Search Results (3,250)

Data annotation serves as a critical foundation for artificial intelligence (AI) and machine learning (ML). Recently, AI agents powered by large language models (LLMs) have emerged as effective solutions to longstanding challenges in data annotation, such as scalability, consistency, cost, and limitations in domain expertise. These agents facilitate intelligent automation and adaptive decision-making, thereby enhancing the efficiency and reliability of annotation workflows across various fields. Despite the growing interest in this area, a systematic understanding of the role and capabilities of AI agents in annotation is still underexplored. This paper seeks to fill that gap by providing a comprehensive review of how LLM-driven agents support advanced reasoning strategies, adaptive learning, and collaborative annotation efforts. We analyze agent architectures, integration patterns within workflows, and evaluation methods, along with real-world applications in sectors such as healthcare, finance, technology, and media. Furthermore, we evaluate current tools and platforms that support agent-based annotation, addressing key challenges such as quality assurance, bias mitigation, transparency, and scalability. Lastly, we outline future research directions, highlighting the importance of federated learning, cross-modal reasoning, and responsible system design to advance the development of next-generation annotation ecosystems. Full article

Understanding vehicle emissions is essential for developing effective carbon reduction strategies in the transport sector. Conventional emission models often assume homogeneity and linearity, overlooking real-world asymmetries that arise from variations in vehicle design and powertrain configurations. This study explores how machine learning and explainable AI techniques can effectively capture both symmetric and asymmetric emission patterns across different vehicle types, thereby contributing to more sustainable transport planning. Addressing a key gap in the existing literature, the study poses the following question: how do structural and behavioral factors contribute to asymmetric emission responses in internal combustion engine vehicles compared to new energy vehicles? Utilizing a large-scale Spanish vehicle registration dataset, the analysis classifies vehicles by powertrain type and applies five supervised learning algorithms to predict CO₂ emissions. SHapley Additive exPlanations (SHAPs) are employed to identify nonlinear and threshold-based relationships between emissions and vehicle characteristics such as fuel consumption, weight, and height. Among the models tested, the Random Forest algorithm achieves the highest predictive accuracy. The findings reveal critical asymmetries in emission behavior, particularly among hybrid vehicles, which challenge the assumption of uniform policy applicability. This study provides both methodological innovation and practical insights for symmetry-aware emission modeling, offering support for more targeted eco-design and policy decisions that align with long-term sustainability goals. Full article

In this study, we examine the impact of mergers and acquisitions (M&As) on firm environmental performance, aiming to address the gap in research and guide firms, investors, and policymakers toward more environmentally conscious decision-making in M&A. Using panel data from Chinese A-share listed firms (2008–2022), we estimate a two-way fixed effect model. The Propensity Score Matching and the instrumental variable method address potential endogeneity concerns, and robustness checks validate the findings. We found that M&As have a significantly positive effect on firm environmental performance, with heterogeneous impacts across regions, industries, and M&A types. The environmental benefits are most pronounced in heavily polluting industries and hybrid M&A deals. Eastern China shows more modest improvements. The results of mechanism tests revealed that M&As enhance environmental performance primarily by boosting total factor productivity and fostering innovation. This study offers a novel perspective by linking M&A activities to environmental sustainability, enriching the literature on both M&As and corporate environmental performance. We show that even conventional M&A deals (not sustainability-focused) can improve environmental performance through operational synergies. Expanding beyond polluting industries, we reveal how sector characteristics shape M&A’s environmental impacts. We identify practical mechanisms through which standard M&A activities can advance sustainability goals, helping firms balance economic and environmental objectives. It provides empirical evidence from China, an emerging market with distinct institutional and regulatory contexts. The findings offer guidance for firms engaging in M&A to strategically improve sustainability performance. Policymakers can leverage these insights to design incentives for M&A in pollution-intensive industries, aligning economic growth with environmental goals. By demonstrating that M&As can enhance environmental outcomes, this study supports the potential for market-driven mechanisms to contribute to broader societal sustainability objectives, such as reduced industrial pollution and greener production practices. Full article

