We propose a novel approach to solving input- and state-constrained parametric mixed-integer optimal control problems using Differentiable Predictive Control (DPC). Our approach follows the differentiable programming paradigm by learning an explicit neural policy that maps control parameters to integer- and continuous-valued decision variables. This policy is optimized via stochastic gradient descent by differentiating the quadratic model predictive control objective through the closed-loop finite-horizon response of the system dynamics. To handle integrality constraints, we incorporate three differentiable rounding strategies. The approach is evaluated on a conceptual thermal energy system, comparing its performance with the optimal solution for different lengths of the prediction horizon. The simulation results indicate that our self-supervised learning approach can achieve near-optimal control performance while significantly reducing inference time by avoiding online optimization, thus implying its potential for embedded deployment even on edge devices.

This paper proposes a deep-learning-based method for recovering a signed distance function (SDF) of a given hypersurface represented by an implicit level set function. Using the flexibility of constructing a neural network, we use an augmented network by defining an auxiliary output to represent the gradient of the SDF. There are three advantages of the augmented network; (i) the target interface is accurately captured, (ii) the gradient has a unit norm, and (iii) two outputs are approximated by a single network. Moreover, unlike a conventional loss term which uses a residual of the eikonal equation, a novel training objective consisting of three loss terms is designed. The first loss function enforces a pointwise matching between two outputs of the augmented network. The second loss function leveraged by a geometric characteristic of the SDF imposes the shortest path obtained by the gradient. The third loss function regularizes a singularity of the SDF caused by discontinuities of the gradient. Numerical results across a wide range of complex and irregular interfaces in two and three-dimensional domains confirm the effectiveness and accuracy of the proposed method. We also compare the results of the proposed method with physics-informed neural networks approaches and the fast marching method.

Data-driven cyberthreat detection has become a crucial defense technique in modern cybersecurity. Network defense, supported by Network Intrusion Detection Systems (NIDSs), has also increasingly adopted data-driven approaches, leading to greater reliance on data. Despite the importance of data, its scarcity has long been recognized as a major obstacle in NIDS research. In response, the community has published many new datasets recently. However, many of them remain largely unknown and unanalyzed, leaving researchers uncertain about their suitability for specific use cases. In this paper, we aim to address this knowledge gap by performing a systematic literature review (SLR) of 89 public datasets for NIDS research. Each dataset is comparatively analyzed across 13 key properties, and its potential applications are outlined. Beyond the review, we also discuss domain-specific challenges and common data limitations to facilitate a critical view on data quality. To aid in data selection, we conduct a dataset popularity analysis in contemporary state-of-the-art NIDS research. Furthermore, the paper presents best practices for dataset selection, generation, and usage. By providing a comprehensive overview of the domain and its data, this work aims to guide future research toward improving data quality and the robustness of NIDS solutions.

The tunable approximated explicit model predictive control (MPC) comes with the benefits of real-time tunability without the necessity of solving the optimization problem online. This paper provides a novel self-tunable control policy that does not require any interventions of the control engineer during operation in order to retune the controller subject to the changed working conditions. Based on the current operating conditions, the autonomous tuning parameter scales the control input using linear interpolation between the boundary optimal control actions. The adjustment of the tuning parameter depends on the current reference value, which makes this strategy suitable for reference tracking problems. Furthermore, a novel technique for scaling the tuning parameter is proposed. This extension provides to exploit different ranges of the tuning parameter assigned to specified operating conditions. The self-tunable explicit MPC was implemented on a laboratory heat exchanger with nonlinear and asymmetric behavior. The asymmetric behavior of the plant was compensated by tuning the controller's aggressiveness, as the negative or positive sign of reference change was considered in the tuning procedure. The designed self-tunable controller improved control performance by decreasing sum-of-squared control error, maximal overshoots/ undershoots, and settling time compared to the conventional control strategy based on a single (non-tunable) controller.

