1. Recent applications of explainable AI (XAI) : a systematic literature reviewMirka Saarela, Vili Podgorelec, 2024, review article Keywords: explainable artificial intelligence, applications, interpretable machine learning, convolutional neural network, deep learning, post-hoc explanations, model-agnostic explanations Published in DKUM: 31.01.2025; Views: 0; Downloads: 2
Full text (1,42 MB) |
2. Predicting the probability of cargo theft for individual cases in railway transportLorenc Augustyn, Małgorzata Kuźnar, Tone Lerher, Maciej Szkoda, 2020, original scientific article Abstract: In the heavy industry, the value of cargo transported by rail is very high. Due to high value, poor security and volume of rail transport, the theft cases are often. The main problem of securing rail transport is predicting the location of a high probability of risk. Because of this,the aim of the presented research was to predict the highest probability of rail cargo theft for areas. It is important to prevent theft cases by better securing the railway lines. To solve that problem the authors' model was developed. The model uses information about past transport cases for the learning process of Artificial Neural Networks (ANN) and Machine Learning (ML).The ANN predicted the probability for 94.7% of the cases of theft and the Machine Learning identified 100% of the cases. This method can be used to develop a support system for securing the rail infrastructure. Keywords: rail transport security, supply chain disruption, drones, security support systems, cargo theft, predicting, logistics, artificial neural network, drone monitoring, machine learning Published in DKUM: 28.01.2025; Views: 0; Downloads: 2
Full text (1,93 MB) This document has many files! More... |
3. Use of the methodology of network thinking for a fatigue criteria investigation based on the example of mining companiesMarcin Butlewski, Grzegorz Dahlke, Milena Drzewiecka-Dahlke, Krzysztof Hankiewicz, Adam Górny, Brigita Gajšek, 2020, original scientific article Abstract: In the paper the factors of workers fatigue were tested by applying network thinking methodology supported by statistical analysis to determine the nature of individual factors for the fatigue management system development. Analysis of the distribution of factors along the intensity map allowed their classification into individual interaction categories, describing directions for miner fatigue management. Active factors were discovered which are: Elevated temperature, Noise and vibration, Oxygen-poor air and mining gases, High humidity, Poor work organization. Critical factors for fatigue management were: Poor technical condition of equipment and Long and time-consuming approach to headings. Keywords: fatigue factors, fatigue management, mine, miners, network thinking, safety Published in DKUM: 15.01.2025; Views: 0; Downloads: 2
Full text (352,28 KB) This document has many files! More... |
4. Optimizing laser cutting of stainless steel using latin hypercube sampling and neural networksKristijan Šket, David Potočnik, Lucijano Berus, Jernej Hernavs, Mirko Ficko, 2025, original scientific article Abstract: Optimizing cutting parameters in fiber laser cutting of austenitic stainless steel is challenging due to the complex interplay of multiple variables and quality metrics. To solve this problem, Latin hypercube sampling was used to ensure a comprehensive and efficient exploration of the parameter space with a smaller number of trials (185), coupled with feedforward neural networks for predictive modeling. The networks were trained with a leave-oneout cross-validation strategy to mitigate overfitting. Different configurations of hidden layers, neurons, and training functions were used. The approach was focused on minimizing dross and roughness on both the top and bottom areas of the cut surfaces. During the testing phase, an average MSE of 0.063 and an average MAPE of 4.68% were achieved by the models. Additionally, an experimental test was performed on the best parameter settings predicted by the models. Initial modelling was conducted for each quality metric individually, resulting in an average percentage difference of 1.37% between predicted and actual results. Grid search was also per formed to determine an optimal input parameter set for all outputs, with predictions achieving an average ac curacy of 98.34%. Experimental validation confirmed the accuracy and robustness of the model predictions, demonstrating the effectiveness of the methodology in optimizing multiple parameters of complex laser cutting processes. Keywords: laser cutting optimization, cut surface quality, dross formation, Latin hypercube sampling, feedforward neural network Published in DKUM: 10.01.2025; Views: 0; Downloads: 12
Full text (3,38 MB) This document has many files! More... |
5. Ranking the invasions of cheaters in structured populationsGuoli Yang, Matteo Cavaliere, Cheng Zhu, Matjaž Perc, 2020, original scientific article Abstract: The identification of the most influential individuals in structured populations is an important research question, with many applications across the social and natural sciences. Here, we study this problem in evolutionary populations on static networks, where invading cheaters can lead to the collapse of cooperation. We propose six strategies to rank the invading cheaters and identify those which mostly facilitate the collapse of cooperation. We demonstrate that the type of successful rankings depend on the selection strength, the underlying game, and the network structure. We show that random ranking has generally little ability to successfully identify invading cheaters, especially for the stag-hunt game in scale-free networks and when the selection strength is strong. The ranking based on degree can successfully identify the most influential invaders when the selection strength is weak, while more structured rankings perform better at strong selection. Scale-free networks and strong selection are generally detrimental to the performance of the random ranking, but they are beneficial for the performance of structured rankings. Our research reveals how to identify the most influential invaders using statistical measures in structured communities, and it demonstrates how their success depends on population structure, selection strength, and on the underlying game dynamics. Keywords: cooperation, cheating, network, population, evolution Published in DKUM: 07.01.2025; Views: 0; Downloads: 2
Full text (6,72 MB) This document has many files! More... |
