Frontiers in Big Data最新文献

Introduction: The expanded BRICS block presents significant opportunities for SMEs (Small and Medium Enterprises), but challenges related to financial literacy and digital access hinder their potential. While global efforts emphasize financial literacy and digitization as key drivers of economic growth, especially in developing regions, their specific impact on SMEs in the BRICS block remains underexplored. This paper contributes to the literature by contextualizing how financial literacy and digital financial access influence SME sustainability and economic progress, particularly in light of ongoing efforts to bridge the digital divide.

Methods: Using Principal Component Analysis to reduce dimensionality, the study uses advanced Random Forest Tree modeling, to evaluate current practices in SME finance, credit access, and digitization.

Results: Results indicate that both financial literacy and digitalization play pivotal roles in driving sustainable economic development, with significant implications for policy interventions aimed at supporting SME growth in emerging economies.

Discussion: This study addresses the crucial intersection of SME financial literacy and digital financial access, focusing on their role in fostering economic development within the expanded BRICS block-a group now comprising major emerging economies that collectively face substantial disparities in financial inclusion. The study results are relevant not only for understanding the BRICS context but also for shaping global strategies toward inclusive financial systems and SME resilience in the digital era.

Introduction: Self-efficacy is a critical determinant of students' academic success and overall life outcomes. Despite its recognized importance, research on predictors of self-efficacy using machine learning models remains limited, particularly within Muslim societies. This study addresses this gap by leveraging advanced machine learning techniques to analyze key factors influencing students' self-efficacy.

Methods: An empirical dataset collected was used to examine self-efficacy among secondary school students in Muslim societies. Four machine learning algorithms-Decision Tree, Random Forest, XGBoost, and Neural Network-were employed to predict self-efficacy using two demographic variables and 10 socio-emotional, cognitive, and regulatory factors. The predictors included culturally relevant variables such as religious/spiritual beliefs and collectivist-individualist orientation. Model performance was assessed using root mean square error (RMSE) and r-squared (R ²) metrics to ensure reliability and validity.

Results: The results showed that Random Forest outperformed the other models in accuracy, as measured by R ² and RMSE metrics. Among the predictors, self-regulation, problem-solving, and a sense of belonging emerged as the most significant factors, contributing to more than half of the model's predictive power. Other variables such as gratitude, forgiveness, empathy, and meaning-making displayed moderate predictive value, while gender, emotion regulation, and collectivist-individualist orientation had minimal impact. Notably, religious/spiritual beliefs and regional factors showed negligible influence on self-efficacy predictions.

Discussion: This study enhances the understanding of factors influencing self-efficacy among students in Muslim societies and offers a data-driven foundation for developing targeted educational interventions. The findings highlight the utility of machine learning in education research, demonstrating its ability to uncover insights for equitable and effective decision-making. By emphasizing the importance of regulatory and socio-emotional factors, this research provides actionable insights to elevate student performance and well-being in diverse cultural contexts.

Introduction: Quantitative global or regional brain imaging measurements, known as imaging-specific or -derived phenotypes (IDPs), are commonly used in genotype-phenotype association studies to explore the genomic architecture of the brain and how it may be affected by neurological diseases (e.g., Alzheimer's disease), mental health (e.g., depression), and neurodevelopmental disorders (e.g., attention-deficit hyperactivity disorder [ADHD]). For this purpose, medical images have been used as IDPs using a voxel-wise or global approach via principal component analysis. However, these methods have limitations related to multiple testing or the inability to isolate high variation regions, respectively.

Methods: To address these limitations, this study investigates a localized, principal component analysis-like approach for dimensionality reduction of cross-sectional T1-weighted MRI datasets utilizing diffeomorphic morphometry. This approach can reduce the dimensionality of images while preserving spatial information and enables the inclusion of spatial locality in the analysis. In doing so, this method can be used to explore morphometric brain changes across specific components and spatial scales of interest and to identify associations with genome regions in a multivariate genome-wide association study. For a first clinical feasibility study, this method was applied to data from the Adolescent Brain Cognitive Development (ABCD) study, including adolescents with ADHD (n = 1,359), obsessive-compulsive disorder (n = 1,752), and depression (n = 1,766).

