Data science for viral genomic surveillance in public health contextsContact person
ANNA BERNASCONIEmail:
anna.bernasconi@polimi.itStudy course: Computer Science and Engineering
Web page:
https://annabernasconi.faculty.polimi.it/Description
Description:
The recent COVID-19 pandemic has posed novel challenges to the big data and knowledge management community. The unprecedented availability of viral genomes on public databases has made possible the data-driven exploration of viruses' evolution (especially of SARS-CoV-2, the virus responsible for COVID-19). This master thesis will deal with analyzing previously developed methods for the identification of new viral variants and recombined genomes (specifically for SARS-CoV-2). Then, it will aim to develop similar methods for alternative viral species (e.g., Ebola, Monkeypox, or Influenza).
Hide Description
FAIRness assessment of biological and virological data sourcesContact person
ANNA BERNASCONIEmail:
anna.bernasconi@polimi.itStudy course: Computer Science and Engineering
Web page:
https://annabernasconi.faculty.polimi.it/Description
Description:
FAIR is an acronym that describes the characteristics of a data resource of being Findable, Accessible, Interoperable, and Reusable. This master thesis will deal with exploring human and viral genomic databases. A small set of important sources will be selected, and a wide FAIRness assessment will be performed 1) with existing automatic assessment tools and 2) developing a novel pipeline for semi-automatic assessment. Both qualitative and quantitative methods will be employed.
Hide Description
User validation studies for domain-specific search systemsContact person
ANNA BERNASCONIEmail:
anna.bernasconi@polimi.itStudy course: Computer Science and Engineering
Web page:
https://annabernasconi.faculty.polimi.it/Description
Description:
Within our research lab, we built two search systems for COVID-19-related literature. This master thesis will deal with exploring available user-centered validation techniques, with the aim of conducting two empirical studies on actual users, using the testbed implementations of the two applications. The student will propose a set of experiments, conduct them, and perform data collection, analysis, and reporting of results with visualizations. The drawn conclusions will be reported along the typical guidelines of empirical studies and will be employed to inform future implementation phases.
Hide Description
Application of a temporal topic modeling architecture to social media text contentContact person
ANNA BERNASCONIEmail:
anna.bernasconi@polimi.itStudy course: Computer Science and Engineering
Web page:
https://annabernasconi.faculty.polimi.it/Description
Description:
A topic model is a statistical model for discovering abstract topics that are mentioned in a collection of textual documents. We built a pipeline that can extract relevant topics from a big corpus of research abstracts and build a dashboard for inspecting temporal trends of topics related to COVID-19 research. This master thesis will deal with re-purposing such existing pipelines for data preparation, processing, and visualization. In this thesis, the approach will be applied to a dataset of social media documents.
Hide Description
Novel Energy and propulsion systeMs for Air dominanceContact person
MICHELE NORGIAEmail:
michele.norgia@polimi.itStudy course: Electronics Engineering
Description
Description:
Si tratta di un Progetto europeo che coinvolge imprese grandi-medie e piccole e diversi centri di ricerca e università europee (Poli incluso). Il progetto è attualmente in corso e la conclusione è prevista nella seconda metà del 2026.
L’obiettivo del progetto è analizzare i requisiti, lo stato dell’arte e le roadmap delle tecnologie dei componenti a semiconduttore per indirizzare le tecnologie e i sistemi abilitanti per lo sviluppo di un powerplant evoluto e altamente efficiente per i velivoli di prossima generazione.
L'attività di tesi si svolgerebbe in collaborazione con la ditta Blu Electronic, che è coinvolta nelle attività legate ai sistemi e alle tecnologie elettriche e di thermal mangement. Più in particolare, BLU Electronic è task manager per le attività di “Power Distribution & Conversion Technologies & Modelling” in collaborazione con le aziende Axter e Saab.
Si contempla anche la possibilità di sviluppare i contenuti agganciandoci a programmi interni di sviluppo con l’obiettivo di costruire un percorso per un dottorato con potenziale sbocco in azienda.
Conoscenze richieste: preparazione in elettronica e conoscenze/interesse in power electronics.
Hide Description
Temperature modulation for gas MOS sensor: a breath analysis challenge for the detection of volatile organic compoundsContact person
PIETRO CERVERIEmail:
pietro.cerveri@polimi.itStudy course: Biomedical Engineering, Electrical Engineering, Electronics Engineering
Other members of the research group:
PhD Student Andrea Rescalli (PhD Bioengineering), Prof. Francesco Cellesi (Dipartimento di Chimica)Web page:
https://www.mdpi.com/2227-9040/11/9/501Description
Description:
Context
Disease diagnosis through biological fluids, particularly exhaled breath analysis, has gained increasing importance. Volatile Organic Compounds (VOCs) present in exhaled breath offer diagnostic potential as they reflect altered and disease-specific metabolic pathways. While Gas Chromatography-Mass Spectrometry (GC-MS) has been traditionally used for VOCs detection, electronic noses have emerged as a promising alternative for disease screening. Metal Oxide Semiconductor (MOS) sensors play an essential role in these devices due to their simplicity and
cost-effectiveness. However, their limited specificity and sensitivity pose challenges for accurate diagnosis at lower VOCs concentrations typical of exhaled breath. To address specificity and
sensitivity issues, temperature modulation (TM) of the heater of the sensors has been extensively investigated to get more insight into MOS sensor detection properties.
Aim of the thesis.
