Search Results (33,607)

This study investigates factors influencing migrants’ decisions to enter Europe via Bulgaria or Greece along the Balkan route, using logistic regression and machine learning models on data from the International Organization for Migration (IOM) Flow Monitoring Survey (August 2022–June 2025, $n=5536$). We examine demographic variables (age), push factors (economic reasons, war/conflict, personal violence, limited access to services, and avoiding military service), and governance clusters derived from the World Bank’s Worldwide Governance Indicators (WGIs). An adapted migration gravity model incorporates corruption control as a key push–pull factor. Key findings indicate that younger migrants are significantly more likely to choose Bulgaria ($\beta \approx -0.021$, $p<0.001$), and governance clusters show that migrants from high-corruption origins (e.g., Syria and Afghanistan) prefer Bulgaria, likely due to governance similarities and facilitation costs. The Cluster Model achieves a slight improvement in fit (McFadden’s $R^2=0.008$, AIC = 7367) compared to the Base (AIC = 7374) and Interaction (AIC = 7391) models. Machine learning extensions using LASSO and Random Forests on a subset of data ($n=4429$) yield similar moderate performance (AUC: LASSO = 0.524, RF = 0.515). These insights highlight corruption’s role in route selection, offering policy recommendations for origin, transit, and destination phases. Full article

Recently, the live commerce market has experienced rapid growth, accompanied by increasingly intense competition. To improve business performance in this dynamic environment, it is essential to foster competent streamers and create effective commerce environments. Therefore, this study developed a research model based on the stimulus–organism–response (S-O-R) framework, focusing on streamer competencies and the commerce environment, to explore ways to effectively enhance live commerce business performance. Data for this study were collected through a questionnaire and analyzed using statistical techniques with 390 respondents. The results revealed that streamers’ competencies (expertise, demonstration skills, and interactive ability) significantly influence consumers’ internal states (perceived functional value of products and perceived trust in product recommendations), which in turn significantly influence purchase intentions. Moreover, the physical surroundings of the studio and the social surroundings, including peers’ perceptions of live commerce, were found to moderate the relationships between consumers’ internal states and their purchase intentions. This study holds academic significance in that it presents a model that effectively understands the mechanisms influencing viewers’ purchase decisions in live commerce contexts. The findings and practical implications discussed in this study are expected to provide valuable insights for developing strategies to enhance the performance of live commerce. Full article

Across digital platforms, large-scale assessment of customer sentiment has become integral to brand management, service recovery, and data-driven marketing in e-commerce. Still, most studies center on single-language settings, with bilingual and culturally diverse environments receiving comparatively limited attention. In this study, a bilingual sentiment analysis of consumer feedback on X (formerly Twitter) was conducted for three global quick-service restaurant (QSR) brands—McDonald’s, Burger King, and KFC—using 145,550 English tweets and 15,537 Turkish tweets. After pre-processing and leakage-safe augmentation for low-resource Turkish data, both traditional machine learning models (Naïve Bayes, Support Vector Machines, Logistic Regression, Random Forest) and a transformer-based deep learning model, BERT (Bidirectional Encoder Representations from Transformers), were evaluated. BERT achieved the highest performance (macro-F1 ≈ 0.88 in Turkish; ≈0.39 in temporally split English), while Random Forest emerged as the strongest ML baseline. An apparent discrepancy was observed between pseudo-label agreement (Accuracy > 0.95) and human-label accuracy (EN: 0.75; TR: 0.49), indicating the limitations of lexicon-derived labels and the necessity of human validation. Beyond methodological benchmarking, linguistic contrasts were identified: English tweets were more polarized (positive/negative), whereas Turkish tweets were overwhelmingly neutral. These differences reflect cultural patterns of online expression and suggest direct managerial implications. The findings indicate that bilingual sentiment analysis yields brand-level insights that can inform strategic and operational decisions. Full article

The rapid digitalization of banking services has transformed consumer interactions, necessitating a deeper understanding of the factors influencing online banking adoption. This research investigates the factors influencing consumer adoption in a country undergoing rapid digital transformation but still facing gaps in digital skills and infrastructure—Romania. The objective of the study is to analyze how key variables such as ease of use, security, speed, usefulness, and social pressure influence online banking behavior of Romanian consumers, especially the most digitally engaged ones. The study utilizes a multi-method empirical approach, hypothesis testing, binary logistic regression for prediction modeling, and segmentation analysis to offer a comprehensive view of customer behavior. The findings identify essential adoption drivers and separate customer profiles, providing useful information for financial organizations aiming to enhance their digital strategy. Perceived ease of use and perceived security are primary factors influencing adoption; nevertheless, decision tree analysis indicates that speed and usefulness have a more significant impact than logistic regression implies, but social pressure unexpectedly serves as an impediment. These results highlight the necessity for banks to customize their digital services, harmonizing security and user-friendliness with improved efficiency and usefulness to promote broader adoption in emerging digital economies like Romania. Full article

