arXiv subjects

Pavle Boškoski

Publications and source records attributed to Pavle Boškoski.

7 recordsLinked to original sources

arXiv2026

Physics-informed distribution of relaxation times estimation and latent-space condition monitoring of solid oxide fuel and electrolysis cells from electrochemical impedance spectroscopy

Estimating the distribution of relaxation times (DRT) fromelectrochemical impedance spectroscopy (EIS) is an ill-posed inverse problem that is highly sensitive to regularisation choices. We propose a physics-informed convolutional autoencoder that estimates DRT directly from EIS data without spectrum-specific tuning. A discretised relation between impedance and the DRT is embedded in the training process, constraining the network to produce impedance-consistent distributions. The model resolves overlapping relaxation processes in synthetic two-ZARC spectra and accurately reconstructs measurements from three independent solid oxide fuel and electrolysis cell datasets, with range-normalised errors below 1.1%. Decoder-probe analysis shows that the learned latent representation is organised according to relaxation timescale. Distances in this latent space capture operating changes, hydrogen-shortage events, and long-term degradation. The same lightweight architecture is applied across all datasets without modification, providing consistent DRT estimation and an interpretable basis for condition monitoring.

stat.AP↗

arXiv2026

Uncertainty-Aware Extrapolation in Bayesian Oblique Trees

Decision trees are widely used due to their interpretability and efficiency, but they struggle in regression tasks that require reliable extrapolation and well-calibrated uncertainty. Piecewise-constant leaf predictions are bounded by the training targets and often become overconfident under distribution shift. We propose a single-tree Bayesian model that extends VSPYCT by equipping each leaf with a GP predictor. Bayesian oblique splits provide uncertainty-aware partitioning of the input space, while GP leaves model local functional behaviour and enable principled extrapolation beyond the observed target range. We present an efficient inference and prediction scheme that combines posterior sampling of split parameters with \gls{gp} posterior predictions, and a gating mechanism that activates GP-based extrapolation when inputs fall outside the training support of a leaf. Experiments on benchmark regression tasks show improvements in the predictive performance compared to standard variational oblique trees, and substantial performance gains in extrapolation scenarios.

cs.LG↗

arXiv2023

Directional coupling detection through cross-distance vectors

Inferring the coupling direction from measured time series of complex systems is challenging. We propose a new state space based causality measure obtained from cross-distance vectors for quantifying interaction strength. It is a model-free noise-robust approach that requires only a few parameters. The approach is applicable to bivariate time series and is resilient to artefacts and missing values. The result is two coupling indices that quantify coupling strength in each direction more accurately than the already established state space measures. We test the proposed method on different dynamical systems and analyse numerical stability. As a result, a procedure for optimal parameter selection is proposed, circumventing the challenge of determining the optimal embedding parameters. We show it is robust to noise and reliable in shorter time series. Moreover, we show that it can detect cardiorespiratory interaction in measured data. A numerically efficient implementation is available at https://repo.ijs.si/mbresar/cd-vec.

physics.data-an↗

arXiv2022

Occupation similarity through bipartite graphs

Similarity between occupations is a crucial piece of information when making career decisions. However, the notion of a single and unified occupation similarity measure is more of a limitation than an asset. The goal of the study is to assess multiple explainable occupation similarity measures that can provide different insights into inter-occupation relations. Several such measures are derived using the framework of bipartite graphs. Their viability is assessed on more than 450,000 job transitions occurring in Slovenia in the period between 2012 and 2021. The results support the hypothesis that several similarity measures are plausible and that they present different feasible career paths. The complete implementation and part of the datasets are available at https://repo.ijs.si/pboskoski/bipartite_job_similarity_code.

cs.SI↗

arXiv2021

Variational Bayes survival analysis for unemployment modelling

Mathematical modelling of unemployment dynamics attempts to predict the probability of a job seeker finding a job as a function of time. This is typically achieved by using information in unemployment records. These records are right censored, making survival analysis a suitable approach for parameter estimation. The proposed model uses a deep artificial neural network (ANN) as a non-linear hazard function. Through embedding, high-cardinality categorical features are analysed efficiently. The posterior distribution of the ANN parameters are estimated using a variational Bayes method. The model is evaluated on a time-to-employment data set spanning from 2011 to 2020 provided by the Slovenian public employment service. It is used to determine the employment probability over time for each individual on the record. Similar models could be applied to other questions with multi-dimensional, high-cardinality categorical data including censored records. Such data is often encountered in personal records, for example in medical records.

stat.AP↗

arXiv2021

Detection of coupling in Duffing oscillator systems

In complex dynamical systems, the detection of coupling and its direction from observed time series is a challenging task. We study coupling in coupled Duffing oscillator systems in regular and chaotic dynamical regimes. By observing the conditional mutual information (CMI) based on the Shannon entropy, we successfully infer the direction of coupling for different system regimes. Moreover, we show that in the weak coupling limit the values of CMI can be used to infer the coupling parameters by computing the derivative of the conditional mutual information with respect to the coupling strength, called the information susceptibility. The complete numerical implementation is available at https://repo.ijs.si/mbresar/duffing-cmi.

nlin.AO↗

arXiv2021

Evaluating uncertainties in electrochemical impedance spectra of solid oxide fuel cells

Electrochemical impedance spectroscopy (EIS) is a widely used tool for characterization of fuel cells and other electrochemical conversion systems. When applied to the on-line monitoring in the context of in-field applications, the disturbances, drifts and sensor noise may cause severe distortions in the evaluated spectra, especially in the low-frequency part. Failure to ignore the random effects can result in misinterpreted spectra and, consequently, in misleading diagnostic reasoning. This fact has not been often addressed in the research so far. In this paper, we propose an approach to the quantification of the spectral uncertainty, which relies on evaluating the uncertainty of the equivalent circuit model (ECM). We apply the computationally efficient variational Bayes (VB) method and compare the quality of the results with those obtained with the Markov chain Monte Carlo (MCMC) algorithm. Namely, MCMC algorithm returns accurate distributions of the estimated model parameters, while VB approach provides the approximate distributions. By using simulated and real data we show that approximate results provided by VB approach, although slightly over-optimistic, are still close to the more realistic MCMC estimates. A great advantage of the VB method for online monitoring is low computational load, which is several orders of magnitude lower compared to MCMC. The performance of VB algorithm is demonstrated on a case of ECM parameters estimation in a 6 cell solid oxide fuel cell (SOFC) stack. The complete numerical implementation for recreating the results can be found at https://repo.ijs.si/lznidaric/variational-bayes-supplementary-material.

stat.CO↗