Iskanje po repozitoriju

Opis: Study of brain function often involves analyzing task-related switching between intrinsic brain networks, which connect various brain regions. Functional brain connectivity analysis methods aim to estimate these networks but are limited by the statistical constraints of windowing functions, which reduce temporal resolution and hinder explainability of highly dynamic processes. In this work, we propose a novel approach to functional connectivity analysis through the explainability of EEG classification. Unlike conventional methods that condense raw data into extracted features, our approach inflates raw EEG data by decomposition into meaningful components that explain processes in the application domain. To uncover the brain connectivity that affects classification decisions, we introduce a new method of dynamic influence data inflation (DIDI), which extracts signals representing interactions between electrode regions. These inflated data are then classified using an end-to-end neural network classifier architecture designed for raw EEG signals. Saliency map estimation from trained classifiers reveals the connectivity dynamics affecting classification decisions, which can be visualized as dynamic connectivity support maps for improved interpretability. The methodology is demonstrated on two publicly available datasets: one for imagined motor movement classification and the other for emotion classification. The results highlight the dual benefits of our approach: in addition to providing interpretable insights into connectivity dynamics it increases classification accuracy.
Ključne besede: EEG, functional connectivity, data inflation, classification, explainability, saliency maps
Objavljeno v RUP: 04.06.2025; Ogledov: 2516; Prenosov: 20
Celotno besedilo (1,74 MB)
Gradivo ima več datotek! Več...

Ključne besede: pseudoline arrangement, quasiline arrangement, projective plane, incidence structure, combinatorial configuration, topological configuration, geometric configuration, sweep, wiring diagram, allowable sequence of permutations, maps on surfaces
Objavljeno v RUP: 03.01.2022; Ogledov: 2578; Prenosov: 32
Celotno besedilo (3,66 MB)

Ključne besede: generalized bent functions, Zq-bent functions, Gray maps, (relative) difference sets, (generalized) Marioana-McFarland class, stream ciphers, filtering generator, guess and determine cryptanalysis, tap positions, (fast) algebraic attacks, algebraic immunity, derivatives, linear structures, planar mappings
Objavljeno v RUP: 09.11.2017; Ogledov: 4844; Prenosov: 69
Povezava na celotno besedilo

Ključne besede: varieties, Grassmanian varieties, regular maps, irreducibility
Objavljeno v RUP: 15.10.2015; Ogledov: 4990; Prenosov: 13
Povezava na celotno besedilo

Opis: A cycle decomposition of a graph ▫$\Gamma$▫ is a set ▫$\mathcal{C}$▫ of cycles of ▫$\Gamma$▫ such that every edge of ▫$\Gamma$▫ belongs to exactly one cycle in ▫$\mathcal{C}$▫. Such a decomposition is called arc-transitive if the group of automorphisms of ▫$\Gamma$▫ that preserve setwise acts transitively on the arcs of ▫$\Gamma$▫. In this paper, we study arc-transitive cycle decompositions of tetravalent graphs. In particular, we are interested in determining and enumerating arc-transitive cycle decompositions admitted by a given arc-transitive tetravalent graph. Among other results we show that a connected tetravalent arc-transitive graph is either 2-arc-transitive, or is isomorphic to the medial graph of a reflexible map, or admits exactly one cycle structure.
Ključne besede: mathematics, graph theory, cycle decomposition, automorphism group, consistent cycle, medial maps
Objavljeno v RUP: 15.10.2013; Ogledov: 8437; Prenosov: 92
Povezava na celotno besedilo