The proposed work takes its root from a custom-developed electronic nose based on multiple and heterogeneous gas sensors located within an analysis chamber (https://www.mdpi.com/2227-9040/9/8/209). The idea is to evolve this system to enable adaptive temperature modulation and perform extensive lab testing about gas mixtures containing known concentrations of specific compounds, mainly alcohols and hydrocarbons which have been described in the literature to be present in exhaled breaths of patients affected by lung cancers.
Technically, the work requires knowledge of sensors, microcontrollers, and firmware development. Experimental tests will be carried out in collaboration with the Department of Chemistry.
Hide Description
Tesi in azienda, argomento da concordareContact person
ARNALDO SPALVIERIEmail:
arnaldo.spalvieri@polimi.itStudy course: Telecommunications Engineering
Description
Modeling and simulation of the high-field behavior of polymeric dielectric layers for galvanic isolationContact person
ALESSANDRO SOTTOCORNOLA SPINELLIEmail:
alessandro.spinelli@polimi.itStudy course: Electronics Engineering
Other members of the research group:
Christian Monzio Compagnoni, Gerardo MalavenaDescription
Description:
Polymeric dielectrics are an innovative class of materials used as isolators in high-voltage applications, and their behavior must be accurately known to properly design them. However, the physics of charge transport and leakage, high-field behavior and so on is still unknown. The work aims at the development of models that account for the experimental evidences gathered in the lab and can predict the behavior of the material under operating conditions. The work takes place in the new lab built in the frame of a collaboration with STMicroelectronics.
Hide Description
Wafer-level characterization of polymeric dielectrics for galvanic isolationContact person
ALESSANDRO SOTTOCORNOLA SPINELLIEmail:
alessandro.spinelli@polimi.itStudy course: Electronics Engineering
Other members of the research group:
Christian Monzio Compagnoni, Gerardo MalavenaDescription
Description:
Polymeric dielectrics are an innovative class of materials used as isolators in high-voltage applications, and their behavior must be accurately known to properly design them. However, the physics of charge transport and leakage, high-field behavior and so on is still unknown. The work aims at assessing the electrical characteristics of polymeric dielectric layers under high-field condition and study the dependence on operating conditions. The work takes place in the new lab built in the frame of a collaboration with STMicroelectronics.
Hide Description
Modeling and simulation of 3D NAND Flash memories at cryogenic temperatures for quantum computingContact person
ALESSANDRO SOTTOCORNOLA SPINELLIEmail:
alessandro.spinelli@polimi.itStudy course: Electronics Engineering
Other members of the research group:
Christian Monzio Compagnoni, Gerardo MalavenaDescription
Description:
Quantum computing applications are fostering new research in low-temperature operation of MOS memory devices. At temperatures below 50K the MOS memory device begins to behave like a single-electron transistor, with performance still to be assessed and the relative physics yet to be studied. The work aims at the development of models describing the single-electron behavior 3D NAND Flash .
Hide Description
Experimental characterization of 3D NAND Flash memories at cryogenic temperatures for quantum computingContact person
ALESSANDRO SOTTOCORNOLA SPINELLIEmail:
alessandro.spinelli@polimi.itStudy course: Electronics Engineering
Other members of the research group:
Christian Monzio Compagnoni, Gerardo MalavenaDescription
Description:
Quantum computing applications are fostering new research in low-temperature operation of MOS memory devices. At temperatures below 50K the MOS memory device begins to behave like a single-electron transistor, with performance still to be assessed and the relative physics yet to be studied. The work aims at studying the electrical characteristics of decananometer 3D NAND Flash in the single-electron regime and evaluate their performance.
Hide Description
Misura degli effetti di bending su sistemi a MEMSContact person
MICHELE NORGIAEmail:
michele.norgia@polimi.itStudy course: Automation Engineering, Electronics Engineering
Description
Description:
Si propone un lavoro di tesi in stretta collaborazione con ST microelectronics, sede di Castelletto, per la realizzazione di un setup automatizzato per misurare le variazioni della sensibilità di sistemi MEMS in presenza di bending.
E' previsto un rimborso spese da parte di ST.
Hide Description
Misura di non-linearità di accelerometri MEMS per elevate accelerazioniContact person
MICHELE NORGIAEmail:
michele.norgia@polimi.itStudy course: Automation Engineering, Electronics Engineering
Description
Description:
Si propone un lavoro di tesi in stretta collaborazione con ST microelectronics, sede di Castelletto, per la realizzazione di un setup di misura delle non-linearità di accelerometri MEMS, in regimi di elevate accelerazioni (200 g)
E' previsto un rimborso spese da parte di ST.
Hide Description
Misure di risposta in frequenza di accelerometri MEMSContact person
MICHELE NORGIAEmail:
michele.norgia@polimi.itStudy course: Automation Engineering, Electronics Engineering
Description
Description:
Si propone un lavoro di tesi in stretta collaborazione con ST microelectronics, sede di Castelletto, per la realizzazione di un setup di caratterizzazione di accelerometri MEMS.
E' previsto un rimborso spese da parte di ST.
