Fiche personnelle: Michele Rossi

The Wireless Networks course offers a comprehensive, mathematically rigorous deep-dive into the foundational mechanics and performance of wireless communication networks. It is designed for advanced students, by bridging fundamental theory with practical system design, balancing physical-layer characterisation with upper-layer protocol behaviour with precise analytical models.

Key course topics include:

- Wireless Channel Dynamics & Physical Layer Principles: Physical characteristics of the wireless channel, path loss, fading models, and modern error-control mechanisms including Hybrid ARQ (HARQ).

- IEEE 802.11 MAC Architecture: In-depth technical breakdown of CSMA/CA protocols, channel access mechanisms, framing, and evolution across standard generations.

- Analytical Modeling & Performance Analysis: Mathematical modeling techniques (including Markov chains and queueing theory) used to simulate, analyze, and evaluate throughput, latency, and contention in 802.11 networks.

- Transport Layer Optimization: Behavior, performance, and adaptation of modern TCP variants over dynamic, loss-prone wireless environments.

Catégorie DEPARTMENT OF INFORMATION ENGINEERING - DEI / A.A.2026 - 2027 / Laurea Magistrale / IN2898 - ICT FOR INTERNET AND MULTIMEDIA - INGEGNERIA PER LE COMUNICAZIONI MULTIMEDIALI E INTERNET

This is an advanced course on wireless networks and systems. The topics that will be covered are: mathematical models of the wireless channel, channel abstraction models for link layer protocols, hybrid ARQ techniques exploiting retransmission and coding, advanced TCP algorithms (CUBIC), IEEE 802.11 systems (MAC protocol, throughput calculations). Additional topics will address modern coding theory (fountain codes) and wireless sensing.

Catégorie DEPARTMENT OF INFORMATION ENGINEERING - DEI / A.A.2025 - 2026 / Corsi di laurea magistrale / IN2898 - ICT FOR INTERNET AND MULTIMEDIA - INGEGNERIA PER LE COMUNICAZIONI MULTIMEDIALI E INTERNET

This is an advanced course on wireless networking. Emphasis will be given on the description and analysis of network protocols for the error and flow control of user's data over wireless systems. Topics of interest are: ARQ and Hybrid ARQ protocols, TCP protocols (transport layer) for wireless communications, combination of ARQ and TCP over mobile protocol stacks, end-to-end performance analysis, routing in ad hoc wireless networks. The following technologies will be presented and analysed in detail:

- Modern TCP algorithms (TCP CUBIC): mathematical modelling and their performance analysis;
- Wi-Fi (IEEE 802.11 family): the communication protocols used at the MAC layer will be presented and analysed in detail.

Research-oriented seminars on novel IEEE 802.11ay/bf technologies will be given, paying attention to their new environment sensing functionalities. This will lead to the presentation of open research avenues and possible Master theses.

Exercises: solved exercises will be shown amounting to (at least) 12 hours of frontal lessons. These will demonstrate how to use the mathematical models presented during the theoretical lessons can be used to quantify the performance of wireless transmission systems in various relevant settings.

Exam mode: the exam will consist of a written test, where the student will have to compute the performance of a (simplified) wireless system in the presence of wireless/wired channel errors.

Lessons mode: lessons will be in presence from the classroom. Videos of all lessons will be made available through the Moodle page of the course.

Catégorie DEPARTMENT OF INFORMATION ENGINEERING - DEI / A.A.2024 - 2025 / Corsi di laurea magistrale / IN2371 - ICT FOR INTERNET AND MULTIMEDIA - INGEGNERIA PER LE COMUNICAZIONI MULTIMEDIALI E INTERNET

This is a course on modern coding theory, covering the theory and the algorithms that are utilised in communication systems to protect the information sent against channel errors. The tools that will be developed are very powerful and widely used, and involve coding techniques for the physical layer of wired and wireless systems as well as packet-based coding and distributed coded dissemination for Internet-based networks.

