Background: Between 10% and 80% of surgical patients experience some form of fear and anxiety before surgery. This is often attributed to inadequate or incorrect preoperative information. Objectives: This study aimed to critically evaluate and compile research that describes the impact of preoperative information on the patient's well-being before surgery. Methods: A systematic search was conducted on PubMed, Medline, CHINAL, Embase, and the Cochrane Library database for qualitative and quantitative literature regarding factors influencing patients' well-being before surgery. An inductive thematic analysis generated categories and subcategories. Nineteen studies were included. Results: Two main categories emerged from the thematic analysis of the included articles. These were the direct impact of information on fear and anxiety and the indirect impact of information on fear and anxiety. Information from healthcare professionals, alternative sources of information, shortage of healthcare professionals, music, and inability to receive information were some of the factors that can influence the well-being of patients before surgery. There are different reasons for the patient's fear and anxiety preoperatively, as well as the importance of direct and indirect information and other methods. For some patients, however, too much information could cause more fear and anxiety. Conclusion: The importance of the patient's discomfort being highlighted by the healthcare professionals emerges clearly and shows negative experiences in those cases where the patient feels his fears and concerns are not being addressed. More qualitative and quantitative research in the same theme, education and using person-centred care, and the right amount of information based on the patient's wishes are needed to improve the patient's well-being.

axiomFP.py is an open-source software developed to diagnose ploidy level and call quality for samples genotyped on Affymetrix Axiom SNP arrays by making frequency plots of normalized SNP call positions among SNPs meeting specific clustering parameters. This research outlines the methods employed in the development of the software, and presents the results obtained through its application on a dataset of mixed ploidy apple (Malus spp.) cultivars and germplasm accessions. The tools required to prepare the input files and operate the software are also described. The frequency plots generated by the software require a visual inspection to assess ploidy and call quality. The results have been validated using the available ploidy data, as well as flow cytometry, and have shown complete accuracy. The software is available on GitHub at https://github.com/allmiraria/axiomFP.

Tumor evolution is driven by various mutational processes, ranging from single-nucleotide vari- ants (SNVs) to large structural variants (SVs) to dynamic shifts in DNA methylation. Current short-read sequencing methods struggle to accurately capture the full spectrum of these genomic and epigenomic alter- ations due to inherent technical limitations. To overcome that, here we introduce an approach for long-read sequencing of single-cell derived subclones, and use it to profile 23 subclones of a mouse melanoma cell line, characterized with distinct growth phenotypes and treatment responses. We develop a computational frame- work for harmonization and joint analysis of different variant types in the evolutionary context. Uniquely, our framework enables detection of recurrent amplifications of putative driver genes, generated by indepen- dent SVs across different lineages, suggesting parallel evolution. In addition, our approach revealed gradual and lineage-specific methylation changes associated with aggressive clonal phenotypes. We also show our set of phylogeny-constrained variant calls along with openly released sequencing data can be a valuable resource for the development of new computational methods.

This paper presents a PMU-data-based methodology for estimating regional inertia constants in power systems during the initial transient period following a disturbance. The power system is partitioned into dynamically coherent regions based on frequency signals from all monitored buses. Empirical Mode Decomposition (EMD) is applied to each nodal frequency signal to extract Intrinsic Mode Functions (IMFs), and the dominant IMF is identified through an energy ratio criterion. Pairwise correlation analysis of these dominant IMFs is then used to group buses with similar dynamic behavior, forming coherent regions. Within each region, the active power imbalance is computed from Phasor Measurement Units (PMU)-measured tie-line power deviations, while the rate of change of frequency (RoCoF) is estimated from residual trends of EMD-processed frequency signals. These residuals are shown to accurately follow the center of inertia (CoI) frequency trajectory, allowing precise CoI RoCoF estimation. To improve robustness against noise and oscillatory distortions, an adaptive Least Mean Squares (LMS) filter is applied. The regional inertia constants are subsequently estimated using an adapted swing equation during the initial transient period. The method is validated on the IEEE 39-bus test system, yielding estimation errors below 3% relative to reference values, demonstrating its effectiveness for inertia monitoring in low-inertia systems.