Results: Meaningful associations of specific morphometric features with genome regions were identified with the data and corresponded to previous found brain regions in the respective mental health and neurodevelopmental disorder cohorts.

Discussion: In summary, the localized, principal component analysis-like approach can reduce the dimensionality of medical images while still being able to identify meaningful local brain region alterations that are associated with genomic markers across multiple scales. The proposed method can be applied to various image types and can be easily integrated in many genotype-phenotype association study setups.

Introduction: The rapid escalation of cyber threats necessitates innovative strategies to enhance cybersecurity and privacy measures. Artificial Intelligence (AI) has emerged as a promising tool poised to enhance the effectiveness of cybersecurity strategies by offering advanced capabilities for intrusion detection, malware classification, and privacy preservation. However, this work addresses the significant lack of a comprehensive synthesis of AI's use in cybersecurity and privacy across the vast literature, aiming to identify existing gaps and guide further progress.

Methods: This study employs the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) framework for a comprehensive literature review, analyzing over 9,350 publications from 2004 to 2023. Utilizing BERTopic modeling, 14 key themes in AI-driven cybersecurity were identified. Topics were clustered and validated through a combination of algorithmic and expert-driven evaluations, focusing on semantic relationships and coherence scores.

Results: AI applications in cybersecurity are concentrated around intrusion detection, malware classification, federated learning in privacy, IoT security, UAV systems and DDoS mitigation. Emerging fields such as adversarial machine learning, blockchain and deep learning are gaining traction. Analysis reveals that AI's adaptability and scalability are critical for addressing evolving threats. Global trends indicate significant contributions from the US, India, UK, and China, highlighting geographical diversity in research priorities.

Discussion: While AI enhances cybersecurity efficacy, challenges such as computational resource demands, adversarial vulnerabilities, and ethical concerns persist. More research in trustworthy AI, standardizing AI-driven methods, legislations for robust privacy protection amongst others is emphasized. The study also highlights key current and future areas of focus, including quantum machine learning, explainable AI, integrating humanized AI and deepfakes.

Objective: Biologics are considered as a promising novel treatment option for patients with chronic rhinosinusitis who failed with the standard of care (medical therapy and surgical interventions). This bibliometric analysis was performed to explore cross-border collaboration, communication, and research frontiers on biologics in chronic rhinosinusitis.

Methods: Original research publications on biologics in chronic rhinosinusitis were retrieved from the Science Citation Index-Expanded (SCI-E) database in the Web of Science Core Collection between 2004 and 2023. Using CiteSpace and R software, the country/region, author, institution, journal, reference, and keywords were extracted to analyze the research focus and global trends in this field.

Results: Research articles exhibited a consistent rising trend from 2004 to 2023, especially the period between 2020 and 2023. Most articles were published by authors from the USA. The USA was the most cited country, enjoying the most active cooperation with other countries/regions. Bachert C owned the most publications and collaborations. Ghent University and Karolinska Institute had the most collaborations with other institutions. Journal of Allergy and Clinical Immunology and Allergy published the most articles and were the most co-cited journals. Research frontiers on biologics in chronic rhinosinusitis would focus on efficacy, quality of life, safety, children, management, etc.

Conclusions: This bibliometric analysis displayed the overall situation and global trend on biologics in chronic rhinosinusitis. The visualization analysis of publications could assist researchers rapidly in understanding the hotspots and trends. Further research is warranted to determine the long-term effects and side effects of biologics in chronic rhinosinusitis.

Introduction: Tech-enabled alternative micro-finance promotes income equality in growing BRICS and Austria across financial crises and pandemics. Are financial access and digital skills equally economically valuable? Our study uses inputs: Human Capital, Alternative Micro-finance, Digitization, Governance, and Entrepreneurship, GDP, inflation, population growth, pandemics, and economic crises using the global 2000-2022 to explain income equality using SWIID Gini disposable and market income index as outputs.

