Il Dottorato di Ricerca in Informatica e Matematica ha avuto dal PON RI 2014-2020 il finanziamento di borse aggiuntive.
Con il Decreto Direttoriale 29 luglio 2016, n. 1540, e D.D. 5 giugno 2017, n.1377, il Ministero dell'Istruzione, dell'Università e della Ricerca (MIUR) ha avviato e proseguito, rispettivamente, l'attuazione delle misure a sostegno del capitale umano previste dal PON Ricerca e Innovazione 2014-2020 (PON RI):
Asse I - Investimenti in capitale umano
Azione I.1 Dottorati Innovativi con caratterizzazione industriale.
L'intervento si inserisce all'interno del Programma Nazionale della Ricerca 2015-2020 e prevede il finanziamento di borse di dottorato di durata triennale, cofinanziate dal Fondo sociale europeo (FSE), aggiuntive rispetto a quelle già finanziate dalle Università.
Il PON RI 2014-2020 interessa le regioni in transizione (Abruzzo, Molise e Sardegna) e le regioni in ritardo di sviluppo (Basilicata, Calabria, Campania, Puglia, Sicilia) con una dotazione finanziaria complessiva di 1.286 milioni di euro. Ulteriori dettagli a http://www.ponricerca.gov.it
Obiettivo prioritario del PON RI è il riposizionamento competitivo delle regioni più svantaggiate allo scopo di produrre mutamenti di valenza strutturale per accrescere la capacità di produrre e utilizzare ricerca e innovazione di qualità per l'innesco di uno sviluppo intelligente, sostenibile e inclusivo. Si intende pertanto intensificare la collaborazione con il mondo imprenditoriale e consentire ai dottorandi di qualificare "in senso industriale" le proprie esperienze formative e di ricerca, con ricadute sia sul tessuto produttivo dei territori interessati dal programma sia occupazionali.
Ciclo XXXII - Anno Accademico 2016/2017
Finanziamento di 166 borse di dottorato innovativo con caratterizzazione industriale (Decreto direttoriale n. 353 del 16 febbraio 2017), di cui:
Il Dottorato in Informatica e Matematica ha avuto il finanziamento di 1 borsa aggiuntiva:
Tema di ricerca: Modelli, tecniche e strumenti per l'analisi predittiva di grandi quantità di dati attraverso tecniche visuali interattive . CUP H96D17000040006, importo del finanziamento € 75.177,60. Per ulteriori dettagli clicca qui
Ciclo XXXIII - Anno Accademico 2017/2018
Finanziamento di 479 borse di dottorato innovativo con caratterizzazione industriale (Decreto direttoriale n. 3749 del 29 dicembre 2017), di cui:
PON fellowship XXXII cycle - PhD Student Alessandra LEGRETTO
Models, techniques and tools for predictive analysis of large quantity of data through interactive visual techniques
The research aims to investigate innovative models, techniques and tools of Predictive Visual Analytics, which may represent a very good support for the Big Data analyst. Today, analysts increasingly deal with Big Data, that are data collections that require storage, management and analysis capabilities that traditional systems cannot provide. Predictive analysis is an important part of data analysis. Statistics and Machine Learning provide various predictive methods mainly for regression and classification purposes. Recent research has begun to consider interactive visual approaches in order to improve predictive analysis. Visual Analytics techniques use interactive visualizations to provide the analysts with additional knowledge about the data allowing them to guide the analysis process. In this area, there are a number of open issues to be investigated.
The research is carried out in collaboration with the Links company in Lecce and the New York University in New York, USA.
PON fellowship XXXIII cycle - PhD Student Lucio COLIZZI
Business Process Management (BPM) e Case Management (CM) for Enhanced Care Pathway
In the last two decades there has been a growing interest in investigating the correlation between funds spent in private/public healthcare and the actual quality of service as perceived by citizens accessing medical care services. This issue, also called disease management, is defined as the complex decision making process aiming to determine a program of coordinated healthcare interventions minimizing both the healthcare costs and the effects of disease for individuals.
This industrial PhD program will focus on how tools and methodologies coming from Business Processes Management (BPM) and Case Management (CM - coordination of services on behalf of an individual person who may be considered a case in different settings such as health care, nursing, rehabilitation, social work, disability insurance, employment, and law) can be integrated in order to support the decision makers, i.e. care managers and medics. In this research stream, one of the main approach will be the Integrated Care Pathway (ICP).