To improve collision risk prediction in high-traffic coastal waters and support real-time decision-making in maritime navigation, this study proposes a regional collision risk prediction system integrating the Computed Distance at Collision (CDC) method with an Adaptive Neuro-Fuzzy Inference System (ANFIS). Unlike Distance at Closest Point of Approach (DCPA), which depends on the position of Global Positioning System (GPS) antennas, Computed Distance at Collision (CDC) directly reflects the actual hull shape and potential collision point. This enables a more realistic assessment of collision risk by accounting for the hull geometry and boundary conditions specific to different ship types. The system was designed and validated using ship motion simulations involving bulk and container ships across varying speeds and crossing angles. The CDC method was used to define collision, almost-collision, and near-collision situations based on geometric and hydrodynamic criteria. Subsequently, the FIS–CDC model was constructed using the ANFIS by learning patterns in collision time and distance under each condition. A total of four input variables—ship speed, crossing angle, remaining time, and remaining distance—were used to infer the collision risk index (CRI), allowing for a more nuanced and vessel-specific assessment than traditional CPA-based indicators. Simulation results show that the time to collision decreases with higher speeds and increases with wider crossing angles. The bulk carrier exhibited a wider collision-prone angle range and a greater sensitivity to speed changes than the container ship, highlighting differences in maneuverability and risk response. The proposed system demonstrated real-time applicability and accurate risk differentiation across scenarios. This research contributes to enhancing situational awareness and proactive risk mitigation in Maritime Autonomous Surface Ship (MASS) and Vessel Traffic System (VTS) environments. Future work will focus on real-time CDC optimization and extending the model to accommodate diverse ship types and encounter geometries. Full article

Analyzing the two-phase flow behavior in bearing lubrication is crucial for understanding friction and wear mechanisms, optimizing lubrication design, and improving bearing operational efficiency and reliability. However, the complexity of oil–air two-phase flow in high-speed bearings poses significant research challenges. Currently, there is a lack of comparative studies employing different simulation strategies to address this issue, leaving a gap in evidence-based guidance for selecting appropriate simulation approaches in practical applications. This study begins with a comparative analysis between experimental and simulation results to validate the reliability of the adopted simulation approach. Subsequently, a comparative evaluation of different simulation methods is conducted to provide a scientific basis for relevant decision-making. Evaluated from three dimensions—adaptability to rotational speed conditions, research focuses (oil distribution and power loss), and computational economy—the findings reveal that FVM excels at medium-to-high speeds, accurately predicting continuous oil film distribution and power loss, while MPS, leveraging its meshless Lagrangian characteristics, demonstrates superior capability in describing physical phenomena under extreme conditions, albeit with higher computational costs. Economically, FVM, supported by mature software ecosystems and parallel computing optimization, is more suitable for industrial design applications, whereas MPS, being more reliant on high-performance hardware, is better suited for academic research and customized scenarios. The study further proposes that future research could adopt an FVM-MPS coupled approach to balance efficiency and precision, offering a new paradigm for multi-scale lubrication analysis in bearings. Full article

The introduction of mobile banking is essential in today’s financial sector, where technological innovation plays a critical role. To remain competitive in the current market, businesses must analyze client attitudes and perspectives, as these influence long-term demand and overall profitability. While previous studies have explored general adoption behaviors, limited research has examined how individual factors such as social influence, lifestyle compatibility, financial technology self-efficacy, and perceived usage cost affect mobile banking adoption among specific generational cohorts. This study addresses that gap by offering insights into these variables, contributing to the growing literature on mobile banking adoption, and presenting actionable recommendations for financial institutions targeting younger market segments. Using a structured questionnaire survey, data were collected from both users and non-users of mobile banking among the Gen Z population in the United States. The regression model significantly predicts mobile banking adoption, with an intercept of $-0.548$ ($p < 0.001$). Among the independent variables, perceived cost of usage has the strongest positive effect on adoption ($B=0.857$, $\beta =0.722$, $p < 0.001$), suggesting that adoption increases when mobile banking is perceived as more affordable. Social influence also has a significant positive impact ($B=0.642$, $\beta =0.643$, $p < 0.001$), indicating that peer influence is a central driver of adoption decisions. However, self-efficacy shows a significant negative relationship ($B=-0.343$, $\beta =-0.339$, $p < 0.001$), and lifestyle compatibility was found to be statistically insignificant ($p=0.615$). These findings suggest that reducing perceived costs, through lower fees, data bundling, or clearer communication about affordability, can directly enhance adoption among Gen Z consumers. Furthermore, leveraging peer influence via referral rewards, Partnerships with influencers, and in-app social features can increase user adoption. Since digital self-efficacy presents a barrier for some, banks should prioritize simplifying user interfaces and offering guided assistance, such as tutorials or chat-based support. Future research may employ longitudinal designs or analyze real-life transaction data for a more objective understanding of behavior. Additional variables like trust, perceived risk, and regulatory policies, not included in this study, should be integrated into future models to offer a more comprehensive analysis. Full article