We propose a complexity-aware extension of the Course–Speed (CS) model that integrates an AIS-derived Traffic Complexity Index (TCI) based on change in speed (ΔV) and course (Δθ) to quantify maneuvering complexity in nonlinear crossing waters. The framework consists of: (i) data preprocessing and gating to ensure navigationally valid AIS samples; (ii) CS index computation using distribution-aware statistics; (iii) TCI estimation from variability in speed and course along intersecting flows; and (iv) an integrated CS–TCI for interpretable mapping and ranking. Using one year of AIS data from a high-density crossing area near the Korean coast, we show that the integrated index reveals crossing hotspots and small-vessel maneuvering burdens that are not captured by spatial regularity metrics alone. The results remain robust across reasonable parameter ranges (e.g., speed filter and σ-based weighting), and they align with operational observations in vessel traffic services (VTS). The proposed CS–TCI offers actionable decision support for port and coastal operations by jointly reflecting traffic smoothness and complexity; it can complement collision-risk screening and efficiency-oriented planning (e.g., energy and emission considerations). The approach is readily transferable to other crossing waterways and can be integrated with real-time monitoring to prioritize control actions in complex marine traffic environments. Full article

Accurately estimating total accident costs is essential for managing construction safety budgets. While direct costs are well-documented, indirect costs—such as productivity loss, material damage, and legal expenses—are difficult to predict and often overlooked. Traditional ratio-based methods lack accuracy due to variability across projects and accident types. This study introduces a two-tiered machine learning framework for real-time indirect cost estimation. In the first tier, classification models (decision tree, random forest, k-nearest neighbor, and XGBoost) predict total cost categories; in the second, regression models (decision tree, random forest, gradient boosting, and light-gradient boosting machine) estimate indirect costs. Using a dataset of 1036 construction accidents collected over two years, the model achieved accuracies above 87% in classification and an R² of 0.95 with a training MSE of 0.21 in regression. Compared to conventional statistical and single-step models, it demonstrated superior predictive performance, reducing average deviations to $362.63 and sometimes achieving zero deviation. This framework enables more precise, real-time estimation of hidden costs, promoting better safety investment, reduced financial risk, and adaptive learning through retraining. When integrated with a national accident cost database, it supports ongoing improvement and informed risk management for construction stakeholders. Full article

Retrieval-augmented generation (RAG) quality depends on how source documents are segmented before indexing; fixed-length chunks can split concepts or add noise, reducing precision. We evaluated whether proposition, semantic, and adaptive chunking improve accuracy and relevance for safer clinical decision support. Using a curated domain knowledge base with Gemini 1.0 Pro, we built four otherwise identical RAG pipelines that differed only in the chunking strategy: adaptive length, proposition, semantic, and a fixed token-dependent baseline. Thirty common postoperative rhinoplasty questions were submitted to each pipeline. Outcomes included medical accuracy and clinical relevance (3-point Likert scale) and retrieval precision, recall, and F1; group differences were tested with ANOVA and Tukey post hoc analyses. Adaptive chunking achieved the highest accuracy—87% (Likert 2.37 ± 0.72) versus baseline 50% (1.63 ± 0.72; p = 0.001)—and the highest relevance (93%, 2.90 ± 0.40). Retrieval metrics were strongest with adaptive (precision 0.50, recall 0.88, F1 0.64) versus baseline (0.17, 0.40, 0.24). Proposition and semantic strategies improved all metrics relative to baseline, though less than adaptive. Aligning chunks to logical topic boundaries yielded more accurate, relevant answers without modifying the language model, offering a model-agnostic, data-source-neutral lever to enhance the safety and utility of LLM-based clinical decision support. Full article

