XL Cycle
Up to 10 students can enroll in the XL Cycle of the PhD Program in Computer and Data Science for Technological and Social Innovation. 8 of these 10 positions are funded with a scholarship:
– 3 scholarships are without a specific topic (the topic can be chosen among the ones available in the first list below)
– 5 scholarships have a specific topic (the topic can be chosen from the lists after the first one)
Themes for the 3 scholarships without specific topic (and for the 2 positions without scholarship)
| a | Autonomic computing for collective self-adaptive systems |
| | Keywords: Autonomic computing, distributed systems, adaptive systems, IoT, autonomous vehicles Research objectives: Collective adaptive systems are more and more spreading in our life. Situations like sets of mobile phones or IoT devices are becoming real and can be exploited to support human activities, but this requires appropriate approaches to be managed; in the future we envision sets of autonomous vehicles that must be coordinated. Autonomic computing is a very good candidate paradigm to address these scenarios. The objective of the research is to define a framework for the development of collective self-adaptive systems, based on autonomic computing. The framework will be composed of a methodology that guides the developers in the development addressing the self-* properties, and of tools enabling the support for the developers. Some case studies will be proposed to test the framework. Proposed research activity: • State of the art in autonomic computing • State of the art in collective adaptive systems • Definition of a framework for autonomic computing in collective adaptive systems • Definition of a methodology • Definition of case studies • Test of the framework • Participation to relevant international school Supporting research projects (and Department) H2020 – FIRST (FIM) Possible connections with research groups, companies, universities. Dr. Antonio Bucchiarone, FBK Trento (I) Dr. Lai Xu, Bournemouth University (UK) Prof. Emma Hart, Edinburgh Napier University (UK) Prof. Marco Aiello, Stuttgart University (D) Supervisor: Prof. Giacomo Cabri |
| b | Software engineering for autonomous vehicles |
| | Keywords: Software engineering, autonomous vehicles, distributed systems, adaptive systems, IoT Research objectives: Autonomous vehicles are spreading and more and more research is needed to enable their engineering. In particular, both the single vehicle and the coordination of sets of vehicles rely on software components that must be designed, implemented and verified; the current methods and methodologies could not be suitable for this new scenario. Appropriate approaches are needed. The objective of the research is studying the (meta)requirements of the development of software components and systems for autonomous vehicles, in order to define one or more approaches that are suitable for this scenario. Proposed research activity: • State of the art in software engineering • State of the art in autonomous vehicles • Definition of approaches to engineer the development of software components and systems for autonomous vehicles • Definition of a methodology • Definition of case studies • Test of the proposed approaches • Participation to relevant international school Supporting research projects (and Department): WASABI 2023 (FIM) Possible connections with research groups, companies, universities: Dr. Antonio Bucchiarone, FBK Trento (I) Prof. Emma Hart, Edinburgh Napier University (UK) Prof. Marco Aiello, Stuttgart University (D) Supervisor: Prof. Giacomo Cabri |
| c | Efficient confidential and verifiable data management strategies |
| | Keywords: Cyber security, Applied cryptography, Databases, Data structures Research objectives: Emerging security solutions try to minimize systems attack surface and mitigate information leakage even in presence of partially compromised systems. Among those, promising advanced cryptographic strategies are being studied to enable efficient query execution on encrypted databases and to verify correct execution of queries on data. These security solutions help mitigating data breaches perpetrated by external adversaries or even worse by legitimate insiders, and enable strong auditing strategies for outsourced data managed by external parties. The research activity focuses on studying state-of-the-art for database security and encryption, analyzing practical techniques for achieving practical performance and acceptable security, designing engineering strategies to embed these techniques within real-world database systems. Proposed research activity: • State of the art on database encryption and verification • Analyzing trade-offs in terms of security and performance • Designing novel strategies for improving security and performance of encrypted data • Evaluating security of existing and novel techniques • Studying solutions for proper integration with existing database management systems • Implementation of proof of concepts for performance evaluation Supervisor: Luca Ferretti |
| d | Multi-level organization of complex systems |
| | Keywords: Information theory, evolutionary computation, nonlinear dynamics, criticality, adaptation Research objectives: The detection of emerging intermediate structures in complex systems is not always a trivial task, while in contrast their characterization can lead to a meaningful description of the overall properties of the system, and in this way to its understanding. A large part of these structures is characterized by groups of variables (genes, chemical species, individuals, agents, robots…) that appear to be well coordinated among themselves and have a relatively weaker interaction with the remainder of the system. Notable examples are functional neuronal regions in the brain, autocatalytic systems in chemistry, or communities in socio-technological systems. We are therefore interested in identifying and studying such structures, proposing algorithms for their understanding and analyzing data from the world of biology, of socio-technological systems and of artificial systems. Supervisor: Prof. Marco Villani |
| e | Evolving artificial systems |
| | Keywords: Information theory, evolutionary computation, nonlinear dynamics, criticality, adaptation Research objectives: Finding general properties of evolving systems has proven extremely difficult. A particularly interesting proposal is that evolution (either natural or artificial) drives complex systems towards “dynamically critical” states, which may have relevant advantages with respect to systems whose dynamics is ordered or disordered. According to this hypothesis, these critical systems can provide an optimal balance between stability and responsiveness. In this thesis we aim at determining under which conditions this turns out to be the case, by using abstract models. The systems described by these models will interact in an abstract “environment”, and the conditions under which critical systems have an edge will be analyzed. To achieve this ambitious goal, we will exploit the synergy among dynamical systems methods, information theory and evolutionary computation. Supervisor: Prof. Marco Villani |
| f | Multi-user activity recognition |
