In this paper authors present a general methodology for age dependent reliability analysis of degrading or ageing systems, structures and this http URL methodology is based on Bayesian methods and inference, its ability to incorporate prior information and on idea that ageing can be thought as age dependent change of believes about reliability parameters, when change of belief occurs not just due to new failure data or other information which becomes available in time, but also it continuously changes due to flow of time and beliefs evolution. The main objective of this paper is to present the clear way of how Bayesian methods can be applied by practitioners to deal with risk and reliability analysis considering ageing phenomena. The methodology describes step by step failure rate analysis of ageing systems: from the Bayesian model building to its verification and generalization with Bayesian model averaging which, as authors suggest in this paper, could serve as alternative for various goodness of fit assessment tools and as universal tool to cope with various sources of uncertainty.

Sentiment analysis is a widely researched area within Natural Language Processing (NLP), attracting significant interest due to the advent of automated solutions. Despite this, the task remains challenging because of the inherent complexity of languages and the subjective nature of sentiments. It is even more challenging for less-studied and less-resourced languages such as Lithuanian. Our review of existing Lithuanian NLP research reveals that traditional machine learning methods and classification algorithms have limited effectiveness for the task. In this work, we address sentiment analysis of Lithuanian five-star-based online reviews from multiple domains that we collect and clean. We apply transformer models to this task for the first time, exploring the capabilities of pre-trained multilingual Large Language Models (LLMs), specifically focusing on fine-tuning BERT and T5 models. Given the inherent difficulty of the task, the fine-tuned models perform quite well, especially when the sentiments themselves are less ambiguous: 80.74% and 89.61% testing recognition accuracy of the most popular one- and five-star reviews respectively. They significantly outperform current commercial state-of-the-art general-purpose LLM GPT-4. We openly share our fine-tuned LLMs online.

Photoplethysmography (PPG) is a widely used non-invasive physiological sensing technique, suitable for various clinical applications. Such clinical applications are increasingly supported by machine learning methods, raising the question of the most appropriate input representation and model choice. Comprehensive comparisons, in particular across different input representations, are scarce. We address this gap in the research landscape by a comprehensive benchmarking study covering three kinds of input representations, interpretable features, image representations and raw waveforms, across prototypical regression and classification use cases: blood pressure and atrial fibrillation prediction. In both cases, the best results are achieved by deep neural networks operating on raw time series as input representations. Within this model class, best results are achieved by modern convolutional neural networks (CNNs). but depending on the task setup, shallow CNNs are often also very competitive. We envision that these results will be insightful for researchers to guide their choice on machine learning tasks for PPG data, even beyond the use cases presented in this work.

Self-assembled monolayers (SAMs) have revolutionized the fabrication of lead-based perovskite solar cells, but they remain underexplored in tin perovskite systems. PEDOT is the material of choice for hole-selective layers in tin perovskite solar cells (TPSCs), but presents challenges for both performance and stability. MeO-2PACz, the only SAM reported for Sn perovskites, enables device fabrication but consistently underperforms when compared to PEDOT. In this work, we identify that MeO-2PACz's limitations arise from excessively strong interactions with perovskite surface and poor lattice matching, leading to poor interface quality. To overcome these issues, we design, synthesize, and characterize a novel SAM-forming molecule called Th-2EPT. Th-2EPT optimizes coordination strength and improves lattice compatibility, contributing to the creation of a high-quality buried interface and dramatically suppressing non-radiative recombination. We used Density Functional Theory (DFT) to evaluate coordination strength and lattice compatibility, complemented by nanosecond-resolution optical characterization techniques to confirm significantly reduced interfacial recombination and enhanced carrier lifetimes in Th-2EPT-Perovskite films. With Th-2EPT, we demonstrated the first SAM-based tin perovskite solar cells to outperform PEDOT-based devices, delivering a record power conversion efficiency (PCE) of 8.2% with a DMSO-free solvent system.