This study evaluates the application of large language models (LLMs) for intent classification within a chatbot with predetermined responses designed for banking industry websites. Specifically, the research examines the effectiveness of fine-tuning SlovakBERT compared to employing multilingual generative models, such as Llama 8b instruct and Gemma 7b instruct, in both their pre-trained and fine-tuned versions. The findings indicate that SlovakBERT outperforms the other models in terms of in-scope accuracy and out-of-scope false positive rate, establishing it as the benchmark for this application.

Nova Scorpii 2023 was first detected as a luminous supersoft X-ray source (SSS) 93 days after outburst and continued emitting soft X-rays for over two months, until it was too close to the Sun to observe. The nova was monitored with the Swift X-ray Telescope (XRT) and the Neutron Star Interior Composition Explorer (NICER) on the International Space Station, and in long exposures with the Chandra High Resolution Camera (HRC) and Low Energy Transmission Grating (LETG) on days 128, 129, and 183-185 after optical maximum. Swift detected a rapidly decaying SSS when observations resumed, constraining the constant bolometric luminosity phase to 9 months. The SSS flux was irregularly variable. A nearly three-fold increase in flux was observed between August and October 2023 in the 15 to 35 Angstrom range, from 3.5 x 10^(-11) to 9.4 x 10^(-11) erg cm^(-2) s^(-1). The SSS duration and effective temperature derived from the October LETG spectra indicate a massive white dwarf with temperature fitting nova evolutionary tracks for a 1.2 solar mass WD; emission lines superimposed on the WD continuum are attributed to surrounding shocked ejecta. We present a timing study based on Chandra and archival NICER data. The irregular variability timescale was days, but a 77.9 second periodic modulation in the SSS flux with varying amplitude was measured in many observations. Our analysis shows that this period was stable; short drifts derived with NICER, but not in long, uninterrupted Chandra exposures, are artifacts of measuring variable amplitude modulation. We suggest the modulations are associated with the WD rotation.

Streamlined weirs which are a nature-inspired type of weir have gained tremendous attention among hydraulic engineers, mainly owing to their established performance with high discharge coefficients. Computational fluid dynamics (CFD) is considered as a robust tool to predict the discharge coefficient. To bypass the computational cost of CFD-based assessment, the present study proposes data-driven modeling techniques, as an alternative to CFD simulation, to predict the discharge coefficient based on an experimental dataset. To this end, after splitting the dataset using a k fold cross validation technique, the performance assessment of classical and hybrid machine learning deep learning (ML DL) algorithms is undertaken. Among ML techniques linear regression (LR) random forest (RF) support vector machine (SVM) k-nearest neighbor (KNN) and decision tree (DT) algorithms are studied. In the context of DL, long short-term memory (LSTM) convolutional neural network (CNN) and gated recurrent unit (GRU) and their hybrid forms such as LSTM GRU, CNN LSTM and CNN GRU techniques, are compared using different error metrics. It is found that the proposed three layer hierarchical DL algorithm consisting of a convolutional layer coupled with two subsequent GRU levels, which is also hybridized with the LR method, leads to lower error metrics. This paper paves the way for data-driven modeling of streamlined weirs.