6. Interlayer connectivity affects the coherence resonance and population activity patterns in two-layered networks of excitatory and inhibitory neuronsDavid Ristič, Marko Gosak, 2022, original scientific article Abstract: The firing patterns of neuronal populations often exhibit emergent collective oscillations, which can display substantial regularity even though the dynamics of individual elements is very stochastic. One of the many phenomena that is often studied in this context is coherence resonance, where additional noise leads to improved regularity of spiking activity in neurons. In this work, we investigate how the coherence resonance phenomenon manifests itself in populations of excitatory and inhibitory neurons. In our simulations, we use the coupled FitzHugh-Nagumo oscillators in the excitable regime and in the presence of neuronal noise. Formally, our model is based on the concept of a two-layered network, where one layer contains inhibitory neurons, the other excitatory neurons, and the interlayer connections represent heterotypic interactions. The neuronal activity is simulated in realistic coupling schemes in which neurons within each layer are connected with undirected connections, whereas neurons of different types are connected with directed interlayer connections. In this setting, we investigate how different neurophysiological determinants affect the coherence resonance. Specifically, we focus on the proportion of inhibitory neurons, the proportion of excitatory interlayer axons, and the architecture of interlayer connections between inhibitory and excitatory neurons. Our results reveal that the regularity of simulated neural activity can be increased by a stronger damping of the excitatory layer. This can be accomplished with a higher proportion of inhibitory neurons, a higher fraction of inhibitory interlayer axons, a stronger coupling between inhibitory axons, or by a heterogeneous configuration of interlayer connections. Our approach of modeling multilayered neuronal networks in combination with stochastic dynamics offers a novel perspective on how the neural architecture can affect neural information processing and provide possible applications in designing networks of artificial neural circuits to optimize their function via noise-induced phenomena. Keywords: neuronal dynamics, coherence resonance, excitatory neurons, inhibitory neurons, neural network, multilayer network, interlayer connectivity Published in DKUM: 20.12.2024; Views: 0; Downloads: 2
Full text (6,72 MB) This document has many files! More... |
7. Association between productivity and journal impact across disciplines and career ageAndre S. Sunahara, Matjaž Perc, Haroldo V. Ribeiro, 2021, original scientific article Abstract: The association between productivity and impact of scientific production is a long-standing debate in science that remains controversial and poorly understood. Here we present a large-scale analysis of the association between yearly publication numbers and average journal-impact metrics for the Brazilian scientific elite. We find this association to be discipline specific, career age dependent, and similar among researchers with outlier and nonoutlier performance. Outlier researchers either outperform in productivity or journal prestige, but they rarely do so in both categories. Nonoutliers also follow this trend and display negative correlations between productivity and journal prestige but with discipline-dependent intensity. Our research indicates that academics are averse to simultaneous changes in their productivity and journal-prestige levels over consecutive career years. We also find that career patterns concerning productivity and journal prestige are discipline-specific, having in common a raise of productivity with career age for most disciplines and a higher chance of outperforming in journal impact during early career stages. Keywords: network, cooperation, social physics, complex system Published in DKUM: 10.12.2024; Views: 0; Downloads: 6
Full text (1,10 MB) This document has many files! More... |
8. |
9. Cross-sectional personal network analysis of adult smoking in rural areasBianca-Elena Mihǎilǎ, Marian-Gabriel Hâncean, Matjaž Perc, Jürgen Lerner, Iulian Oană, Marius Geanta, José Luis Molina González, Cosmina Cioroboiu, 2024, original scientific article Abstract: Research on smoking behaviour has primarily focused on adolescents, with less attention given to middle-aged and older adults in rural settings. This study examines the influence of personal networks and sociodemographic factors on smoking behaviour in a rural Romanian community. We analysed data from 76 participants, collected through face-to-face interviews, including smoking status (non-smokers, current and former smokers), social ties and demographic details. Multilevel regression models were used to predict smoking status. The results indicate that social networks are essential in shaping smoking habits. Current smokers were more likely to have smoking family members, reinforcing smoking within familial networks, while non-smokers were typically embedded in non-smoking environments. Gender and age patterns show that women were less likely to smoke, and older adults were more likely to have quit smoking. These findings suggest that targeted interventions should focus not only on individuals but also on their social networks. In rural areas, family-based approaches may be particularly effective due to the strong influence of familial ties. Additionally, encouraging connections with non-smokers and former smokers could help disrupt smoking clusters, supporting smoking cessation efforts. Keywords: network science, human behaviour, data science, smoking, social physics Published in DKUM: 03.12.2024; Views: 0; Downloads: 0
Full text (1,07 MB) This document has many files! More... |
10. Global synchronization in generalized multilayer higher-order networksPalash Kumar Pal, Md Sayeed Anwar, Matjaž Perc, Dibakar Ghosh, 2024, original scientific article Abstract: Networks incorporating higher-order interactions are increasingly recognized for their ability to introduce novel dynamics into various processes, including synchronization. Previous studies on synchronization within multilayer networks have often been limited to specific models, such as the Kuramoto model, or have focused solely on higher-order interactions within individual layers. Here, we present a comprehensive framework for investigating synchronization, particularly global synchronization, in multilayer networks with higher-order interactions. Our framework considers interactions beyond pairwise connections, both within and across layers. We demonstrate the existence of a stable global synchronous state, with a condition resembling the master stability function, contingent on the choice of coupling functions. Our theoretical findings are supported by simulations using Hindmarsh-Rose neuronal and Rössler oscillators. These simulations illustrate how synchronization is facilitated by higher-order interactions, both within and across layers, highlighting the advantages over scenarios involving interactions within single layers. Keywords: synchronization, network, phase transition, statistical physics Published in DKUM: 27.11.2024; Views: 0; Downloads: 0
Full text (1,51 MB) This document has many files! More... |