Abstract
Purpose This study aims to explore how technology-enabled services influence the overall experience of participants in running events by applying a structured service design methodology. Specifically, it examined how recreational runners engage with technology-enabled services throughout the customer journey of a running event, and how the application of the MINDS method contributes to enhancing the runners' experience. Design/methodology/approach Thirty-nine running event participants were interviewed to explore their experiences. The interviews took place in Greece in 2023, across various mass-participation events from marathons to 5K city races. Using the Management and INteraction Design for Service (MINDS) method, qualitative data were thematically analyzed. Findings The study identified how recreational runners interact with technology-enabled services across the pre-, during-, and post-event stages. Using the MINDS method, participants' experiences were mapped to reveal emotional touchpoints, service gaps, and opportunities to enhance the event experience. These findings were translated into service design proposals through the MINDS method, resulting in visual outputs that illustrate how technology-enabled services could be better integrated across the event journey. Originality/value This study is among the first to examine running event experiences from the participants' perspective using a service design methodology. It also contributes to the advancement of the MINDS by introducing customer journey and emotional journey extensions, offering richer insights into how participant experiences can be optimized across the event lifecycle.

Abstract
This paper aims to clarify the characteristics of Digital Twins (DTs) in their most advanced conceptual development, Cognitive Digital Twins (CDTs), and analyze their support for the implementation of the Circular Economy (CE). A systematic literature review was conducted using a specially developed five-dimensional analytical framework to characterize DT proposals and their potential for CE based on an established framework for circularity strategies. The study indicates that cognitive and hybrid DT approaches tend to cover high levels of interoperability, data flow, system levels, and cognitive processes. However, CDT use in CE demands harmonizing different strategies to cover the complete product lifecycle, which recent research on DTs has not fully addressed. This study is the first to systematically review cognitive digital twins and their relation to circularity, offering an analytical framework that can be expanded for future research in various application areas of Industry 5.0.

Abstract
Synthetic data has become a crucial enabler for training deep learning models in robotic perception tasks. This work presents a configurable synthetic data generation pipeline, built on BlenderProc, that leverages CAD model annotations to produce part-based labels directly at the geometry level. The proposed approach enables the automatic generation of Oriented Bounding Box (OBB) annotations and supports the definition of multiple regions of interest through a vertex-level annotation tool. The pipeline is validated in an warehouse environment use case involving a storage container for automotive parts for autonomous forklift operations. Experimental results show that YOLO11m-Oriented Bounding Box model trained exclusively on synthetic data achieve strong performance on real-world images, reaching up to 0.768 mAP@0.5:0.95. Furthermore, increasing synthetic data diversity consistently improves detection performance, and hybrid training with a small amount of real data provides an effective trade-off between annotation effort and accuracy.

Abstract
Early detection of gastrointestinal lesions such as intestinal metaplasia (IM), dysplasia, and polyps remains challenging due to their subtle appearance and the scarcity of well-annotated medical image datasets. To address this limitation, we introduce Cut Instance Mixing (CIM), a domain-specific data augmentation method designed to generate anatomically plausible lesion-containing images through the identification of biologically relevant regions of interest and seamless lesion blending using Poisson image editing and gradient-based mixing. CIM was evaluated across three distinct endoscopic datasets (IM, dysplasia, and polyps) using a ResNet50 classifier and five-fold cross-validation. The proposed method consistently outperformed state-of-the-art augmentation techniques. In IM classification, CIM with alpha = 0.8 achieved the highest performance (AUC: 0.879, Accuracy: 0.823), surpassing MixUp, CutMix and random copy-paste. In dysplasia detection, CIM reached near-perfect results (AUC: 0.997, Accuracy: 0.966), and demonstrated strong generalization on an external polyp dataset (AUC: 0.830, Accuracy: 0.769). Grad-CAM analyses further confirmed that CIM preserves clinically relevant features, improving model attention on lesion regions. These findings demonstrate that CIM enables the generation of realistic and biologically coherent synthetic samples, effectively mitigating data imbalance and enhancing classification robustness. The method is architecture-agnostic and broadly applicable to tasks requiring anatomically consistent augmentation, providing a promising direction for improving deep learning systems in gastrointestinal imaging.

Abstract

Abstract
This study explores the application of multiple predictive algorithms under general versus route-specialized modeling strategies to estimate passenger boarding demand in public bus transportation systems. Accurate estimation of boarding patterns is essential for optimizing service planning, improving passenger comfort, and enhancing operational efficiency. This research evaluates a range of predictive models to identify the most effective techniques for forecasting demand across different routes and times. Two modeling strategies were implemented: a generalistic approach and a specialized one. The latter was designed to capture route-specific characteristics and variability. A real-world case study from a medium-sized metropolitan region in Brazil was used to assess model performance. Results indicate that ensemble-tree-based models, particularly XGBoost, achieved the highest accuracy and robustness in handling nonlinear relationships and complex interactions within the data. Compared to the generalistic approach, the specialized approach demonstrated superior adaptability and precision, making it especially suitable for long-term and strategic planning applications. It reduced the average RMSE by 19.46% (from 13.84 to 11.15) and the MAE by 17.36% (from 9.60 to 7.93), while increasing the average R2 from 0.289 to 0.344. However, these gains came with higher computational demands and mean Forecast Bias (from 0.002 to 0.560), indicating a need for bias correction before operational deployment. The findings highlight the practical value of predictive modeling for transit authorities, enabling data-driven decision making in fleet allocation, route planning, and service frequency adjustment. Moreover, accurate demand forecasting contributes to cost reduction, improved passenger satisfaction, and environmental sustainability through optimized operations.