In this page you will find a list of PhD scientific/technical courses offered for the students of the JD ICE Doctoral Course
| Title | Duration (hours) | Description | Professor |
| Cognitive Self-Aware Ego-Things | 25 | The course aims at providing PhD Candidates with knowledge of the basic state of the art and advanced theories/techniques for learning from multisensory signals and data Bayesian models for jointly predicting, processing, filtering, and interpreting observed interactions. | C.Regazzoni P.Zontone |
| Machine Learning for Autonomous Systems | 25 | The course is aimed at providing machine learning basic and advanced techniques for data driven signal processing models to be used within autonomous systems design. Specific attention will be devoted to high dimensional data processing on the edge (with real practical examples in Python), showing how deep learning approaches can be adapted and optimized for working with limited computational capabilities. | L.Marcenaro |
| Introduction to deep learning | 20 | The goal of the course is to introduce the main topics (particularly: architectures and training strategies) of machine learning with deep neural networks, in an application-oriented approach. | F.Bellotti |
| Internet of Things (IoT) communication protocols | 20 | The course offers a detailed overview about the communication protocols defined ad-hoc and the ones modified to be suitable for the IoT application requirements, including details about packet formats, network architectures, and procedures and interactions among the involved communication entities. Finally, some examples of practical applications of these communication technologies will be mentioned in order to show how they are used in real scenarios. | F.Patrone |
| Advanced Programming in Matlab and Simulink | 20 | The course provides elements of advanced programming in MATLAB and Simulink environment, for typical engineering applications such as regression, simulation of dynamical systems, optimization. A part of the course will be devoted to the realization of plots suitable to be included in scientific papers. | A.Oliveri M.Lodi |
| Advanced Techniques for Wireless Positioning and Localization | 15 | The course provides a detailed overview of the main wireless positioning and localization techniques available in the literature, both concerning indoor and outdoor scenarios. The topics cover the fundamental principles of positioning and localization, explaining the basic theory and key concepts related to state-of-the-art techniques. Special focus will be given on system architecture, approach and methodology, algorithms and accuracy of the considered solutions. The course will also delve into advanced wireless positioning methods and their latest applications in different frameworks, such as the Internet of Things, smart cities and smart mobility, discussing related challenges and open issues. | C.Garibotto |
| Analysis of (Networks of) Non-linear Oscillators | 20 | This course aims to provide the students with mathematical and numerical tools for the analysis of nonlinear dynamical systems, even networked, with either fixed or changing parameters (in the latter case the lessons’ topic will be the so-called bifurcation analysis). In particular, the lessons will be focused on both geometrical methods for qualitative analysis and the most diffused numerical methods for quantitative analysis. The main theoretical results will be applied to dynamical systems arising from different fields and will be illustrated through computer demos in the MATLAB programming environment. | M.Storace M.Lodi |
| Cyber security approaches for Cloud/Edge Environments | 20 | The course will describe the advanced technologies and solutions for cyber-security in a cloud/edge environment. The knowledge provided by this course covers various fields such as telecommunications, computer science, software engineering, and electronics, and includes some hints at economic aspects. | A.Carrega |
| Deep Neural Networks for Constrained Devices | 12 | The course provides basic knowledge about the key aspects that should be considered when deploying a deep neural network on a constrained device. The course provides a brief introduction to the topic and presents a survey of the most important tools and techniques. Practical examples of quantization, pruning, and design of efficient architectures are provided using Tensorflow lite. In addition, two examples of deployment on Jetson Nano and Arduino Nano are presented. | E.Ragusa |
| Emerging Ultra-Low Power Analog-Mixed-Signal ICs for ubiquitous sensor nodes | 15 | The course aims to provide an overview of low frequency analog and mixed signal integrated circuit design challenges and circuit solutions emerged in the last years, with a special emphasis on ultra-low-voltage (ULV), ultra-lowpower (ULP) design techniques and topologies suitable to operation in energy autonomous sensor nodes for the IoT. For each functional blocks (amplifiers, references, oscillators, A/D and D/A converters, etc...) the main ULV/ULP design tradeoffs and figures-of-merit (FOMs) will be first introduced. Then, an overview of emerging design techniques and circuit topologies will be given | O.Aiello |
| Microcontroller Programming | 12 | The course is designed to analyze the different features of the microcontroller with a practical approach. This is done by going directly to solve some typical control problems, making best use of the devices internal to the chip. During the course will be described the architecture and internal units of an ARM Cortex-M4 microcontroller; Interfacing of analogue and digital signals, including basics of electronics; Serial communications; Low level programming in C, interrupts service routines; Management of parallel processes without the aid of an operating system, process priority, timing analysis; Instruction and register sets and addressing modes for a given microcontroller family; Efficiency aspects on different data types and code snippets in C; Development tools. | F.Ansovini |
| Queueing Theory and Teletraffic Engineering | 25 | Queueing Theory is a fundamental tool for performance evaluation in many Engineering areas, particularly in the fields of Computer and Telecommunications Systems. The aim of the course is to provide a self-contained treatment of some basic and advanced material in these two fields, to highlight analytical modelling tools that can be used for both purposes of performance evaluation and control. | F.Davoli |
| Introduction to Cognitive Dynamic Systems | 20 | The course will cover the fundamentals of Cognitive Dynamic Systems, focusing on Dynamic Bayesian Networks, Bayesian filtering, and unsupervised learning algorithms, using data from multiple sensors with varying dimensions. Practical examples and corresponding results, including lab exercises using MATLAB, will also be discussed. | P.Zontone |
| AI-based Methods for Secured Wireless Communications | 20 | This course is designed to provide a fundamental understanding of security threats on the physical layer of wireless communications, including jamming and spoofing attacks. It will give an overview of how security issues have evolved from 1G to 6G wireless communication and will also explore potential solutions to address these evolving threats. The course will focus on the advancements in AI and illustrate how AI can enhance wireless communications to achieve high levels of intelligence and provide high-security solutions. Furthermore, it will delve into new approaches to incorporating radio signals with various sensors (e.g., GPS and video cameras) to enable integrated sensing and communication. This will enhance understanding of how the physical and cyber worlds interact, informing the development of advanced defence strategies to tackle security concerns and ensure safe operations in critical applications like V2X and UAV communications | A.Krayani |