Vera Miguéis

Abstract
In the pharmaceutical industry, noncompliance with any good manufacturing practice (GMP) leads to deviation, resulting in potential retention of finished product batches, reprocessing, or rejection-consequently increasing lead time and cost. This study aimed to outline a strategy to define, classify, and mitigate recurrent deviations occurring more than once within 12 months. This research followed an action research methodology, carried out within a Portuguese pharmaceutical company. A transversal analysis of the deviation management process was conducted across three phases: recording, investigation, and conclusion. The intervention included defining objective recurrence criteria, developing investigation models based on structured problem-solving, and redesigning the deviation management information system. The implementation decreased recurrent deviations by 78 percent, and a new process was established, facilitated by the participation and involvement of everyone in the organization. This article introduces pioneering contributions to the pharmaceutical industry by presenting novel criteria for assigning recurrence to recorded deviations and integrating Good Manufacturing Practices (GMP) with big data and analytics. Our approach enhances decision-making and manufacturing processes by structurally incorporating all types of causes beyond the human factor, emphasizing recurring deviations over extended periods. It defines conditions for correct deviation classification and constructs a decision matrix for investigation models. Additionally, it presents workshop management, providing analysis templates and a prototype information system, and outlines key steps to mitigate deviations, highlighting research limitations and future directions.

Abstract
Achieving sustainable urban mobility requires shifting travelers toward public transport. However, policies often assume uniform preferences, leaving a critical gap in understanding how different travelers prioritize mobility factors. To address this, the study examines behavioral heterogeneity among urban travelers using a data-driven clustering approach based on the relative importance assigned to cost, comfort, environmental sustainability, and flexibility. Using data from 698 respondents in the Asprela area of Porto, Portugal, a mixed-use district combining universities, hospitals, and commercial facilities, the study applies principal component analysis (PCA) and K-means clustering to derive distinct traveler profiles. Unlike segmentation based solely on socio-demographics or observed mode choice, this approach groups individuals according to their underlying value structures. Six clusters were identified, ranging from car-dependent, comfort-oriented users to environmentally conscious and low-engagement groups. The findings show that one-size-fits-all policies are unlikely to address behavioral diversity effectively. Building on these insights, the study proposes tailored and cross-cutting policies to enhance the attractiveness of public transport and promote sustainability. By uncovering latent preference structures, the study contributes to more inclusive and value-informed mobility planning.

Abstract
Quality performance in manufacturing has a direct influence on efficiency, generated waste, and costs. In collaboration with a textile manufacturer as a case study, this paper develops an automated defect detection system for a weaving process and evaluates its impact on operational performance. The system identifies defects immediately at their onset and prevents their propagation to subsequent fabric and production stages. A deep learning image classification model is developed, with six well-established network architectures being compared, leveraging a non-invasive image acquisition method that averts machinery disturbances for data collection. Based on the best-performing model, key indicators of operational performance are estimated using Markov Chain modelling, addressing a gap in linking model performance to operational impacts. Notable operational gains are demonstrated, namely a cost reduction of 1.3% and over 90% of waste reduction. A sensitivity analysis guides the definition of the image acquisition frame rate to minimise false alarms and shows that different operational indicators are impacted differently by different predictive performance metrics, affecting model selection. This research not only underscores the potential of integrating deep learning into textile production but also guarantees the effective communication of its impact to industry stakeholders, thus offering valuable practical insights to enhance operational performance.

Abstract
Food sustainability is a vital global challenge, as dietary choices affect both human health and the environment. This study evaluates Portuguese dietary patterns' environmental and nutritional sustainability dimensions using data from the National Food, Nutrition, and Physical Activity Survey (IAN-AF) 2015-2016. Environmental indicators (carbon footprint, water footprint, and land use) and a nutritional quality index (NRD9.3) were analysed. Sustainability scores were calculated based on deviations from population medians, with the environmental score estimated from a weighted mean of the three indicators. A quadrant analysis classified individuals into four sustainability segments: better environmental and better nutritional scores (reference group); worse environmental and worse nutritional scores; worse environmental and better nutritional scores; and better environmental and worse nutritional scores. The reference group, with higher plant-based food consumption, had the lowest environmental impacts, 33% lower carbon footprint, 36% lower water footprint, and 50% lower land use, while exhibiting 87% better nutritional quality. In contrast, the worse environmental and worse nutritional scores group, with a diet rich in red and processed meats, sweets, and alcohol, showed higher environmental impacts and poorer nutritional quality. The group with worse environmental and better nutritional scores favored dairy and seafood, whereas the group with better environmental and worse nutritional scores had higher intakes of white meat, sweets, and alcohol. Sociodemographic factors, including sex, age, and education, show to influence the sustainability dimensions. These findings highlight the need for tailored dietary strategies that consider differing environmental and nutritional profiles, supporting more effective and practical public health interventions.

Abstract
The effectiveness of digital marketing relies on the seamless integration of intelligent technology, enabling encounters that closely resemble those experienced with physical vendors in the real world. Thus, the importance of scalable artificial intelligence (AI) systems guided by a multimodal approach cannot be overstated, as they can be used to gain a deeper understanding of user preferences and engagement behaviors. The investigation conducted concerning multimodal learning in this review uncovers a variety of benefits and limitations on the available data, presenting consistency in finding the relationship between modalities. The results suggest multimodality as a topic with a noticeable dearth of research, yet a promising path to reduce uncertainty and develop innovative perspectives on decision-making for Digital Marketing improvement tasks. The complexity inherent in data processes like analysis, processing, and granular modulation requires a lot of effort for researchers to build accurate multimodal representations while trying to suppress imprecision in these new elements. Therefore, our approach aims to explore how theoretical foundations are successfully applied to learning operational procedures, considering real-life case comprehension, the technical challenges of the learning process, and the importance given to each feature. Even so, comparing the restrictions found in the state-of-the-art made possible the reformulation of limitations to this particular type of technology and encouraged the search for more guidelines on the entire process.