Hide Description
METODI INNOVATIVI PER LO STUDIO E L’ANALISI DI SEGNALE ELETTRONEUROGRAFICI PROVENIENTI DA NERVO PERIFERICOContact person
MAURIZIO MAGARINIEmail:
maurizio.magarini@polimi.itStudy course: Automation Engineering, Biomedical Engineering, Computer Science and Engineering, Telecommunications Engineering
Other members of the research group:
Ing. Antonio CovielloDescription
Description:
La tesi propone lo studio e l'elaborazione di segnali elettroneurografici (ENG) di nervi periferici per sviluppare un accurato algoritmo di riconoscimento di segnali con origini diverse. Si considereranno il pre-processing, la classificazione tramite tecniche innovative di machine learning e deep learning, incluso il training dei dati e l'accentuazione delle caratteristiche, oltre a possibili operazioni di post-processing. L'obiettivo sarà quello di massimizzare l'accuratezza dell'algoritmo nell'individuare le differenze attraverso l'analisi di varie caratteristiche del segnale. Questo argomento di tesi fa parte di un progetto più ampio che mira a creare un bypass nervoso per ripristinare una funzione persa in un paziente. La durata prevista per il lavoro di tesi è di circa 9-12 mesi, con l'inizio delle attività a settembre. Sono previste collaborazioni con l'Università di Toronto, professori e studenti del Polimi e del Polito con cui sarà possibile confrontarsi.
Hide Description
IMAGING DI NERVO SCIATICO PER NEUROMODULAZIONE E LOCALIZZAZIONE DELL’ATTIVITA’ NERVOSAContact person
MAURIZIO MAGARINIEmail:
maurizio.magarini@polimi.itStudy course: Automation Engineering, Biomedical Engineering, Computer Science and Engineering, Telecommunications Engineering
Other members of the research group:
Ing. Antonio CovielloDescription
Description:
La tesi si divide in due aree principali: elaborazione di immagini ottenute con risonanza magnetica di un nervo periferico per creare un modello COMSOL, consentendo la definizione di una strategia di neuromodulazione; lo sviluppo e l'analisi di algoritmi di backprojection per identificare il punto di origine di un segnale nel nervo mediante il modello creato, testandoli poi l’algoritmo finale su segnali campionati in vivo. Il modello permetterà di estrarre nuove informazioni usate per addestrare un classificatore basato su reti neurali (NN), confrontandone le prestazioni con tecniche tradizionali. Questo argomento di tesi fa parte di un progetto più ampio che mira a creare un bypass nervoso per ripristinare una funzione persa in un paziente. La durata prevista per il lavoro di tesi è di circa 9-12 mesi, con l'inizio delle attività a settembre. Sono previste collaborazioni con l'Università di Toronto, professori e studenti del Polimi e del Polito con cui sarà possibile confrontarsi.
Hide Description
PROGETTAZIONE DI UNA BATTERIA PER UN SISTEMA DI ALIMENTAZIONE RIDONDANTE PER DISPOSITIVI IMPIANTATIContact person
MAURIZIO MAGARINIEmail:
maurizio.magarini@polimi.itStudy course: Automation Engineering, Biomedical Engineering, Electrical Engineering, Electronics Engineering, Telecommunications Engineering
Other members of the research group:
Ing. Anonio CovielloDescription
Description:
La tesi mira a sviluppare un sistema ridondante che includa un sistema di alimentazione wireless intelligente con una batteria ricaricabile di emergenza. Attraverso la progettazione di un circuito elettrico compatibile con il sistema di alimentazione, seguita da test simulati e sperimentali, si garantirà il corretto funzionamento del dispositivo impiantato anche in condizioni non ideali. Questo lavoro contribuirà ad aumentare la stabilità e l'affidabilità del sistema, fornendo un'alimentazione continua e adeguata in ogni situazione. Questo argomento di tesi fa parte di un progetto più ampio che mira a creare un bypass nervoso per ripristinare una funzione persa in un paziente. La durata prevista per il lavoro di tesi è di circa 9-12 mesi, con l'inizio delle attività a settembre. Sono previste collaborazioni con l'Università di Toronto, professori e studenti del Polimi e del Polito con cui sarà possibile confrontarsi.
Hide Description
SCRITTURA CODICE FIRMWARE PER APPLICAZIONI REAL TIME DI UN MICROCONTROLLOREContact person
MAURIZIO MAGARINIEmail:
maurizio.magarini@polimi.itStudy course: Automation Engineering, Biomedical Engineering, Computer Science and Engineering, Telecommunications Engineering
Other members of the research group:
Ing. Antonio CovielloDescription
Description:
Questa tesi si concentra sull'ottimizzazione del sistema di acquisizione dei segnali biomedicali per migliorare la loro classificazione. Verranno sviluppati un protocollo di selezione dei canali meno rumorosi, tecniche di compressione dei dati e un codice firmware per implementare tali operazioni su un microcontrollore impiantato. Al contempo, si affronteranno questioni relative alla normativa e al trattamento dei dati sensibili per garantire un'applicazione in tempo reale che sia conforma alle norme vigenti. Questo argomento di tesi fa parte di un progetto più ampio che mira a creare un bypass nervoso per ripristinare una funzione persa in un paziente. La durata prevista per il lavoro di tesi è di circa 9-12 mesi, con l'inizio delle attività a settembre. Sono previste collaborazioni con l'Università di Toronto, professori e studenti del Polimi e del Polito con cui sarà possibile confrontarsi.
Hide Description
FARCOS frontend electronics qualification and optimizationContact person
CHIARA GUAZZONIEmail:
chiara.guazzoni@polimi.itStudy course: Biomedical Engineering, Electronics Engineering
Description
Description:
FARCOS is a novel Femtoscope Array for Correlation and Spectroscopy designed to perform studies of two- and multi-particle and Intermediate Mass Fragments (IMFs) correlations in heavy-ion collisions at Fermi energies with stable and radioactive beams. The FARCOS system is a modular assembly of up to 20 telescopes to be used in combination with 4pi detectors like the CHIMERA multidetector. This thesis aims at the experimental qualification of the whole FARCOS system with a particular emphasis on achieving the ultimate performance in terms of energy and time resolution. The work activity can foresee also - if the student is willing to and if the GPA is sufficient for the association with INFN - travels to Catania for the final qualification and installation of the system.