| | Keywords: activity recognition, inertial sensor, machine learning Research objectives: Human Actitivy Recognition (HAR) is a set of techniques which identifies the activity a user is performing, through the analysis of a set of sensors which describe actions and movements from users. This allows to configure a computing system based on the current scenario of the user, and provide a more tailored experience. More recently classic HAR system have also been proposed to detect and classify group actions, in which it is not only important to classify signals obtained from a single person, but also to share data among a set of devices carried by different people, which is the main topic of this thesis work. Proposed research activity: • State of the art on HAR for groups of people • Design and development of a data gathering platform • Analysis and study of techniques to realize HAR for groups of people • Participation to relevant international schools and conferences Possible connections with research groups, companies, universities: University of Stuttgart (Germany), University of Bamberg (Germany), University of New South Wales (Australia) Supervisor: Prof. Luca Bedogni |
| g | Real-time Collaborative 3D Editing |
| | Keywords: Research objectives: Collaborative editing ala Google Docs is still not widespread in the 3D world. The goal of this thesis is to explore real-time collaborative models for 3D. We obtain encouraging first results by extending distributed version control, ala git and GitHub, to 3D content. In this thesis, we plan to explore the design space of real-time collaborative 3D editing, focusing on local-first models such as CRDTs and differential synchronization. The thesis work be fully focused on developing new algorithm and data structure for graphics, disregarding all other aspects of real-world collaborative systems, such as security, networking, authentication, etc. No prior knowledge of distributed systems is required.Our prior work on version control for 3D includes: • MeshGit • MeshHisto • cSculpt • SceneGit • others under review Supervisor: Prof. Fabio Pellacini |
| h | AI-assisted Computer Graphics: Diffusion Models on Surfaces |
| | Keywords: Computer Graphics, Artificial Intelligence, Neural Networks, Diffusion Models Research objectives: Diffusion models, like Stable Diffusion, Dalle, etc, are the backbone of modern image synthesis. The goal of this project is to adapt these models for the generation of textures for 3D assets, normally used in design, games and movies. Diffusion models are designed to work on the image plane. The goal of this project is to adapt the use of diffusion models to generate images onto the surface of 3d objects. We expect the work to focus on the AI aspects of the synthesis, rather than its graphics counterparts. Supervisor: Prof. Fabio Pellacini |
| i | AI-assisted Computer Graphics: Procedural Proxies for Parameter Estimation and Program Synthesis |
| | Keywords: Computer Graphics, Artificial Intelligence, Neural Networks, Automatic Differentiation Research objectives: The textures and patterns used to define the appearance of 3D objects are either measured, hand-painted, or synthesized by programs. The latter category, sometimes called procedural models, is the most scalable in the production of large amounts of content. But procedural models are hard to control. The goal of this project is to explore new algorithms for controlling procedural appearance models using recent results in artificial intelligence. In particular, we will explore the idea of building neural network proxies that for each model produce a simplified program that is easier to control. The proxy will be used to determine the program parameters via automatic differentiation, and possibly change the program via program synthesis. We expect the work to focus on the AI aspects of the synthesis, rather than its graphics counterparts. Supervisor: Prof. Fabio Pellacini |
| j | Innovation ecosystems, industrial districts, and global value chains: a network approach |
| | Keywords: social network analysis, industrial districts, global value chain, sustainability, innovation Research objectives: Globalization has increased the speed of competition, continuously generating new opportunities and threats, where flexibility and innovation play a fundamental role. Industrial districts and global value chains are particularly affected by international dynamics and processes, and innovation is key for companies – located in industrial districts and embedded in global value chains – aiming to be successful in global markets. As part of their strategy, these companies rely on business networks to become more innovative and improve their performance. Social Network Analysis (SNA) is a powerful tool to assess the importance of (local and global) business networks and their impact on companies’ performance, and the proposed research will be focusing on the analysis of: • inter-organizational networks; • intra-organizational networks; • dynamic business networks; • novel approaches for mapping business networks. Supervisor: Prof. Stefano Ghinoi Possible connections with other international universities: • Prof. Bodo Steiner, University of Helsinki (FI) • Prof. Riccardo De Vita, Manchester Metropolitan University (UK) • Prof. Guido Conaldi, University of Greenwich (UK) |
| k | A modern and innovative learning system to enable efficient, lean and cost-effective public administration |
| | Keywords: digital twins, recommendation systems, video lectures, learning experience Research Objectives: Topics are digital transition, big data, accessibility and inclusiveness within educational systems. In particular, the research program focuses on the development of personalized learning models able to achieve two sustainability objectives specified by the United Nations General Assembly. These are SDG4 (Quality education — Ensure inclusive and equitable quality education and promote university learning opportunities for all) and SGD 10 (Reduced inequality — Reduce inequalities among on-site and on-line students and limit digital barriers to students with disabilities). Supervisor: Prof. Marco Furini Co-supervisor: Prof. Manuela Montangero |
| l | Phylogenetic algorithms for evolutionarily modeling of natural language syntax |
| | Keywords: quantitative phylogenetics, Bayesian analysis, syntactic parameters, natural language, historical reconstruction Research objectives: Work out dedicated phylogenetic algorithms to extract a historical signal from abstract natural language data (syntactic parameters), to reconstruct their ancestral states, and to explain their transmission and diversification across time. The novelty of the project consists in the implementation of computational phylogenetic algorithms on a type of abstract structures (syntactic parameters) which are not traditionally employed in quantitative phylogenetics, ad whose formal properties (a multilayered deductive structure, www.parametricomparison.unimore.it) require purposedly devised tools (Ceolin et al 2021). Possible connections with research groups, companies, universities: Research on this project will be conducted in collaboration with the Center for Language history and diversity, of which the Dipartimento di Comunicazione ed Economia is a member, and the Department of Linguistics at York, with whom the DCE has an academic cooperation agreement. Supervisor: Prof. Cristina Guardiano |
| m | Modeling structural interdependencies and their effects in constraining language diversity |