Advanced wastewater management systems are necessary to effectively direct severely contaminated initial rainwater runoff to the treatment facility only when pollutant concentrations are elevated during the initial flush event, thereby reducing the risk of water pollution caused by urban drainage systems. This necessitates the implementation of intelligent decision-making systems, forecasting, and monitoring. However, conventional “deterministic” forecasts are inadequate for making informed decisions in the presence of uncertainty regarding future values, despite the fact that a variety of modeling techniques have been employed to predict total suspended solids at specific locations. The literature contains a number of “probabilistic” forecasting approaches that take into account uncertainty. Among them, this paper proposes the Model Conditional Processor (MCP), which is well-known in hydrological, hydraulic, and climatological fields, to forecast the predictive probability density of total suspended solids based on one or more deterministic predictions. This is intended to address the issue. The decision to divert the first flush is subsequently guided by the predictive density and probabilistic thresholds. The effective implementation of the MCP approach is demonstrated in a real case study that is part of the USGS’s extensive and long-term stormwater monitoring initiative, based on observations of a real stormwater drainage system. The results obtained confirm that probabilistic approaches are suitable instruments for enhancing decision-making. Full article

The growing demand for fast and sustainable urban deliveries has accelerated exploration of the use of Unmanned Aerial Vehicles as viable logistics solutions for the last mile. This study investigates the integration of a distributed multi-agent system with a structured three-dimensional Urban Aerial Network (3D-UAN) for drone delivery operations. The proposed architecture models each drone as an autonomous agent operating within predefined air corridors and communication protocols. Unlike traditional approaches, which rely on simplified 2D models or centralized control systems, this research exploits a multi-layered 3D network structure combined with decentralized decision-making for improving scalability, safety, and responsiveness in complex environments. Through agent-based simulations, this study evaluates the operational performance of the proposed system under varying fleet size conditions, focusing on travel times and system scalability. Preliminary results demonstrate that the potential of this approach in supporting efficient, adaptive, resilient logistics within Urban Air Mobility frameworks depends on both the size of the fleet operating in the 3D-UAN and constraints linked to the current regulations and technological properties, such as the maximum allowed operational height. These findings contribute to ongoing efforts to define robust operational architectures and simulation methodologies for next-generation urban freight transport systems. Full article

Spatially explicit tools are essential for assessing biodiversity and guiding land use decisions at broad scales. This study presents a national-level approach for evaluating habitat quality as a proxy indicator for biodiversity, using Latvia as a case study. The approach integrates land use data, landscape structure, and habitat characteristics to generate habitat quality indices for agricultural and forest land. It addresses a common limitation in biodiversity planning, namely, the lack of consistent species-level data, by providing a comparative and conceptually robust way to assess how different land use types support biodiversity potential. The methodology was applied to assess current habitat quality and to simulate changes under two policy-relevant land use scenarios: the expansion of protected areas and a shift to organic farming. Results showed that expanding protected areas increased the national habitat quality index by 8.47%, while conversion to organic farming produced a smaller but still positive effect of 0.40%. Expansion of protected areas, therefore, led to a greater improvement in habitat quality compared to converting farmland to organic systems. However, both strategies offer complementary benefits for biodiversity at the landscape scale. Although national-level changes appear moderate, their spatial distribution enhances connectivity, particularly near existing protected areas, and may facilitate species movement. This approach enables national-level modelling of biodiversity outcomes under different policy measures. While it does not replace detailed species assessments, it provides a practical and scalable method for identifying conservation priorities, particularly in regions with limited biodiversity monitoring capacity. Full article

Solar panel deployment is vital to generate clean energy and reduce carbon emissions, but sustaining energy output requires regular monitoring and maintenance. This is particularly critical in countries with harsh environmental conditions, such as Qatar, where high dust density reduces solar radiation reaching panels, thereby lowering generating efficiency and increasing maintenance costs. This paper introduces a data-driven model that uses the relationship between generated and consumed energy to track changes in solar panel performance. By applying statistical analysis to real and simulated data, the model identifies when efficiency losses are within the parameters of normal variation (e.g., daily fluctuations) and when they are likely caused by dust accumulation or system ageing. The findings demonstrate that the model provides a reliable and cost-effective way to support timely cleaning and maintenance decisions. It offers decision-makers a practical tool to improve residential solar panel management, reducing unnecessary costs, and ensuring more consistent renewable energy generation. Full article