Hide Description
Smart Radiation Hard Detection System for Radioactive Ion BeamsContact person
CHIARA GUAZZONIEmail:
chiara.guazzoni@polimi.itStudy course: Biomedical Engineering, Electronics Engineering
Other members of the research group:
Andrea CastoldiDescription
Description:
Radioactive Ion Beams (RIBs) of large intensity (10^6 pps or higher) are at the frontier in nuclear physics and are available since one decade in different facilities and new ones are presently under construction. We are designing a novel detection system for RIBs diagnostics and tagging based on Silicon Carbide detectors and on custom frontend electronics ready to be coupled with a Real Data Management Unit, supported by machine learning techniques. In this thesis you will take care of the full design of the proposed system together with the qualification of the individual components. Thesis open to one or two people working together. Several thesis on this subject are possible.
Hide Description
Deep learning to classify sport events using wearablesContact person
PIETRO CERVERIEmail:
pietro.cerveri@polimi.itStudy course: Biomedical Engineering
Other members of the research group:
Matteo Zago - Soccerment srlDescription
Description:
Background: The market for wearable devices is constantly evolving and expanding. In the sports field,
these devices allow for the monitoring and collection of performance metrics.
Thesis Objective:
The candidate will work alongside the R&D team (4 biomedical engineers, one mathematician, and a full
stack developer, and suppliers) in the process of improving artificial intelligence algorithms used for
the identification and recognition of technical gestures in football (e.g., shots, passes) based on
measurements collected from the XSEED device. The candidate will participate in the experimental
data collection phase and in the labeling and processing of the data in order to improve the accuracy
of the models under examination.
Requirements:
- Passion for sports
- Availability to work in an operational and dynamic environment (field, office, suppliers)
- Knowledge of Python development environments
- Familiarity with Deep Learning concepts.
Hide Description
Wearable device and Sport ScienceContact person
PIETRO CERVERIEmail:
pietro.cerveri@polimi.itStudy course: Biomedical Engineering
Other members of the research group:
Matteo Zago - SoccermentDescription
Description:
Background: il mercato dei wearable devices è in continua evoluzione ed espansione. In ambito
sportivo, questi dispositivi permettono il monitoraggio e la raccolta di metriche di performance.
Obiettivo della tesi:
Il candidato affiancherà il team R&D (4 ing. Biomedici, un ing. Matematico, uno sviluppatore full stack
e i fornitori) nel processo di miglioramento degli algoritmi di stima delle metriche atletiche di interesse
per calciatori (e.g.: distanza percorsa, velocità, accelerazione) stimate dalle misure raccolte dal
dispositivo XSEED. Il candidato parteciperà alla fase sperimentale di raccolta dati e all'analisi degli
stessi e parteciperà allo sviluppo di nuovi algoritmi per la stima di parametri di consumo metabolico
derivati dai dati attualmente raccolti.
Requisiti:
- Passione per lo sport
- Disponibilità a lavorare in un contesto operativo e dinamico (campo, ufficio, fornitori)
- Conoscenza ambienti di sviluppo Python
- Familiarità con concetti di signal processing
Hide Description
AI-assisted Distributed Control for Zero-Touch end-to-end Optical NetworkingContact person
FRANCESCO MUSUMECIEmail:
francesco.musumeci@polimi.itStudy course: Computer Science and Engineering, Telecommunications Engineering
Web page:
https://musumeci.faculty.polimi.it/Description
Description:
The thesis will be developed in the context of the Italian PRIN project "Zero-Touch end-to-end Optical Networks (ZeTON)", targeting the definition and control of an optical network architecture able to face the traffic increase and massive connectivity upgrades brought by NextGen/IoT devices together with the definition of new communication services.
Novel data-plane devices, deployed together with disaggregated optical transmission system, are envisaged to achieve agility and to support for massive traffic loads. At the basis of this new paradigm, novel optical white box architectures, using pluggable optics, are conceived.
The thesis will focus in particular on multi-domain scenarios, following the optical-continuum paradigm, by fosting the removal of fix boundaries between network segments. Thus, distributed control functionalities will be designed to support novel data-plane nodes and the new “domain-less” network architectures. The control plane will be devised in the context of the Zero-Touch Networking (ZTN), relying on physical layer abstraction, impairment modelling and a telemetry-based monitoring system, enabling the intent-based autonomous networking and the application of Machine Learning (ML)-driven network operation for network self-diagnosis.
Hide Description
Open-Source and Scalable Optical Network Design in the Rust+Python StackContact person
FRANCESCO MUSUMECIEmail:
francesco.musumeci@polimi.itStudy course: Computer Science and Engineering, Telecommunications Engineering
Other members of the research group:
Nicola Di CiccoWeb page:
https://musumeci.faculty.polimi.it/Description
Description:
Popular tools for optical network design struggle between low-level languages (hard to use and maintain) and high-level languages (poor runtime performance). Rust provides a safe platform for easy development of performant Python libraries. The thesis will seek to contribute to a network design codebase for optical networking by researching and implementing novel simulation and algorithms, with an emphasis on robustness and scalability of the implementation.