Currently, various pruning strategies including different methods and distribution types are commonly used to reduce the number of FLOPs and parameters in deep learning models. However, their impact on actual energy savings remains insufficiently studied, particularly in resource-constrained settings. To address this, we introduce PruneEnergyAnalyzer, an open-source Python tool designed to evaluate the energy efficiency of pruned models. Starting from the unpruned model, the tool calculates the energy savings achieved by pruned versions provided by the user, and generates comparative visualizations based on previously applied pruning hyperparameters such as method, distribution type (PD), compression ratio (CR), and batch size. These visual outputs enable the identification of the most favorable pruning configurations in terms of FLOPs, parameter count, and energy consumption. As a demonstration, we evaluated the tool with 180 models generated from three architectures, five pruning distributions, three pruning methods, and four batch sizes, using another previous library (e.g. FlexiPrune). This experiment revealed the significant impact of the network architecture on Energy Reduction, the non-linearity between FLOPs savings and energy savings, as well as between parameter reduction and energy efficiency. It also showed that the batch size strongly influences the energy consumption of the pruned model. Therefore, this tool can support researchers in making pruning policy decisions that also take into account the energy efficiency of the pruned model. Full article

In this research project a large linear electromagnetic actuator (LLEA) was designed and manufactured. The electromagnetic performance was published in previous works, but in this paper we focus on the technological challenges related to the manufacturing in particular. This LLEA was based on the magnet-free switched-reluctance principle, having six effective energised stator “teeth” and four passive mover parts (4:6 ratio). Various aspects and challenges encountered during the manufacturing, transport, and assembly are discussed. Thermal expansion of steel contributed to the decision of the modular design, with each module having 1.3 m in length, with a 2 mm longitudinal dilatation gap. The initial prototype was tested with a 10.6 m length, with plans to extend the test track to 60 m, which was fully achievable due to the modular design and required 29 tons of electrical steel to be built. The stator laminations were cut by a bespoke progressive tool with stamping, and other parts by a CO₂ laser. Mounting was based on welding (back of the stator) and clamping plates (through insulated bolts). The linear longitudinal force was on the order of 8 kN, with the main air gap of 7.5–10 mm on either side of the mover. The lateral forces could exceed 40 kN and were supported by appropriate construction steel members bolted to the concrete floor. The overall mechanical tolerances after installation remained below 0.5 mm. The technology used for constructing this prototype demonstrated the cost-effective way for a semi-industrial manufacturing scale. Full article

Background/Objectives: The simulation of human movement offers transformative potential for the design of medical devices, particularly in understanding the cause–effect dynamics in individuals with neurological or musculoskeletal impairments. This study presents a simulation-driven framework to determine the optimal ankle–foot orthosis (AFO) stiffness for mitigating the risk of ankle sprains due to excessive subtalar inversion during high-impact activities, such as landing from a free fall. Methods: We employed biomechanical simulations to assess the influence of translational stiffness on subtalar inversion control, given that inversion angles exceeding 25 degrees are strongly correlated with injury risk. Simulations were conducted using a musculoskeletal model with and without a passive AFO; the stiffness varied in three anatomical directions. A Design of Experiments (DoE) approach was utilized to capture nonlinear interactions among stiffness parameters. Results: The results indicated that increased translational stiffness significantly reduced inversion angles to safer levels, though direction–dependent effects were noted. Based on these insights, we developed a 4D visualization tool that integrates simulation data with an interactive color–coded interface to depict ”safe design” zones for various AFO stiffness configurations. This tool supports clinicians in selecting stiffness values that optimize both safety and functional performance. Conclusions: The proposed framework enhances clinical decision-making and engineering processes by enabling more accurate and individualized AFO designs. Full article