The research is carried out in collaboration with the Openwork srl company in Bari and the University of Castilla Lamancia in Spain.
PON fellowship XXXIII cycle - PhD Student Loredana VERARDI
Pattern-Based Business Process Digitalization
Effective digitalization of business processes is fundamental in order to offer efficient services to users who, for example, would like to connect to the website or make a call to the call center of energy suppliers and have the service activated in a few minutes.
The digitalization of business processes, and their subsequent re-engineering, is a complex task that small and medium-sized enterprises (SMEs) do not always sustain, making necessary maximizing the reuse in different contexts of well-established solutions to recurring problems. The objective of this industrial PhD program is the definition of methodologies and tools for the digitalisation, based on patterns, of business processes in the context of Smart Communities and Industry 4.0. The Internet of Everything (IoE) technological paradigm will be integrated, which allows people and objects to collaborate through the exchange of data and information made available by digital business processes integrated and shared on the network.
The research is carried out in collaboration with AQC Lab in Spain (the only European laboratory accredited by ENAC for the certification of ISO 25,000 products) and with Sincon srl, an SME in Taranto, very active in the field of Digitization.
PON fellowship XXXIV cycle - PhD Student Vincenzo PASQUADIBISCEGLIE
Big Data Analytics for Process Improvement in Organizational Development
Modern information systems that support complex organizational processes maintain significant amounts (event logs) of process execution data describing the sequence of activities of actors involved in the organizational development of a business process. Process mining techniques have recently gained momentum in the analysis of data extracted from event logs as they provide surprising insights for managers, system developers, auditors and end users. Being able to describe and predict behaviour and organization of a process is an important business capability. In particular, the effectiveness of a managerial decision-making response to variation in the environment may strongly depend on the extent to which it can reduce the impact of uncertainty through prediction and conformance.
This industrial PhD project will focus on models, techniques and tools coming from Process Mining, Machine Learning and Big Data analytics, in order to support the organization decision makers in the optimization of productive processes (e.g. marketing strategy, risk planning, resource organization).
The research is carried out in collaboration with the MTMProject srl company in Monopoli and the RWTH Aachen University in Germany.
PON fellowship XXXIV cycle - PhD Student Cristiano TAMBORRINO
Change detection in remote sensing
Technological innovation in recent years has made available various sources of geospatial data, such as satellite and aerial images, optical, radar and point clouds data, elevation models. Big Data in the geospatial field refer to large aggregations of data, whose size and complexity requires more advanced tools than the traditional ones, at all stages of their processing. The Big Data determine several challenges, but also opportunities. Main challenges are related to their complexity, as well as to the difficulty of properly integrate and process data from completely different sources and different in type, characteristics, resolution, size, etc. The proposed research will try to extract high quality information from the available data. In particular we look for change detection strategy, by using a holistic combination of statistical, numerical and spatio-temporal data mining methods. Such a combined approach allows us to obtain information of higher quality and value because they are based on the most comprehensive and integrated analysis.
The research is carried out in collaboration with the company Planetek Italia and with TETIS Lab of Irstea (National Research Institute of Science and Technology for Environment and Agriculture) in Montpellier.
PON fellowship XXXVI cycle - PhD Student Malik Mohammad Mnahi AL-Essa
Machine Learning for Cyber Threat Investigation and Cyber Defense
As the world is becoming more and more digitalized, powerful security precautions are required to make public and private infrastructures more resilient to a broad range of cyber-threats (e.g. network intrusions, malware). During the last decade, the cybersecurity literature has conferred a high-level role to machine learning and, in particular, deep learning as a powerful learning paradigm to detect ever-evolving cyber-threats in modern security systems. Despite the amazing results recently achieved with deep learning methods in securing the digital infrastructures of modern organizations, the security of neural models can easily be jeopardized by adversarial attacks. In addition, neural models are commonly trained as deep neural network black boxes. The explanation of neural model decisions is difficult due to the complexity of the neural network architecture. On the other hand, decision explanations can provide measurable factors whose features influence the detection of cyber-threats and to what extent by disclosing useful insights to strengthen the robustness of cybersecurity systems to evolving cyber-attacks.
This industrial PhD project will focus on models, techniques and tools coming from Machine Learning, Deep Learning, Adversarial Learning and eXplainable Artificial Intelligence, in order to improve the performance of modern machine learning-based cyber-defence systems.
The research is carried out in collaboration with the Security Architect srl company in Bari and the Informatics Department of the King’s College in UK.