Pristine polycrystalline boron-doped diamond electrodes (BDDEs) -- microcrystalline (B-MCDE) and ultrananocrystalline (B-UNCDE) were applied for the electrochemical reduction of several selected purine nucleotides -- Guanosine 5'-monophosphate (GMP), 2'-Deoxyguanosine 5'-monophosphate (dGMP), Adenosine 5'-monophosphate (AMP), Adenosine 5'-diphosphate (ADP), Adenosine 5'-triphosphate (ATP), and pyrimidine nucleotides -- Cytidine 5'-monophosphate (CMP), Thymidine 5'-monophosphate (TMP), as well as low-molecular-weight double-stranded DNA (dsDNA) at very negative potentials via linear sweep voltammetry (LSV). Three different types of electrode surfaces were employed -- "H-terminated" B-MCDE (H-B-MCDE) and "O-terminated" B-MCDE/B-UNCDE (O-B-MCDE/O-B-UNCDE). It was found that electrochemical reduction of all tested analytes (except GMP) is possible at H-B-MCDE. On the other hand, electrochemical reduction of all selected analytes (except dsDNA) is possible at O-B-MCDE/O-B-UNCDE. Ambient oxygen and preadsorption step in the manner of incubation of the corresponding sensor in the analyte solution for 30 s had a profound effect on the repeatability of the results and, in the case of H-B-MCDE, also on the magnitude of voltammetric signals and the possibility of electrochemical reduction of dGMP. The use of the proposed sensors and their main advantages and disadvantages for the voltammetric determination of the tested analytes (demonstrated via electrochemical reduction of AMP) in the presence of hydrogen evolution reaction (HER) is also discussed.

Growing amount of comments make online discussions difficult to moderate by human moderators only. Antisocial behavior is a common occurrence that often discourages other users from participating in discussion. We propose a neural network based method that partially automates the moderation process. It consists of two steps. First, we detect inappropriate comments for moderators to see. Second, we highlight inappropriate parts within these comments to make the moderation faster. We evaluated our method on data from a major Slovak news discussion platform.

The aim of this paper is the reconstruction of a smooth surface from an unorganized point cloud sampled by a closed surface, with the preservation of geometric shapes, without any further information other than the point cloud. Implicit neural representations (INRs) have recently emerged as a promising approach to surface reconstruction. However, the reconstruction quality of existing methods relies on ground truth implicit function values or surface normal vectors. In this paper, we show that proper supervision of partial differential equations and fundamental properties of differential vector fields are sufficient to robustly reconstruct high-quality surfaces. We cast the $p$-Poisson equation to learn a signed distance function (SDF) and the reconstructed surface is implicitly represented by the zero-level set of the SDF. For efficient training, we develop a variable splitting structure by introducing a gradient of the SDF as an auxiliary variable and impose the $p$-Poisson equation directly on the auxiliary variable as a hard constraint. Based on the curl-free property of the gradient field, we impose a curl-free constraint on the auxiliary variable, which leads to a more faithful reconstruction. Experiments on standard benchmark datasets show that the proposed INR provides a superior and robust reconstruction. The code is available at \url{this https URL}.

The automated segmentation and tracking of macrophages during their migration are challenging tasks due to their dynamically changing shapes and motions. This paper proposes a new algorithm to achieve automatic cell tracking in time-lapse microscopy macrophage data. First, we design a segmentation method employing space-time filtering, local Otsu's thresholding, and the SUBSURF (subjective surface segmentation) method. Next, the partial trajectories for cells overlapping in the temporal direction are extracted in the segmented images. Finally, the extracted trajectories are linked by considering their direction of movement. The segmented images and the obtained trajectories from the proposed method are compared with those of the semi-automatic segmentation and manual tracking. The proposed tracking achieved 97.4% of accuracy for macrophage data under challenging situations, feeble fluorescent intensity, irregular shapes, and motion of macrophages. We expect that the automatically extracted trajectories of macrophages can provide pieces of evidence of how macrophages migrate depending on their polarization modes in the situation, such as during wound healing.

Linear control theory provides a rich source of inspiration and motivation for development in the matrix theory. Accordingly, in this paper, a generalization of Matrix Determinant Lemma to the finite sum of outer products of column vectors is derived and an alternative proof of one of the fundamental results in modern control theory of the linear time--invariant systems $\dot x=Ax+Bu,$$y=Cx$ is given, namely that the state controllability is unaffected by state feedback, and even more specifically, that for the controllability matrices $\mathcal{C}$ of the single input open and closed loops the equality $\det\left(\mathcal{C}_{(A,B,C)}\right)$ $=\det\left(\mathcal{C}_{(A-BK,B,C)}\right)$ holds.

