Machine Learning for Wireless Communications

Објавено: June 28, 2022
1. Course Title Machine Learning for Wireless Communications
2. Code 4ФЕИТ10З016
3. Study program ТКИИ
4. Organizer of the study program (unit, institute, department) Faculty of Electrical Engineering and Information Technologies
5. Degree (first, second, third cycle) First cycle
6. Academic year/semester IV/7 7. Number of ECTS credits 6
8. Lecturer D-r Venceslav Kafedjski
9. Course Prerequisites Mathematics 4
10. Course Goals (acquired competencies): The student will acquire fundamental knowledge of the methods and techniques of supervised, unsupervised and reinforcement machine learning and their applications in current and future wireless communication systems from physical lаyer to application layer. The student will be able to detect and solve telecommunication problems that relate to the transmission techniques, wireless channels, radio access and network optimization, multimedia caching and 6G applications with the use of machine learning.
11. Course Syllabus: Supervised learning. Regression. Classification: naive Bayes, K-NN, decision trees, support vector machines, ensemble methods. Supervised learning: neural networks, deep learning. Unsupervised learning: clustering, density estimation, dimensionality reduction. Reinforcement learning. Application of machine learning for modulation, detection and coding of signals, for channel modeling, estimation and prediction, for spectrum sensing, localization and positioning, for resource allocation and network optimization. Analysis of network data, end devices and user mobility for machine learning needs. Machine learning for multimedia communications and content caching. Distributed machine learning/federated learning and application in wireless communications. Machine learning for new applications towards 6G (including intelligent reflective surfaces, drones, Internet of Things, vehicle networks).
12. Learning methods: Lectures, Recitations, Laboratory Excersises, Self Learning, Project, Homework, Company Visits and Lectures by Experts from Industry.
13. Total number of course hours 3 + 1 + 1 + 0
14. Distribution of course hours 180
15. Forms of teaching 15.1. Lectures-theoretical teaching 45
15.2. Exercises (laboratory, practice classes), seminars, teamwork 30
16. Other course activities 16.1. Projects, seminar papers 50
16.2. Individual tasks 0
16.3. Homework and self-learning 55
17. Grading 17.1. Exams 10
17.2. Seminar work/project (presentation: written and oral) 30
17.3. Activity and participation 0
17.4. Final exam 60
18. Grading criteria (points) up to 50 points 5 (five) (F)
from 51to 60 points 6 (six) (E)
from 61to 70 points 7 (seven) (D)
from 71to 80 points 8 (eight) (C)
from 81to 90 points 9 (nine) (B)
from 91to 100 points 10 (ten) (A)
19. Conditions for acquiring teacher’s signature and for taking final exam Attending Lectures, Recitations and Laboratory Excersises.
20. Forms of assessment During the semester, two partial written exams are conducted (at the middle and at the end of the semester, duration 120 minutes), tests that are conducted during the classes and a test covering the laboratory exercises. For students who have passed the partial exams and the laboratory exercise test, a final oral exam (of duration 60 minutes) may be administered. The final grade includes points from the partial exams, tests and the final oral exam.
In the planned exam sessions, a written exam is taken (duration 120 minutes). For students who have passed the written exam and the laboratory exercise test, a final oral exam (duration 60 minutes) may be administered. The final grade includes points from the written exam, tests and the final oral exam. The student should prepare a project assignment and submit it by the exam date at the latest.
It is not allowed to use books, lecture notes, written material and notes of any kind during the exam, as well as a mobile phone, tablet or any other electronic device, except a calculator.
21. Language Macedonian and English
22. Method of monitoring of teaching quality Internal Evaluation and Survey Questionnaire.
23. Literature
23.1. Required Literature
No. Author Title Publisher Year
1 Fa-Long Luo (editor) Machine Learning for FutureWireless Communications John Wiley & Sons 2020
2 Andriy Burkov The Hundred-Page Machine Learning Book Andriy Burkov 2019
23.2. Additional Literature
No. Author Title Publisher Year
1 Ruisi He, Zhiguo Ding (editors) Applications of Machine Learning in Wireless Communications The Institution of Engineering and Technology 2019
2 Christopher M. Bishop Pattern Recognition and Machine Learning Springer 2006