University of Applied Sciences Potsdam

Accurate assessment of burn depth remains a clinical challenge and requires specific training. To improve diagnostic accuracy, various technical methods have been developed. This review summarizes current evidence on indocyanine green (ICG) fluorescence imaging for burn depth assessment and compares its performance with clinical, histological, and alternative modalities such as Laser Doppler imaging (LDI). A systematic literature search was conducted in PubMed/MEDLINE, Cochrane and Google Scholar to identify studies evaluating burn depth using ICG fluorescence imaging. Studies from 1995 to 2024 were included if they compared ICG to at least one reference method (clinical assessment, biopsy, or other technical modalities). Data extraction was performed independently by two reviewers. Risk of bias was assessed using the Newcastle-Ottawa Scale. The study selection workflow is shown in the PRISMA 2020 flow diagram for systematic reviews. Nine studies with a total of 151 patients, published between 1995 and 2024, met the inclusion criteria. Results were synthesized descriptively due to substantial methodological heterogeneity. Two studies reported high accuracy of ICG fluorescence imaging for identifying nonviable tissue and supporting surgical planning, although differentiation between superficial and deep partial-thickness burns (SPTBs/DPTBs) was inconsistent. In one study, ICGA-guided assessment reduced or avoided excision in 10 of 20 burn sites (50%). Yet heterogeneity in measurement protocols, cut-off values, and reference standards limited comparability across studies. Due to its limited accuracy in differentiating SPTBs and DPTBs, ICG imaging has restricted utility for burn depth assessment, though it may still offer intraoperative benefit during necrosectomy. PROSPERO International prospective register of SRs by the National Institute of Health Research (CRD420251161190).

Effectively characterizing uncertainty and error in flood prediction is essential for informed decision-making. This study combines advanced deep neural network architectures, i.e., Neural Hierarchical Interpolation for Time Series Forecasting (N-HiTS), and Long Short-Term Memory (LSTM), with multiple uncertainty quantification frameworks to evaluate flood forecasts across several watersheds in the southeastern United States. Bayesian inference, Monte Carlo–based methods, and quantile regression are applied to estimate predictive uncertainty. The comparative analysis examines how different uncertainty approaches perform across a range of flood magnitudes, highlighting their respective advantages and limitations at multiple scales. Results indicate that N-HiTS generally yields narrower and more reliable uncertainty bounds than LSTM. The findings further demonstrate that prior specification in MCMC sampling strongly influences uncertainty estimates and requires careful calibration. While Monte Carlo dropout, which is an approximate Bayesian technique, primarily captures uncertainty near flood peaks, MCMC offers a more complete characterization across the full hydrograph. In addition, this study investigates multi-site training to evaluate model adaptability under diverse hydrological regimes. Collectively, these results advance the integration of deep neural networks and uncertainty quantification to enhance flood modeling capabilities and risk management.

Abstract Knowledge of the range of bird vocalisations is crucial not only for estimating the range of species acoustic communication but also for the detection radius of an observer in monitoring projects and expert assessments. Using calibrated sound recordings and parallel acoustic localisation, we assessed three methods of determining the sound pressure level for four species of rail [Corn Crake ( Crex crex ), Water Rail ( Rallus aquaticus ), Spotted Crake ( Porzana porzana ), Little Crake ( Zapornia parva )], whose calls differ significantly in temporal organisation and spectral composition. We calculated sound propagation over long distances, taking into account spherical propagation losses and atmospheric absorption. Atmospheric absorption was calculated including all frequencies contained in the signal. In the case of the Corn Crake in particular, we demonstrated that all spectral components of the signal must be considered when estimating its range. To ensure comparability between studies, we recommend establishing a reference library containing calibrated sound recordings . The results were discussed in the context of their significance for the acoustic communication of the species.

The use of social robotics in care for older persons is increasingly discussed as one way of meeting emerging care needs due to scarce resources. While many potential benefits are associated with robotic care technologies, there is a variety of ethical challenges. To support steps towards a responsible implementation and use, this review develops an overview on ethical aspects of the use of social robots in care for older people from a decision-makers' perspective. Electronic databases were queried using a comprehensive search strategy based on the key concepts of "ethical aspects", "social robotics" and "elderly care". Abstract and title screening was conducted by two authors independently. Full-text screening was conducted by one author following a joint consolidation phase. Data was extracted using MAXQDA24 by one author, based on a consolidated coding framework. Analysis was performed through modified qualitative content analysis. A total of 1,518 publications were screened, and 248 publications were included. We have organized our analysis in a scheme of ethical hazards, ethical opportunities and unsettled questions, identifying at least 60 broad ethical aspects affecting three different stakeholder groups. While some ethical issues are well-known and broadly discussed our analysis shows a plethora of potentially relevant aspects, often only marginally recognized, that are worthy of consideration from a practical perspective. The findings highlight the need for a contextual and detailed evaluation of implementation scenarios. To make use of the vast knowledge of the ethical discourse, we hypothesize that decision-makers need to understand the specific nature of this discourse to be able to engage in careful ethical deliberation.

ABSTRACT Accurately predicting scientific impact and ranking researchers remains a central yet complex challenge in research evaluation. Traditional metrics such as citation counts, publication totals, hybrid measures, and h‐type indices each capture limited aspects of scholarly influence, making it difficult to establish a universally accepted standard. This study proposes a novel composite index designed to enhance the robustness and fairness of researcher ranking. A dataset of 1060 neuroscience researchers comprising both awardees and non‐awardees was analysed to evaluate the ability of existing indices to identify top‐performing scientists. The five indices most strongly associated with awardees were selected and further refined using deep learning models to determine their distinctiveness and combined effectiveness. Eleven statistical models were then tested to integrate the most independent pair of indices. The H2 upper and K indices exhibited the highest disjointness value (0.97), and their harmonic mean produced the most balanced and consistent performance with an average impact score of 0.76. The resulting composite index outperformed traditional metrics, offering a more comprehensive and unbiased measure of researcher impact. This approach demonstrates a scalable and data‐driven framework for improving the accuracy of scientific evaluation and ranking systems.

Plant diseases threaten global food security and agricultural productivity, particularly in regions heavily dependent on farming. Early and accurate disease detection is essential for minimizing crop loss, improving yields, and supporting sustainable agriculture. This study presents a deep learning-based framework for automated plant disease detection using transfer learning with the ResNet18 architecture. A subset of the publicly available PlantVillage dataset comprising <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\text{2, 0 0 0}$</tex> leaf images across 16 classes (healthy and diseased) was used for experimentation. Images were preprocessed, resized to <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$128 \times 128$</tex> pixels, normalized, and split into training, validation, and test sets. The pretrained ResNet18 model, fine-tuned for this task, was trained using the Adam optimizer and cross-entropy loss. Experimental results demonstrated a test accuracy of 98.67 % and a weighted <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$F 1$</tex>-score of 0.9867, outperforming several prior benchmarks. Confusion matrix analysis showed strong generalization across diverse disease categories, with only minor misclassifications among visually similar leaf conditions such as early blight and bacterial spot. Visualizations of correct and incorrect predictions further confirmed the model's robustness. These findings highlight the effectiveness of transfer learning in agriculture and suggest that lightweight CNN-based solutions like ResNet18 can enable scalable, accurate, and practical plant disease detection tools for real-world deployment.