Abstract
Clinical diagnosis of syndromes benefits strongly from objective facial phenotyping. This study introduces a novel approach to enhance clinical diagnosis through the development and exploration of a low-dimensional metric space referred to as the clinical face phenotypic space (CFPS). As a facial matching tool for clinical genetics, such CFPS can enhance clinical diagnosis. It helps to interpret facial dysmorphisms of a subject by placing them within the space of known dysmorphisms. In this paper, a triplet loss-based autoencoder developed by geometric deep learning (GDL) is trained using multi-task learning, which combines supervised and unsupervised learning approaches. Experiments are designed to illustrate the following properties of CFPSs that can aid clinicians in narrowing down their search space: a CFPS can 1) classify syndromes accurately, 2) generalize to novel syndromes, and 3) preserve the relatedness of genetic diseases, meaning that clusters of phenotypically similar disorders reflect functional relationships between genes. The proposed model consists of three main components: an encoder based on GDL optimizing distances between groups of individuals in the CFPS, a decoder enhancing classification by reconstructing faces, and a singular value decomposition layer maintaining orthogonality and optimal variance distribution across dimensions. This allows for the selection of an optimal number of CFPS dimensions as well as improving the classification capacity of the CFPS, which outperforms the linear metric learning baseline in both syndrome classification and generalization to novel syndromes. We further proved the usefulness of each component of the proposed framework, highlighting their individual impact. From a clinical perspective, the unique combination of these properties in a single CFPS results in a powerful tool that can be incorporated into current clinical practices to assess facial dysmorphism.

Abstract
[No abstract available]

Abstract

Abstract
This study presents an explainable content-based image retrieval system for predicting post-surgical aesthetic outcomes in breast cancer patients, comparing state-of-theart vision transformers, convolutional neural networks, and B-cos architectures. Results show that vision transformers, particularly GC ViT and DaViT, outperform convolutional neural networks and B-cos architectures, achieving an adjusted discounted cumulative gain of up to 80.18%. This superior performance is attributed to their ability to model long-range dependencies while effectively capturing local information. Bcos networks underperform (64.28-70.19% adjusted discounted cumulative gain), likely due to oversimplified feature alignment unsuitable for clinical tasks. Explainability analysis using Integrated Gradients reveals that models primarily focus on breast regions but occasionally attend to irrelevant features (e.g., arm positioning, leading to retrieval errors and highlighting a semantic gap between learned visual similarities and clinical relevance. Future work aims to integrate anatomical segmentation and ensemble learning methods to enhance clinical alignment and address attention inaccuracies. Clinical Relevance-The content-based image retrieval system developed in this study aids clinicians by supporting surgical outcome prediction in breast cancer patients and streamlining the traditionally time-intensive task of manually identifying similar reference images for patient consultation. © 2025 IEEE.

Abstract
This study employs Integer Linear Programming (ILP) to optimize gross profit for a local coffee shop, addressing challenges in inventory management and sale revenue optimization. A dataset comprising of 40 menu items and 34 ingredients was developed, incorporating constraints such as capital budget, ingredient availability, costs, and sales ratios to simulate monthly revenue. By applying the ILP methodology, the study achieved a gross profit margin of 42.28% of total sales revenue within a single month, underscoring its efficacy in improving profitability. The sensitivity analysis indicated that an increase in budget resulted in a proportional rise in sales revenue and gross profit, while inventory costs escalated at a comparatively slower pace. The research pinpointed high-performing items, including coffee, tea, and cold beverages, as significant contributors to profit, thereby highlighting the necessity for effective inventory management.

Abstract
Supervised Machine Learning (ML) models require large amounts of labeled data for training. However, this becomes challenging when dealing with resource- and network-constrained Internet of Things (IoT) devices that collect data. Furthermore, in scenarios where the acquired data is fast-changing and highly temporal, continuous and online learning becomes necessary. In this paper, we address the problem of efficiently training ML models using data from IoT nodes. We specifically focus on two aspects: i) selecting the nodes that provide data for the re/training, and ii) determining the optimal amounts of data to be acquired from these nodes, considering network and time constraints, while minimizing learning errors. To tackle this optimization problem, we propose ONDS: an Optimum Node and Data Selection algorithm with linear complexity in the worst-case. ONDS offers a model-agnostic solution applicable to different data modalities and ML architectures. To evaluate the performance of ONDS, we conduct experiments using various models and real-world datasets. The results demonstrate the effectiveness of ONDS, as it outperforms existing alternatives in both classification and regression tasks.