EAI Endorsed Transactions on Tourism, Technology and Intelligence

Higher Education and Student Short-Term Mobility in ASEAN Countries: Current Trends and Priorities - A Case of Passage to ASEAN

Hoa D. Tran — 2025-07-29

In the twenty-first century, international student mobility is among the most notable phenomena in Higher Education. While the current literature on its opportunities and challenges is still expanding, the majority of research recognizes its transformative potential along with a costly barrier to entry for most students. Long-term student mobility also takes priority in most scholarly works, despite the growing demand for short-term exchanges. Among the organizations seeking to alleviate said challenge and foster human capital is Passage to ASEAN (P2A) Network, a regional organization of Institutions of Higher Education (IHEs), businesses and government agencies in Southeast Asia. P2A has, since its inception, been dedicated to fostering academic exchanges, cultural understanding, collaboration prospects, and technological integration among ASEAN member IHEs. This study explores the P2A Network’s structure, its goals and impacts on regional education, especially tourism and technology, and its potential to further enhance collaborations in the region. This study employs a mixed-method approach, synthesizing document analysis and stakeholder interviews. P2A published material is closely examined and combined with emerging themes from a total of 12 interviews with individuals who have worked with P2A. This study highlights Passage to ASEAN’s role in expanding accessible Short-Term Mobility (STM) through cultural exchanges and virtual programs. By reducing cost barriers and leveraging online platforms, P2A has successfully increased participation and provided valuable educational benefits. These findings offer insights into effective STM models and serve as a reference for institutions aiming to enhance their mobility initiatives.

The Relationship Between Perception and Actual Behavior of Students Regarding Responsible Tourism A Case Study of Hospitality and Tourism Institute - Duy Tan University

Ly T. Thuong — 2025-06-26

This study investigated the relationship between students’ perceptions of responsible tourism and their actual travel behaviors within the Hospitality and Tourism Institute - Duy Tan University. The primary objective was to determine whether students' understanding of responsible tourism influences their travel behaviors in practice. The study used quantitative methods with a survey instrument designed based on a 5-point Likert scale. A sample of 490 students participated in a structured questionnaire, followed by semi-structured interviews with a selected subset of participants. The results are expected to reveal a significant correlation between students' perceptions of responsible tourism and their actual travel behaviors. Additionally, the study aimed to identify gaps between knowledge and practice, highlighting the need for stronger educational programs to bridge this divide. Overall, the study underscores the importance of promoting deeper awareness to foster more responsible actions among future tourism professionals.

GS-MultiRC: Multi-step Reservoir Computing Leveraging Grid Search for Stock Indices Prediction

Quan Thanh Dao — 2025-08-04

Stock market prediction plays a crucial role in investment decision-making, portfolio management, and risk assessment, significantly impacting financial stability and economic growth. Accurately forecasting stock prices, which are chaotic and nonlinear, has become a main point of financial research. Deep learning approaches, such as neural networks and long-short-term memory (LSTM) models, have been more reliable than traditional approaches such as the ARMA and ARIMA models. However, these methods require a lot of computational power, complex fine-tuning procedures, and often overfit, especially with limited or noisy data. Reservoir Computing (RC) has emerged as a potential alternative for financial time series prediction. It uses a fixed, randomly connected reservoir to capture patterns in data, requiring only the output layer to be trained. This design makes RC computationally efficient and simpler to use. However, RC models can struggle with overfitting when the reservoir is too large compared to the data or when the model can not adapt well to unseen data. To address these drawbacks, we propose a multi-step RC model, focusing on popular stock indices, including CSI300, FTSE100, S&P500, and SSE50. Our approach includes a retraining step where the reservoir evolves by forecasting some of the training data and simulating real-world testing conditions. These evolved internal states, affected by prediction errors, are used to retrain the output layer, making the model more robust and less likely to overfit. Our experiments show that our model performs more accurately and efficiently than conventional RC and LSTM models, making it a workable and trustworthy option for stock market prediction. This work contributes to utilizing RC-based approaches in terms of the financial
forecasting domain.

The Tourism-Migration Nexus: Accessing Care and Support as a Retired British National in Spain

Kelly Hall — 2025-07-08

INTRODUCTION: The movement of older people from one country to another has been described in a multitude of ways, including ‘Residential Tourism’ and ‘International Retirement Migration’. Tourism is often the stepping stone to retirement migration and many older retirees live fluid lifestyles where home ownership, access to welfare and social networks are maintained across the home and host countries both physically and through technology.

OBJECTIVES: This paper focuses on older British people in Spain, and explores the strategies employed to access support in later life. It draws on Grid-Group cultural theory to explore the social network configurations that include the individual, their local and transnational community, as well as the wider socio-cultural context within which they are located.

METHODS: The paper draws on data from narrative interviews with 25 older British people in Spain.

CONCLUSION: The paper exemplifies four different ‘types’ of social network organization and how these relate to help seeking behavior in later life.

Efficient Machine Learning for Wi-Fi CSI-based Human Activity Recognition Using Fast Monte Carlo based Feature Extraction

Emelia Logah — 2025-07-16

High-dimensional doppler data extracted from Wi-Fi channel state information (CSI) offers distinctive velocity and time patterns that are useful for human activity recognition (HAR), but its scale poses significant challenges for real-time inference and deployment on resource-constrained devices. This work proposes an efficient, fast monte carlo (MC) feature selection framework based on the frieze-kannanvempala (FKV) algorithm and coefficient estimation to address this bottleneck. The CSI is preprocessed, and doppler traces are computed to encode the velocity and direction of distinct activities. Afterwards, we perform FKV to decompose the doppler data, and the coefficient of the resulting singular vectors is estimated. Using rejection sampling, the topmost features are selected on the basis of their weights, thereby reducing the size of our features. The method identifies a compact set of velocity-time features that preserve critical motion information while significantly reducing computational overhead. The experimental evaluations demonstrated that the decision tree classifier achieved the highest precision at 99.8%, followed by convolutional neural networks (CNN) 96%, the hybrid CNN-long-short-term memory (CNN-LSTM) achieved 87%, while the LSTM model lagged at 53%. These results demonstrated that the integration of fast MC-based feature selection significantly reduced computational overhead without sacrificing classification performance, making it suitable for scalable and real-time HAR applications.