Abstract
The learning from continuous data streams is a relevant area within machine learning, focusing on the creation and updating of predictive models in real time as new data becomes available for training and prediction. Among the most widely used methods for this type of task, Hoeffding Trees are highly valued for their simplicity and robustness across a variety of applications and are considered the primary choice for generating decision trees in data stream contexts. However, Hoeffding Trees tend to continuously expand as new data is incorporated, resulting in increased processing time and memory consumption, often without providing significant gains in accuracy. In this study, we propose an instance selection scheme that combines different strategies to regularize Hoeffding Trees and their variants, mitigating excessive growth without compromising model accuracy. The method selects misclassified instances and a fraction of correctly classified instances during the training phase. After extensive experimental evaluation, the instance selection scheme demonstrates superior predictive performance compared to the original models (without selection), for both real and synthetic datasets for data streams, using a reduced subset of examples. Additionally, the method achieves relevant improvements in processing time, model complexity, and memory consumption, highlighting the effectiveness of the proposed instance selection scheme.

Abstract
PurposeThis paper aims to identify the critical success factors (CSFs) for managing remote project teams (RPT) within project environments. In other words, it focuses on identifying the crucial elements for the success of projects executed by RPT.Design/methodology/approachAn exploratory mixed-method was used combining a case study approach with the application of surveys. Document analysis and direct observation were also applied. The analyzed company is a well-known project-based company acting in the coffee industry and is justified due to its multilocation and multicultural perspectives.FindingsThrough an initial literature review, 93 CSFs were identified and then organized into 7 categories. The subsequent phase involved the relevance evaluation of the identified CSFs through surveys conducted in an international company. The first results analysis identified 20 CSFs. A deeper analysis identified the most relevant factors for each category (Project Managers, 33 factors; Team Leaders, 15; and Team Members, 29). Combining these results, 11 CSFs were identified.Originality/valueWith the trend of remote work that is being kept after the pandemic, this study contributes to identify the most relevant issues that must be taken into account in managing remote teams. By identifying those issues, or CSFs, managers and team members might focus on the most relevant factors.

Abstract
Highlights What are the main findings? UAV multispectral data combined with machine learning enabled the estimation of grapevine biophysical parameters, including LAI, pruning wood biomass, and yield. Geometric features, such as canopy area and volume, improved model accuracy and reduced the number of predictors, while the integration of spectral and geometric data improved prediction robustness across different phenological stages. What is the implication of the main finding? UAV-based monitoring can be applied in different grapevine varieties without cultivar-specific calibration, providing a non-invasive tool for vineyard assessment. Identifying the most informative features and suitable acquisition periods supports more accurate decisions in vineyard management, including pruning, canopy control, and yield estimation.Highlights What are the main findings? UAV multispectral data combined with machine learning enabled the estimation of grapevine biophysical parameters, including LAI, pruning wood biomass, and yield. Geometric features, such as canopy area and volume, improved model accuracy and reduced the number of predictors, while the integration of spectral and geometric data improved prediction robustness across different phenological stages. What is the implication of the main finding? UAV-based monitoring can be applied in different grapevine varieties without cultivar-specific calibration, providing a non-invasive tool for vineyard assessment. Identifying the most informative features and suitable acquisition periods supports more accurate decisions in vineyard management, including pruning, canopy control, and yield estimation.Abstract The accurate estimation of grapevine biophysical parameters is important for decision support in precision viticulture. This study addresses the use of unmanned aerial vehicle (UAV) multispectral data and machine learning (ML) techniques to estimate leaf area index (LAI), pruning wood biomass, and yield, across mixed-variety vineyards in the Douro Region of Portugal. Data were collected at three phenological stages, from veraison to maturation and two modeling approaches were tested: one using only spectral features, and another combining spectral and geometric features derived from photogrammetric elevation data. Multiple linear regression (MLR) and five ML algorithms were applied, with feature selection performed using both forward and backward selection procedures. Logarithmic transformations were used to mitigate data skewness. Overall, ML algorithms provided better predictive performance than MLR, particularly when geometric features were included. At harvest-ready, Random Forest achieved the highest accuracy for LAI (R2 = 0.83) and yield (R2 = 0.75), while MLR produced the most accurate estimates for pruning wood biomass (R2 = 0.83). Among geometric variables, canopy area was the most informative. For spectral data, the Modified Soil-Adjusted Vegetation Index (MSAVI) and the Soil-Adjusted Vegetation Index (SAVI) were the most relevant. The models performed well across grapevine varieties, indicating that UAV-based monitoring can serve as a practical, non-invasive, and scalable approach for vineyard management in heterogeneous vineyards.

Abstract
Inherited retinal diseases (IRDs) are rare and genetically diverse disorders that cause progressive vision loss and affect 1 in 3000 individuals worldwide. Their rarity and genetic variability pose a challenge for deep learning models due to the limited amount of data. Generative models offer a promising solution by creating synthetic data to improve training datasets. This study carried out a systematic literature review to investigate the use of generative models to augment data in IRDs and assess their impact on the performance of classifiers for these diseases. Following PRISMA 2020 guidelines, searches in four databases identified 32 relevant studies, 2 focused on IRD and the rest on other retinal diseases. The results indicate that generative models effectively augment small datasets. Among the techniques identified, Deep Convolutional Adversarial Generative Networks (DCGAN) and the Style-Based Generator Architecture of Generative Adversarial Networks 2 (StyleGAN2) were the most widely used. These architectures generated highly realistic and diverse synthetic data, often indistinguishable from real data, even for experts. The results highlight the need for more research into data generation in IRD to develop robust diagnostic tools and improve genetic studies by creating more comprehensive genetic repositories.

Abstract
Polarization optical fiber sensors are based on modifications of fiber birefringence by an external measurand (e.g., strain, pressure, acoustic waves). Yet, this means that different input states of polarization will result in very distinct behaviors, which may or may not be optimal in terms of sensitivity and signal-to-noise ratio. To tackle this challenge, this manuscript presents an optimization technique for the input polarization state using the Fisher information formalism, which allows for achieving maximal precision for a statistically unbiased metric. By first measuring the variation of the Mueller matrix of the optical fiber in response to controlled acoustic perturbations induced by piezo speakers, we compute the corresponding Fisher information operator. Using maximal information states of the Fisher information, it was possible to observe a significant improvement in the performance of the sensor, increasing the signal-to-noise ratio from 4.3 to 37.6 dB, attaining an almost flat response from 1.5 kHz up to 15 kHz. As a proof-of-concept for dynamic audio signal detection, a broadband acoustic signal was also reconstructed with significant gain, demonstrating the usefulness of the introduced formalism for high-precision sensing with polarimetric fiber sensors. (c) 2025 Optica Publishing Group. All rights, including for text and data mining (TDM), Artificial Intelligence (AI) training, and similar technologies, are reserved.

Abstract