Catégorie DEPARTMENT OF INFORMATION ENGINEERING - DEI / A.A. 2023 - 2024 / Corsi di laurea magistrale / Master's degrees / IN2371 - ICT FOR INTERNET AND MULTIMEDIA - INGEGNERIA PER LE COMUNICAZIONI MULTIMEDIALI E INTERNET

This is a course on network coding algorithms. It will teach you how to transmit and distribute digital content over a distributed network reliably. These algorithms are nowadays used for nearly all telecommunications systems at several layers of the protocol stack.

Catégorie DEPARTMENT OF INFORMATION ENGINEERING - DEI / A.A. 2022 - 2023 / Corsi di laurea magistrale / Master's degrees / IN2371 - ICT FOR INTERNET AND MULTIMEDIA - INGEGNERIA PER LE COMUNICAZIONI MULTIMEDIALI E INTERNET

This is an advanced course on wireless networking. Emphasis will be given on the description and analysis of network protocols for the error and flow control of user's data over wireless systems. Topics of interest are: ARQ and Hybrid ARQ protocols, TCP protocols, combination of ARQ and TCP over mobile protocol stacks, end-to-end performance analysis, routing in ad hoc wireless networks. Of particular interest, the following technologies will be presented and analysed in detail: 1) Modern TCP algorithms (TCP CUBIC): mathematical modelling and their performance analysis; 2) Wi-Fi (IEEE 802.11 family): the communication protocols used at the MAC layer will be presented and analysed in detail. If time allows, research-oriented seminars on novel 802.11ay/bf technologies will be given, paying attention to their new environment sensing functionalities. This will lead to the presentation of open research avenues and possible Master theses. Exercises: solved exercises will be shown amounting to (at least) 12 hours of frontal lessons. These will demonstrate how to use the mathematical models presented during the theoretical lessons can be used to quantify the performance of wireless transmission systems in various relevant settings.

Catégorie DEPARTMENT OF INFORMATION ENGINEERING - DEI / A.A. 2022 - 2023 / Corsi di laurea magistrale / Master's degrees / IN2371 - ICT FOR INTERNET AND MULTIMEDIA - INGEGNERIA PER LE COMUNICAZIONI MULTIMEDIALI E INTERNET

This advanced Master-level course explores modern machine and deep learning techniques tailored for biological signal processing and human data analysis. Moving beyond static text and images, the curriculum emphasizes dynamic, spatio-temporal signals that exhibit complex correlations across both spatial dimensions (e.g., sensor arrays) and temporal domains (e.g., physiological time series).

The course places a strong, distinct focus on unsupervised learning and anomaly detection, a critical and yet often neglected skill set, necessary to analyze unannotated biomedical data. Students will gain theoretical mastery and practical expertise across unsupervised feature extraction (SOMs, DBSCAN, autoencoders, one class support vector machines), supervised deep architectures (CNNs, RNNs, GNNs, Transformers, SNNs), and advanced model optimization.

Hands-on laboratory sessions with tested reference code prepare students to build custom end-to-end deep learning models. Assessment is project-based (groups of max 2), requiring students to analyze real-world datasets, deliver a scientific-style report, submit working code, and complete an oral defense.

Catégorie DEPARTMENT OF MATHEMATICS "Tullio Levi-Civita" - DM / A.A.2026 - 2027 / Laurea Magistrale / SC2738 - DATA SCIENCE

Machine Learning for Human Data is an advanced course on machine learning and neural network models with selected applications to human data (e.g., ECG, movement data, audio, biomedical images). The material will revolve around unsupervised and supervised learning, as follows. Unsupervised learning: Self Organising Maps, Neural Gas Networks, the DBSCAN algorithm, denoising auto encoders (CNN and RNN-based). Supervised learning: recurrent neural networks (RNN), graph neural networks (GNN), attention mechanisms (the transformer model), spiking neural networks (towards neuromorphic computing). A key aspect of the course is the rich laboratory activity, where students will learn to implement their learning architectures (in the Python programming language, using TensorFlow), train and test them on selected datasets.