Monitoring PM2.5 in mining areas is essential for air quality management; however, most studies focus on single-step forecasts, limiting timely decision making. This work addresses the need for accurate multi-step PM2.5 prediction to support proactive pollution control in mining regions. So, a new model for multi-step PM2.5 time series forecasting is proposed, which is based on historical data such as the last day observed (LDO), retrieved data by correlation levels, and linear interpolation. As case studies, data from three environmental monitoring stations in mining areas of Peru were considered: Tala station near the Cuajone mine, Uchumayo near the Cerro Verde mine, and Espinar near the Tintaya mine. The proposed model was compared with benchmark models, including Long Short-Term Memory (LSTM), Bidirectional LSTM (BiLSTM), Gated Recurrent Unit (GRU), and Bidirectional GRU (BiGRU). The results show that the proposed model achieves results similar to those obtained by the benchmark models. The main advantages of the proposed model over the benchmark models lie in the amount of data required for predictions and the training time, which represents less than 0.2% of that required by deep learning-based models. Full article

Economic disinformation causes significant harm, resulting in substantial losses for the global economy. Each year, it is estimated that around USD 78 billion is lost due to the spread of false or misleading information, with a major share stemming from stock market fluctuations and misguided decisions. In Croatia, the rapid spread of economic misinformation further threatens decision-making and institutional credibility. The EkonInfoChecker project was established to address this issue by combining human fact-checking with AI-based detection. This paper presents the project’s AI component, which adapts English-language datasets (FakeNews Corpus 1.0 and WELFake) into Croatian, yielding over 170,000 articles in economics, finance, and business. We trained and evaluated six models—FastText, NBSVM, BiGRU, BERT, DistilBERT, and the Croatian-specific BERTić—using precision, recall, F1-score, and ROC-AUC. Results show that transformer-based models consistently outperform traditional approaches, with BERTić achieving the highest accuracy, reflecting its advantage as a language-specific model. The study demonstrates that AI can effectively support fact-checking by pre-screening economic content and flagging high-risk items for human review. However, limitations include reliance on translated datasets, reduced performance on complex categories such as satire and pseudoscience, and challenges in generalizing to real-time Croatian media. These findings underscore the need for native datasets, hybrid human-AI workflows, and governance aligned with the EU AI Act. Full article

Distributed denial of service (DDoS) attacks pose a serious risk to the operational stability of a network for companies, often leading to service disruptions and financial damage and a loss of trust and credibility. The increasing sophistication and scale of these threats highlight the pressing need for advanced mitigation strategies. Despite the numerous existing studies on DDoS detection, many rely on large, redundant feature sets and lack validation for real-time applicability, leading to high computational complexity and limited generalization across diverse network conditions. This study addresses this gap by proposing a feature-optimized and computationally efficient ML framework for DDoS detection and mitigation using benchmark dataset. The proposed approach serves as a foundational step toward developing a low complexity model suitable for future real-time and hardware-based implementation. The dataset was systematically preprocessed to identify critical parameters, such as packet length Min, Total Backward Packets, Avg Fwd Segment Size, and others. Several ML algorithms, involving Logistic Regression, Decision Tree, Random Forest, Gradient Boosting, and Cat-Boost, are applied to develop models for detecting and mitigating abnormal network traffic. The developed ML model demonstrates high performance, achieving 99.78% accuracy with Decision Tree and 99.85% with Random Forest, representing improvements of 1.53% and 0.74% compared to previous work, respectively. In addition, the Decision Tree algorithm achieved 99.85% accuracy for mitigation. with an inference time as low as 0.004 s, proving its suitability for identifying DDoS attacks in real time. Overall, this research presents an effective approach for DDoS detection, emphasizing the integration of ML models into existing security systems to enhance real-time threat mitigation. Full article

The increasing use of artificial intelligence (AI) in athlete health monitoring and injury prediction presents both technological opportunities and complex ethical challenges. This narrative review critically examines 24 empirical and conceptual studies focused on AI-driven injury forecasting systems across diverse sports disciplines, including professional, collegiate, youth, and Paralympic contexts. Applying an IMRAD framework, the analysis identifies five dominant ethical concerns: privacy and data protection, algorithmic fairness, informed consent, athlete autonomy, and long-term data governance. While studies commonly report the effectiveness of AI models—such as those employing decision trees, neural networks, and explainability tools like SHAP and HiPrCAM—few offers robust ethical safeguards or athlete-centered governance structures. Power asymmetries persist between athletes and institutions, with limited recognition of data ownership, transparency, and the right to contest predictive outputs. The findings highlight that ethical risks vary by sport type and competitive level, underscoring the need for sport-specific frameworks. Recommendations include establishing enforceable data rights, participatory oversight mechanisms, and regulatory protections to ensure that AI systems align with principles of fairness, transparency, and athlete agency. Without such frameworks, the integration of AI in sports medicine risks reinforcing structural inequalities and undermining the autonomy of those it intends to support. Full article