Hide Description
Development of the first Ge drift detectors for high-resolution spectroscopy of hard X-raysContact person
ANDREA CASTOLDIEmail:
andrea.castoldi@polimi.itStudy course: Electronics Engineering
Other members of the research group:
Chiara GuazzoniDescription
Description:
The activity concerns the experimental study of the first prototypes of Germanium Drift Detectors in planar technology. Germanium is a natural candidate for drift topologies given the superior qualities of carrier transport and high-quality fabrication capability. The availability of a new generation of germanium drift detectors will open to high-performance spectroscopy in the range of hard X-rays (e.g. 20-100 keV) and in the detection of events at ultra-low noise with Ge detectors.
The candidate will contribute to the development of the experimental apparatus and to the qualification of the first Ge-DD prototypes to understand the transport of the generated carriers and the expected performances.
Hide Description
3-D Simulation of the Dynamics of the Electron-Hole Distribution at High Injection Levels in Semiconductor DetectorsContact person
ANDREA CASTOLDIEmail:
andrea.castoldi@polimi.itStudy course: Electronics Engineering
Other members of the research group:
Chiara GuazzoniDescription
Description:
The activity concerns the study and optimization of a 3D simulation code of the electrostatic potential and of the dynamics of the mobile carriers in the volume of semiconductor detectors in conditions of high injection levels. The correct simulation of Coulomb “explosion” and plasma effects, of charge sharing effects and collection times, as well as how all this impacts on the shape of the signals are key aspects to optimize detector performances.
The work starts from an existing code and needs to extend its application to the range of high injection levels, taking care of studying, implementing and validating appropriate numerical techniques. The final goal is a first version of the simulation code, that can run on small workstations. If feasible, it will be possible to participate in experimental campaigns for a first validation of the developed code in the frame of international collaborations.
The activity requires sufficient skills in scientific programming / numerical computation.
Hide Description
Dynamic 6G connectivityContact person
UMBERTO SPAGNOLINIEmail:
umberto.spagnolini@polimi.itStudy course: Electronics Engineering, Telecommunications Engineering
Web page:
https://spagnolini.faculty.polimi.it/Description
Description:
Autonomous vehicles will be characterized by the need of keeping the mutual vehicles connected using future 6G wireless systems. Goal of the thesis is to be part of the Team in designing the connectivity between vehicles using the Xilinx and Sivers boards. Electronic control methods will be developed and tested in challenging context with testing-cars. Know how on VHDL programming is preferred. Contact is below.
Project is part of RESTART strategic project https://www.fondazione-restart.it/, and new High Frequency Campus Lab (see https://www.deib.polimi.it/ita/notizie/dettagli/1196 ), framed in Spoke on technology of communication and electronics.
Hide Description
Multimodal Large Language Models for Network SummarizationContact person
MASSIMO TORNATOREEmail:
massimo.tornatore@polimi.itStudy course: Telecommunications Engineering
Description
Description:
LLMs are recently being leveraged for building all sorts of virtual assistants, from writing aids to coding copilots. This thesis will explore the development of a “network operator’s virtual assistant” based on multimodal LLMs able to reason on multiple modalities of data (text, graph, and possibly other sources). The objective is to summarize in a human-interpretable way the state of a communication network, answering high level questions such as “how is my network handling Netflix’s traffic?” or “what is causing a bottleneck?”
Hide Description
Deep Reinforcement Learning-based Black-Box Network Optimization MetaheuristicsContact person
MASSIMO TORNATOREEmail:
massimo.tornatore@polimi.itStudy course: Telecommunications Engineering
Other members of the research group:
Nicola Di CiccoDescription
Description:
Recent advances in optimization literature showed that autonomously learning selected subroutines of black-box metaheuristics (e.g., Genetic Algorithms, Variable Neighbourhood Search) with Reinforcement Learning can bring a significant performance boost, often outperforming handcrafted solutions. This thesis will explore the potential of DRL-assisted optimization for hard networking problems, such as routing in optical networks, VNF placement, etc.
Hide Description
Data-driven Optimization of Optical Networks Under Physical Layer UncertaintyContact person
MASSIMO TORNATOREEmail:
massimo.tornatore@polimi.itStudy course: Telecommunications Engineering
Other members of the research group:
Nicola Di CiccoDescription
Description:
Data-driven Optimization of Optical Networks Under Physical Layer Uncertainty
The complexity of physical layer constraints and the imprecise knowledge of physical layer parameters make it hard to plan over optical networks without introducing overly-conservative safety margins. However, leveraging historical data through Machine Learning can allow us to reduce our uncertainty about the real world, while preserving statistical guarantees. This thesis will explore the integration of Robust Optimization and Machine Learning in the context of optical network planning, with the goal of producing planning solutions that are both cost-effective and robust to the uncertainties of the real world.
Hide Description
Network Topology Design with Deep Learning on GraphsContact person
MASSIMO TORNATOREEmail:
massimo.tornatore@polimi.itStudy course: Telecommunications Engineering
Other members of the research group:
Nicola Di CiccoDescription
Description:
Deep Learning approaches as Reinforcement Learning and Generative Flow Networks have achieved groundbreaking achievements in generating complex graph structures (e.g., molecules) that satisfy arbitrary user-defined desiderata. This thesis will explore such methods in the context of communications network design, e.g., “what is the topology that will give me the maximum throughput?”
Hide Description
Large Language Models at the EdgeContact person
MASSIMO TORNATOREEmail:
massimo.tornatore@polimi.itStudy course: Telecommunications Engineering
Other members of the research group:
Nicola Di CiccoDescription
Description:
Recent advances in LLM implementations have made possible to run “small” (ie, few billions parameters) LLMs on edge devices, from commodity laptops down to Raspberry PIs, at the obvious expense of the generated answer quality. Still, it is reasonable to expect that simple prompts may be answered more than satisfactorily by simpler LLMs deployed at the edge, lightening the load in network and especially on the cloud servers. This thesis will explore the (possibly Machine Learning-aided) optimal placement of “small” LLMs at the edge and scheduling “easy” and “hard” user prompts to the appropriate LLM models.