Generalized fractional maps of the orders 0 < alpha < 1 are Volterra difference equations of convolution type with kernels, which differences are absolutely summable, but the series of kernels are diverging. Commonly used in applications fractional (with the power-law kernels) and fractional difference (with the falling factorial kernels) maps of the orders 0 < alpha < 1 belong to this class of maps. We derived the algebraic equations which allow the calculation of bifurcation points of generalized fractional maps. We calculated the bifurcation points and drew bifurcation diagrams for the fractional and fractional difference logistic maps. Although the transition to chaos on individual trajectories in fractional maps may be characterized by the cascade of bifurcations type behavior and zero Lyapunov exponents, the results of our numerical simulations allow us to make a conjecture that the cascade of bifurcations scenarios of transition to chaos in generalized fractional maps and regular maps are similar, and the value of the generalized fractional Feigenbaum constant df is the same as the value of the regular Feigenbaum constant delta = 4.669....

Recent advancements in Large Language Models (LLMs) and their utilization in code generation tasks have significantly reshaped the field of software development. Despite the remarkable efficacy of code completion solutions in mainstream programming languages, their performance lags when applied to less ubiquitous formats such as OpenAPI definitions. This study evaluates the OpenAPI completion performance of GitHub Copilot, a prevalent commercial code completion tool, and proposes a set of task-specific optimizations leveraging Meta's open-source model Code Llama. A semantics-aware OpenAPI completion benchmark proposed in this research is used to perform a series of experiments through which the impact of various prompt-engineering and fine-tuning techniques on the Code Llama model's performance is analyzed. The fine-tuned Code Llama model reaches a peak correctness improvement of 55.2% over GitHub Copilot despite utilizing 25 times fewer parameters than the commercial solution's underlying Codex model. Additionally, this research proposes an enhancement to a widely used code infilling training technique, addressing the issue of underperformance when the model is prompted with context sizes smaller than those used during training. The dataset, the benchmark, and the model fine-tuning code are made publicly available.

Buildings energy efficiency is a widely researched topic, which is rapidly gaining popularity due to rising environmental concerns and the need for energy independence. In Northern Europe heating energy alone accounts for up to 70 percent of the total building energy consumption. Industry 4.0 technologies such as IoT, big data, cloud computing and machine learning, along with the creation of predictive and proactive digital twins, can help to reduce this number. However, buildings thermal dynamics is a very complex process that depends on many variables. As a result, commonly used physics-based white box models are time-consuming and require vast expertise. On the contrary, black box forecasting models, which rely primarily on building energy consumption data, lack fundamental insights and hinder re-use. In this study we propose an architecture to facilitate grey box modelling of building thermal dynamics while integrating real time IoT data with 3D representation of buildings. The architecture is validated in a case study creating a digital twin platform that enables users to define the thermal dynamics of buildings based on physical laws and real data, thus facilitating informed decision making for the best heating energy optimization strategy. Also, the created user interface enables stakeholders such as facility managers, energy providers or governing bodies to analyse, compare and evaluate buildings thermal dynamics without extensive expertise or time resources.

In this paper, we demonstrate a way to generalize learning with errors (LWE) to the family of so-called modular-maximal cyclic groups which are non-commuting. Since the group M2t has two cycles of maximal multiplicative order, we use this fact to construct an accurate criterion for restoring the message bit with overwhelming probability. Furthermore, we implement the original idea by O. Regev in the considered group to gain benefits from the non-commutativity of M2t . Also we prove that using this approach we can achieve a level of security comparable to the original idea.

