Predicting future cellular network traffic volume patterns is crucial for optimizing network resource management and enhancing user experience. Recently, with cellular traffic data represented as pseudo-image data, state-of-the-art frameworks based on Deep Neural Networks (DNNs) have been introduced to enable effective modeling of spatiotemporal dependencies for the prediction tasks. Nonetheless, highly parameterized DNNs require large datasets, which are often missing for cellular network traffic prediction task and thus underscore the need for effective data augmentation strategies. Our preliminary analysis shows that the augmentation methods for natural images prove ineffective in enhancing performance on this task due to its pseudo-image nature. We identify that the reason lies in image augmentations introducing missing values and misalignments, with masking and geometric alterations disrupting the real-world cellular traffic patterns. On top of this, we propose an adaptation of underlying augmentation process into a tailored strategy suitable for the spatial and temporal complexities of the data, which stem from interactions between base stations and evolving traffic patterns. Specifically, we introduce MixScale, an augmentation technique designed for pseudo-image cellular network traffic data. MixScale integrates constrained spatio-temporal data mixing with multi-scaling to better align with the unique characteristics of the dataset. Evaluation on two real-world datasets, including a 5G dataset, demonstrates promising results; MixScale consistently achieves reductions between 16% and 32% in root mean square error (RMSE) compared to the baseline.
This study incorporates the concept of infrastructure (evacuation resource) into the existing PRISM simulation framework to optimize infrastructures allocation during radiological emergencies. A reinforcement learning methodology is applied to derive spatiotemporal allocation strategies for these infrastructures by explicitly reflecting the dynamic movements of evacuees. The reinforcement learning-optimized infrastructure distributions reduce evacuation completion time compared to uniform and population-proportional allocations, thereby providing decision makers with an efficient infrastructure allocation strategy that accounts for both dynamic evacuation conditions and limited infrastructure availability.
Monastery stay tourism is an emerging niche within spiritual and transformative tourism, offering immersive experiences that facilitate personal and emotional growth. Despite its rising popularity, limited research has explored how such experiences shape tourists' emotional bonds, identity formation, and revisit intention. Drawing on mindfulness theory, this study examines the role of mindfulness cultivated during Buddhist monastery retreats in influencing emotional solidarity, experience self-connection, place identity, and behavioural intention. Data were collected from 430 visitors and analyzed using partial least squares structural equation modelling (PLS-SEM) and multi-group analysis (MGA). The PLS-SEM results underscore the critical role of mindfulness in shaping tourists’ social interactions, emotional attachment to the destination, and self-connection, all of which significantly impact their intention to engage in spiritual retreats. Emotional solidarity and self-connection are found to significantly influence place identity and future behavioural intention. The MGA findings indicate that generational and experiential segmentation reveals that Generation Z is more responsive to mindfulness and experience self-connection, while older cohorts are more influenced by emotional solidarity. Repeat visitors report stronger mindfulness effects across all outcomes, whereas first-time visitors rely more on emotional bonding. These insights underscore the value of tailoring mindful retreat experiences to foster deeper engagement and sustained support for religious tourism destinations.
This study examines how affective emoji messages (happiness vs. sadness) influence the effectiveness of pro-environmental messages in hospitality and tourism contexts. Drawing on the Emotions as Social Information (EASI) model, the research focuses on the affective reaction pathway through which emoji messages shape message effectiveness. Experiments and field studies show that happiness emoji messages elicit stronger affective reactions and enhance message effectiveness. This effect is stronger among individuals with high future self-continuity, who respond less favorably to sadness messages. Social relational framing further moderates this effect: happiness messages are more persuasive when directed at a general audience, whereas when messages reference close social ties, the difference between affective frames diminishes. Theoretically, the study shows that pro-environmental persuasion can operate through an affective pathway and is contingent on boundary conditions. In practice, the findings provide guidance for designing pro-environmental messages that promote responsible behavior while preserving travel enjoyment.
