Abstract
Stroke, a vascular disorder affecting the nervous system, is the third-leading cause of death and disability combined worldwide. One in every four people aged 25 and older will face the consequences of this condition, which typically causes loss of limb function, among other disabilities. The proposed review analyzes the mechanisms of stroke and their influence on the disease outcome, highlighting the critical role of rehabilitation in promoting recovery of the upper limb (UL) and enhancing the quality of life of stroke survivors. Common outcome measures and the specific targeted UL features are described, along with emerging supplementary therapies found in the literature. Stroke survivors often develop compensatory strategies to cope with limitations in UL function, which must be detected and corrected during rehabilitation to facilitate long-term recovery. Recent research on the automated detection of compensatory movements has explored pressure, wearable, marker-based motion capture systems, and vision sensors. Although current approaches have certain limitations, they establish a strong foundation for future innovations in post-stroke UL rehabilitation, promoting a more effective recovery.

Abstract
Effective project management is crucial to the success of any industry, particularly in metalworking, where deadlines, resources, and costs play critical roles. However, accurately predicting project execution times remains a significant challenge, directly impacting companies' competitiveness and profitability. In this context, the integration of Artificial Intelligence (AI) tools emerges as a promising solution to improve the accuracy of time predictions and optimise project management in the metal-working industry.AI, particularly through techniques such as Machine Learning (ML), has demonstrated significant potential in predicting timeframes for engineering projects. Predictive activity-based models can be trained with historical data to identify patterns and forecast future durations with high accuracy. In the metalworking sector, where projects are often complex and subject to variability, AI can provide notable advantages in terms of precision and efficiency.This study aims to formulate an activity-based model, represented in IDEF0 (part of the Integration Definition for Function Modelling), for predicting activity durations using AI to support project management in the metalworking industry. By applying the principles of the IDEF0 tool, the objective is to develop a robust and adaptable system capable of analysing historical data, environmental factors, project characteristics, and other relevant inputs to produce more accurate time forecasts.With this work, we aim to contribute to the advancement of Project Management (PM) in the metal-working industry, particularly by providing an activity-based model to support the creation of an innovative AI tool for predicting execution times with greater accuracy.

Abstract

Abstract
Large language model (LLM)-powered assistants are increasingly used for generating program code and unit tests, but their application in acceptance testing remains underexplored. To help address this gap, this paper explores the use of LLMs for generating executable acceptance tests for web applications through a two-step process: (i) generating acceptance test scenarios in natural language (in Gherkin) from user stories, and (ii) converting these scenarios into executable test scripts (in Cypress), knowing the HTML code of the pages under test. This two-step approach supports acceptance test-driven development, enhances tester control, and improves test quality. The two steps were implemented in the AutoUAT and Test Flow tools, respectively, powered by GPT-4 Turbo, and integrated into a partner company's workflow and evaluated on real-world projects. The users found the acceptance test scenarios generated by AutoUAT helpful 95% of the time, even revealing previously overlooked cases. Regarding Test Flow, 92% of the acceptance test cases generated by Test Flow were considered helpful: 60% were usable as generated, 8% required minor fixes, and 24% needed to be regenerated with additional inputs; the remaining 8% were discarded due to major issues. These results suggest that LLMs can, in fact, help improve the acceptance test process, with appropriate tooling and supervision.

Abstract
Nuclear-derived morphological features and biomarkers provide relevant insights regarding the tumour microenvironment, while also allowing diagnosis and prognosis in specific cancer types. However, manually annotating nuclei from the gigapixel Haematoxylin and Eosin (H&E)-stained Whole Slide Images (WSIs) is a laborious and costly task, meaning automated algorithms for cell nuclei instance segmentation and classification could alleviate the workload of pathologists and clinical researchers and at the same time facilitate the automatic extraction of clinically interpretable features for artificial intelligence (AI) tools. But due to high intra- and inter-class variability of nuclei morphological and chromatic features, as well as H&Estains susceptibility to artefacts, state-of-the-art algorithms cannot correctly detect and classify instances with the necessary performance. In this work, we hypothesize context and attention inductive biases in artificial neural networks (ANNs) could increase the performance and generalization of algorithms for cell nuclei instance segmentation and classification. To understand the advantages, use-cases, and limitations of context and attention-based mechanisms in instance segmentation and classification, we start by reviewing works in computer vision and medical imaging. We then conduct a thorough survey on context and attention methods for cell nuclei instance segmentation and classification from H&E-stained microscopy imaging, while providing a comprehensive discussion of the challenges being tackled with context and attention. Besides, we illustrate some limitations of current approaches and present ideas for future research. As a case study, we extend both a general (Mask-RCNN) and a customized (HoVer-Net) instance segmentation and classification methods with context- and attention-based mechanisms and perform a comparative analysis on a multicentre dataset for colon nuclei identification and counting. Although pathologists rely on context at multiple levels while paying attention to specific Regions of Interest (RoIs) when analysing and annotating WSIs, our findings suggest translating that domain knowledge into algorithm design is no trivial task, but to fully exploit these mechanisms in ANNs, the scientific understanding of these methods should first be addressed.

Abstract
Crowdsourced data streams are popular and extremely valuable in several domains, namely in tourism. Tourism crowdsourcing platforms rely on past tourist and business inputs to provide tailored recommendations to current users in real time. The continuous, open, dynamic and non-curated nature of the crowd-originated data demands specific stream mining techniques to support online profiling, recommendation, change detection and adaptation, explanation and evaluation. The sought techniques must, not only, continuously improve and adapt profiles and models; but must also be transparent, overcome biases, prioritize preferences, master huge data volumes and all in real time. This article surveys the state-of-art of adaptive and explainable stream recommendation, extends the taxonomy of explainable recommendations from the offline to the stream-based scenario, and identifies future research opportunities.