Nina Omejc

Mrs. Nina Omejc

orcid

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
29 May 2024 in Machine Learning
Verified
Journal Article
Open access
PDF file
NONina Omejc
Nina Omejc
BGBoštjan Gec
Boštjan Gec
JBJure Brence
Jure Brence
LTLjupco Todorovski
Ljupco Todorovski
SDSašo Džeroski
Sašo Džeroski
Ordinary differential equations (ODEs) are a widely used formalism for the mathematical modeling of dynamical systems, a task omnipresent in scientific domains. The paper introduces a novel method for inferring ODEs from data, which extends ProGED, a method for equation discovery that allows users to formalize domain-specific knowledge as probabilistic context-free grammars and use it for constraining the space of candidate equations. The extended method can discover ODEs from partial observations of dynamical systems, where only a subset of state variables can be observed. To evaluate the performance of the newly proposed method, we perform a systematic empirical comparison with alternative state-of-the-art methods for equation discovery and system identification from complete and partial observations. The comparison uses Dynobench, a set of ten dynamical systems that extends the standard Strogatz benchmark. We compare the ability of the considered methods to reconstruct the known ODEs from synthetic data simulated at different temporal resolutions. We also consider data with different levels of noise, i.e., signal-to-noise ratios. The improved ProGED compares favourably to state-of-the-art methods for inferring ODEs from data regarding reconstruction abilities and robustness to data coarseness, noise, and completeness.

9 January 2025 in IEEE Transactions on Neural Systems and Rehabilitation Engineering
Verified
Journal Article
Open access
NONina Omejc
Nina Omejc
Tomislav StankovskiTomislav Stankovski
Tomislav Stankovski
MPManca Peskar
Manca Peskar
MKMiloš Kalc
Miloš Kalc
PMPaolo Manganotti
Paolo Manganotti
UMUros Marusic
Uros Marusic
Introduction: Parkinson's disease (PD) is characterized by enhanced beta-band activity (13–30 Hz) in the motor control regions. Simultaneously, cortico-muscular (CM) connectivity in the beta-band during iso-metric contractions tends to decline with age, in various diseases, and under dual-task conditions. Objective: This study aimed to characterize electroencephalograph (EEG) and electromyograph (EMG) power spectra during a motor task, assess CM phase connectivity, and explore how these measures are modulated by an additional cognitive task. Specifically, we focused on the beta-band to explore the relationship between heightened beta amplitude and reduced beta CM connectivity. Methodology: Early-stage people with PD and age-matched controls performed an isometric knee extension task, a cognitive task, and a combined dual task, while EEG (128ch) and EMG (2x32ch) were recorded. CM phase connectivity was assessed through phase coherence and a phase dynamics model. Results: The EEG power spectrum revealed no cohort differences in the beta-band. EMG also showed no differences up to 80 Hz. However, the combined EEG-EMG analysis uncovered reduced beta phase coherence in people with early PD during the motor task. CM phase coherence exhibited distinct scalp topography and frequency ranges compared to the EEG power spectrum, suggesting different mechanisms for pathological beta increase and CM connectivity. Additionally, phase dynamics modelling indicated stronger directional coupling from the cortex to the active muscle and less prominent phase coupling across people with PD. Despite high inter-individual variability, these metrics may prove useful for personalized assessments, particularly in people with heightened CM connectivity.

6 November 2022
Verified
Book Chapter
Closed access
PDF file
BGBoštjan Gec
Boštjan Gec
NONina Omejc
Nina Omejc
JBJure Brence
Jure Brence
SDSašo Džeroski
Sašo Džeroski
LTLjupco Todorovski
Ljupco Todorovski

