AIMS AND CONTENT

LEARNING OUTCOMES

This subject introduces the students to main problems and development of pervasive computing platforms for networks of dynamically connected ego-things realized as electronic systems. Attendees will understand and implement self-organizing systems using modern machine-learning techniques as enablers for many autonomous and semiautonomous tasks.

AIMS AND LEARNING OUTCOMES

The teaching unit aims to equip students with a comprehensive understanding of the design, development, and deployment of pervasive computing systems composed of dynamically connected electronic entities—referred to as ego-things. These systems are characterized by their ability to operate autonomously or semi-autonomously in distributed environments, leveraging self-organization and machine learning to adapt to changing conditions and tasks. The teaching unit emphasizes both theoretical foundations and practical implementation, preparing students to innovate in fields such as smart environments, autonomous systems, and the Internet of Things (IoT).

Upon successful completion of this teachin unit, students will be able to:

1. Conceptual Understanding

   • Explain the principles of pervasive computing and its role in modern electronic systems.
   • Describe the architecture and behavior of ego-things within dynamic, decentralized networks.

2. System Design and Implementation

   • Design and prototype embedded electronic systems capable of dynamic connectivity and autonomous operation.
   • Integrate sensors, actuators, and communication modules to build context-aware devices.

3. Self-Organizing Systems

   • Analyze and implement self-organizing mechanisms in distributed systems.
   • Evaluate the performance and robustness of decentralized coordination strategies.

4. Machine Learning Integration

   • Apply modern machine learning techniques (e.g., reinforcement learning, federated learning, unsupervised learning) to enable adaptive behavior in electronic systems.
   • Develop and train models that support real-time decision-making in resource-constrained environments.

5. Practical Application and Innovation

   • Develop and test a complete pervasive system prototype addressing a real-world problem.
   • Critically assess the ethical, societal, and technical implications of deploying autonomous electronic systems in everyday environments.

PREREQUISITES

Integrated sensing and communications

Tiny machine learning

Sensors

TEACHING METHODS

The lessons alternate theoretical explanations with practical exercises. The theoretical explanations are frequently exemplified with the analysis, execution and debugging of code fragments directly on the teacher's PC. All the material seen in class (slides and practical examples) is shared through the AulaWeb and Teams platforms. Students can interact directly with the teacher during the lessons or through the Teams platform.

Students with valid certifications for Specific Learning Disorders (SLDs), disabilities or other educational needs are invited to contact the teacher and the School's contact person for disability at the beginning of teaching to agree on possible teaching arrangements that, while respecting the teaching objectives, take into account individual learning patterns. Contacts of the School's disability contact person can be found at the following link Comitato di Ateneo per l’inclusione delle studentesse e degli studenti con disabilità o con DSA | UniGe | Università di Genova

SYLLABUS/CONTENT

1. Introduction to Pervasive Computing: history and evolution of pervasive systems, characteristics: ubiquity, context-awareness, autonomy, applications in smart environments, security, and mobility
2. Ego-Things and Dynamic Connectivity: concept of ego-things and self-awareness in devices, communication protocols
3. Embedded Systems for Pervasive Platforms: microcontrollers and SoCs (e.g., ESP32, STM32), real-time operating systems (RTOS)
4. Sensors, Actuators, and Context Awareness: sensor integration and data acquisition, signal conditioning and preprocessing, context modeling and interpretation
5. Self-Organizing Systems: principles of self-organization and emergence, swarm intelligence and distributed coordination
6. Machine Learning for Embedded Systems: pverview of ML models suitable for edge devices, model compression and quantization
7. Learning in Dynamic Environments: online learning and continual adaptation, reinforcement learning basics, federated learning
8. System Integration and Prototyping: hardware/software co-design, communication stack integration
9. Security and Ethical Considerations: security in pervasive systems (e.g., authentication, encryption), ethical implications of autonomous systems, data privacy and responsible AI
10. Case Studies and Industry Applications: smart cities, autonomous vehicles, industrial IoT

RECOMMENDED READING/BIBLIOGRAPHY

Pervasive Computing: Engineering Smart Systems
Author: Natalia Silvis-Cividjian
Publisher: Springer, 2017
A comprehensive introduction to pervasive computing, covering signal processing, control systems, machine learning, and system engineering.

Embedded System Design
Author: Peter Marwedel
Covers hardware/software co-design, real-time systems, and power-aware computing.
Ideal for understanding the architecture and constraints of embedded platforms.

Computers as Components: Principles of Embedded Computing System Design
Author: Wayne Wolf
Focuses on system-level design and integration of embedded systems.
Includes case studies and practical design methodologies.

Making Embedded Systems
Author: Elecia White
A hands-on guide for engineers and students, with practical advice on debugging, testing, and real-world deployment.

Swarm Intelligence: From Natural to Artificial Systems
Authors: Eric Bonabeau, Marco Dorigo, Guy Theraulaz
A foundational text on decentralized coordination and emergent behavior in distributed systems.

Self-Organization in Biological Systems
Authors: Scott Camazine et al.
Though biologically oriented, this book provides deep insights into principles applicable to engineered self-organizing systems.

TinyML: Machine Learning with TensorFlow Lite on Arduino and Ultra-Low-Power Microcontrollers
Authors: Pete Warden, Daniel Situnayake
A practical guide to deploying ML models on resource-constrained devices.

Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow
Author: Aurélien Géron
While not edge-specific, this book is excellent for building foundational ML skills needed for model development and optimization.

TEACHERS AND EXAM BOARD

LESSONS

LESSONS START

https://corsi.unige.it/corsi/11970/studenti-orario

Class schedule

The timetable for this course is available here: Portale EasyAcademy

EXAMS

EXAM DESCRIPTION

Project based evaluation

ASSESSMENT METHODS

Technical Functionality and Innovation

• Does the prototype meet the functional requirements?
• Is the system robust, scalable, and well-integrated?
• Does it demonstrate innovation in design or application?

System Design and Documentation

• Clarity and completeness of system architecture
• Justification of design choices (hardware, protocols, ML models)
• Quality of diagrams, code documentation, and testing strategy

Presentation and Communication

• Clarity and professionalism of the oral presentation
• Ability to explain technical concepts to a mixed audience
• Effectiveness of visual aids and live demo

Teamwork and Project Management

• Evidence of collaboration and task distribution
• Use of project management tools (e.g., Git)
• Peer assessment of individual contributions