ECTS credits ECTS credits: 3
ECTS Hours Rules/Memories Hours of tutorials: 4.5 Expository Class: 14 Interactive Classroom: 14 Total: 32.5
Use languages Spanish, Galician
Type: Ordinary subject Master’s Degree RD 1393/2007 - 822/2021
Departments: Electronics and Computing
Areas: Languages and Computer Systems
Center Higher Technical Engineering School
Call: Second Semester
Teaching: With teaching
Enrolment: Enrollable | 1st year (Yes)
This course introduces students to the advanced use of machine learning for the development and optimization of digital twins in dynamic industrial environments, characterized by their changing nature and strong temporal dependencies. To address these challenges, upon completion of the course, students are expected to be able to:
- Discern and apply machine learning paradigms that adapt to the evolution of processes and effectively model their temporal sequences.
- Know and understand the fundamentals of preprocessing, anomaly detection, and process control for industrial plants.
- Employ techniques to perform cleaning and preprocessing of IoT data for machine learning algorithms.
The content of the subject will be developed through the following topics:
• Incremental machine learning.
• Concept drift.
• Machine learning with memory. Recurrent Neural Networks.
• Anomaly detection.
• Introduction to process control.
Basic bibliography
[1]. A. Bosch Rué, J. Casas-Roma, T. Lozano Bagén (2019): Deep learning : principios y fundamentos
[2]. A. Zhang, Z.C. Lipton, A.J. Smola (2023): Dive into Deep Learning
[3]. Gama, J., Žliobaitė, I., Bifet, A., Pechenizkiy, M., & Bouchachia, A. (2014). A survey on concept drift adaptation. ACM computing surveys (CSUR), 46(4), 1-37.
[4]. Hoi, S. C., Sahoo, D., Lu, J., & Zhao, P. (2021). Online learning: A comprehensive survey. Neurocomputing, 459, 249-289.
Complementary bibliography
[1]. Bifet, A., Gavalda, R., Holmes, G., & Pfahringer, B. (2018). Machine learning for data streams: with practical examples in MOA. MIT press
[2]. Gomes, H. M., Read, J., Bifet, A., Barddal, J. P., & Gama, J. Machine learning for streaming data: state of the art, challenges, and opportunities. ACM SIGKDD Explorations Newsletter,21(2), 6-22, 2019.
[3]. Li, J., Cheng, K., Wang, S., Morstatter, F., Trevino, R. P., Tang, J., & Liu, H. Feature selection: A data perspective. ACM computing surveys (CSUR), 2017, 50(6), 1-45.
[4]. Lu, J., Liu, A., Dong, F., Gu, F., Gama, J., & Zhang, G. (2018). Learning under concept drift: A review. IEEE Transactions on Knowledge and Data Engineering, 31(12), 2346-2363.
The degree program outlines the following competencies for this course:
- I-CP3: Analyze and interpret IoT data streams in the Industry.
The contents of the course will be taught indistinctly between lectures and interactive classes. The completion of all the proposed activities is necessary and mandatory to pass the course.
Lecture Classes (theory): they will consist of explaining the different sections of the course syllabus, with the help of electronic media (presentations, videos, etc.).
Interactive classes (laboratory): different practical problems related to the content of the subject will be posed for the student to solve individually or in groups.
Supervised laboratory exercises: pactical problems that students must develop, with the teacher's support, during the interactive sessions and deliver progressively during the bimester.
Practical assignment: a mandatory group development problem where students must demonstrate and apply the knowledge acquired in the course.
Autonomous work: the scope and objectives of the projects, use cases and/or practical problems may require autonomous work on the part of the students, albeit under the supervision of the teaching staff.
Office hours: Office hours will be used to solve students' doubts related to the contents of the subject. These office hours can be both face-to-face and virtual (via email, virtual campus or video conferencing platforms). Synchronous office hours will require a prior appointment.
First Call
To pass the course, the student must complete and pass the proposed practical assignments (30%) and the supervised laboratory exercises (30%) work, which represents 60% of the final grade, as well as pass the final exam, which constitutes the remaining 40%. To do this, it is necessary to obtain a grade equal to or higher than 5 in the overall assessment. Additionally, it is required to achieve at least a 4 in each evaluated part to average.
Supervised laboratory exercises will have progressive submissions throughout the bimester. They will be presented in the different interactive classes, through Notebooks, as a means for developing the practical syllabus. Students will have approximately 14 days from the presentation of each Notebook to its final submission. The Notebooks will contain small individual exercises that will allow them to consolidate the concepts seen during the classes. Their submission is mandatory and forms part of the continuous assessment of the subject.
The practical assignment will consist of a group-based, assessable, and mandatory problem to be developed during the bimester. This work includes a mandatory and assessable presentation during the final interactive session.
In accordance with Article 1 of the USC's regulations on class attendance in official undergraduate and master's degree programs, it is explicitly stated that class attendance will not have any weight in the subject's evaluation. However, it is strongly recommended, as it is fundamental for the acquisition of knowledge.
The final exam questions will focus on the specific content developed in the course in relation to its competencies and may have been acquired by the student in both the lecture and interactive parts.
Mid-term Exams: No mid-term exams will be conducted.
Second call
The qualification obtained in the laboratory part (practical and supervised work) during the course as well as its weight in the final grade are maintained. Students who did not reach the cutoff qualification in the proposed activities during the previous call may submit similar activities to those not passed, which will be proposed by the professors, before the final exam of the second opportunity. Once all the evaluated parts are separately passed, the exam will account for 40% of the final grade, and the laboratory part will constitute the remaining 60% (practical work 30% and supervised work 30%). To pass the course, a global average grade of 5 or higher is necessary. Additionally, it is required to achieve at least a 4 in each evaluated part to average.
The final exam questions will focus on the specific content developed in the course in relation to its competencies and may have been acquired by the student in both the lecture and interactive parts.
Repeating students:
In case of repeating students, they will be examined under the same conditions as students in the first round.
No-show qualification:
The student will receive the qualification of "no-show" when he/she does not take the final exam.
Fraudulent performance of exercises or tests:
For cases of fraudulent completion of exercises or tests, the provisions of the regulations for the evaluation of students' academic performance and review of qualifications will apply.
In particular, if any form of plagiarism is detected in any tests or exams, the final grade will be FAIL (0), and the incident will be reported to the appropriate academic authorities.
According to the master's program outline, the course has a workload of 3.0 ECTS. Given that 25 hours are allocated per ECTS, the total workload for the course is 75 hours (3 ECTS x 25 hours per ECTS).
The workload includes 12 hours of lecture classes and 12 hours of laboratory classes. Therefore, personal study time for students should account for 51 hours.
The student should keep up to date with the content subject in order to be able to apply the knowledge acquired in theory in laboratory exercises.
Primary language: the subject will be taught in Spanish.
David Mera Perez
Coordinador/a- Department
- Electronics and Computing
- Area
- Languages and Computer Systems
- david.mera [at] usc.es
- Category
- Professor: Temporary PhD professor
| Tuesday | |||
|---|---|---|---|
| 15:30-17:00 | Grupo /CLE_01 | Spanish | Aula A10 |
| 17:00-18:30 | Grupo /CLIL_01 | Spanish | Classroom A5 |
| 06.16.2026 12:00-14:00 | Grupo /CLIL_01 | Aula A10 |
| 06.16.2026 12:00-14:00 | Grupo /CLE_01 | Aula A10 |
| 07.07.2026 12:00-14:00 | Grupo /CLIL_01 | Aula A10 |
| 07.07.2026 12:00-14:00 | Grupo /CLE_01 | Aula A10 |