In this paper, we propose the neural shortest path (NSP), a vector-valued implicit neural representation (INR) that approximates a distance function and its gradient. The key feature of NSP is to learn the exact shortest path (ESP), which directs an arbitrary point to its nearest point on the target surface. The NSP is decomposed into its magnitude and direction, and a variable splitting method is used that each decomposed component approximates a distance function and its gradient, respectively. Unlike to existing methods of learning the distance function itself, the NSP ensures the simultaneous recovery of the distance function and its gradient. We mathematically prove that the decomposed representation of NSP guarantees the convergence of the magnitude of NSP in the $H^1$ norm. Furthermore, we devise a novel loss function that enforces the property of ESP, demonstrating that its global minimum is the ESP. We evaluate the performance of the NSP through comprehensive experiments on diverse datasets, validating its capacity to reconstruct high-quality surfaces with the robustness to noise and data sparsity. The numerical results show substantial improvements over state-of-the-art methods, highlighting the importance of learning the ESP, the product of distance function and its gradient, for representing a wide variety of complex surfaces.

We present X-ray observations of novae V2491 Cyg and KT Eri about 9 years post-outburst, of the dwarf nova and post-nova candidate EY Cyg, and of a VY Scl variable. The first three objects were observed with XMM-Newton, KT Eri also with the Chandra ACIS-S camera, V794 Aql with the Chandra ACIS-S camera and High Energy Transmission Gratings. The two recent novae, similar in outburst amplitude and light curve, appear very different at quiescence. Assuming half of the gravitational energy is irradiated in X-rays, V2491 Cyg is accreting at $\dot{m}=1.4\times10^{-9}-10^{-8}M_\odot/yr$, while for KT Eri, \dot{m}<2\times10^{-10}M_\odot/yr. V2491 Cyg shows signatures of a magnetized WD, specifically of an intermediate polar. A periodicity of ~39 minutes, detected in outburst, was still measured and is likely due to WD rotation. EY Cyg is accreting at $\dot{m}\sim1.8\times10^{-11}M_\odot/yr$, one magnitude lower than KT Eri, consistently with its U Gem outburst behavior and its quiescent UV flux. The X-rays are modulated with the orbital period, despite the system's low inclination, probably due to the X-ray flux of the secondary. A period of ~81 minutes is also detected, suggesting that it may also be an intermediate polar. V794 Aql had low X-ray luminosity during an optically high state, about the same level as in a recent optically low state. Thus, we find no clear correlation between optical and X-ray luminosity: the accretion rate seems unstable and variable. The very hard X-ray spectrum indicates a massive WD.

In this research, dew point temperature (DPT) is simulated using the data-driven approach. Adaptive Neuro-Fuzzy Inference System (ANFIS) is utilized as a data-driven technique to forecast this parameter at Tabriz in East Azerbaijan. Various input patterns, namely T min, T max, and T mean, are utilized for training the architecture whilst DPT is the model's output. The findings indicate that, in general, ANFIS method is capable of identifying data patterns with a high degree of accuracy. However, the approach demonstrates that processing time and computer resources may substantially increase by adding additional functions. Based on the results, the number of iterations and computing resources might change dramatically if new functionalities are included. As a result, tuning parameters have to be optimized inside the method framework. The findings demonstrate a high agreement between results by the data-driven technique (machine learning method) and the observed data. Using this prediction toolkit, DPT can be adequately forecasted solely based on the temperature distribution of Tabriz. This kind of modeling is extremely promising for predicting DPT at various sites. Besides, this study thoroughly compares the Bilayered Neural Network (BNN) and ANFIS models on various scales. Whilst the ANFIS model is extremely stable for almost all numbers of membership functions, the BNN model is highly sensitive to this scale factor to predict DPT.

