Inter Intelligent
For students and professionals who want to move from classical signal processing to modern AI-driven methods and learn how to design complete, practical solutions for real-world signal analysis.
This course is designed for students, researchers, and early-career professionals who want a strong and modern foundation in signal processing across both mathematical and data-driven paradigms.
You will fit this course if you are:
In electrical engineering, applied mathematics, computer science, Al, data science, or biomedical engineering.
Working with time series, sensor data, biomedical signals, audio, communications, or radar.
Or analysts who want to understand not only how to apply a method, but how to choose the right one.
No prior deep learning specialization is required, but basic familiarity with coding and mathematical.
Integrates classical DSP, statistical modeling, and modern Al into one coherent framework.
Emphasizes decision-making: not just how to run an algorithm, but when to use it, why it works, and what trade-offs it involves.
Is built around real analytical practice, where hybrid solutions often outperform purely modelbased or purely data-based approaches.
Combines mathematical rigor with implementation-oriented thinking. preparing students for both research and applied innovation.
Understand the core language of signal processing, including signals, systems, noise, uncertainty, transforms, and optimization, so you can frame problems correctly from the start.
Learn how to build and apply classical signal models, filters, and estimation methods, including FIR/IIR filtering, spectral methods, state-space models, Kalman filtering, and particle filtering.
Use machine learning and deep learning for temporal data, including feature-based models, CNNs, recurrent architectures, transformers, and representation learning for signals
Discover how to combine domain knowledge and learning through structured models, modelinformed neural networks, unrolled optimization, and learning-augmented estimation pipelines.
Work with realistic datasets, evaluation protocols, computational constraints, and deploymentaware decisions, then bring everything together in a final comparative project.
with clear progression from fundamentals to advanced methods
aligned with their interests, such as biomedical signals, audio, radar, communications, or sensor systems
through labs, project milestones, and consultations
around personal research goals, academic interests, or workplace challenges
Students are supported by a modern digital learning environment that may include:
trained on course materials
is a Professor at the Opole University of Technology (Poland) and Lead Researcher in Institute of Telecommunications and Global Information Space of the National Academy of Sciences of Ukraine. He is Full Professor (2011), Doctor of Technical Sciences (2011), Academician of the Academy of Sciences of the Higher School of Ukraine (2021). Lupenko Serhii is the founder and long-term (2004-2015) Head of the Department of Radio Computer Systems and the Department of Computer Systems and Networks at Ternopil Ivan Pul’uj National Technical University. He was awarded various diplomas, in particular in 2020 he was awarded a Diploma of the Prime Minister of Ukraine.
Lupenko Serhii is a well-known specialist in the field of mathematical modelling and computational methods. He is the author of the modern theory of modelling and processing of cyclic signals in information systems of their analysis, diagnosis and forecasting. This theory from the standpoint of a unified theoretical-methodological approach takes into account a wide range of possible attributes of cyclicity within deterministic, stochastic, fuzzy and interval modelling paradigms, takes into account the significant variety of changes in rhythm of cyclic signals. Under the leadership of Serhii Lupenko operates a scientific school “Modelling and Mathematical Support of Intellectualized Information Systems in Medicine, Technology and Economics.” He was the Research Supervisor of 8 PhD level theses and 1 Doctor of Technical Sciences level theses. He was the Head of 7 funded international and national scientific and educational projects. During his scientific and scientific-pedagogical activity, Serhii Lupenko has published about 400 scientific and scientific-methodical papers, including 10 scientific monographs and 9 textbooks.
Where applicable, the course may include:
Potential use cases include: biomedical signal interpretation, intelligent monitoring,
predictive maintenance, audio enhancement, communications, and radar analytics.
Students are assessed through a combination of:
Certificate: Certificate of Completion / Professional Certificate
Badge: [If applicable]
ECTS: [If applicable]
Suggested weighting:
This course helps students build a portfolio of skills relevant to roles such as:
Students finish the course with a concrete project artifact that can be included in an academic
or professional portfolio, demonstrating the ability to compare and justify different technical
paradigms for real-world signal analysis.
No. A basic technical background is recommended, but the course is structured to build from
foundations toward more advanced methods.
Most students should expect around 6–8 hours per week, including lectures, readings, labs, and
project work.
It is both. The course combines rigorous concepts with implementation-oriented assignments and a
final project.
Yes, students who successfully complete the course requirements receive a certificate, depending on
the credential format selected.
Primarily Python, including standard scientific and machine learning libraries. Additional tools may
be introduced depending on the course format.
Yes. The capstone is designed to be adaptable to personal academic or professional interests.
