Guide in PDF format

Artificial Intelligence Applied to Next-Generation Mobile Communications

Code: 45625
Credits: 6

2026/2027

Degree programme	Type	Course
Telecommunication Engineering	OB	1

Contact lecturer

Name :: Ivan Pisa Dacosta
Email :: ivan.pisa@uab.cat

Teaching staff

: Vanessa Moreno Font
: Marc Codina Barberà

Group languages

You can consult this information at the end of the document.

Prerequisites

Students are expected to have prior knowledge of signals and systems, digital communication techniques, mobile communication systems, and basic programming of digital devices.

Objectives

The main objective of this course is to provide students with a comprehensive understanding of how Artificial Intelligence (AI) can be applied to next-generation mobile communication systems. The specific objectives are:

To understand data preprocessing techniques and evaluation metrics that are essential for the development and deployment of AI models.
To distinguish between and apply supervised and unsupervised learning methods in the context of telecommunications.
To understand and use deep learning algorithms to solve complex problems related to mobile communications.
To explore the various applications of AI in resource management, radio interfaces, digital twins, and advanced sensing techniques for mobile networks.
To develop and deploy AI-based solutions on digital platforms and embedded devices for real-time mobile communication applications.

Learning outcomes

(CA01) Implement solutions based on artificial intelligence in current and emerging mobile communications systems, such as digital twins and advanced sensing techniques, guaranteeing the quality and efficiency of the service and the minimum environmental impact.
(CA02) Assess the inequalities that can occur in different domains due to the use of intelligent systems and computational learning.
(KA01) Relate the fundamental concepts of artificial intelligence and machine learning to their application to mobile communications, including data preprocessing techniques and evaluation metrics.
(KA02) List supervised, unsupervised, and deep learning algorithms (CNNs, RNNs, transformers), illustrating their specific applications in signal processing and mobile network optimisation.
(SA01) Apply supervised and unsupervised learning techniques to solve practical problems in mobile communications.
(SA02) Deploy deep learning models to improve the performance and efficiency of mobile networks.

1- Introduction to AI in Mobile Communications

Fundamental concepts of Artificial Intelligence and Machine Learning.
Data preprocessing and evaluation metrics.

2- Supervised and unsupervised learning

Classification and regression.
Clustering and anomaly detection.

3- Deep learning algorithms

Convolutional Neural Networks (CNNs)
Recursive Neural Networks (RNNs)
Specific applications of deep learning in signal processing and network optimization.

4- AI applications in mobile communications

Design and implementation of AI solutions for mobile communications.
Deployment of AI algorithms on digital platforms and embedded devices.

Learning activities and methodology

Title	Hours	ECTS	Learning outcomes
Type: Autonomous
Development of a project related to the subject and individual work	80	3.2	CA01, CA02, KA01, KA02, SA01, SA02
Type: Guided
Laboratory Sessions	15	0.6	CA01, CA02, KA01, SA01, SA02
Lectures	30	1.2	CA01, CA02, KA01, KA02, SA01
Type: Supervised
Tutorial Sessions	15	0.6	CA01, CA02, KA01, KA02, SA01, SA02

Directed Activities

Lectures

Presentation of theoretical concepts combined with practical examples and case studies related to Artificial Intelligence applications in next-generation mobile communication systems.

Laboratory Sessions

Hands-on activities involving data analysis, development of machine learning and deep learning models, and implementation of AI-based solutions using software tools and digital platforms relevant to mobile communications.

Autonomous Activities

Individual study of the course material.
Preparation of laboratory assignments.
Development of a semester-long project involving the design, implementation, and evaluation of AI solutions for mobile communication systems.
Preparation of technical reports and project deliverables.

Supervised Activities

Tutorial Sessions

Individual or small-group meetings aimed at clarifying doubts, providing guidance on laboratory activities, and supervising the development of the course project.

Annotation: within the schedule set by the centre or degree programme, 15 minutes of one class will be reserved for students to evaluate their lecturers and their courses or modules through questionnaires.

Assessment

Continuous assessment activities

Title	Weight	Hours	ECTS	Learning outcomes
Course Project	40%	3	0.12	CA01, CA02, KA01, KA02, SA01, SA02
Individual Validation Examination	30%	2	0.08	CA01, CA02, KA01, KA02, SA01, SA02
Laboratory Reports	30%	5	0.2	CA01, CA02, KA01, KA02, SA01, SA02

This course does not provide a single assessment system.

1- Assessment Activities:

Laboratory Reports (LR) – 30%: Assessment based on laboratory participation and the reports delivered.

Course Project (CP) – 40%: Design, implementation, and evaluation of an AI-based solution addressing a problem related to next-generation mobile communication systems. The assessment will consider the technical quality of the solution, project documentation, and final presentation.

Individual Validation Examination (IVE) – 30%: Individual examination consisting of short questions and practical exercises related to the project and course contents. Its objective is to verify each student's understanding of the developed solution and their personal contribution to the project.

2- Evaluation activities schedule:

IVE: Individual Validation Examination dates will be public in the Campus Virtual and the web page of the Engineering School.

LR: Laboratory Activities schedule of lab sessions and deliverables will be made public in Campus Virtual.

CP: CP presentation date will be arranged during the semester. Predictably, at the end of the semester.

Notice that the schedule can be modified due to unexpected events. Please, check Campus Virtual often since any modification will be published there.

3- Final Grade

The final grade will be calculated as:

Final Grade = 0.30 × LR + 0.40 × CP + 0.30 × IVE

To pass the course, students must obtain:

A minimum grade of 5.0/10 in LR, CP, and IVE.
A final grade equal to or greater than 5.0/10.

If a student hasn't participated in any of the activities, their grade will be 'Not Present'. For students who haven't reached a Final Grade >= 5.0 in the previous activities, there will be a Final Assessment (FA) and a Course Project Recovery (CPR) to allow the students to pass the subject provided that they have completed 2/3 of the course's continuous assessment activities. In this case, the Final Grade will be obtained using the following expression:

Final Grade = 0.30 x LR + 0.40 x CPR + 0.30 x FA

Notice that LR is not recoverable.

4- Request for rescheduling

There is a protocol for the “request for rescheduling assessment activities” according to the cases specified in the assessment criteria and guidelines of the School of Engineering.

5- Student Misconduct, Copying, and Plagiarism

Without prejudice to any other disciplinary measures that may be deemed appropriate, any irregularities committed by a student that may lead to an alteration of the assessment results will be graded with a mark of zero. Therefore, copying, plagiarism, cheating, allowing others to copy, or any similar misconduct in any assessment activity will result in a grade of zero for that activity.

Note: The use of AI tools in writing and completing assessment activities is strictly prohibited. If such use is detected, that activity will be graded a 0.

6- Assessment of Repeat Students

There is no differentiated assessment procedure for repeat students. Therefore, no grades from previous academic years will be retained.

Bibliography

Ian Goodfellow, Yoshua Bengio, & Aaron Courville (2016). Deep Learning. MIT Press.

Rappaport, T. S. (2014). Millimeter wave wireless communications. Prentice Hall.

Software

Matlab

Python

Course groups and languages

The information provided is provisional until November 30. After this date, you will be able to consult the language of each group through this link. To access the information, you will need to enter the course CODE

Type of teaching	Group	Language	Semester	Shift
(TEmRD) Teoria (màster RD)	1	English	second semester	afternoon
(PLABsmRD) Suport a les pràctiques de laboratori (màster RD)	1	English	second semester	afternoon