Ohbyung Kwon

The Nature Relationship Index (NRI) evaluates human–nature relationships through three dimensions (nature thriving, used with care, and safeguarded), but it exists only at the national level, whereas many policies are implemented regionally. Regional statistics describe resource use and protection, but harmonized information on ecological condition is rarely available for regions. This study examines whether satellite imagery can fill this gap. Transformer-based models were trained to estimate the Thriving (ecological condition) dimension from Sentinel-2 and Landsat-8 imagery of 136 countries, with labels constructed from forest cover and two satellite-derived land-condition indicators, while Care and Safeguarded were computed directly from emission, energy, and protected-area statistics. In repeated country-level cross-validation, imagery was essential for Thriving: a statistics-only model had no predictive skill (R² = −0.04), whereas the image model reached R² = 0.36 (p < 0.001), and transformer backbones performed similarly, with no gain from ensembling. The image-based Thriving estimates agreed with regional reference values across 42 Japanese prefectures (Spearman ρ = 0.63) and nine Korean provinces (ρ = 0.85) but not for small metropolitan cities. Combining image-based Thriving with statistics-based Care and Safeguarded yields a sub-national NRI whose profiles show whether a region’s standing is driven by ecological condition, resource use, or protection.

Large language model (LLM)-based multi-agent systems are increasingly being explored as tools for supporting structured collective decision-making, but it remains unclear how the diversity structure of agent groups affects decision-making performance. This study examined the effects of agent diversity in a Delphi-based multi-agent system by applying Harrison and Klein’s framework of variety, separation, and disparity. An LLM-based Multi-Agent Delphi System (MADS) was implemented, and 11 agent-group conditions were constructed by manipulating personality-based variety, belief-orientation-based separation, and influence asymmetry. Each condition consisted of eight agents and was tested across four open-weight LLMs with repeated experimental runs. Performance was evaluated in terms of idea exploration extent, consensus quality, and consensus efficiency, using a human expert Delphi study as an external benchmark. The results showed that diversity had differentiated effects across performance dimensions. The maximum diversity group achieved the highest idea exploration but showed low consensus quality and efficiency, whereas the homogeneous group achieved stable consensus quality and efficiency but limited exploration. The separation diversity conditions formed Pareto-efficient alternatives, indicating balanced trade-offs between idea exploration and consensus. These findings indicate that agent diversity does not uniformly improve collective decision-making performance; instead, its appropriate structure depends on whether the task prioritizes exploration, consensus quality, or consensus efficiency.

This study examines how socioeconomic factors influence the effectiveness of generative AI education in bridging the digital divide. While AI tools like DALL-E, Midjourney, and Canva enhance self-efficacy, economic expectations, cultural engagement, and entrepreneurial intent, their benefits vary across disadvantaged groups. Generative AI plays a crucial role in tourism by enabling AI-driven content creation and personalized recommendations. However, individuals affected by the digital divide may struggle to leverage these tools for tourism experiences or business opportunities. The study analyzes how gender, education, age, income, digital literacy, and prior AI usage impact AI education effectiveness. Findings offer insights into reducing social costs and addressing digital inequality through targeted policies and training programs. By improving access to generative AI, this study highlights its potential to empower marginalized groups and foster economic and creative opportunities.

Given that decision‐making typically encompasses stages such as problem recognition, the generation of alternatives, and the selection of the optimal choice, Large Language Models (LLMs) are progressively being integrated into tasks requiring the enumeration and comparative evaluation of alternatives, thereby promoting more rational decision‐making frameworks. Analysing the extent to which LLMs exhibit meaningful performance at each stage of the decision‐making process has thus become a critical area of inquiry. In particular, LLMs hold the potential to identify latent relationships within contextual information and data related to the problem domain. This capability enables them to propose novel evaluation criteria or alternatives that may otherwise be overlooked by human designers. This study seeks to advance the modelling and evaluation of the analytical hierarchy process (AHP), a widely utilised multiple criteria decision making (MCDM) method, by leveraging LLMs. To achieve this, a methodology was developed for constructing AHP models using LLMs fine‐tuned with domain‐specific documents. The performance of the proposed methodology was assessed by evaluating the extent to which its outputs aligned with reference hierarchies and criteria created by human experts under predefined AHP frameworks. Additionally, the study examined the model's efficacy in generating complete AHP hierarchies and criteria in scenarios where these were not predefined. For empirical validation, the proposed methodology was applied to assess and improve the management performance of six‐sector agricultural enterprises. Comparative analysis of the LLM‐based AHP results with human expert evaluations was conducted to determine the validity and robustness of the approach. The findings provide insights into the potential of LLMs to contribute to structured decision‐making and enhance the application of MCDM methods.

The class imbalance problem presents a critical challenge in real-world applications, particularly in high-stakes domains such as healthcare, finance, disaster management, and fault diagnosis, where accurate anomaly detection is paramount. Class imbalance often disrupts the inherent symmetry of data distributions, resulting in suboptimal performance of traditional machine learning models. Conventional approaches such as undersampling and oversampling are commonly employed to address this issue; however, these methods can introduce additional asymmetries, including information loss and overfitting, which ultimately compromise model efficacy. This study introduces an innovative approach leveraging quantum machine learning (QML), specifically the Variational Quantum Classifier (VQC), to restore and capitalize on the symmetrical properties of data distributions without relying on resampling techniques. By employing quantum circuits optimized to mitigate the asymmetries inherent in imbalanced datasets, the proposed method demonstrates consistently superior performance across diverse datasets, with notable improvements in Recall for minority classes. These findings underscore the potential of quantum machine learning as a robust alternative to classical methods, offering a symmetry-aware solution to class imbalance and advancing QML-driven technologies in fields where equitable representation and symmetry are of critical importance.

Space tourism is a growing industry sector that faces challenges of cost, risk, environmental impact, and sustainability. However, few studies address space tourism in an Asian culture, particularly in the context of artificial intelligence (AI), which is an increasingly significant topic b oth in the tourism sector and in society overall. To address the research gap, this work establishes an analytical framework which contrasts three varieties of space tourism using partial least squares, multi-group analysis, and fuzzy-set Qualitative Comparative Analysis. It surveyed 1,000 prospective space travelers from South Korean who are eager to take part in space to urism to examine AI's role in enhancing sustainable space tourism. Findings indicate that recognizing AI benefits are crucial for sustainable on-Earth, suborbital, and orbital space tourism, particularly the latter. The study offers both conceptual and applied knowledge to enhance the sustainability of space tourism.0000