Vol. 8 No. 07 (2026): Volume 08 Issue 07

This study explores which eye-tracking and face-reading indicators differentiate respondents with higher and lower tendencies toward compulsive buying when processing advertising leaflets. The objective was to examine whether compulsive buying tendencies are reflected in real-time visual attention and facial-emotional responses to specific leaflet elements. Data were collected from 177 respondents using an online panel. Participants viewed standardized advertising leaflets while eye-tracking and automated facial expression data were recorded. Compulsive buying tendencies were measured using a short questionnaire scale, and respondents were compared according to their CBB scores. The analysis focused on areas of interest including product image, product name, price, discount symbol, product description, and country-of-origin information. The results show that respondents with higher compulsive buying tendencies differed mainly in visual-attentional processing. The strongest differentiating indicator was shorter time to first fixation on the product image, suggesting faster orientation toward the product visual among higher-CBB respondents. Secondary patterns indicated weaker processing of country-of-origin information and slightly greater repeated attention to the product name. Face-reading indicators provided weaker differentiation, as facial responses were predominantly neutral. Although discount symbols generated relatively higher engagement and joy overall, they did not clearly distinguish higher- from lower-CBB respondents. The findings suggest that compulsive buying tendencies are expressed less through strong facialemotional reactions and more through subtle shifts in attention toward product-related cues. Eye-tracking and facereading should therefore be viewed as complementary exploratory tools rather than diagnostic substitutes for validated CBB questionnaires.  

This article focuses on analyzing the system of international and national legal foundations concerning Vietnam's sovereignty, sovereign rights, and jurisdiction over the East Sea (or South China Sea). By comparative analysis between the 1982 United Nations Convention on the Law of the Sea (UNCLOS 1982) and the 2012 Law on the Sea of Vietnam, the research clarifies the legal substance, boundaries, and administrative-security management regimes for each specific maritime zone: internal waters, the territorial sea, the contiguous zone, the exclusive economic zone, and the continental shelf. Furthermore, the article analyzes the practical value of the 2016 Arbitral Award by the Permanent Court of Arbitration (PCA) in invalidating China's baseless claims over the "nine-dash line," as well as Vietnam's consistent strategic position in protecting national interests and upholding the rule of law across the oceans.

Adaptive ensemble learning has emerged as a critical paradigm for addressing non-stationarity, heterogeneity, and scalability challenges in modern signal intelligence systems. Traditional signal processing frameworks rely heavily on static model assumptions, limiting their effectiveness in dynamic environments such as IoT networks, wireless communications, and cyber-physical systems. This paper proposes an Adaptive Ensemble Signal Intelligence Architecture (AESIA) designed to integrate meta-learning, bilevel optimization, and differentiable architecture search to enable robust, self-adjusting neural network systems capable of quantitative equity trend estimation in signal-driven domains.

The proposed architecture synthesizes key advances in model-agnostic meta-learning (Finn et al., 2017), robust few-shot learning frameworks (Killamsetty et al., 2022), and hyperparameter optimization techniques (Pedregosa, 2016), alongside bilevel optimization strategies (Ghadimi and Wang, 2018; Liu et al., 2020). These components collectively support adaptive model reconfiguration in response to evolving signal distributions and operational constraints. Furthermore, differentiable architecture search (Liu et al., 2018) is incorporated to automate neural architecture design under computational constraints, ensuring efficiency in deployment scenarios.

The study also incorporates insights from signal intelligence applications in IoT authentication and emitter identification (McGinthy et al., 2019; Zhang et al., 2019), as well as security-driven signal analytics frameworks (Sang and Jun, 2021). A key contribution is the formulation of a quantitative neural architecture equity trend estimation model, which evaluates model fairness, stability, and predictive consistency across heterogeneous signal environments. This is further aligned with multi-model forecasting principles demonstrated in large-scale temporal systems (Vollem et al., 2026), which provide foundational guidance for hybrid statistical-deep learning integration.

Results from theoretical modeling indicate that AESIA improves adaptability under distribution shifts, reduces optimization instability, and enhances ensemble robustness compared to conventional deep learning pipelines. The architecture demonstrates strong potential for deployment in real-time signal intelligence systems requiring continuous learning and structural adaptation.