| | Keywords: syntactic parameters, networks, binary strings, implicational structure, machine learning, language transmission and change Research objectives: Explore the multi-layered deductive structure of natural language grammars and its eWects in constraining language diversity. In formal cognitive approaches to language structure and diversity, crosslinguistic structural variation is assumed to be universally constrained by a finite set of abstract points of variation (syntactic parameters, www.parametricomparison.unimore.it) whose reciprocal interactions generate the observed surface diversity across languages. The latter turns out to be entirely predictable once the subset of variable abstract structures and their reciprocal interactions is fully defined and formalized (Bortolussi et al 2011). The purpose of this project is to investigate parameter interdependencies and their eWects on language acquisition and change, through the implementation of machine learning techniques and data-driven approaches able to disclose dependencies which cannot be identified through manual data analysis, to formalize implicational rules among parameters, and to compare them with those produced by linguists’ expert judgement. These procedures will be aimed at: (a) discovering parameters that can be entirely dispensable as fully deducible from other parameters; (b) detecting partial dependencies among parameters; (c) observing the distribution of parameter states and implications within selected language families and across families. Possible connections with research groups, companies, universities: The envisaged research is part of the project “Parameter theory on historical corpora: Measuring the power of parameter setting theory on historical corpora” (MUR PRIN 2022 20224XEE9P – PARTHICO). Research will be also conducted in collaboration with the Center for Language history and diversity, of which the Dipartimento di Comunicazione ed Economia is a member, and the Department of Linguistics at York, with whom the DCE has an academic cooperation agreement. Supervisor: Prof. Cristina Guardiano |
| n | Extending monolithic kernels to increase robustness, security and maintainability |
| | Keywords: operating-system design, safety, security, performance. Research objectives: Important operating-system kernels, such as Linux, have a monolithic structure. That is, they have a single memory address space, and any piece of their code can access any location of the address space. This comes with various benefits and drawbacks. The most obvious benefit is performance and implementation simplicity, the disadvantage is increased system fragility and attack surface. In addition, they suffer from an important maintenance issue: in mainstream kernels, components that depend on each other often happen to be developed independently from each other. But independent changes in some of those component easily break dependent components. The goal of this research activity is to find ways for improving monolithic kernels, so as to mitigate (hopefully substantially) all problems above, while retaining most of the benefits of the original monolithic model. Supervisor: Dr. Paolo Valente |
| o | Digital Twins on Mobile devices |
| | Keywords: digital twins, mobile development, simulation Research objectives: In recent years, the concept of a Digital Twin— a digital replica of physical systems used for monitoring, simulation, and optimization—has gained significant traction across various industries. This thesis investigates the technological advancements enabling this transition, including the integration of mobile sensing, real-time data processing, and edge computing. It focus specifically on mobile devices, owned by user, to raise the privacy of the data produced by such mobile devices, without the need to offload it completely to an edge or cloud server. Several case studies are examined to demonstrate the practical applications of mobile-based Digital Twins across different sectors such as healthcare, manufacturing, and smart cities. In healthcare, for instance, the implementation of Digital Twins on smartphones can enhance personalized health monitoring and predictive analytics. In manufacturing, mobile Digital Twins enable real-time monitoring and maintenance of equipment even in remote locations. For smart cities, they provide dynamic management and optimization of urban infrastructure. Proposed research activity: • State of the art on DT and mobile devices • design and development of mobile DT • implementation of shadowing • user acceptance Possible connections with research groups, companies, universities: UCI, UNSW, Bonfiglioli consulting Supervisor: Prof. Luca Bedogni |
| p | Efficient, scalable and flexible device to edge offloading |
| | Keywords: edge computing, machine learning, smart systems, context-aware-computing Research objectives: Edge computing refers to computing units which are placed at the edge of the network, close to the end devices. They typically serve as a lower latency computing unit to process information which devices cannot process on their own, due to battery or computational constraints. However the problem of defining how, when and what data has to be offloaded from a device to an Edge server is yet to be solved, as it encompasses a series of different parameters to take into account such as the operational characteristics of both the device and the edge server, the network, the time contraints on the results and so on. In this research these the PhD candidate will work towards a generalized model for Edge computing offloading from smart devices, which must take into account the heterogeneity of the data, the operational constraints of the device and of the edge server, the service quality to meet. Proposed research activity: • State of the art on Edge computing offloading • Design and implementation of a general purpose testbed for Device-to-edge offloading • Design, implementation and evaluation of Device-to-edge offloading protocols and techniques • Participation to relevant international schools and conferences Possible connections with research groups, companies, universities: University of California, Irvine (USA) Supervisor: Prof. Luca Bedogni |
| q | Automated Cyber Operations |
| | Keywords: cyber security, graph theory, planning, automation, artificial intelligence Research objectives: The volume and complexity of modern attacks and defenses (as testified by the size of the CVE, CWE, CAPEC, MITRE ATTACK catalogues) is making manual exploitation and hardening of systems increasingly unfeasible. In the next few years we foresee an adoption of even more automated offensive and defensive tools and decision makers. This research thesis is motivated by the need for frameworks, algorithms, tools that help the human operator to carry on offensive operations (vulnerability assessments, penetration testing) and defensive operations (systems hardening, source code auditing) in a semi-automated fashion. The main goal is to explore the potential for automation and artificial intelligence in the activities involved in classical security assessments (representation of security-related knowledge, decision making, task planning and execution, creating digital twins, monitoring of progress, reporting) in order to improve efficiency and efficacy. Supervisor: Mauro Andreolini |
| r | Privacy, Security and Resiliency of Authentication and Authorization |