The recent observation of a compact star with a mass of $M=0.77^{+0.20}_{-0.17}~{\rm M_{\odot}}$ and a radius of $R=10.4^{+0.86}_{-0.78}$ km, located within the supernova remnant HESS J1731-347, has substantially reinforced the evidence for the presence of exotic matter in neutron stars core. This finding has markedly enhanced our comprehension of the equation of state for dense nuclear matter. In the present work, we investigate the possible existence of a kaon condensation in hadronic neutron stars by employing and comparing two theoretical frameworks: the Relativistic Mean Field model with first order kaon condensate and the Momentum-Dependent Interaction model complemented by chiral effective theory. To the best of our knowledge, this represents a first alternative attempt aimed to explain the bulk properties of the specific object with the inclusion of a kaon condensation in dense nuclear matter. The application of two different models enriches the research, providing insights from the aspect of different theoretical frameworks that accurately predict the existence of HESS J1731-347. In both cases significant insights are extracted for the parameter space of models, emphasizing to those concerning the nucleon-kaon potential, the threshold density for the appearance of a kaon condensation, as well as the parameter $a_{3}m_{s}$ which is related to the strangeness content of the proton. Concluding, the present research indicates that a more systematic investigation of similar objects could offer valuable constraints on the properties of dense nuclear matter.

The conceptually new approach based on the logarithmic norm to design of robust adaptive state-feedback controller for linear time-varying (LTV) systems under system's modeling uncertainty and nonlinear external disturbance is proposed. This controller, consisting of two independent parts - adaptive and robust ones - globally asymptotically stabilizes every LTV system regardless how large the disturbance is.

The recent observation of the compact star XTE J1814-338 with a mass of $M=1.2^{+0.05}_{-0.05}~{\rm M_{\odot}}$ and a radius of $R=7^{+0.4}_{-0.4}$ km, together with the HESS J1731-347, which has a mass of $M=0.77^{+0.20}_{-0.17}~{\rm M_{\odot}}$ and a radius of $R=10.4^{+0.86}_{-0.78}$ km, they provide evidence for the possible presence of exotic matter in the core of neutron stars and significantly enhance our understanding of the equation of state for the dense nuclear matter. In the present srtudy, we investigate the possible existence of neutral anti-kaons and negative charged kaons in neutron stars by employing the Relativistic Mean Field model with first order kaonic (${K^{-}}$ and ${\bar{K^{0}}}$) condensates. To the best of our knowledge, this represents a first alternative attempt aimed to explain the bulk properties of the XTE J1814-338 object and at the same time the HESS J1731-347 object, using a mixture of kaons condensation in dense nuclear matter. In addition, we compare our analysis approach with the recent observation of PSR J0437-4715 and PSR J1231-1411 pulsars, proposing that to explain all objects simultaneously, it is essential to consider two distinct branches, each corresponding to a different composition of nuclear matter.

Adaptive binarization methodologies threshold the intensity of the pixels with respect to adjacent pixels exploiting the integral images. In turn, the integral images are generally computed optimally using the summed-area-table algorithm (SAT). This document presents a new adaptive binarization technique based on fuzzy integral images through an efficient design of a modified SAT for fuzzy integrals. We define this new methodology as FLAT (Fuzzy Local Adaptive Thresholding). The experimental results show that the proposed methodology have produced an image quality thresholding often better than traditional algorithms and saliency neural networks. We propose a new generalization of the Sugeno and CF 1,2 integrals to improve existing results with an efficient integral image computation. Therefore, these new generalized fuzzy integrals can be used as a tool for grayscale processing in real-time and deep-learning applications. Index Terms: Image Thresholding, Image Processing, Fuzzy Integrals, Aggregation Functions

This paper introduces an approach for building a Named Entity Recognition (NER) model built upon a Bidirectional Encoder Representations from Transformers (BERT) architecture, specifically utilizing the SlovakBERT model. This NER model extracts address parts from data acquired from speech-to-text transcriptions. Due to scarcity of real data, a synthetic dataset using GPT API was generated. The importance of mimicking spoken language variability in this artificial data is emphasized. The performance of our NER model, trained solely on synthetic data, is evaluated using small real test dataset.