Due to the fast pace of life and online communications and the prevalence of English and the QWERTY keyboard, people tend to forgo using diacritics, make typographical errors (typos) when typing in other languages. Restoring diacritics and correcting spelling is important for proper language use and the disambiguation of texts for both humans and downstream algorithms. However, both of these problems are typically addressed separately: the state-of-the-art diacritics restoration methods do not tolerate other typos, but classical spellcheckers also cannot deal adequately with all the diacritics missing. In this work, we tackle both problems at once by employing the newly-developed universal ByT5 byte-level seq2seq transformer model that requires no language-specific model structures. For a comparison, we perform diacritics restoration on benchmark datasets of 12 languages, with the addition of Lithuanian. The experimental investigation proves that our approach is able to achieve results (> 98%) comparable to the previous state-of-the-art, despite being trained less and on fewer data. Our approach is also able to restore diacritics in words not seen during training with > 76% accuracy. Our simultaneous diacritics restoration and typos correction approach reaches > 94% alpha-word accuracy on the 13 languages. It has no direct competitors and strongly outperforms classical spell-checking or dictionary-based approaches. We also demonstrate all the accuracies to further improve with more training. Taken together, this shows the great real-world application potential of our suggested methods to more data, languages, and error classes.

Pre-trained transformer models shine in many natural language processing tasks and therefore are expected to bear the representation of the input sentence or text meaning. These sentence-level embeddings are also important in retrieval-augmented generation. But do commonly used plain averaging or prompt templates sufficiently capture and represent the underlying meaning? After providing a comprehensive review of existing sentence embedding extraction and refinement methods, we thoroughly test different combinations and our original extensions of the most promising ones on pretrained models. Namely, given 110 M parameters, BERT's hidden representations from multiple layers, and many tokens, we try diverse ways to extract optimal sentence embeddings. We test various token aggregation and representation post-processing techniques. We also test multiple ways of using a general Wikitext dataset to complement BERT's sentence embeddings. All methods are tested on eight Semantic Textual Similarity (STS), six short text clustering, and twelve classification tasks. We also evaluate our representation-shaping techniques on other static models, including random token representations. Proposed representation extraction methods improve the performance on STS and clustering tasks for all models considered. Very high improvements for static token-based models, especially random embeddings for STS tasks, almost reach the performance of BERT-derived representations. Our work shows that the representation-shaping techniques significantly improve sentence embeddings extracted from BERT-based and simple baseline models.

Data are often sampled irregularly in time. Dealing with this using Recurrent Neural Networks (RNNs) traditionally involved ignoring the fact, feeding the time differences as additional inputs, or resampling the data. All these methods have their shortcomings. We propose an elegant straightforward alternative approach where instead the RNN is in effect resampled in time to match the time of the data or the task at hand. We use Echo State Network (ESN) and Gated Recurrent Unit (GRU) as the basis for our solution. Such RNNs can be seen as discretizations of continuous-time dynamical systems, which gives a solid theoretical ground to our approach. Our Task-Synchronized ESN (TSESN) and GRU (TSGRU) models allow for a direct model time setting and require no additional training, parameter tuning, or computation (solving differential equations or interpolating data) compared to their regular counterparts, thus retaining their original efficiency. We confirm empirically that our models can effectively compensate for the time-non-uniformity of the data and demonstrate that they compare favorably to data resampling, classical RNN methods, and alternative RNN models proposed to deal with time irregularities on several real-world nonuniform-time datasets. We open-source the code at this https URL .

This paper introduces the Adaptive Gradient Least Squares Progressive iterative Approximation (AdagradLSPIA), an accelerated version of the Least Squares Progressive Iterative Approximation (LSPIA) method, enhanced with adaptive optimization techniques inspired by the adaptive gradient (Adagrad) algorithm. By using historical (accumulated) gradient information to dynamically adjust weights, AdagradLSPIA achieves faster convergence compared to the standard LSPIA method. The effectiveness of AdagradLSPIA is demonstrated through its application to tensor product B-spline surface fitting, where this method consistently outperforms LSPIA in terms of accuracy, computational efficiency, and robustness to variations in global weight selection.