| | Keywords: Cyber security, Applied cryptography, Authentication, Authorization, Distributed systems, Anonymity, Tracking Research objectives: The emergence of novel computing systems is showing limitations of existing security solutions for authentication and authorization procedures, either due to limited capabilities of constrained devices and networks, limited usability and scalability within systems consisting of a huge amount of devices, attack surfaces including physical access to devices. Moreover, novel security paradigms require designing augmented security guarantees including increased privacy of users identities and reduced trust in identity providers. This research involves students in studying state-of-the-art authentication and authorization protocols, applied cryptography, and network security, acquiring expertise in analyzing and designing threat models and for novel secure computer systems. Proposed research activity: • State of the art on Web Authentication and Authorization, on privacy preserving protocols and distributed architectures • Analyzing and measuring trade-offs of privacy-preserving authentication • Analyzing deployment in real-world systems • Designing secure and practical authentication systems • Implementation of proof of concepts for heterogeneous platforms Supervisor: Luca Ferretti |
| s | Scoring Systems for Cyber Security |
| | Keywords: cyber security, graph theory, algorithms, cyber ranges, monitoring To increase the resilience of their infrastructures, both military and civilian organizations have started to train security personnel on cyber ranges, pre-arranged virtual environments through which it is possible to effectively simulate realistic security scenarios on a system architecture closely resembling the original one. Training goals are many and diverse in nature: to discover vulnerabilities in existing systems, to harden existing systems, to evaluate the security of a soon-to-be deployed component, to teach secure programming practices, to perform incident response on a compromised system. Unfortunately, current evaluation strategies of student performance in an exercise share a severe limitation: they are focused exclusively on goal achievement (yes or no), and not on the specific path followed by the student. Therefore, giving a more precise assessment and, more generally, understanding the reasons behind success or failure, is impossible. This research is motivated by the need for techniques, algorithms and tools to model user activities in an exercise, compare the path carried out by the student with an “optimal” path devised by an instructor and suggest avenues for improvement. The goal is to propose novel cyber scores that can be used to capture the abilities of a student (speed, precision, ability to discover new vulnerabilities), highlight potential weaknesses, compare different students in the same scenario. Supervisor: Mauro Andreolini |
| t | Innovative and collaborative digital platforms to support effective computer science education |
| | Keywords: computer science education, collaborative platforms, data science, performance evaluation Research objectives: The European job market is suffering an increased mismatch due to a severe shortage of workers with STEM and computer science skills. Several factors contribute to this issue, such as the need to train and support educators to include computer science in teaching activities and the low levels of self-efficacy of students towards this discipline. The main goal of this research is to design and develop a collaborative platform that supports educators in sharing projects, methodologies and experiences related to computer and data science education, including evaluation methodologies focused on continuous monitoring of students’ self-efficacy. The aim of the platform will be twofold: on one hand, giving educators the possibility to share their successful projects and innovative teaching approaches; on the other hand, allowing educators to find resources and communities that can be helpful to improve their experience. Proposed research activity: ● Analysis on state of the art on educational collaborative platforms and tools ● Analysis of the literature about methodologies to improve and monitor students self-efficacy ● Definition of a framework for best practices sharing, collaborative creation of educational activities and continuous monitoring ● Design and development of a collaborative platform, fostering active collaboration with educators in computer science ● Eventual integration of computer science educational tools ● Test and validation of the developed platform ● Participation to relevant international schools and conferences Supervisor: Prof. Claudia Canali |
| u | Edge computing systems to support modern IoT applications |
| | Keywords: edge computing, IoT applications, network simulators, microservices, performance evaluation Research objectives: In the last few years Edge computing has emerged as a novel approach to support modern IoT applications based on microservices.These applications typically involve sensors located in multiple geographic locations producing big amounts of data. In such scenarios, traditional cloud approaches are not suitable due to latency constraints: an intermediate layer of edge nodes can host pre-processing and data aggregation tasks that can reduce the response time of latency sensitive operations. The main goal of this research is to design and develop scalable edge computing systems equipped with effective load balancing algorithms and adaptive management mechanisms. The research will involve the analysis of realistic smart mobility traces and the use of network simulators to design, develop, test and validate effective management solutions. Proposed research activity: ● State of the art of edge computing systems for modern IoT applications ● Analysis of smart mobility traces ● Analysis of real modern IoT applications ● Design of load balancing algorithms for edge computing systems ● Development of simulation models for edge distributed systems ● Test and validation of the proposed solutions platform ● Participation to relevant international schools and conferences Supervisor: Prof. Claudia Canali |
| v | Latency Sensitive and Safety Critical GPU-accelerated real-time computing |
| | Keywords: GP-GPU, Massively parallel computing, Real-Time, Compute Architecture, Programming Models. Research Objectives: Nowadays cyber physical systems are characterized by data hungry algorithms within a wide variety of applications. This implies facing notable challenges for reaching the desired performance, hence the hardware deployed in domain such as Automotive, Robotics, Telecommunication and industrial automation are implemented as heterogeneous systems in which multi-core CPU hosts work in concert with massively parallel accelerators. In this context, a widely known accelerator is the Graphic Processing Unit (GPU), a hardware device designed to maximize compute throughput for general purpose computations (GP-GPU). It is not trivial, however, to exploit the full potential of the GPU processing power due to the notable architectural differences between GPUs and more traditional multi-core CPUs. Significant effort is therefore required, for instance, to exploit the recently released architectural features of modern GPUs, such as specialized cores for tensor processing and traversal of bounding volume hierarchies. Moreover, GPUs are designed to maximize throughput, hence inherently sacrificing latencies. This research aims at understanding how programming models, APIs and compilers could be enhanced in order to facilitate the work of the system engineer when implementing GPU accelerated applications, but also for accounting for stringent latency and safety requirements imposed by modern applications in the autonomous systems domain. Proposed research activity: ● State of the art on GP-GPU computing: from programming models to applications. ● Design and implementation of mechanisms that act at the level of APIs/programming models to enable real-time/safety critical GPU computing. ● Enhancing current compilers/source-to-source translators for simplyfing the programmer access to the GPU’s specilized cores (e.g. for tensor operations). ● Participation to relevant international schools and conferences. Supervisor: Nicola Capodieci Co-supervisor: Andrea Marongiu |