Hide Description
Online learning for failure management in microwave networksContact person
MASSIMO TORNATOREEmail:
massimo.tornatore@polimi.itStudy course: Telecommunications Engineering
Other members of the research group:
Memedhe IbrahimiDescription
Description:
Our research group has already developed several Machine Learning – based approaches for fault management in microwave networks. Given the characteristics of a microwave network, unpredictable changes may appear leading to failures never seen before, or to a slow degradation due to phenomena such as aging. The thesis will target real-world needs in microwave industry such as risk-sensitive decision making and real-time operations. Online monitoring allows to promptly detect anomalies and as it is re-trained on fresh data, it acts to take counter-measure to minimize any possible outage time. This thesis will investigate online learning and monitoring techniques with the goal of building real-time processing pipelines of monitoring data and promptly flagging any unknown, anomalous behavior. As a result, even in case of unexpected failure events, the time-to-repair will be kept to minimum.
The thesis will be developed as part of an industrial project in collaboration with SIAE-Microelettronica (see: https://www.siaemic.com/)
Hide Description
Cross-layer optimization of hierarchical traffic-grooming boards in optical metro networksContact person
MASSIMO TORNATOREEmail:
massimo.tornatore@polimi.itStudy course: Telecommunications Engineering
Other members of the research group:
Memedhe IbrahimiDescription
Description:
Emerging 5G services are changing the way operators manage and optimize their optical metro networks. Therefore, the transmission technology and network design process must be tailored to the specific conditions in this segment of the network.
• This thesis will explore the implementation physical layer modelling considering mixed coherent (100G/200G/400G) and non-coherent (10G) transmission technologies, into an existing framework that optimizes the deployment of traffic grooming boards and establishes mixed (coherent and non-coherent) lightpaths.
• PoliMi has recently acquired a testbed that allows students to develop hands-on experience with real-world equipment. Failure-detection and failure-localization in optical networks can be modelled as Machine Learning (ML) classification problems. A possible thesis work is to make use of the testbed for data collection for various failure scenarios and then develop ML-based approaches for failure detection and/or localization.
• The thesis work will be developed as part of an industrial project in collaboration with SM-Optics (see: https://www.sm-optics.com/)
Hide Description
100-Mbit/s 10-bit low-power analog-to-digital converters based on noise-shaping SAR architecture in 28-nm CMOSContact person
SALVATORE LEVANTINOEmail:
salvatore.levantino@polimi.itStudy course: Electronics Engineering
Other members of the research group:
Carlo Samori, Andrea Bonfanti, Luca BertulessiDescription
2-GSample/s 12-bit analog-to-digital converters in 28nm CMOSContact person
SALVATORE LEVANTINOEmail:
salvatore.levantino@polimi.itStudy course: Electronics Engineering
Other members of the research group:
Carlo Samori, Andrea Bonfanti, Luca BertulessiDescription
Phased-array transmitters for MIMO radar applications in 28nm CMOSContact person
SALVATORE LEVANTINOEmail:
salvatore.levantino@polimi.itStudy course: Electronics Engineering
Other members of the research group:
Simone Dartizio, Francesco Tesolin, Andrea LacaitaDescription
Ultra-low-power frequency synthesizers in 22nm CMOS for IoT applicationsContact person
SALVATORE LEVANTINOEmail:
salvatore.levantino@polimi.itStudy course: Electronics Engineering
Other members of the research group:
Simone Dartizio, Francesco Tesolin, Andrea LacaitaDescription
High-efficiency high-power-density resonant DC/DC converters in in 0.18um-BCD processContact person
MAURO LEONCINIEmail:
mauro.leoncini@polimi.itStudy course: Electronics Engineering
Other members of the research group:
Mauro Leoncini, Massimo GhioniDescription
Open RAN-Empowered V2X ArchitectureContact person
MAURIZIO MAGARINIEmail:
maurizio.magarini@polimi.itStudy course: Computer Science and Engineering, Telecommunications Engineering
Other members of the research group:
Ing. Eugenio Moro, Ing. Francesco LinsalataDescription
Description:
ns3 is a simulation platform of networks. Millicar is a module for ns3 that allows simulating scenarios of vehicular communication. O-RAN is the new architecture of cellular networks. It is based on concepts of softwarization, disaggregation and flexibility to allow a level of control of all network aspects without precedent. The purpose of this thesis is to integrate millicar within an architecture O-RAN-based network control architecture. The final product will be the first existing simulation platform that integrates communiations vehicular and O-RAN.
Hide Description
E-Motor real-time model learning for mechatronic systemsContact person
FREDY ORLANDO RUIZ PALACIOSEmail:
fredy.ruiz@polimi.itStudy course: Automation Engineering, Electrical Engineering, Electronics Engineering, Computer Science and Engineering
Description
Description:
Pierburg Pump Technology Italy Spa is focused on developing mechatronic products for automotive industry. The Torino Engineering Center develops electronic solutions serving automotive applications including coolant, oil, hydrogen electrical pumps, proportional coolant valves, and advanced development for e-mobility – in all ranges of voltage and power. The focus of the thesis will be on the motors used in the automotive industry for smart-actuators, e-water pumps, and e-oil pumps.