Catégorie DEPARTMENT OF MATHEMATICS "Tullio Levi-Civita" - DM / A.A.2025 - 2026 / Corsi di laurea magistrale / SC2738 - DATA SCIENCE (Ord. 2025)

Short Intro: this is an advanced Master level course on machine and deep learning for human data analysis. Emphasis will be put on learning models and specifically on unsupervised learning techniques. The student will be trained on modern unsupervised data reduction and clustering algorithms, with deep learning models, including convolutional and recurrent neural networks. The teaching style will follow, at first, a presentation of the theoretical and technical tools, to then delve into their use within selected applications, their implementation and testing via extensive and carefully planned laboratory activity.

Selected topics in ML:
1. Unsupervised learning: Self Organising Maps, Neural Gas Networks, DBSCAN, denoising auto encoders (CNN and RNN-based).
2. Neural networks: convolutional neural networks (CNN), recurrent neural networks (RNN), batch normalisation, residual networks (ResNets), attention mechanisms (the transformer model).

Lab. activity: a key section of the course will be devoted to the lab. activity. Through this, the student will learn to implement the models and algorithms presented during the theoretical lessons. Special focus will be put on deep learning, including the implementation of convolutional (CNN) and recurrent neural networks (RNN). Various optimizations such as regularization techniques, and recent architectures such as autoencoders, residual networks (ResNets) and CNN inception layers will be discussed and implemented. The attention mechanism and the transformer model will be as well presented. Reference (tested) source code will be provided for each lab. lesson, which can be used by the student to develop their own projects both for this course and beyond.

Catégorie DEPARTMENT OF MATHEMATICS "Tullio Levi-Civita" - DM / A.A.2024 - 2025 / Corsi di laurea magistrale / SC2738 - DATA SCIENCE

Short Intro: this is an advanced Master level course on machine and deep learning for human data analysis. Emphasis will be put on learning models and specifically on unsupervised learning techniques. The student will be trained on modern unsupervised data reduction and clustering algorithms, with deep learning models, including convolutional and recurrent neural networks. The teaching style will follow, at first, a presentation of the theoretical and technical tools, to then delve into their use within selected applications, their implementation and testing via extensive and carefully planned laboratory activity.

Selected topics in ML:
1. Unsupervised learning: Self Organising Maps, Neural Gas Networks, DBSCAN, denoising auto encoders (CNN and RNN-based).
2. Neural networks: convolutional neural networks (CNN), recurrent neural networks (RNN), batch normalisation, residual networks (ResNets), attention mechanisms (the transformer model).

Lab. activity: a key section of the course will be devoted to the lab. activity. Through this, the student will learn to implement the models and algorithms presented during the theoretical lessons. Special focus will be put on deep learning, including the implementation of convolutional (CNN) and recurrent neural networks (RNN). Various optimizations such as regularization techniques, and recent architectures such as autoencoders, residual networks (ResNets) and CNN inception layers will be discussed and implemented. The attention mechanism and the transformer model will be as well presented. Reference (tested) source code will be provided for each lab. lesson, which can be used by the student to develop their own projects both for this course and beyond.

Catégorie DEPARTMENT OF MATHEMATICS "Tullio Levi-Civita" - DM / A.A. 2023 - 2024 / Corsi di laurea magistrale / SC2738 - DATA SCIENCE (first year)

Human Data Analytics is an advanced course on Machine Learning techniques applied to data from human sensor systems. Typical signals that will be considered are ECG, speech, inertial signals. The course will present theory and tools for both unsupervised (1st half of the program) and supervised (2nd half) learning. Advanced neural networks (including recurrent neural networks, attention mechanisms and transformers) will be also covered, showing their application to the analysis of human data. Carefully designed laboratory classes will complement the theoretical lessons, allowing the student to implement and apply the tools presented in the theory part. The final exam is project based.

Catégorie DEPARTMENT OF MATHEMATICS "Tullio Levi-Civita" - DM / A.A. 2022 - 2023 / Corsi di laurea magistrale / SC2377 - DATA SCIENCE