| w | Recommendation systems to personalize entertainment systems |
| | Keywords: Personalized entertainment, artificial intelligence, music/video sequencing, crossmedia promotion. Research objectives: The use of artificial intelligence (AI) to develop innovative and personalized multimedia experience. These models can personalize the music/video consumption process, help users to discover new sources, avoid the selection process, define strategies to engage users and multimedia material over social platforms, and more. Proposed research activity: • Design algorithms to understand the user’s habits in terms of multimedia material consumption • Design of AI-based algorithms to select material based on the user’s understanding obtained in step 1 • Design of recommender algorithms to personalize the multimedia experience • Design of strategies to engage users and multimedia material over social platforms • Design of sequencing strategies to meet the user’s habits and preferences in terms of multimedia material consumption Supervisor: Marco Furini Co-supervisor: Manuela Montangero |
| x | Time response analysis of scheduling policies on multiprocessors systems for real-time activities |
| | Keywords: Schedulability, Worst-case response times, real-time systems, multiprocessor systems Research Objectives: This research activity aims to investigate the response time analysis of scheduling policies on multiprocessors for real-time systems. Real-time systems are characterized by stringent timing constraints where tasks must meet their deadlines to ensure correct and reliable operation. Multiprocessor platforms offer increased computational power and can handle multiple tasks concurrently, making them suitable for real-time applications. However, the scheduling policies employed in these systems significantly impact task response times and meeting the required deadlines.The research will focus on evaluating scheduling policies and their impact on response time in multiprocessor environments, i.e, evaluate and quantify the time it takes for a task or job to complete its execution in a system. In the context of real-time systems, response time analysis is crucial to assess the predictability and performance of scheduling policies in meeting the timing requirements, ensuring reliable and timely system operation.The objective of the research is to analytically derive bounds to the worst case delays caused by the scheduling policies when completing task jobs, with respect to their deadlines. Supervisor: Prof. Manuela Montangero |
| y | Digital Intelligent Assistants for Industry 5.0 |
| | Keywords: voice assistant, human-in-the-loop, digital factory, data analytics Research objectives: Voice assistants, alternatively mentioned as conversational agents or Digital Intelligent Assistants (DIA), allow users to interact intuitively by using their natural language. In the industrial sector, the adoption of conversational agents has the potential to drive the digital transformation of organizations, improve both customer and user experience, and make their internal processes more efficient. This PhD project proposal aims to delve into the main research challenges that emerge in the design and development of DIAs in the industrial context where shopfloor operators need to interact with the available physical assets and data sources to solve data analytics requests. Topics of interest are, for instance, the integration of LLMs, approaches for DIA evaluations in realistic contexts and their continuous improvements. Proposed research activity: ● Investigate platforms and technology stacks for DIA development ● Address DIA benchmarking and evaluation issues in Industry 5.0 ● Explore Tool-augmented LLMs solutions ● Explore continual learning solutions in the context of DIA models Supporting research projects (and Department): The PhD student will be hosted at the Department of Physics Informatics and Math where she/he will be a member of the ISGroup (www.isgroup.unimore.it) led by Prof. Federica Mandreoli. The group has been working in different projects on digital factories and it is currently involved in the Horizon Europe project WASABI https://wasabiproject.eu/ . Possible connections with research groups, companies, universities: On the topics of the proposal, the ISGroup has connections with BIBA – Bremer Institut für Produktion und Logistik (Germany), ICCS (Greece), and Sapienza University of Rome (Italy). Moreover, connections with the companies involved in the WASABI project are currently active. Supervisor: Prof. Federica Mandreoli |
| z | Data Analytics and Machine Learning for P4 medicine |
| | Keywords: Big data, data analytics, machine learning, health data Research objectives: Medical practice is evolving rapidly, away from the traditional but inefficient detect-and-cure approach, and towards a Preventive, Predictive, Personalised and Participative (P4) vision. This vision is increasingly data-driven, and is underpinned by many forms of “Big Health Data”. The main research objective of this PhD project is to contribute to the above ambitious goals with big data analytics and machine learning solutions for collections that include a broad variety of (longitudinal) data including genetics, electronic health records, patient reported outcomes, lifestyle indicators and wearables. The project is in collaboration with the Unit of Infection Diseases of the University Hospital Policlinico di Modena and the School of Computing at Newcastle University (UK). The PhD candidate will have the opportunity to work with retrospective and prospective health data collections mainly in the context of infection diseases, also including COVID-19 data. Proposed research activity: ● Data cleaning techniques and application to clinical and self-generated datasets; ● Study of the state of the art of data mining and machine learning techniques in the field of medicine and people wellness; ● Study of Machine Learning solutions for P4 medicine; ● Model Interpretability and P4 medicine; ● ML model evaluation and assessment; ● Standardization of new data-driven clinical scores. Supporting research projects: The PhD student will be hosted at the Department of Physics Informatics and Math. Prof. Mandreoli has active projects with Prof. Guaraldi and Prof. Missier. The project will use retrospective Electronic Health Data, mainly from Policlinico of Modena, prospective health data generated by IRB approved studies. Possible connections with research groups, companies, universities: The study will be conducted together with Prof. Giovanni Guaraldi (Dipartimento Chirurgico, Medico, Odontoiatrico e di Scienze Morfologiche con Interesse Trapiantologico, Oncologico e di Medicina Rigenerativa), physician of the Infection Disease Unit of Policlinico of Modena, and his research group. The co-tutor Prof. Paolo Missier is a reader with the School of Computing at Newcastle University. Joint research activities are also currently active with the National Innovation Centre for Data (NICD -UK). Supervisor: Prof. Federica Mandreoli |
