Abstract

Abstract
Monitoring vineyard diseases such as downy mildew (Plasmopara viticola) is important for viticulture, enabling an early intervention and optimized disease management. This is crucial for disease monitoring, and the use of high-spatial-resolution multispectral data from unmanned aerial vehicles (UAVs) can allow to for a better understanding of disease progression. This study explores the application of UAV-based multispectral data for monitoring downy mildew infection in vineyards through multi-temporal analysis. This study was conducted in a vineyard plot in the Vinho Verde region (Portugal), where 84 grapevines were monitored, half of which received phytosanitary treatments while the other half were left untreated in this way during the growing season. Seven UAV flights were performed across different phenological stages to assess the effects of infection using spectral bands, vegetation indices, and morphometric parameters. The results indicate that downy mildew affects canopy area, height, and volume, restricting the vegetative growth. Spectral analysis reveals that infected grapevines show increased reflectance in the visible and red-edge bands and a progressive decline in near-infrared (NIR) reflectance. Several vegetation indices demonstrated a suitable response to the infection, with some of them being capable of detecting early-stage symptoms, while vegetation indices using red edge and NIR allowed us to track disease progression. These results highlight the potential of UAV-based multi-temporal remote sensing as a tool for vineyard disease monitoring, supporting precision viticulture and the assessment of phytosanitary treatment effectiveness.

Abstract
This article investigates sampling strategies in latent space navigation to enhance co-creative music systems, focusing on timbre latent spaces. Adopting Villa-Rojo's 'Lamento' for tenor saxophone and tape as a case study, we conducted two experiments. The first assessed traditional corpus-based concatenative synthesis sampling within the RAVE model's latent space, finding that sampling strategies gradually deviate from a given target sonority while still relating to the original morphology. The second experiment aims at defining sampling strategies for creating variations of an input signal, namely parallel, contrary, and oblique motions. The findings expose the need to explore individual model layers and the geometric transformation nature of the contrary and oblique motions that tend to dilate the original shape. The findings highlight the potential of motion-aware sampling for more contextually aware and expressive control of music structures via CBCS.

Abstract
To get products delivered, clients and retailers agree on a delivery time window. We collaborated with an online retailer to develop a real-world application aimed at dynamically determining the delivery fee for each time window while ensuring the explainability of the pricing policy. This sequential decision-making problem arises as new customers continuously arrive. The objective is to maximize the final profit, given by the sum of baskets and delivery fees, discounted by the transportation and fleet costs. As multiple customers share the same delivery route, the costs are distributed among them, complicating the calculation of the marginal cost of each customer. Our study employs Genetic Programming (GP) to create explainable and easy-to-compute pricing policies to determine the delivery fees. These policies, expressed as mathematical formulas, rank price panels combinations of time slots and corresponding fees to identify optimal prices for each customer. The inputs to the GP algorithm capture the current state of the system, including factors such as capacity, customer location, and basket value. The resulting expressions offer operational managers a transparent pricing policy that allows them to maximize total profit.

Abstract
Lung cancer remains one of the most common and lethal forms of cancer, with approximately 1.8 million deaths annually, often diagnosed at advanced stages. Early detection is crucial, but it depends on physicians' accurate interpretation of computed tomography (CT) scans, a process susceptible to human limitations and variability. ByMe has developed a medical image annotation and anonymization tool designed to address these challenges through a human-centered approach. The tool enables physicians to seamlessly add structured attribute-based annotations (e.g., size, location, morphology) directly within their established workflows, ensuring intuitive interaction.Integrated with Picture Archiving and Communication Systems (PACS), the tool streamlines the annotation process and enhances usability by offering a dedicated worklist for retrospective and prospective case analysis. Robust anonymization features ensure compliance with privacy regulations such as the General Data Protection Regulation (GDPR), enabling secure dataset sharing for research and developing artificial intelligence (AI) models. Designed to empower AI integration, the tool not only facilitates the creation of high-quality datasets but also lays the foundation for incorporating AI-driven insights directly into clinical workflows. Focusing on usability, workflow integration, and privacy, this innovation bridges the gap between precision medicine and advanced technology. By providing the means to develop and train AI models for lung cancer detection, it holds the potential to significantly accelerate diagnosis as well as enhance its accuracy and consistency.

Abstract
Formal verification can be a complementary approach to UCD, offering a systematic and repeatable process to address the demands of designing safety and mission-critical interactive systems. However, the practical application of formal verification often encounters barriers to accessibility for non-technical stakeholders. In the case of model checking, although the verification step is fully automated, developing the required specifications and interpreting the verification results requires considerable technical expertise in formal methods. Recent developments in generative Artificial Intelligence (AI) have driven proposals for Large Language Models (LLMs) to be applied throughout various phases of software engineering. This begs the question of whether LLMs might be used to help bridge the gap between formal techniques and tools and stakeholders lacking technical expertise. This paper explores how these questions might be addressed in the context of an ongoing effort aimed at translating model-checking counter-examples into natural language explanations, making them accessible to designers and domain experts.