Abstract
Early identification of failures is a critical task in predictive maintenance, preventing potential problems before they manifest and resulting in substantial time and cost savings for industries. We propose an approach that predicts failures in the near future. First, a deep learning model combining long short-term memory and convolutional neural network architectures predicts signals for a future time horizon using real-time data. In the second step, an autoencoder based on convolutional neural networks detects anomalies in these predicted signals. Finally, a verification step ensures that a fault is considered reliable only if it is corroborated by anomalies in multiple signals simultaneously. We validate our approach using publicly available Air Production Unit (APU) data from Porto metro trains. Two significant conclusions emerge from our study. Firstly, experimental results confirm the effectiveness of our approach, demonstrating a high fault detection rate and a reduced number of false positives. Secondly, the adaptability of this proposal allows for the customization of configuration of different time horizons and relationship between the signals to meet specific detection requirements.

Abstract
Purpose Citizen engagement plays a crucial role in transitioning to sustainable service ecosystems. While customer engagement has been extensively studied in service research, citizen engagement has received significantly less attention. By synthesizing customer and citizen engagement literatures, this study develops an integrated framework to conceptually clarify the dual role of customer-citizen engagement for sustainability. Design/methodology/approach This study builds on a systematic literature review of customer engagement literature in service research and citizen engagement literature. Following a theory synthesis approach, we qualitatively analyzed 126 articles to develop an integrated conceptual framework of customer-citizen engagement for sustainability through a process of abductive reasoning. Findings The analysis showed that customer engagement and citizen engagement literatures have developed mostly separately but provide complementary views. While the customer engagement literature has traditionally focused on business-related facets, such as engagement with brands, the citizen perspective broadens the engagement scope to other citizens, communities and society in general. The integrated framework highlights the interplay between citizen and customer roles and the impact of their relationships with multiple objects on sustainability. Originality/value This integrated framework contributes to advancing our understanding of customer-citizen engagement, broadening the scope of subject-object engagement by examining the interplay between these roles in how they engage for sustainability and moving beyond the traditional dyadic perspective to a multi-level perspective of service ecosystems. This framework also enables the development of a set of research directions to advance the understanding of engagement in sustainable service ecosystems.

Abstract
Laser-based additive manufacturing (LAM) offers the ability to produce near-net-shape metal parts with unparalleled energy efficiency and flexibility in both geometry and material selection. Despite advantages, these processes are inherently, as they are characterized by multiphysics interactions, multiscale phenomena, and highly dynamic behaviors, making their modeling and optimization particularly challenging. Artificial intelligence (AI) has emerged as a promising tool for enhancing the monitoring and control of additive manufacturing. This paper presents a systematic review of AI applications for real-time control of laser-based manufacturing processes, analyzing 16 relevant articles sourced from Scopus, IEEE Xplore, and Web of Science databases. The primary objective of this work is to contribute to the advancement of autonomous manufacturing systems capable of self-monitoring and self-correction, ensuring optimal part quality, enhanced efficiency, and reduced human intervention. Our findings indicate that 62.5 % of the 16 analyzed studies have deployed AI-driven controllers in real-world scenarios, with over 56 % using AI for control strategies, such as Reinforcement Learning. Furthermore, 62.5 % of the studies employed AI for process modeling or monitoring, which was integral to the development or data pipelines of the controllers. By defining a groundwork for future developments, this review not only highlights current advancements but also hints future innovations that will likely include AI-based controllers.

Abstract
Among transportation researchers, pedestrian issues are highly significant, and various solutions have been proposed to address these challenges. These approaches include Multi-Criteria Decision Analysis (MCDA) and machine learning (ML) techniques, often categorized into two primary types. While previous studies have addressed diverse methods and transportation issues, this research integrates pedestrian modeling with MCDA and ML approaches. This paper examines how MCDA and ML can be combined to enhance decision-making in pedestrian dynamics. Drawing on a review of 1574 papers published from 1999 to 2023, this study identifies prevalent themes and methodologies in MCDA, ML, and pedestrian modeling. The MCDA methods are categorized into weighting and ranking techniques, with an emphasis on their application to complex transportation challenges involving both qualitative and quantitative criteria. The findings suggest that hybrid MCDA algorithms can effectively evaluate ML performance, addressing the limitations of traditional methods. By synthesizing the insights from the existing literature, this review outlines key methodologies and provides a roadmap for future research in integrating MCDA and ML in pedestrian dynamics. This research aims to deepen the understanding of how informed decision-making can enhance urban environments and improve pedestrian safety.

Abstract
Precision agriculture seeks to optimize crop yields while minimizing resource use. A key challenge is achieving uniform pesticide spraying to prevent crop damage and environmental contamination. Water-sensitive paper (WSP) is a common tool used for assessing spray quality, as it visually registers droplet impacts through color change. This work introduces a smartphone-based solution for capturing WSP images within vegetation, offering a tool for farmers to assess spray quality in real-world conditions. To achieve this, two approaches were explored: classical computer vision techniques and machine learning (ML) models (YOLOv8, Mask-RCNN, and Cellpose). Addressing the challenges of limited real-world data and the complexity of manual annotation, a programmatically generated synthetic dataset was employed to enable sim-to-real transfer learning. For the task of WSP segmentation within vegetation, YOLOv8 achieved an average Intersection over Union of 97.76%. In the droplet detection task, which involves identifying individual droplets on WSP, Cellpose achieved the highest precision of 96.18%, in the presence of overlapping droplets. While classical computer vision techniques provided a reliable baseline, they struggled with complex cases. Additionally, ML models, particularly Cellpose, demonstrated accurate droplet detection even without fine-tuning.

Abstract
Non-adherence to medication is a pervasive issue worldwide, affecting 50% of prescription users, resulting in suboptimal therapy outcomes and premature death. One of the key factors contributing to non-adherence is the complexity associated with managing medication regimens. To address this challenge, an automated pill dispenser “SelfMed, your medication partner” has been proposed. This study focuses on studying determinants of medication non-adherence, its ramifications and alternatives available in the market in order to increase medication adherence among adults aged 60 and over. The overarching goal of this research is to evaluate whether digital solutions like SelfMed are required for addressing non-compliance issues in Portugal while assessing their effectiveness over time for our target audience within the marketplace. The research was conducted using primary data collected through a questionnaire distributed to users and care institutions/companies in Portugal (Northern area). According to the analysis, 40% of users and 40% of care companies are interested in obtaining SelfMed to simplify the complex medication management and prescription regimen for the end user. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.