| aa | Enhancing Performance and Efficiency of Deep Learning Models for Human-machine Interaction Applications |
| | Keywords: neural machine translation, image captioning, language detection, performance, deep learning Research Objectives: Human-machine interaction domain is composed of important applications such as neural machine translation, image captioning, and language detection. However, these models often suffer from issues such as poor performance, high computational complexity, and limited scalability. The proposed research project aims to investigate and develop novel techniques to improve the performance of these models. The research project also aims to evaluate the effectiveness of these techniques on various benchmark datasets and compare them with existing state-of-the-art techniques. Proposed Research Activity: ● Literature review and state-of-the-art analysis of neural machine translation, image captioning, and language detection models ● Development of novel techniques to improve the performance of these models, such as attention mechanisms, transfer learning, and model compression ● Evaluation of the proposed techniques on various benchmark datasets, such as WMT, COCO, and LDC ● Comparison of the proposed techniques with existing state-of-the-art techniques ● Participation in relevant international conferences and workshops Supervisor: Roberto Cavicchioli Co-supervisor: Alessandro Capotondi |
| bb | Efficient HW/SW solutions for constrained intelligent autonomous systems |
| | Keywords: TinyML; Deep Learning; HW/SW co-design; embedded systems; Research Objectives: This project focuses on developing advanced embedded autonomous platforms for intelligent edge systems. The main objective is to enable devices with limited resources to run AI applications, including deep learning workloads and Spiking Neural Networks, targeting HW/SW co-design methodologies. These include software development methodologies tailored for embedded and IoT autonomous systems and Hardware Description Languages (HDL) or High-Level Synthesis (HLS) languages for the design of reconfigurable architectures. These methodologies will be integrated into commercially available and open-hardware devices, particularly those based on the RISC-V architecture. Prior works on the topic: ● CMIX-NN: https://ieeexplore.ieee.org/document/9049084 ● HERO: https://dl.acm.org/doi/10.1145/3295816.3295821 ● PULP: https://pulp-platform.org/ Supporting research projects (and Department): AI4CSM (https://ai4csm.eu/). Possible connections with research groups, companies, universities: The project will be carried out in collaboration with European academic institutions like SUPSI Lugano, ETH Zurich, KU Leuven, and extra-EU like Technology Innovation Institute of Abu Dhabi. Supervisor: Prof. Andrea Marongiu Co-supervisor: Alessandro Capotondi |
| cc | Compiler-aided parallel programming model for next generation high performance predictable heterogeneous platforms |
| | Keywords: Compilers; Parallel Programming Models; Runtime; Heterogenous Systems; Research Objectives: The primary focus of this project is to address the programming challenges associated with emerging high-performance heterogeneous systems. The project aims to develop compiler and runtime support for heterogeneous and parallel programming models, explicitly targeting the cyber-physical systems domain (robotics, automation, manufacturing). The objective is to enhance the adoption of these systems by improving performance and timing predictability, while maintaining a simple programming interface. Proposed Research Activity: ● In-depth study of the challenges involved ● Design and development of compiler and runtime system extensions specifically tailored for Commercial-off-the-Shelf (COTS) platforms and open-source hardware architectures like RISC-V. ● Validate the proposed solutions on real-life problems from the targeted application domains ● Participation in relevant international conferences and workshopsPrior works on the topic: ● HEPREM: https://ieeexplore.ieee.org/document/9035630 ● HERO: https://dl.acm.org/doi/10.1145/3295816.3295821 ● PULP: https://pulp-platform.org/ Supporting research projects (and Department): AI4CSM (https://ai4csm.eu/). Possible connections with research groups, companies, universities: ● ETH Zurich, Switzerland ● University of Massachussets, Lowell, USA Supervisor: Prof. Andrea Marongiu Co-supervisor: Alessandro Capotondi |
| dd | Environmental information and communication: fake news, bias and distortion, and data analysis. Possible impacts on policy and public opinion. |
| | Informazione e comunicazione ambientale: fake news, distorsioni e analisi dei dati. Possibili impatti sulle politiche e sull’opinione pubblica. Keywords: Environmental information, Information and communication theory, social media and conversation analysis, Cognitive and perceptual biases and climate change, Qualitative and quantitative methods in data analysis. Research objectives: The purpose of this research area is to analyze the processes of dissemination and production of fake news, cognitive bias related to information on the issues of environment, climate crisis and climate change. The intention is to work on textual corpora and conversations regarding environmental communication and information issues, both online and social media, and offline, by: (a) acquiring skills regarding the relationship between quantitative and qualitative data analysis; and (b) using tools such as NVivo and Altas and qualitative methodologies related to thematic, narrative analysis and different forms of “netnography” of data. Supervisor: Prof. Federico Montanari, DCE |
| ee | Formal Verification of Autonomous Systems |
| Keywords: Formal Methods, Formal Verification, Model Checking, Runtime Verification, Multi-Agent Systems, Robotics Research objectives: The rapid advancement in autonomous systems, particularly multi-agent systems (MAS), has significantly increased their application across various domains, including robotics, transportation, and smart infrastructure. Ensuring the reliability and safety of these systems is paramount, given their potential impact on human lives and critical operations. Formal methods, which provide rigorous mathematical guarantees, present a promising solution for verifying the correctness of such systems. However, the integration of AI components introduces challenges due to the complexity, learning dynamics, and high dimensionality inherent in these systems. This PhD project aims to advance the field of formal verification by developing novel algorithms and techniques tailored to AI-based autonomous systems, with a specific focus on MAS. The research will begin with a comprehensive survey of existing formal methods and their application to AI-driven systems, identifying the limitations and gaps in current verification techniques. The primary objective is to create innovative approaches that can handle the dynamic and adaptive nature of MAS, ensuring their correctness and robustness in various real-world scenarios. The proposed research will involve the theoretical development of new verification methods, followed by their practical implementation and validation through case studies and real-world applications. While the emphasis will be on MAS, the techniques developed will be generalisable to other AI-based systems, broadening the impact of the research. The outcomes are expected to contribute significantly to the reliability and safety of autonomous systems, providing robust tools for their formal verification. Supervisor: Angelo Ferrando | |