31 January 2023 in Life
Verified
Journal Article
Open access
PDF file
NONina Omejc
Nina Omejc
MPManca Peskar
Manca Peskar
AMAleksandar Miladinovic
Aleksandar Miladinovic
VKVOJKO KAVCIC
VOJKO KAVCIC
SDSašo Džeroski
Sašo Džeroski
Uros MarusicUros Marusic
Uros Marusic
The utilization of a non-invasive electroencephalogram (EEG) as an input sensor is a common approach in the field of the brain–computer interfaces (BCI). However, the collected EEG data pose many challenges, one of which may be the age-related variability of event-related potentials (ERPs), which are often used as primary EEG BCI signal features. To assess the potential effects of aging, a sample of 27 young and 43 older healthy individuals participated in a visual oddball study, in which they passively viewed frequent stimuli among randomly occurring rare stimuli while being recorded with a 32-channel EEG set. Two types of EEG datasets were created to train the classifiers, one consisting of amplitude and spectral features in time and another with extracted time-independent statistical ERP features. Among the nine classifiers tested, linear classifiers performed best. Furthermore, we show that classification performance differs between dataset types. When temporal features were used, maximum individuals’ performance scores were higher, had lower variance, and were less affected overall by within-class differences such as age. Finally, we found that the effect of aging on classification performance depends on the classifier and its internal feature ranking. Accordingly, performance will differ if the model favors features with large within-class differences. With this in mind, care must be taken in feature extraction and selection to find the correct features and consequently avoid potential age-related performance degradation in practice.

13 March 2023 in Research Square
Verified
Preprint
Open access
PDF file
NONina Omejc
Nina Omejc
BGBoštjan Gec
Boštjan Gec
JBJure Brence
Jure Brence
LTLjupco Todorovski
Ljupco Todorovski
SDSašo Džeroski
Sašo Džeroski
Ordinary differential equations (ODEs) are a widely used formalism for the mathematical modeling of dynamical systems, a task omnipresent in scientific domains. The paper introduces a novel method for inferring ODEs from data. It extends ProGED, a method for equation discovery that employs probabilistic context-free grammars for constraining the space of candidate equations. The extended method can discover ODEs from partial observations of dynamical systems, where only a subset of state variables can be observed. To evaluate the performance of the newly proposed method, we perform a systematic empirical comparison with alternative state-of-the-art methods for equation discovery and system identification from complete and partial observations. The comparison involves a set of ten dynamical systems, an extension of the standard Strogatz benchmark. We compare the ability of methods to reconstruct the known ODEs from synthetic data simulated at different temporal resolutions and involving different signal-to-noise levels. The improved ProGED compares favorably to state-of-the-art methods for inferring ODEs from data regarding reconstruction abilities and robustness to data coarseness, noise, and completeness.

Verified
Open access
PDF file
NONina Omejc
Nina Omejc
SRSabin Roman
Sabin Roman
LTLjupčo Todorovski
Ljupčo Todorovski
SDSašo Džeroski
Sašo Džeroski
Neural population models are widely used to interpret electroencephalography (EEG), yet the relationship between the two remains far less systematically understood as compared with single-neuron models. More fundamentally, it remains unclear whether EEG can support a uniquely plausible population-level mechanism, or whether multiple structurally distinct models can explain the data equally well. To address this question, we combine comparative analysis of canonical model families with grammar-based generation of new candidate architectures. We assemble 17 canonical neural mass and phenomenological models and embed them in a shared structural space. From their common processes, we define a probabilistic grammar over interpretable dynamical components and develop ENEEGMA (Exploring Neural EEG Model Architectures), a Julia-based framework for grammar-based model generation, simulation, and parameter optimization. With this grammar, we generate additional candidate models. We then assess both canonical and generated models by fitting them to EEG independent-component spectra from four datasets for two conditions, i.e., resting state and steady-state visual evoked potentials (SSVEP). Canonical models form six structural clusters. Across conditions, compact low-dimensional polynomial oscillators perform best overall, with generalized Montbrió–Pazó–Roxin, FitzHugh–Nagumo, and Stuart–Landau models offering the best balance of fit quality, stability, and simplicity. Grammar-based exploration further showed that the space of viable EEG node models extends beyond canonical formulations: Even a restricted search over 1,000 generated models produces compact alternatives competitive with nearly all canonical families, with the generated cluster achieving the strongest Bayesian expected rank for SSVEP fits. These findings suggest that EEG spectra constrain classes of plausible population-level dynamical architectures without uniquely determining them and that grammar-based model exploration provides a principled, data-driven framework for EEG-constrained model discovery.