Abstract
Breast cancer treatments often affect patients’ body image, making aesthetic outcome predictions vital. This study introduces a Deep Learning (DL) multimodal retrieval pipeline using a dataset of 2,193 instances combining clinical attributes and RGB images of patients’ upper torsos. We evaluate four retrieval techniques: Weighted Euclidean Distance (WED) with various configurations and shallow Artificial Neural Network (ANN) for tabular data, pre-trained and fine-tuned Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs), and a multimodal approach combining both data types. The dataset, categorised into Excellent/Good and Fair/Poor outcomes, is organised into over 20K triplets for training and testing. Results show fine-tuned multimodal ViTs notably enhance performance, achieving up to 73.85% accuracy and 80.62% Adjusted Discounted Cumulative Gain (ADCG). This framework not only aids in managing patient expectations by retrieving the most relevant post-surgical images but also promises broad applications in medical image analysis and retrieval. The main contributions of this paper are the development of a multimodal retrieval system for breast cancer patients based on post-surgery aesthetic outcome and the evaluation of different models on a new dataset annotated by clinicians for image retrieval. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

Abstract
Context. The dust- and gas-rich protoplanetary disks around young stellar systems play a key role in star and planet formation. While considerable progress has recently been made in probing these disks on large scales of a few tens of astronomical units (au), the central au requires further investigation. Aims.We aim to unveil the physical processes at play in the innermost regions of the strongly accreting T Tauri Star S CrA N by means of near-infrared interferometric observations. As recent spectropolarimetric observations suggest that S CrA N might undergo intense ejection processes, we focus on the accretion-ejection phenomena and on the star-disk interaction region. Methods. We obtained interferometric observations with VLTI/GRAVITY in the K-band during two consecutive nights in August 2022. The analysis of the continuum emission, coupled with the differential analysis across the Br gamma line, allows us to constrain the morphology of the dust and the gas distribution in the innermost regions of S CrA N and to investigate their temporal variability. These observations are compared to magnetospheric accretion-ejection models of T Tauri stars and to previous observations in order to elucidate the physical processes operating in these regions. Results. The K-band continuum emission is well reproduced with an azimuthally modulated dusty ring with a half-light radius of 0.24 au (similar to 20 R*), an inclination of similar to 30 degrees, and a position angle of similar to 150 degrees. As the star alone cannot explain such a large sublimation front, we propose that magnetospheric accretion is an important dust-heating mechanism leading to this continuum emission. The Br gamma-emitting region (0.05-0.06 au; 5-7 R*) is found to be more compact than the continuum, to be similar in size or larger than the magnetospheric truncation radius. The on-sky displacements across the Br gamma spectral channels are aligned along a position angle offset by 45 degrees from the disk, and extend up to 2 R*. This is in agreement with radiative transfer models combining magnetospheric accretion and disk winds. These on-sky displacements remain unchanged from one night to another, while the line flux decreases by 13%, suggesting a dominant contribution of wind to the origin of the Br gamma line. Conclusions. Our observations support the scenario where the Br gamma line originates from a combination of (variable) accretion-ejection processes in the inner disk region.

Abstract
PurposeThis study aims to identify and explore the factors affecting social entrepreneurial intentions considering an educational institution in Portugal. It also intends to determine the relevance of moderating factors in the antecedents and entrepreneurial intention of these students. Design/methodology/approachA panel of 177 undergraduate students enrolled in a social entrepreneurship course between the academic years 2018 and 2021 is considered. The data is explored quantitatively considering descriptive analysis techniques, correlational analysis and hypothesis testing. FindingsThe findings reveal that entrepreneurial intention depends on multiple individual, organizational and contextual dimensions. Students' entrepreneurial intention remains unchanged regardless of the student's profile. However, students' professional experience is a more relevant factor for the identification of organizational dimensions related to curriculum and critical pedagogy, while previous involvement in volunteer activities contributes to a higher prevalence of individual factors. Originality/valueTo the best of the authors' knowledge, this study is original in exploring the role of entrepreneurial intention and its antecedents considering a heterogeneous students' profile. It offers theoretical and practical contributions by extending the literature on social entrepreneurial intention that can be used by higher education institutions to offer specific training more focused on the student's profile.

Abstract
This paper presents an approach to enhancing sensitivity in optical sensors by integrating self-image theory and graphene oxide coating. The sensor is specifically engineered to quantitatively assess glucose concentrations in aqueous solutions that simulate the spectrum of glucose levels typically encountered in human saliva. Prior to sensor fabrication, the theoretical self-image points were rigorously validated using Multiphysics COMSOL 6.0 software. Subsequently, the sensor was fabricated to a length corresponding to the second self-image point (29.12 mm) and coated with an 80 mu m/mL graphene oxide film using the Layer-by-Layer technique. The sensor characterization in refractive index demonstrated a wavelength sensitivity of 200 +/- 6 nm/RIU. Comparative evaluations of uncoated and graphene oxide-coated sensors applied to measure glucose in solutions ranging from 25 to 200 mg/dL showed an eightfold sensitivity improvement with one bilayer of Polyethyleneimine/graphene. The final graphene oxide-based sensor exhibited a sensitivity of 10.403 +/- 0.004 pm/(mg/dL) and demonstrated stability with a low standard deviation of 0.46 pm/min and a maximum theoretical resolution of 1.90 mg/dL.

Abstract

Abstract
Data valuation, the process of assigning value to data based on its utility and usefulness, is a critical and largely unexplored aspect of data markets. Within the Machine Learning Data Market (MLDM), a platform that enables data exchange among multiple agents, the challenge of quantifying the value of data becomes particularly prominent. Agents within MLDM are motivated to exchange data based on its potential impact on their individual performance. Shapley Value-based methods have gained traction in addressing this challenge, prompting our study to investigate their effectiveness within the MLDM context. Specifically, we propose the Gain Data Shapley Value (GDSV) method tailored for MLDM and compare it to the original data valuation method used in MLDM. Our analysis focuses on two common learning algorithms, Decision Tree (DT) and K-nearest neighbors (KNN), within a simulated society of five agents, tested on 45 classification datasets. results show that the GDSV leads to incremental improvements in predictive performance across both DT and KNN algorithms compared to performance-based valuation or the baseline. These findings underscore the potential of Shapley Value-based methods in identifying high-value data within MLDM while indicating areas for further improvement.