The target of the thesis is to perform an analysis of the state of art in estimation techniques helpful in learning the electric parameters of E-motors in real-time. The analysis must lead to select the approaches most suitable for applications in the automotive industry, considering the limitations in computational complexity and sampling times. The comparison shall be conducted on a test bench, site in Turin, where it is possible to set the environmental conditions of different working points of the motor in a climate chamber.
The mentioned approaches will be implemented on a rapid-prototyping platform and must be suitable for 3-phases brushless motor, dc-motor and stepper-motor with permanent magnet excitation. To complete the thesis the student will acquire abilities in rapid-prototyping embedded system, in NI instrumentations and testing tools used in the automotive R&D field.
Required skills:
• Capability to design data-driven models
• Capability to formulate physical models of electromechanical systems
• Capability to implement and validate numerical simulations of dynamic systems
• Familiarity with Matlab-Simulink
• Experience with system identification and dynamic modeling
Hide Description
Hybrid Modelling for SOC and SOH of lithium battery for automotive applicationContact person
FREDY ORLANDO RUIZ PALACIOSEmail:
fredy.ruiz@polimi.itStudy course: Automation Engineering
Description
Description:
In the automotive industry, the most common battery technology uses lithium, whose autonomy is currently in the order of a few hundred kilometers. The reliability and performance of these batteries are influenced by the management of the charging and discharging phases. Continuous and accurate monitoring of the battery state takes on significant importance to extend the battery lifetime, effectively plan the trip route and charging stops, and optimize the energy flow management of HEVs. The main parameters to be assessed for correct battery monitoring are the state of charge (SOC), and the state of health (SOH). These two states cannot be directly measured since the technology is unavailable. Many approaches are proposed in the literature to estimate these parameters. The objective of this thesis is to perform a deep literature analysis of the state of the art on the main industrial approaches and to develop a hybrid physical-data-driven approach design to estimate the SOC and SOH of batteries in automatic applications.
Required skills:
• Capability to design data-driven models
• Capability to formulate physical modeling approach
• Capability to implement and validate numerical simulations of dynamic systems
• Solid background in estimation
Desirable:
• Familiarity with Matlab-Simulink
• Experience with system identification and dynamic modeling
• Basic knowledge of process control and modeling of chemical processes
Hide Description
On the UAV Communications Coverage Problem: A Black-Box Optimization ApproachContact person
LORENZO MARIO FAGIANOEmail:
lorenzo.fagiano@polimi.itStudy course: Automation Engineering
Other members of the research group:
Prof. Fredy Ruiz, Prof. Lorenzo FagianoWeb page:
https://www.sas-lab.deib.polimi.it/Description
Description:
Context
There has been an increased interest in the utilization of unmanned aerial vehicles (UAVs) for different civilian, military, and commercial applications. In particular, the communications sector has been testing the usage of UAVs to either augment existing infrastructure, or to replace them in particular scenarios. This is achieved by mounting base stations on the UAVs, which are then flown to the desired location to provide coverage to users. With their advantages such as ease of deployment, lower costs than base station towers, and flexible location capabilities, these so-called aerial base stations (ABSs) are a promising technology for emergency response, e.g., in cases when the terrestrial communication infrastructure is inoperable due to extreme phenomena like typhoons or earthquakes. However, with these advantages to ABSs, there lies an open problem with regards to their optimal placement as to maximize their coverage in terms of the users count and quality of service (QoS).
There have been several proposed approaches to deal with the UAV placement problem. These approaches can be based on clustering, coverage circles optimization, or the use of virtual forces on the UAV agents. However, most of these solutions assume known ground client (GC) locations, which is not realistic especially in emergency situations when ground towers are unpowered and we do not have information on user locations to save bandwidth, and due to privacy issues. However, we can have information on the sensed QoS of the connected users–whether individual QoS or the aggregate–which can be associated with the user coverage of the ABS. Due to the a priori unknown user locations, there is an intrinsic trade-off between exploitation of existing data from previously-sensed locations, and exploration to different locations around the target region to acquire more information on user QoS, and in turn, coverage fitness.
In this master thesis, you will be investigating a black-box optimization approach to the ABS coverage problem, in the context of an ABS formation. Using the respective ABS locations and their sensed user QoS, the formation automatically decides on the best placement combinations and trajectories of the member ABSs, according to the trade-off between exploitation and exploration.
Tasks
The master student will perform the following
- Literature review on UAV usage for wireless network coverage applications
- Study of a black-box optimization technique to be used for the problem
- Formulation of a scheme for ABS formation placement for coverage, using real-time optimization
- Development of a simulation testbed
- Testing with time-invariant (but a priori unknown) client locations
- Documentation of performed work
Expected profile
Currently-enrolled master student in Computer Engineering or Automation Engineering
Highly skilled (or willing to learn) in programming in any language, but preferably Python and/or MATLAB/Simulink
Analytical thinking and applied mathematical skills
Willing to be trained on new concepts and skills
Initial references
Viet, P. Q., & Romero, D. (2022). Aerial Base Station Placement: A Tutorial Introduction. IEEE Communications Magazine, 60(5), 44–49. https://doi.org/10.1109/MCOM.001.2100861
Cao, X., Yang, P., Alzenad, M., Xi, X., Wu, D., & Yanikomeroglu, H. (2018). Airborne communication networks: A survey. IEEE Journal on Selected Areas in Communications, 36(9), 1907–1926. https://doi.org/10.1109/JSAC.2018.2864423
Mozaffari, M., Saad, W., Bennis, M., Nam, Y. H., & Debbah, M. (2019). A Tutorial on UAVs for Wireless Networks: Applications, Challenges, and Open Problems. IEEE Communications Surveys and Tutorials, 21(3), 2334–2360. https://doi.org/10.1109/COMST.2019.2902862
Alzenad, M., El-Keyi, A., & Yanikomeroglu, H. (2018). 3-D Placement of an Unmanned Aerial Vehicle Base Station for Maximum Coverage of Users with Different QoS Requirements. IEEE Wireless Communications Letters, 7(1), 38–41. https://doi.org/10.1109/LWC.2017.2752161
Hayajneh, K. F., Bani-Hani, K., Shakhatreh, H., Anan, M., & Sawalmeh, A. (2021). 3D deployment of Unmanned aerial vehicle-base station assisting ground-base station. Wireless Communications and Mobile Computing, 2021. https://doi.org/10.1155/2021/2937224
Contact
Prospective students are to send their CV, master coursework grades, and code portfolio (if present) to:
prof. Fredy Ruiz, Ph.D.