Neural network models have recently demonstrated impressive prediction performance in complex systems where chaos and unpredictability appear. In spite of the research efforts carried out on predicting future trajectories or improving their accuracy compared to numerical methods, not sufficient work has been done by using deep learning techniques in which they characterize the unpredictability of chaotic systems or give a general view of the global unpredictability of a system. In this work we propose a novel approach based on deep learning techniques to measure the fractal dimension of the basins of attraction of the Duffing oscillator for a variety of parameters. As a consequence, we provide an algorithm capable of predicting fractal dimension measures as accurately as the conventional algorithm, but with a computation speed about ten times faster.

Purpose: Comprehensive legal medicine documentation includes both an internal but also an external examination of the corpse. Typically, this documentation is conducted manually during conventional autopsy. A systematic digital documentation would be desirable, especially for the external examination of wounds, which is becoming more relevant for legal medicine analysis. For this purpose, RGB surface scanning has been introduced. While a manual full surface scan using a handheld camera is timeconsuming and operator dependent, floor or ceiling mounted robotic systems require substantial space and a dedicated room. Hence, we consider whether a mobile robotic system can be used for external documentation. Methods: We develop a mobile robotic system that enables full-body RGB-D surface scanning. Our work includes a detailed configuration space analysis to identify the environmental parameters that need to be considered to successfully perform a surface scan. We validate our findings through an experimental study in the lab and demonstrate the system's application in a legal medicine environment. Results: Our configuration space analysis shows that a good trade-off between coverage and time is reached with three robot base positions, leading to a coverage of 94.96 %. Experiments validate the effectiveness of the system in accurately capturing body surface geometry with an average surface coverage of 96.90 +- 3.16 % and 92.45 +- 1.43 % for a body phantom and actual corpses, respectively. Conclusion: This work demonstrates the potential of a mobile robotic system to automate RGB-D surface scanning in legal medicine, complementing the use of post-mortem CT scans for inner documentation. Our results indicate that the proposed system can contribute to more efficient and autonomous legal medicine documentation, reducing the need for manual intervention.

Obstructive sleep apnea (OSA) is believed to contribute significantly to atrial fibrillation (AF) development in certain patients. Recent studies indicate a rising risk of AF with increasing OSA severity. However, the commonly used apnea-hypopnea index in clinical practice may not adequately account for the potential cardiovascular risks associated with OSA. (1) Objective: to propose and explore a novel method for assessing OSA severity considering potential connection to cardiac arrhythmias. (2) Method: the approach utilizes cross-recurrence features to characterize OSA and AF by considering the relationships among oxygen desaturation, pulse arrival time, and heart-beat intervals. Multinomial logistic regression models were trained to predict four levels of OSA severity and four groups related to heart rhythm issues. The rank biserial correlation coefficient, rrb, was used to estimate effect size for statistical analysis. The investigation was conducted using the MESA database, which includes polysomnography data from 2055 subjects. (3) Results: a derived cross-recurrence-based index showed a significant association with a higher OSA severity (p < 0.01) and the presence of AF (p < 0.01). Additionally, the proposed index had a significantly larger effect, rrb, than the conventional apnea-hypopnea index in differentiating increasingly severe heart rhythm issue groups: 0.14 > 0.06, 0.33 > 0.10, and 0.41 > 0.07. (4) Significance: the proposed method holds relevance as a supplementary diagnostic tool for assessing the authentic state of sleep apnea in clinical practice.

