Abstract
The broadband absorption coefficient spectrum of the rabbit lung presents some particular characteristics that allow the identification of the chromophores in this tissue. By performing a weighted combination of the absorption spectra of water, hemoglobin, DNA, proteins and the pigments melanin and lipofuscin, it was possible to obtain a good match to the experimental absorption spectrum of the lung. Such reconstruction provided reasonable information about the contents of the tissue components in the lung tissue, and allowed to identify a similar accumulation of melanin and lipofuscin. The broadband absorption coefficient spectrum of the rabbit lung was reconstructed from the absorption spectra of tissue components. The similar accumulation of melanin and lipofuscin was retrieved from the broadband baseline in the absorption coefficient spectrum, and the calculation of the absorption fold ratios for proteins, DNA and hemoglobin provided good results. The method used is innovative and can be improved to allow the quantification of tissue components concentrations directly. image

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-the-art 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. B-cos 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.

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.

Abstract
This study introduces a secure, adaptable, and decentralized learning framework empowered by blockchain technology to enhance smart grid security and efficiency. Security is achieved through blockchain's ledger, ensuring data integrity, privacy, and resilience. Adaptability refers to the framework's ability to adjust to changing conditions, supporting multiple learning paradigms. Decentralization enhances fault tolerance by distributing control across nodes. Our framework excels in scalability, data-exchange security, and rapid response times, aiming to establish an intelligent blockchain-based smart grid supporting centralized learning (CL), federated learning (FL), and active federated learning (AFL). We present an innovative blockchain-based architecture customized to optimize information sharing and security within the blockchain. Our solution addresses various learning paradigm requirements by: (i) Selecting reliable entities for participation based on high-quality training data models; (ii) Acquiring a reliable subset of data for CL and AFL, balancing learning performance, latency, and cost; (iii) Adjusting blockchain configuration to align with specific learning paradigm requirements. Results from real-world datasets demonstrate superior performance compared to existing solutions. Our framework achieves high learning performance while minimizing latency and blockchain costs.