The integration of deep learning into symbolic music generation presents new opportunities for emulating artist-specific musical styles. In this paper, we propose a multi-branch Long Short-Term Memory (LSTM) network designed to generate monophonic melodies conditioned on note pitch, duration, and playback, with a focus on stylistic imitation of The Beatles. Unlike existing approaches that model music solely as sequences of pitches, our model processes three distinct streams of musical attributes and learns joint temporal dependencies through a custom architecture. We introduce a structured data representation derived from 193 MIDI files of Beatles songs using the music21 toolkit, extracting pitch and duration features and quantizing them into a format suitable for sequential prediction. Experimental results demonstrate that the model captures artist-specific musical patterns with moderate accuracy across output branches, and a listening test involving 71 participants validates the perceptual plausibility of the generated compositions. Our findings suggest that feature-aware sequence modeling is effective for stylistically informed symbolic music generation, and we discuss limitations and future extensions toward polyphonic modeling and conditional generation.

Alzheimer’s disease (AD) is a progressive neurodegenerative disorder and the most common cause of dementia worldwide. Early and accurate forecasting of cognitive decline in AD patients is essential for personalized treatment planning and effective clinical trial design. However, modeling disease progression is complicated by the irregular timing of clinical visits and heterogeneous data sources. This study presents a Time-aware Long Short-Term Memory (T-LSTM) model that captures temporal dependencies in patient data by integrating time gaps between visits directly into the learning process. Data from multiple large-scale cohorts—including ADNI, NACC, and CPAD—are harmonized and preprocessed to construct a unified longitudinal dataset for training and evaluation. Our approach forecasts Mini-Mental State Examination (MMSE) scores for an unlimited time horizon, demonstrating strong predictive performance and highlighting the effectiveness of temporally sensitive neural network architectures for long-term cognitive trajectory modeling in AD.

Motion tracking achieved via conventional video processing and machine vision algorithms is often hindered by challenges such as motion blur and the lack of distinctive visual features, particularly when tracking fast-moving objects. To address these limitations, active visual markers are often used. In this paper, we present the design and prototype implementation of an active marker that is compact, detachable, and self-powered, making it well-suited for real-world tracking applications. Furthermore, the marker is fully configurable through an accompanying software solution and an additional wireless communication controller via an infrared protocol. The applicability of the developed markers is demonstrated using both conventional RGB and event-based cameras, highlighting their versatility and robustness across diverse sensing modalities. Their tracking capabilities are validated in both single- and multi-object scenarios. Overall, the developed multi-functional markers provide a flexible and practical foundation for high-speed motion tracking under challenging visual conditions, paving the way for further research and advanced applications in related fields.

Air pollution, particularly the concentration of particulate matter ($\mathbf{P M}_{\mathbf{1 0}}$), poses significant risks to human health and the environment. In this study, we employed the FB Prophet forecasting model to predict PM10 levels in Sarajevo and applied SHAP to enhance model interpretability. Using historical meteorological data and PM10 concentration records, we evaluated the model’s performance across three prediction horizons: 30, 60, and 90 days ahead. SHAP analysis identified the key meteorological drivers influencing $\mathbf{P M}_{10}$ concentrations. Accurate long-horizon predictions can support timely planning and decision-making, while also enhancing our understanding of air pollution dynamics in Sarajevo and providing valuable guidance for environmental management and public health strategies.