Wet-chemistry synthesized Gold nanourchins (Au NUs), characterized by spiky morphologies with spherical cores, exhibit complex and geometry-dependent plasmonic properties distinct from those of symmetrical nanostructures. While plasmon hybridization and mode coupling in branched nanostructures have been broadly studied, the specific optical behavior of Au NUs-particularly regarding spike length distribution and ultrafast dynamics-remains underexplored. This study investigates the steady-state and transient absorption spectra of Au NUs with 50-80 nm cores and 5-20 nm spikes, revealing multiple resonance bands. Transient absorption spectroscopy at various excitation wavelengths confirmed the presence of distinct resonances. Electromagnetic simulations based on TEM tomography-inspired models identified two key extinction bands: a green-wavelength dark mode resonance and a red-nIR spike-induced resonance attributed to the lightning rod effect. Simulations further showed that short, uniformly distributed spikes (aspect ratio <= 1) weakly excite dark resonances, while longer spikes (aspect ratio > 1) induce hybridized longitudinal resonances and significant redshifts. Broad spike length distributions result in multiple coexisting resonances, aligning with experimental extinction spectra. A preliminary surface-enhanced Raman scattering study using 2-naphthalene thiol confirmed stronger enhancement for long-spiked Au NUs under 785 nm excitation, validating the field enhancement potential of the identified resonances.

This paper explores the needs \& expectations of educational stakeholders for AI (Artificial Intelligence)-enhanced learning environments. Data was collected following two-phased participatory workshops. The first workshop outlined stakeholders' profiles in terms of technical and pedagogical characteristics. The qualitative data collected was analysed using deductive thematic analysis with Activity Theory, explicating the user needs. The second workshop articulated expectations related to the integration of AI in education. Inductive thematic analysis of the second workshop led to the elicitation of users' expectations. We cross-examined the needs and expectations, identifying contradictions, to generate user requirements for emerging technologies. The paper provides suggestions for future design initiatives that incorporate AI in learning environments.

Thermally activated delayed fluorescence (TADF) emitters consisting of donor and acceptor molecules are potentially highly interesting for electroluminescence (EL) applications. Their strong fluorescence emission is considered to be due to reverse intersystem crossing (RISC), in which energetically close triplet and singlet charge transfer (CT) states, also called exciplex states, are involved. In order to distinguish between different mechanisms and excited states involved, temperature-dependent spin-sensitive measurements on organic light-emitting diodes (OLEDs) and thin films are essential. In our work we apply continuous wave (cw) and time-resolved (tr) photoluminescence (PL) spectroscopy as well as spin-sensitive EL and PL detected magnetic resonance to films and OLED devices made of three different donor:acceptor combinations. Our results clearly show that triplet exciplex states are formed and contribute to delayed fluorescence (DF) via RISC in both electrically driven OLEDs and optically excited films. In the same sample set we also found molecular triplet excitons, which occurred only in PL experiments under optical excitation and for some material systems only at low temperatures. We conclude that in all investigated molecular systems exciplex states formed at the donor:acceptor interface are responsible for TADF in OLEDs with distinct activation energies. Molecular (local) triplet exciton states are also detectable, but only under optical excitation, while they are not found in OLEDs when excited states are generated electrically. We believe that the weakly bound emissive exciplex states and the strongly bound non-emissive molecular triplet excited states coexist in the TADF emitters, and it is imperative to distinguish between optical and electrical generation paths as they may involve different intermediate excited states.

Machine learning and deep learning techniques are contributing much to the advancement of science. Their powerful predictive capabilities appear in numerous disciplines, including chaotic dynamics, but they miss understanding. The main thesis here is that prediction and understanding are two very different and important ideas that should guide us about the progress of science. Furthermore, it is emphasized the important role played by that nonlinear dynamical systems for the process of understanding. The path of the future of science will be marked by a constructive dialogue between big data and big theory, without which we cannot understand.

Large Language Models (LLMs) with billions of parameters are known for their impressive predicting capabilities but require lots of resources to run. With their massive rise in popularity, even a small reduction in required resources could have an impact on environment. On the other hand, smaller models require fewer resources but may sacrifice accuracy. In this work, we are proposing an implementation of ``stairs'' assisted greedy generation. It is a modified assisted generation methodology that makes use of a smaller model's fast generation, large model's batch prediction, and "stairs" validation in order to achieve a speed up in prediction generation. Results show between 9.58 and 17.24 percent inference time reduction compared to a stand-alone large LLM prediction in a text generation task without a loss in accuracy.