public administrations that can benefit from the use of GIS systems, municipalities, which make up the mesh of elementary administrative territory, are located in the front row.

The horse trail is a route walking horse, almost never paved, reaching and crossing places such as natural parks, reserves, forests, hills and valleys beyond, along lakes and rivers, and reach cultural places like archaeological sites, buildings historic houses and villages . The horse trail allows, therefore, the practice dell'equiturismo (tourism horse), but can also be used for the Walk (hiking) or mountain biking (cycling). Born as horseback riding trails mainly on horseback, in it it is generally provided seats and stage, ie stations equipped rest, preferably not too far apart, where rider and horse can find assistance, refreshments and the chance to spend the night (in guesthouses , cottages, farmhouses private or public shelters).