Carotid Atherosclerosis (CAS) is a key risk factor for cardiovascular diseases and stroke, requiring early and accurate detection. This study evaluates machine learning (ML) models to classify CAS severity using Doppler ultrasound-derived features. A dataset of ultrasound signals was processed using MATLAB, extracting key biomarkers such as spectral entropy, peak frequency shifts, spectral energy, and estimated blood flow velocity. Three classification models?Support Vector Machine (SVM), Random Forest (RF), and K-Nearest Neighbors (KNN)?were trained and optimized through hyperparameter tuning with five-fold cross-validation. Feature standardization and noise augmentation were applied to improve model generalization. Results indicate that SVM and Random Forest achieved the highest classification accuracy (83.33%), outperforming KNN (66.67%). The optimized SVM model with a linear kernel and fine-tuned hyperparameters demonstrated superior robustness in distinguishing CAS cases. Additionally, the study highlights the significance of frequency-domain features and velocity estimations in CAS diagnosis. The best-performing model was saved for future deployment in clinical decision support systems. This research underscores the potential of AI-driven diagnostic tools in enhancing non-invasive screening, facilitating early detection, and aiding in stroke prevention. Future work will explore deep learning approaches and multi-modal integration for improved diagnostic accuracy.

With the expansion of the EC market, the range of product choices has grown, making it easier for consumers to search for and compare products. However, the diversification of choices has complicated the evaluation criteria used by consumers when selecting products, making it difficult for companies to understand what elements influence purchase decisions. Traditional methods primarily analyze consumer interest factors at a single point in time, lacking approaches to track changes over time. This study addresses this gap by generating topics from review data annually and evaluating the similarity between these topics. Additionally, by analyzing changes within similar topics and their underlying causes, this research aims to verify whether the characteristics of a company's product are accurately recognized and evaluated by consumers.

Since Peirce pointed out the three types of inference (deduction, induction and abduction), prior researches were conducted to apply "abduction" to algorithm of machine learning so as to develop general artificial intelligence. Nevertheless, less effort has been done yet in this regard to utilize large language model (LLM) to this direction. Furthermore, no single use case of artificial intelligence in business, which is capable of abductive reasoning, has been scientifically reported so far. This concept paper describes a research plan to apply abduction based on LLM combined with retrieval augmented generation (RAG) to analysis and forecasting of international affairs, which could give tremendous positive impacts to decision making in business. While ordinary abductive reasoning only finds out hypothesis to observed fact, the herewith proposed system could help users to make relevant future scenarios in line with the abductively selected hypothesis. To realize the concept, the key is how to pick up controversial fact of importance in vast sphere of open source, so as to kick off the entire process of abduction with the appropriate algorithm and prompts.

This study introduces multiagent conversation models utilizing generative AI to overcome the challenges of traditional rule-based multiagent simulations (MAS) and proposes an appropriate evacuation instruction method through simulations considering psychological factors and information transmission during disasters. Using an earthquake as the disaster scenario, the correlation between agent conversations and evacuation behaviors was evaluated, and the optimal evacuation instructions were verified. Additionally, the evacuation instruction methods were analyzed, and the improvement of prediction accuracy was verified. This research deepens the understanding of evacuation behavior during disasters and contributes to the development of realistic disaster response simulations, offering insights for improving actual evacuation instruction methods.

This study investigates the impact of Mega Sport Events (MSEs) on innovation, as measured through patent applications, by examining financial expenditure, economic indicators, and Environmental, Social, and Governance (ESG) factors. This research analyzes data from six host nations between 2000-2020 utilizing advanced machine learning methodologies. The findings indicate that population demographics, operational costs, and sustainability metrics significantly influence the national innovation capacity. This study reveals that while well-strategically planned operational spending enhances patent applications or host innovation capability, excessive expenditure can impede innovation outcomes. Hance and ESG factors, such as social rights and renewable energy investment, demonstrate varied impacts contingent on the context. This study elucidates how strategic financial planning, sustainability practices, and social inclusion can maximize the long-term innovation benefits of MSE investments. These insights provide valuable guidance for policymakers and organizers for optimizing MSE resource allocation.

Amid rising concerns about global warming and finite energy resources, reevaluating fossil fuel usage and curbing greenhouse gas emissions are urgent priorities. Our previous research introduced a Japanese gas energy model that integrates Ene-Farm, the J-Credit Scheme, and Community-Based Rate Plans (CBRPs). In this study, we build upon that framework by factoring consumer heterogeneity into key decision parameters. Ene-Farm boosts energy efficiency while reducing CO? emissions and simultaneously increasing gas demand, whereas the J-Credit Scheme monetizes these emission reductions. CBRPs incentivize communal conservation efforts through discounts triggered when total emissions remain below a specified threshold. Our enhanced agent-based model simulates individual behaviors and interactions to evaluate outcomes at the community level. The findings reveal that this integrated approach fosters sustainable energy use by benefiting gas utilities, consumers, and the environment, while also accommodating diverse consumer responses.

This study aims to quantitatively analyze the impact of AI advancements on young women's career orientation and adaptive behavior.The theoretical foundation is Dr. Osborne's discussion in The Future of Employment. Free-response data from 2,657 individuals were collected and analyzed using machine learning-based natural language processing. Additionally, data on the career anchor index, which measures values related to occupational choice with eight distinct orientations, were obtained and statistically examined to explore its relationship with perspectives on AI adaptation. This study clarifies the correlation between career orientation and AI adaptation and constructs adaptation patterns. The findings provide insights that contribute to educational institutions' corporate human resource strategies and reskilling initiatives.

This study investigates the relationship between perceived partner similarity and relationship intimacy among university students. A web-based survey was administered at a private humanities university in Japan, yielding 110 respondents, with 44 participants reporting past or current romantic relationships. The survey instrument assessed partner similarity across multiple dimensions including attributes, personality traits, lifestyle factors, and preferences, while simultaneously measuring relationship satisfaction and perceived importance. Statistical analyses, including correlation and covariance structure analyses, indicated that although relationship satisfaction and importance demonstrated strong association, the majority of similarity dimensions failed to show significant correlation with intimacy measures. Only select factors, specifically fashion preferences and relationship prioritization, exhibited modest correlations. These results suggest that perceived partnersimilarity does not function as a robust predictor of relationship intimacy among university students.

The food delivery market has increasingly grown during the COVID-19 pandemic all over the world. The purpose of this study is to propose a research model to better understand diffusion of food delivery innovation before and after the COVID-19 pandemic in ASEAN countries. The paper presents structural and measurement models of the diffusion of food delivery innovation. The model is based on literature search of diffusion of innovation, e.g., the Technology Acceptance Model, and statistical analysis results conducted in ASEAN countries. The model includes specified moderators, e.g., eating situation, family structure, and national culture, in addition to ordinal factors from the previous research models. The future research includes statistical analyses on data gathered in Vietnam and Thailand, and extensions to global comparison research.