Associate Professor
fredy.ruiz@polimi.it
prof. Lorenzo Fagiano, Ph.D.
Associate Professor
lorenzo.fagiano@polimi.it
Hide Description
3D Sensing and Silicon PhotonicsContact person
MICHELE NORGIAEmail:
michele.norgia@polimi.itStudy course: Electronics Engineering
Description
Description:
The thesis is In collaboration with ST-Microelectronics, and provides for reimbursement of expenses.
The thesis will start practicing on some specific technologies (MEMS mirrors, lasers, SPADs and Silicon-photonics), but also optical and embedded systems, then he/she will join the MEMS LiDAR or Silicon-Photonics program
Role may vary upon specific project needs.
Task examples that can be assigned to the intern are:
Design and develop a control system for a LIDAR projection system realized in Silicon Photonics; build a test environment; characterize the device in real conditions.
Design and develop a control system for a gyroscope realized in Silicon Photonics; build a test environment; characterize the device in real conditions.
Design and develop a new CFD (Constant Fraction Discriminator); build a test environment; characterize the device in real conditions.
Technical skills:
Willing to learn and autonomy
HW-SW skills (mandatory): Digital and analog electronics, schematic diagrams, C, C++, Matlab
Other skills (appreciated): VHDL, 3D modeling (Solidworks), optics
ST contact: daniele.caltabiano@st.com
Hide Description
Green and Efficient IoT: an adaptive monitoring system to decrease latency and improve energy efficiencyContact person
MONICA VITALIEmail:
monica.vitali@polimi.itStudy course: Computer Science and Engineering
Web page:
https://vitali.faculty.polimi.itDescription
Description:
A huge amount of information is generated every day by a countless number of sensors. These sensor data are used to take important decisions and improve the welfare of users and citizens. However, the most of these data is never used and its storage and maintenance have a relevant cost in terms of finance and energy. This thesis aims at explore a different approach for sensor data management and will investigate methods and tools to adapt the data collection from sensor in terms of data generation frequency and level of detail according to several factor: actual usage of the data, data location, and energy efficiency of data storage and movement. This thesis will provide a methodology to solve issues related to where, when, and how to store sensor data in the cloud continuum. KEYWORDS: Green IT, IoT, adaptive monitoring system, cloud continuum, fog computing
Hide Description
Monitoring the Sustainability of Multi-Component ApplicationsContact person
MONICA VITALIEmail:
monica.vitali@polimi.itStudy course: Computer Science and Engineering
Web page:
https://vitali.faculty.polimi.itDescription
Description:
Modern applications are composed of several components (microservices, functions, monoliths) that cooperate together for reaching the overall application goal. Most of the existing infrastructures don’t provide information about the energy consumption at the application component level. Thus, some models to derive this information are needed if we want to envision a real sustainable application future. The aim of this thesis is to explore the current state of the art and the existing tools for deriving energy consumption of single-component applications and their emissions and to propose a method to extend these tools for measuring the impact of multi-component applications. KEYWORDS: Green IT, CO2 estimation, energy consumption, cloud native applications
Hide Description
Green Distributed AI: a data preparation perspectiveContact person
MONICA VITALIEmail:
monica.vitali@polimi.itStudy course: Computer Science and Engineering
Web page:
https://vitali.faculty.polimi.itDescription
Description:
The adoption of AI is sensitively increasing the number of computing instances in the cloud. The training phase uses a huge amount of data coming from different data sources. The training data volume is one of the most relevant contributors to the power consumption of model training in ML, while having a limited impact on the model accuracy. At the same time, distributed ML approaches are becoming more and more popular (e.g., federated learning). In this context, the thesis should provide an approach to decrease the energy consumption of AI without affecting the accuracy of the model by taking decisions on where and how to store the training data and to execute the model training. KEYWORDS: data preparation, Green AI, Data quality, distributed learning
Hide Description
Sustainable Applications Deployment in a Fog EnvironmentContact person
MONICA VITALIEmail:
monica.vitali@polimi.itStudy course: Computer Science and Engineering
Web page:
https://vitali.faculty.polimi.itDescription
Description:
Sustainability and Energy Efficiency are a driver for the improvement of our society and a necessity for a better future. While Data Centers are getting greener, this is not the case for other computing locations like fog and edge computing, composed of small and inefficient data centers. Considering applications as composed of several microservices interconnected in a workflow and exchanging data, the research question is how it is possible to adaptively allocate each component by considering the trade-off between QoS and Energy Efficiency. KEYWORDS: micro services, fog computing, cloud continuum, green IT, scheduler
Hide Description
