Anomaly Detection in Time Series 4010-ATS
The lecture will be divided into three parts: (i) time series analysis, (ii) anomaly detection, and (iii) anomaly detection in time series. Each part will cover important ideas and practical skills.
In the first part, students will learn what a time series is and why it matters in fields like finance, healthcare, and engineering. They will understand how to break down time series data into trends, seasonal patterns, and residuals. Students will also explore different models for time series forecasting, including additive, multiplicative, and pseudo-additive models, and how to apply these models using Python. The concept of stationarity will be explained, along with methods to make time series data stationary, such as differencing, detrending, and using logarithms. Students will learn how to tell the difference between stationary and nonstationary time series. Data smoothing techniques, from simple moving averages to more complex triple exponential smoothing, will be covered. The importance of autocorrelation and partial autocorrelation functions will be discussed, as well as how to use them in modeling. Models like ARMA, ARIMA, and SARIMA will be explained, and students will learn how to build and use these models. Signal processing techniques, including Fourier transformations and filters, will also be introduced. Additionally, students will be introduced to advanced methods like recurrent neural networks (RNNs) and long short-term memory (LSTM) networks for time series forecasting.
In the second part, the focus will be on anomaly detection. Students will learn about different types of anomalies, such as point, contextual, and collective anomalies, and their applications in areas like fraud detection and network security. The course will cover the basic statistics and mathematics needed for anomaly detection. Students will study probabilistic models, including Bayesian approaches and extreme value analysis, and methods like angle-based techniques for finding anomalies. Algorithms for detecting anomalies, such as support vector machines (SVMs), local outlier factor (LOF), k-nearest neighbors (KNN), and k-means clustering, will be explored. The course will also address the challenges of working with high-dimensional data, including techniques like subspace methods, feature bagging, and isolation forests. Students will learn about cost-sensitive learning, adaptive resampling, and boosting methods to improve anomaly detection. Statistical process control methods and techniques for streaming anomaly detection using autoregressive models will also be covered.
The final part will combine the knowledge from the first two sections. Students will apply time series analysis techniques to anomaly detection problems. Practical skills will be developed through lab sessions where students work on projects involving time series data and anomaly detection. All examples and techniques will be implemented in Python, giving students hands-on experience with real-world data.
Participants in the course will have the knowledge and skills to independently analyze time series data and detect anomalies, especially in time series, using Python tools.
Założenia (opisowo)
Koordynatorzy przedmiotu
Rodzaj przedmiotu
Tryb prowadzenia
Ogólnie: mieszany: w sali i zdalnie | W cyklu 2024Z: mieszany: w sali i zdalnie lektura monograficzna |
Efekty kształcenia
Knowledge:
W1 - Knows the basic computer science terminology used in time series analysis and anomaly detection and understands its sources and applications in related scientific disciplines [K_W02]
W2 - Knows the basic mathematical terminology used in time series analysis and anomaly detection and understands its sources and applications in related scientific disciplines [K_W04]
W3 - Understands what a scientific theory is and its role in explaining phenomena and predicting them [K_W07]
W4 - Understands the role of computer science in time series analysis and anomaly detection [K_W08]
W5 - Understands the role of mathematics in time series analysis and anomaly detection [K_W10]
W6 - Knows and understands the role of scientific theory in time series analysis and anomaly detection [K_W11, K_W12]
W7 - Has basic knowledge of the place of time series analysis and anomaly detection in the system of sciences and of its subject-related and methodological connections with other scientific disciplines [K_W13]
W8 - Has basic knowledge of the subject matter and methodological connections between time series analysis and anomaly detection and the sciences dealing with artificial intelligence and modeling of cognitive processes [K_W14]
W9 - Knows various mathematical methods, particularly statistical ones, that are used to analyze data describing phenomena remaining in time series analysis and anomaly detection [K_W21]
W10 - Knows the tools used in time series analysis and anomaly detection and understands the advantages and disadvantages of individual research methods [K_W24]
W11 - Knows the tools used in time series analysis and anomaly detection and understands the advantages and disadvantages of individual methods [K_W25]
W12 - Knows the mathematical tools used in time series analysis and anomaly detection and understands the advantages and disadvantages of individual methods [K_W27]
W13 - Knows what a programming language is and understands how it is constructed [K_W38]