Methods: The study uses Principal component analysis for reducing data dimensionality and collinearity. The study uses OLS, Dynamic Mixed Model, and random forest tree, a machine learning technique, as models to model digitally enable micro-finance.

Results: RFT model diagnostics consistently were better than OLS and GMM. Reduced income inequalities resulted from public and private infrastructure investments, government policy interventions to fight pandemics, economic crises, and conflicts, as well as from expansion in GDP.

Discussion: The study concludes that digitally enabled micro-finance plays a crucial role in reducing income inequalities, particularly during times of crisis. Key policy implications include the need for government support in digital infrastructure to enhance financial inclusion. By pooling their resources, the BRICS block can empower micro-finance organizations to ameliorate disruptions from COVID-19 and economic crises.

Artificial intelligence (AI) technologies (re-)shape modern life, driving innovation in a wide range of sectors. However, some AI systems have yielded unexpected or undesirable outcomes or have been used in questionable manners. As a result, there has been a surge in public and academic discussions about aspects that AI systems must fulfill to be considered trustworthy. In this paper, we synthesize existing conceptualizations of trustworthy AI along six requirements: (1) human agency and oversight, (2) fairness and non-discrimination, (3) transparency and explainability, (4) robustness and accuracy, (5) privacy and security, and (6) accountability. For each one, we provide a definition, describe how it can be established and evaluated, and discuss requirement-specific research challenges. Finally, we conclude this analysis by identifying overarching research challenges across the requirements with respect to (1) interdisciplinary research, (2) conceptual clarity, (3) context-dependency, (4) dynamics in evolving systems, and (5) investigations in real-world contexts. Thus, this paper synthesizes and consolidates a wide-ranging and active discussion currently taking place in various academic sub-communities and public forums. It aims to serve as a reference for a broad audience and as a basis for future research directions.

Background: Accurate sentiment analysis and intent categorization of tobacco and e-cigarette-related social media content are critical for public health research, yet they necessitate specialized natural language processing approaches.

Objective: To compare pre-trained and fine-tuned Flan-T5 models for intent classification and sentiment analysis of tobacco and e-cigarette tweets, demonstrating the effectiveness of pre-training a lightweight large language model for domain specific tasks.

Methods: Three Flan-T5 classification models were developed: (1) tobacco intent, (2) e-cigarette intent, and (3) sentiment analysis. Domain-specific datasets with tobacco and e-cigarette tweets were created using GPT-4 and validated by tobacco control specialists using a rigorous evaluation process. A standardized rubric and consensus mechanism involving domain specialists ensured high-quality datasets. The Flan-T5 Large Language Models were fine-tuned using Low-Rank Adaptation and evaluated against pre-trained baselines on the datasets using accuracy performance metrics. To further assess model generalizability and robustness, the fine-tuned models were evaluated on real-world tweets collected around the COP9 event.

Results: In every task, fine-tuned models performed much better than pre-trained models. Compared to the pre-trained model's accuracy of 0.33, the fine-tuned model achieved an overall accuracy of 0.91 for tobacco intent classification. The fine-tuned model achieved an accuracy of 0.93 for e-cigarette intent, which is higher than the accuracy of 0.36 for the pre-trained model. The fine-tuned model significantly outperformed the pre-trained model's accuracy of 0.65 in sentiment analysis, achieving an accuracy of 0.94 for sentiments.

Conclusion: The effectiveness of lightweight Flan-T5 models in analyzing tweets associated with tobacco and e-cigarette is significantly improved by domain-specific fine-tuning, providing highly accurate instruments for tracking public conversation on tobacco and e-cigarette. The involvement of domain specialists in dataset validation ensured that the generated content accurately represented real-world discussions, thereby enhancing the quality and reliability of the results. Research on tobacco control and the formulation of public policy could be informed by these findings.