Manipulating deformable objects such as textiles remains a significant challenge in robotics due to their complex dynamics, unpredictable configurations, and high-dimensional state space. In this paper, we present an integrated planning and execution framework for robotic cloth manipulation that combines symbolic task planning, physics-based simulation, and vision-guided real-world control. High-level plans are generated using Planning Domain Definition Language (PDDL) and translated into low-level primitive actions executed on a Franka Emika Panda robot. To enable perceptual grounding, we employ a vision-based pipeline using an adapted CeDiRNet model for cloth corner detection and grasp point estimation. The system is first validated in IsaacSim using a particle-based deformable cloth model and then transferred to a real-world setup with consistent performance. Our results demonstrate successful Sim2Real transfer of high-level plans, enabling reliable execution of folding tasks in both simulated and physical environments.

With the emergence of advanced techniques in the field of artificial intelligence, risk management in the financial sector has undergone significant transformation. This paper proposes a deep learning–based approach for risk modeling using Bidirectional Long Short-Term Memory (BiLSTM) networks, adapted for tabular data by excluding explicit temporal dependencies. The model is tailored to support accurate decision-making in financial risk assessment. One notable component of this study is the use of automated hyperparameter optimization (HPO) methods, which further enhance the model’s overall effectiveness. These tuning strategies yield models that are less complex, faster to train, and capable of adapting to dynamic data environments, making them suitable for integration into automated credit approval systems. The model was evaluated against baseline approaches, demonstrating improved predictive performance across key evaluation metrics, with statistical significance confirmed by McNemar’s test.

While traditional sampling-based path planning approaches for robotic manipulators, such as RRT (Rapidly-Exploring Random Trees) and PRM (Probabilistic Roadmaps), provide feasible solution paths, convex optimization-based techniques offer some additional features. Some of these methods unfortunately require a representation of the manipulator’s configuration space as a set of convex volumes, which can be challenging to obtain due to the high dimensionality and complexity of the configuration space. This work presents an algorithm for computing convex volumes in the manipulator’s configuration space, called GBur-IRIS. The algorithm combines the structure known as the generalized bur of free C-space with the convex volume-inflating algorithm IRIS (Iterative Regional Inflation by Semidefinite Programming). It follows a simple iterative procedure. First, it computes a generalized bur. Then, it encloses the bur in an ellipsoid. Finally, it uses this ellipsoid to initialize the IRIS algorithm. The paper provides a detailed description of the algorithm and shows an extensive simulation study. This study is conducted on several robotic manipulators and environments, and the results are discussed and compared with existing approaches from the literature.

High-throughput plant phenotyping using RGB imaging offers a scalable and non-invasive solution for monitoring plant growth and extracting various traits. However, achieving accurate segmentation across experiments remains a challenging task due to image variability usually caused by shifts in pot positions. This study introduces a customized image stabilization method to align pots consistently across time-series images of Arabidopsis thaliana, enhancing spatial consistency. A large-scale RGB dataset was collected and prepared, with 4,000 manually annotated images used to train multiple encoder–decoder deep learning models. Various CNN-based encoders were paired with well-known decoders, including U-Net, $\mathbf{U}^{2}$-Net, PANet, and DeepLabv3. Stabilization significantly improved performance of models, with the $EffNetB1 +\mathbf{U}^{2}$-Net encoder-decoder combination achieving the highest precision score of 0.95 and Intersection over Union of 0.96. These results demonstrate the value of spatial consistency and offer a robust, scalable pipeline for automated plant segmentation in indoor phenotyping systems.

This paper presents the design and evaluation of a Virtual Reality (VR) application developed to educate young adults on flood safety. The simulation, playable on the Oculus Quest 2, was created using Unity and features assets modeled in Blender. It adopts a scenario-based learning approach, set within a school setting, where users navigate a seven-stage flood emergency by locating survival equipment and making contextually relevant decisions. The effectiveness of the application was assessed using pre- and post-intervention Likert scale questionnaires. The results indicate improved knowledge retention, enhanced decision-making skills, and increased user engagement. Qualitative feedback highlighted the simulation’s realism and emotional resonance. This preliminary study highlights the potential of VR-enabled experiential learning in disaster preparedness, providing ethical considerations and recommendations for broader implementation.