548-0083/04 – GeoComputation (GC)
Gurantor department | Department of Geoinformatics | Credits | 5 |
Subject guarantor | prof. Ing. Jiří Horák, Dr. | Subject version guarantor | prof. Ing. Jiří Horák, Dr. |
Study level | undergraduate or graduate | Requirement | Compulsory |
Year | 2 | Semester | winter |
| | Study language | Czech |
Year of introduction | 2021/2022 | Year of cancellation | |
Intended for the faculties | HGF | Intended for study types | Follow-up Master |
Subject aims expressed by acquired skills and competences
The objective is to learn student how to use basic methods of artificial intelligence namely machine learning such as decision trees, support vector machines and neural analysis in geoinformatics, explain them pronciples and methods of data mining, theory of chaos and fractals, and selected methods of stochastic spatial simulations.
Teaching methods
Lectures
Tutorials
Summary
The subject introduces basic approaches and methods of artificial intelligence, especially machine learning and focus on their utilization in geoinformatics, where it is necessary to evaluate spatial properties, to adapt spatial sampling, and perform appropriate data transformation. Classification methods such as Bayes classifiers, decision trees, support vector machines. Variants for regression analysis. Neural network, including advanced methods such as deep learning and convolution neural network. The further part demonstrates problems and methods of data mining, detection of patterns, sequences and association rule mining, basic techniques of text mining and clustering methods. Introduction to chaos theory and fractals, utlization in geoinformatics. Stochastic spatial simulations.
Compulsory literature:
AWANGE, J.M., PALÁNCZ, B., LEWIS, R.H., VOLGYESI, L. Mathematical geosciences. Springer Berlin Heidelberg, New York, NY, 2017.
BRAMER, M.A. Principles of data mining. Springer, London, 2020.
KANEVSKI M. F., Poudnoukhov A., Timonin V. Machine learning for spatial environmental data. CRC Press 2009. 377 s., 978-0-8493-8237-6
ZAKI, M.J., MEIRA, W. Data mining and machine learning: fundamental concepts and algorithms. Cambridge University Press, Cambridge, United Kingdom, 2020; New York, NY.
Recommended literature:
Additional study materials
Way of continuous check of knowledge in the course of semester
Students are asked about knowledge from areas that they should have already known from previous lectures. Students also work on individual tasks. Tasks are frequently based on understanding of previous, simpler tasks.
E-learning
Other requirements
No additional requirements are imposed on the student.
Prerequisities
Subject has no prerequisities.
Co-requisities
Subject has no co-requisities.
Subject syllabus:
1) Artificial intelligence, basic aproaches, methods.
2) Machine learning, basic concepts, supervised learning, unsupervised learning, backpropagation, hybrid methods. Review of machine learning tasks. Model complexity, loss function, dimenzionality.
3) Spatial aspects – spatial constinuity, stacionarity, spatial sampling, bootstrapping. Preparation of analysis– analysis of sample network, Morisita diagram, data transformation.
4) Introduction to classification. Naive Bayes classification. K-means neighbors algorithm.
5) Decision trees. Selection of attributes using entropy, frequency tables, Gini index. Evaluation of classification accuracy.
6) Support vector machines, regression with SVM (SVR).
7) Neural networks, multilayer perceptron, regression neural networks, probable neural networks, Kohonen maps, radial function, deep learing, convolutional neural network.
8) Data mining, data science. Data mining methodology. Pattern mining, sequences. Association rules learning..
9) Text mining. Text preprocessing. Information lift. Weight normalisation.
10) Cluster analysis, hierarchical and nonhierarchical clustering, association rules, density clusters
11) Introduction to chaos and fractals theories. Model dynamics and dynamic basics. Chaos detection in geography.
12) Fractals. Fractal dimension and its estimation using selected algorithms. Application in geoinformatics
13) Introduction to genetic programming. Sworm intelligence.
Conditions for subject completion
Occurrence in study plans
Occurrence in special blocks
Assessment of instruction