| ff | Attacking and defending cryptographic protocols implementations |
| Keywords: Cyber security, applied cryptography, secure development, side channel attacks Research objectives: Implementing cryptographic schemes and protocols is a hard task, related to having interdisciplinary knowledge on theoretical and applied cryptography, secure code development, and real-world attacks to code and system architectures. Moreover, many dedicated attack and defense techniques specifically related to cryptographic implementations have been designed throughout years of research, and novel techniques are still emerging, in particular related to implementation of post-quantum cryptography and to defense against advanced attack surfaces encompassing gray and white -box security. This research thesis involves the study of such techniques, on studying their applicability to existing and emerging protocols and systems, and on designing novel tools to detect non-secure implementations. Proposed research activity: State of the art in cryptographic engineering attacks and defenses Analyzing emerging security threats due to implementation of post-quantum cryptography Designing and implementation of known and novel strategies for attacking and defending cryptographic implementations Advisor: Luca Ferretti Co-advisor: Mauro Andreolini |
Themes for the 5 scholarships with specific topic
PNRR – DM 630
PNRR, Missione 4 “Istruzione e ricerca”,
Componente 2 “Dalla Ricerca all’Impresa”
Investimento 3.3 “Introduzione di dottorati innovativi che rispondono ai fabbisogni di innovazione delle imprese e promuovono l’assunzione dei ricercatori dalle imprese”
| 1 | GraphRAG: Retrieval Augmented Generation and Knowledge Graph integration |
| | Keywords: Knowledge graph, large language models, deep learning, natural language understanding Research objectives: The objectives of the project are to explore the integration of Retrieval Augmented Generation (RAG), LLMs, and Knowledge Graph (KG) to improve conversational artificial intelligence. The RAG approach has seen great popularity due to its ability to reduce the hallucinations caused by the use of LLMs, but it has considerable limitations, in particular the ability to relate information contained in different documents in a consistent manner. On the other hand, the use of KGs has been successfully applied as a methodology to map knowledge and relationships in a navigable manner but their enrichment and generalization are still open problems. The project aims to explore both the capabilities of LLMs to support Natural Language Understanding (NLU) and Knowledge Graph Enrichment processes via Named Entity Recognition, Node, and Link Prediction, as well as the use of information within semantic search engines that can be queried via Natural Language. Proposed research activity — (max 10 rows) ● Study of the state of the art in LLM, RAG, and KG and their Python software packages. ● Study of innovative solutions capable of integrating the three areas for research objectives. ● Development of Python pipelines and testing on suitable infrastructures. ● Study of performance against international benchmarks and comparison with alternative solutions. Supporting research projects This PhD project is financed by the Italian Ministery of University and Research under the PNRR Program. The PhD student will be hosted at the Department of Physics Informatics and Math where she/he will work within the ISGroup led by Prof. Federica Mandreoli. The group is already committed to research topics related to the proposed PhD project. The position is partially funded by PwC BS, a consulting company with approximately 4200 employees and 600 million in turnover in 2023. PwC Digital Innovation (DIG) is a service line of PwC BS in which more than 300 experienced professionals in all areas of software development are dedicated to the study and application of emerging technologies for the realisation of innovative solutions that can be applied within the company or at customer sites. Within DIG there is the Centre of Excellence for Artificial Intelligence (AI CoE), consisting of around 60 AI engineers. The AI CoE has developed several applications in the NLU area. The PhD student will spend at least 6 months at PwC AI CoE located in Bologna. Possible connections with research groups, companies, universities. The PhD student will spend at least 6 months at the University of Lyon 1 under the supervision of Prof. Angela Bonifati. Supervisor: Prof. Federica Mandreoli Co-supervisor: Dr. Mara Elisabetta Ziri (PwC BS) |
| 2 | Perception and localization algorithms for self-driving racing cars |
| | Keywords: perception, state estimation, localization, object detection, artificial intelligence Research objectives: The objective of the research project is to develop novel algorithms and artificial intelligence methods to enhance the perception and localization of autonomous vehicles in racing environments. In this particular context, accuracy and redundancy in the detection pipeline are crucial for the correct execution of complex maneuvers during overtakes and obstacle avoidance. Furthermore, the enhancement of ego vehicle state estimation is also an open topic in state-of-the-art solutions using vision-based low-cost sensors. Proposed research activity: Compare and validate the latest approaches in real applications, such as full-scale sportscars and racecars. Design and develop new solutions capable of detecting objects with higher accuracy. Design and develop new solutions to estimate vehicle dynamics without expensive sensors. Supporting research projects: This PhD project is financed by the Italian Ministery of University and Research under the PNRR Program, with the involvement of HipeRT SRL. The research project will be conducted with the UNIMORE Racing team and Hipert srl within the context of the Indy Autonomous Challenge and the Abu Dhabi Autonomous Racing League, which the university has been participating in for several years. Possible connections with research groups, companies, universities. The successful candidate will spend 6 months at HipeRT SRL and 6 months abroad for research activities, potentially at ETH Zurich or Technische Universität München (TUM) Supervisor: Prof. Marko Bertogna |
PNRR – DM 629
Missione 4, Componente 1“Potenziamento dell’offerta dei servizi di istruzione: dagli asili nido all’Università”
Investimento 3.4 “Didattica e competenze universitarie avanzate”
Investimento 4.1 “Estensione del numero di dottorati di ricerca e dottorati innovativi per la pubblica amministrazione e il patrimonio culturale”
| 3 | Distributed embedded intelligence systems for smart city applications |
| Keywords: Embedded systems, AI, Smart City, distributed systems, IoT Research objectives: The target of this project is to deploy an innovative smart city system to the city of Mantova, following the guidelines of the experience developed in the Modena Automotive Smart Area (MASA). The system will be composed of a heterogeneous set of smart cameras and Road Side Units (RSU) strategically distributed throughout the city, leveraging data processing and artificial intelligence technologies for real-time recognition and geolocation of people, vehicles, and operators. The smart cameras, equipped with advanced sensors and connected through an Internet of Things (IoT) network, continuously collect visual data that is analyzed using machine learning and deep learning algorithms. These algorithms can identify specific characteristics and track movements, providing detailed information on the location and behavior of various subjects. The integration of various data sources, including images from smart cameras, GPS data, and other sensory information, creates a dynamic and interactive city view. The metadata produced by the Smart RSUs (Road Side Units) has a maximum latency of 100 ms, ensuring a timely and precise response to operational needs. The platform offers advanced visualization capabilities through an intuitive user interface, allowing urban operators to effectively monitor public safety, manage traffic, and optimize city resources. The main benefits of the project include improving public safety through the immediate detection of abnormal or emergency situations, optimizing traffic flow through real-time traffic monitoring, and increasing operational efficiency in urban resource management. UrbanVision represents a significant step towards creating safer, more efficient, and resilient smart cities, fully leveraging the potential of digital technologies to enhance citizens’ quality of life. Proposed Research Activities: ● Enhance the performance and accuracy of machine learning and deep learning algorithms by incorporating additional training data and fine-tuning hyperparameters. ● Optimize data processing pipelines to minimize latency, ensuring that the metadata produced by Smart RSUs is processed within the maximum latency of 100 ms. ● Implement efficient resource management techniques to balance the computational load across available hardware, reducing bottlenecks and improving real-time processing capabilities. ● Establish a continuous monitoring system to track the performance of algorithms and software in real-time, using feedback loops to make iterative improvements and quickly address any emerging issues. Supporting research projects: This PhD project is financed by the Italian Ministery of University and Research under the PNRR Program, with the involvement of the city council of Mantova. The project will leverage funding from regional smart city projects, as well as from the national center for sustainable mobility (MOST). It will also use the technological background provided by the Modena Automotive Smart Area (MASA), funded through multiple European projects. Possible connections with research groups, companies, universities: The successful candidate will spend 6 months with the premises of the city council of Mantova and 6 months abroad for research activities, potentially at ETH Zurich or Technische Universität München (TUM) Supervisor: Prof. Marko Bertogna |
Scholarship funded by the Department of Communication and Economics
| 4 | Measuring the power of parameter setting theory on historical corpora – Parametric phylogenetic analyses of language families/subfamilies |
| | Keywords: Parameter theory, Language family, Comparative methods, Parametric comparison, Quantitative phylogenetics, Synchronic and Diachronic variation, Parameter change, Historical corpora Research objectives: Implement the Parametric Comparison Method (PCM, www.parametricomparison.unimore.it) to the analysis of the phylogenetic structure of a selected historical language family and of its relations with other families, through the investigation of contemporary and/or historical varieties. Concerning currently spoken languages, data can (and will) be gathered from native speakers; by contrast, the investigation of historical varieties requires parsing of closed collections of linguistic material attesting the relevant diachronic stages. The tools implemented by the PCM to extract parameter values from surface language data will be tested and refined to deal with both scenarios and to unveil patterns of parameter change across time and space. Research tools. (1) a set of binary syntactic parameters defining syntactic variation in nominal structures across the World’s languages; (2) a set of implicational formulas defining parameter interdependencies; (3) a set of co-varying surface manifestations for each parameter; (4) a formal parameter setting procedure that converts the observed surface patterns to a string of binary values representing the deep structure of each language; (5) a set of computer-based procedures to extract a historical signal from parameter values and automatically generate language phylogenies. Possible connections with research groups, companies, universities: The envisaged research is part of the project “Parameter theory on historical corpora: Measuring the power of parameter setting theory on historical corpora” (MUR PRIN 2022 20224XEE9P – PARTHICO). Research will be also conducted in collaboration with the Center for Language history and diversity, of which the Dipartimento di Comunicazione ed Economia is a member, and the Department of Linguistics at York, with whom the DCE has an academic cooperation agreement. Supervisor: Prof. Cristina Guardiano |
Scholarship funded by the COFUND – Marie Curie EU
| 5 | Data science for sustainable mobility (Marie Skłodowska-Curie Actions – COFUND FutureData4EU Programme) |
| Keywords: Smart-mobility, smart-cities, autonomous vehicles, distributed systems, data science Research objectives: Smart mobility has the potential to enhance street safety as well as the driving experience in smart cities, whose streets will be soon populated by autonomous vehicles. To reach this goal, the implementation of smart mobility requires not only a robustly connected infrastructure connecting vehicles and their environment but also appropriated algorithms and methods for effective management and coordination of vehicle movements. Indeed, road traffic is an extremely complex system and intersections pose a significant challenge: a delicate balance is required between assigning priority in a fair way and the flexibility needed for emergency situations. The goal of this project is to study infrastructures and algorithms that take advantage of the analysis of data to improve the sustainability of mobility, in particular in urban context. At the end of the project, the PhD student will have acquired knowledge and skills about the management of complex systems by defining algorithms that start from the data and define strategies. Proposed research activity — (max 10 rows) ● State of the art in smart cities ● State of the art in autonomous vehicles ● Definition of data useful to address sustainable mobility ● Definition of algorithms to elaborate data to achieve sustainable mobility ● Definition of case studies ● Test of the proposed algorithms ● Participation to relevant international school Supporting research projects FutureData4EU – MSCA COFUND Possible connections with research groups, companies, universities. Dr. Antonio Bucchiarone, FBK Trento (I) Prof. Marco Aiello, Stuttgart University (D) Supervisor: Prof. Giacomo Cabri Information on the admission process for this scholarship can be found at this link |