Intelligent IoT

• To understand and analyse the implications of remote intelligent sensing in the environment.
• To understand how decentralised data analysis techniques work in perimeter or federated learning environments.

THEORY PROGRAMME:
Theme 1: Smart IoT basics
Theme 2: HW/SW platforms for smart IoT
Theme 3: IoT protocols for building intelligent systems
Theme 4: Deploying AI on IoT devices: decentralised inference models
Theme 5: Intelligent monitoring

Session Content
1-USC Theme 1: Smart IoT basics
2-USC Theme 1: Smart IoT basics
3-USC Theme 2: HW/SW platforms for smart IoT
4-USC Theme 2: HW/SW platforms for smart IoT
5-USC Theme 2: HW/SW platforms for smart IoT
6-UDC Theme 3: IoT protocols for building intelligent systems
7-UDC Theme 3: IoT protocols for building intelligent systems
8-UDC Theme 4: Deploying AI in IoT devices
9-UDC Theme 4: Deploying AI in IoT devices
10-UDC Theme 5: Intelligent monitoring


LAB PROGRAMME:
Deployment of learning projects for inference in perimeter devices:
• Machine Learning on low power devices. [UDC]
• Deployment of CNN on RaspberryPi for computer vision. [USC]
The approximate distribution of the practical sessions is shown in the following table. It should be borne in mind that the specific distribution may vary in each academic year depending on both the timetable and the development of the subject.
Session Duration Content
USC 5 hours CNN on RaspberryPi for computer vision
UDC 5 hours ML on low-power device (e.g., ESP8266, Arduino-compatible microcontroller)

BASIC BIBLIOGRAPHY:
Jan Holler, Vlasios Tsiatsis, Catherine Mulligan, Stefan Avesand, Stamatis Karnouskos David Boyle, From Machine-to-Machine to the Internet of Things: Introduction to a new Age of Intelligence, Academic Press; 1 edition.

Peter Waher , Learning Internet of Things, Packt Publishing (January 27, 2015)

Samuel Greengard (2015). The Internet of Things. MIT Press

S. P. Yadav, B. S. Bhati, D. P. Mahato, S. Kumar, "Federated Learning for IoT Applications", Springer (2022)

COMPLEMENTARY BIBLIOGRAPHY:
Vijay Madisetti, Arshdeep Bahga, Internet of Things (A Hands-on-Approach), Publisher: VPT; 1 edition (August 9, 2014).

Adrian McEwen, Hakim Cassimally, Designing the Internet of Things. Publisher: Wiley; 1 edition

BASIC AND GENERAL
GC1 - Maintain and extend sound theoretical approaches to enable the introduction and exploitation of new and advanced technologies in the field of Artificial Intelligence.
GC2 - Successfully tackle all stages of an Artificial Intelligence project.
GC4 - To elaborate adequately and with some originality written compositions or motivated arguments, to write plans, work projects, scientific articles and to formulate reasonable hypotheses in the field.
GC5 - Work in teams, especially multidisciplinary teams, and be skilled in time management, people management and decision-making.
CB6 - Possess and understand knowledge that provides a basis or opportunity for originality in the development and/or application of ideas, often in a research context.
CB7 - Students are able to apply their acquired knowledge and problem-solving skills in new or unfamiliar environments within broader (or multidisciplinary) contexts related to their field of study.
CB9 - Students are able to communicate their conclusions and the ultimate knowledge and rationale behind them to specialist and non-specialist audiences in a clear and unambiguous way.
CB10 - Students possess the learning skills that will enable them to continue studying in a largely self-directed or autonomous manner.

CROSS-CUTTING
TC5 - Understand the importance of entrepreneurial culture and know the means available to entrepreneurs.
CT8 - Value the importance of research, innovation and technological development in the socio-economic and cultural progress of society.
TC9 - Have the ability to manage time and resources: develop plans, prioritise activities, identify critical ones, set deadlines and meet them.

SPECIFIC
SC19 - Knowledge of different fields of application of AI-based technologies and their capacity to offer a differentiating added value.
CE20 - Ability to combine and adapt different techniques, extrapolating knowledge between different fields of application.
CE21 - Knowledge of the techniques that facilitate the organisation and management of AI projects in real environments, the management of resources and the planning of tasks in an efficient way, taking into account concepts of knowledge dissemination and open science.
SC22 - Knowledge of techniques that facilitate the security of data, applications and communications and their implications in different AI application domains.
CE30 - Be able to pose, model and solve problems that require the application of artificial intelligence methods, techniques and technologies

The subject is developed through lectures and interactive hours, which will be carried out basically in the assigned practical laboratories. In the lectures, the lecturer will present the theoretical content of the subject, supported by multimedia materials.

For the lab sessions, students will be provided with a script reflecting their objectives, materials and methods for carrying them out. Each lab session will take place on-site on the corresponding site (USC or UDC).

For the study of the subject, students will have at their disposal the basic bibliography of the subject as well as the support material used by the teacher.

The assessment of the subject will be carried out by means of a final written test, which will account for 50% of the final mark.

The completion of the lab sessions is compulsory in order to pass the course and will account for 50% of the final mark. This evaluation will be based on the work carried out in the laboratory. Students enrolled part-time: the dates for the delivery of the practicals will be flexible.

In order to pass, a minimum mark of 4 out of 10 is required for both the written exam and the practical exam.

Students who do not take the final written test will be marked as NOT PRESENT in the final report.

In the event of failing the subject, the evaluation obtained on the lab sessions may be maintained for the second opportunity if the obtained mark is higher than 50% of the maximum mark to be awarded. If it is not higher than 50%, the student, in this second opportunity, will take a written test, which will account for 70% of the mark, and a practical exam, which will provide the other 30%.

This evaluation process applies to both newly enrolled and repeating students.

In cases of fraudulent performance of exercises or tests, the provisions of the Regulations on the assessment of students' academic performance and the review of grades shall apply.

According to what is stated in the degree report, this subject includes a total of 10 hours of lectures and 10 hours of practical laboratory classes and/or problem-based learning.

Due to the high correlation between the concepts developed in the lectures and the content of the practicals, students are recommended to be consistent in their study of the subject, coming to the practical sessions with the concepts already worked on. By doing the lab work, these will become clear and established, thus facilitating the study and understanding of the subject.

Teaching will be in English.