W14 - Knows basic theorems and operations on matrices and basic theorems in real and complex analysis [K_W43]
W15 - Knows the basic concepts used in mathematical analysis [K_W47]
W16 - Knows the basic components of computer programs in the imperative paradigm, the basics of the software programming paradigm, and programming tools that allow you to create programs that run on multiple operating systems [K_W48]
W17 - Knows and understands the basic concepts, values and principles of research ethics [K_W51]
W18 - Knows how to cite research and scientific work conducted in large teams or other environments. Knows the rules governing the use of so-called intellectual property [K_W52]
Skills:
U1 - Is able to use basic theoretical knowledge of time series analysis and anomaly detection [K_U01]
U2 - Is able to use basic terms in time series analysis and anomaly detection [K_U02]
U3 - Is able to prepare scientific studies using appropriate IT tools, taking into account computational (IT) aspects [K_U03, K_U04]
U4 - is able to prepare a short scientific report on the master's thesis project allowing [K_U05, K_U06]
U5 - Is able to determine directions for further professional self-development [K_U07]
U6 - Is able to process and analyze data using mathematical tools known to him, especially statistical ones [K_U09]
U7 - Is able to use telecommunications tools for effective collaboration and is able to plan and implement numerical simulations for a selected application field of time series analysis and anomaly detection, analyze their results and draw conclusions [K_U10, K_U11]
U8 - Is able to formulate and test hypotheses and assess the usefulness and possibility of using new hardware and software solutions for time series analysis and anomaly detection [K_U12, K_U13]
U9 - Knows the principles of health and safety at work with a computer and is able to perform basic economic analysis of the calculations carried out [K_U14, K_U15]
U10 - Is able to analyze a research problem and determine the algorithms and computational methods appropriate for its solution, taking into account the complexity of the problem and the computational complexity of the algorithm [K_U16, K_U17]
U11 - Is able to critically analyse and evaluate theoretical proposals in the field of time series analysis and anomaly detection, and is also able to analyse and evaluate empirical research in this field and the conclusions drawn from it [K_U20]
U12 - Can perform scientific reasoning typical of machine learning, understanding the relationship between theory and empirical data [K_U28]
U13 - Is able to concisely and clearly present (orally and in writing) selected issues in the field of time series analysis and anomaly detection, summarizing the most important information and providing arguments in favor of a given solution [K_U33]
U14 - Can write simple Python programs that process input data [K_U36]
U15 - Can write and compile a simple program using the imperative programming paradigm. Can perform an object-oriented analysis of programming problems and design a program in the object-oriented paradigm based on this analysis [K_U37]
U16 - Can evaluate the effectiveness of competing machine learning systems [K_U38]
U17 - Is able to use mathematical techniques necessary for time series analysis and anomaly detection [K_U39, K_U40]
U18 - Is able to use programming tools documentation to find solutions to programming problems [K_U45]
U19 - Can write various types of written works in English in which he/she can report on a problem, discuss selected research and analyse the conclusions drawn from it, report on other people's arguments, and present his/her own arguments in support of a given thesis [K_U50]
U20 - Knows at least one foreign language at CEFR B2 level [K_U51]
Competences:
K1 - Knows the limitations of his/her own knowledge and understands the need for further education [K_K01]
K2 - Knows the limitations of his/her own knowledge and understands the need for further education [K_K02]
K3 - Able to work in a team [K_K03]
K4 - Understands the need for systematic work on all projects that are long-term in nature [K_K04]
K5 - Understands and appreciates the importance of intellectual honesty in one's own actions and those of others [K_K05]
K6 - Using the necessary professional terminology, in an accessible form, he conveys his knowledge to a wide audience [K_K06]
K7 - Strives to acquire new knowledge, skills and experiences, understanding the importance of self-development, improvement and raising professional competences in the modern labor market [K_K07]
K8 - Independently plans, systematically and timely implements research goals, making difficult decisions when necessary [K_K08, K_K09]
K9 - Is able to participate in substantive discussions, is able to work out compromises and define a common position [K_K10]
K10 - Is able to behave politely during a discussion without offending other participants [K_K11]
K11 - Knows how to use the knowledge and skills acquired during studies on the labor market [K_K12]
Kryteria oceniania
laboratories - semester work
lecture - exam
Literatura
Materials and courses available online.
|
W cyklu 2024Z:
Materials and courses available online. |
Więcej informacji
Dodatkowe informacje (np. o kalendarzu rejestracji, prowadzących zajęcia, lokalizacji i terminach zajęć) mogą być dostępne w serwisie USOSweb: