OVERVIEW

The course provides the theoretical foundations and practical aspects of Internet of Things (IoT) systems and the application of Artificial Intelligence techniques to distributed sensing environments. It covers IoT architectures, communication technologies, networking protocols, edge and cloud computing paradigms, and the main Artificial Intelligence techniques for sensor data analysis. Particular emphasis is placed on Deep Learning, Edge AI, TinyML, and Federated Learning for the development of intelligent IoT systems.

AIMS AND CONTENT

LEARNING OUTCOMES

The combination of IoT and Artificial Intelligence is already a reality—though still not widely known—and represents the integration of two frontier technologies that are expected to see growing adoption. Students will acquire the skills to understand and design AIoT systems by integrating IoT devices, connectivity, and intelligent algorithms. They will be able to collect, process, and transmit data across edge, fog, and cloud layers; apply machine and deep learning techniques for predictive and decision-making analysis; and develop solutions for real-world applications (industry, mobility, smart home, healthcare), addressing scalability and reliability challenges.

AIMS AND LEARNING OUTCOMES

Upon successful completion of the course, Students will be able to:

• understand the architecture, enabling technologies, and main communication protocols of Internet of Things (IoT) systems;

• describe the operation of the main devices, networks, and protocols used in IoT systems, from data acquisition to cloud services;

• analyze and design basic IoT solutions by selecting the most appropriate communication technologies and architectures according to application requirements;

• understand the fundamental principles of Artificial Intelligence applied to IoT and the main machine learning techniques for sensor data analysis;

• explain the role of neural networks, Deep Learning, Edge AI, TinyML, and Federated Learning in the development of intelligent IoT systems;

• evaluate the potential and limitations of Artificial Intelligence techniques for monitoring, automation, and decision-support applications based on IoT systems.

PREREQUISITES

Sono richieste conoscenze di base di reti di telecomunicazioni, protocolli di comunicazione, elaborazione dei segnali, probabilità e statistica, nonché competenze di programmazione. Costituiscono inoltre prerequisiti utili le conoscenze fondamentali di sistemi distribuiti e di architetture di calcolo.

TEACHING METHODS

The course is delivered through face-to-face lectures supported by multimedia presentations and practical examples. Teaching materials, including lecture slides, scientific papers, and additional documentation, are made available to students through the AulaWeb platform. Practical examples and case studies are used to illustrate the application of IoT technologies and Artificial Intelligence techniques in real-world scenarios.

SYLLABUS/CONTENT

Introduction to IoT systems: definitions, applications, and enabling technologies. IoT components: from sensors to gateways (sensors and actuators, basic functions of electronic boards, and data acquisition techniques). Machine-to-Machine (M2M) communications: technologies for WPANs (BLE, IEEE 802.15.4), LPWANs (LoRa/LoRaWAN), and WSANs. Network architectures and routing protocols (IPv6, 6LoWPAN, RPL). Gateway-to-cloud communications: data acquisition and messaging protocols (CoAP, MQTT, AMQP).

Fundamentals of Artificial Intelligence for IoT: machine learning for sensor data analysis, including supervised, unsupervised, and reinforcement learning; classification, regression, clustering, anomaly detection, and time-series analysis. Introduction to neural networks, Deep Learning, Edge AI, TinyML, and Federated Learning for distributed intelligence and decentralized model training on interconnected IoT devices.

RECOMMENDED READING/BIBLIOGRAPHY

Teaching materials prepared by the instructors (lecture slides, lecture notes, scientific papers, and additional documentation) will be made available through the AULAWEB platform and will constitute the primary study material for the course.

Additional reference textbooks and supplementary bibliographic material, if required, will be indicated through the AULAWEB platform during the course.

TEACHERS AND EXAM BOARD

LESSONS

LESSONS START

Please refer to the University's Easy Academy platform by clicking here.

Class schedule

The timetable for this course is available here: Portale EasyAcademy

EXAMS

EXAM DESCRIPTION

The examination consists of a written test followed by an oral examination. The written test covers both Internet of Things and Artificial Intelligence topics and consists of multiple-choice questions administered through the AulaWeb platform.

Passing the written test is a prerequisite for admission to the oral examination and does not directly contribute to the final grade. The oral examination covers the entire course syllabus and is designed to assess the student's understanding of the course topics, ability to integrate the different course contents, and capability to apply the acquired knowledge.

ASSESSMENT METHODS

The assessment is designed to verify the achievement of the course learning outcomes. In particular, it evaluates students' understanding of Internet of Things (IoT) architectures and technologies, the main communication protocols, and Artificial Intelligence techniques for sensor data analysis, as well as their ability to integrate this knowledge in the analysis and design of intelligent IoT systems.

The written test, consisting of multiple-choice questions, is intended to assess whether students possess the fundamental knowledge required for admission to the oral examination. The oral examination evaluates students' ability to present the course topics using appropriate technical terminology, establish connections among the different course contents, and critically discuss the main technological and methodological solutions covered during the course.

FURTHER INFORMATION

For any further information or clarification, students are encouraged to contact the course instructors.