Data visualization is a key activity in data-driven decision making and is gaining momentum in many organizational contexts. However, the role and contribution of both end-user development (EUD) and artificial intelligence (AI) technologies for data visualization and analytics are still not clear or systematically studied. This work investigates how effectively AI-supported EUD tools may assist visual analytics tasks in organizations. An exploratory case study with eight interviews with key informants allowed a deep understanding of data analysis and visualization practices in a large Italian company. It aimed at identifying the various professional roles and competencies necessary in the business context, understanding the data sources and data formats exploited in daily activities, and formulating suitable hypotheses to guide the design of AI-supported EUD tools for data analysis and visualization. In particular, the results of interviews with key informants yielded the development of a prototype of an LLM-based EUD environment, which was then used with selected target users to collect their opinions and expectations about this type of intervention in their work practice and organization. All the data collected during the exploratory case study finally led to defining a set of design guidelines for AI-supported EUD for data visualization. Full article

We present a model that integrates the mapping of the phenology and climatic suitability for the spotted lanternfly (SLF), Lycorma delicatula (White, 1845) (Hemiptera: Fulgoridae), to provide guidance on when and where to conduct surveillance and management of this highly invasive pest. The model was designed for use in the Degree-Day, Establishment Risk, and Phenological Event Maps (DDRP) platform, which is an open-source decision support tool to help to detect, monitor, and manage invasive threats. We validated the model using presence records and phenological observations derived from monitoring studies and the iNaturalist database. The model performed well, with more than >99.9% of the presence records included in the potential distribution for North America, a large proportion of the iNaturalist observations correctly predicted, and a low error rate for dates of the first appearance of adults. Cold and heat stresses were insufficient to exclude the SLF from most areas of the conterminous United States (CONUS), but an inability for the pest to complete its life cycle in cold areas may hinder establishment. The appearance of adults occurred several months earlier in warmer regions of North America and Europe, which suggests that host plants in these areas may experience stronger feeding pressure. The near-real-time forecasts produced by the model are available at USPest.org and the USA National Phenology Network to support decision making for the CONUS. Forecasts of egg hatch and the appearance of adults are particularly relevant for surveillance to prevent new establishments and for managing existing populations. Full article

Emerging markets face growing pressures to integrate sustainable English business practices while maintaining economic growth, particularly in addressing environmental challenges and achieving carbon neutrality goals. English Financial information extraction becomes crucial for supporting green finance initiatives, Environmental, Social, and Governance (ESG) compliance, and sustainable investment decisions in these markets. This paper presents FinATG, an AI-driven autoregressive framework for extracting sustainability-related English financial information from English texts, specifically designed to support emerging markets in their transition toward sustainable development. The framework addresses the complex challenges of processing ESG reports, green bond disclosures, carbon footprint assessments, and sustainable investment documentation prevalent in emerging economies. FinATG introduces a domain-adaptive span representation method fine-tuned on sustainability-focused English financial corpora, implements constrained decoding mechanisms based on green finance regulations, and integrates FinBERT with autoregressive generation for end-to-end extraction of environmental and governance information. While achieving competitive performance on standard benchmarks, FinATG’s primary contribution lies in its architecture, which prioritizes correctness and compliance for the high-stakes financial domain. Experimental validation demonstrates FinATG’s effectiveness with entity F1 scores of 88.5 and REL F1 scores of 80.2 on standard English datasets, while achieving superior performance (85.7–86.0 entity F1, 73.1–74.0 REL+ F1) on sustainability-focused financial datasets. The framework particularly excels in extracting carbon emission data, green investment relationships, and ESG compliance indicators, achieving average AUC and RGR scores of 0.93 and 0.89 respectively. By automating the extraction of sustainability metrics from complex English financial documents, FinATG supports emerging markets in meeting international ESG standards, facilitating green finance flows, and enhancing transparency in sustainable business practices, ultimately contributing to their sustainable development goals and climate action commitments. Full article

This study presents a comprehensive analysis of CO₂ trapping mechanisms in subsurface reservoirs by integrating numerical reservoir simulations, geochemical modeling, and machine learning techniques to enhance the design and evaluation of carbon capture and storage (CCS) strategies. A two-dimensional reservoir model was developed to simulate CO₂ injection dynamics under realistic geomechanical and geochemical conditions, incorporating four primary trapping mechanisms: residual, solubility, mineralization, and structural trapping. To improve computational efficiency without compromising accuracy, advanced machine learning models, including random forest, gradient boosting, and decision trees, were deployed as smart proxy models for rapid prediction of trapping behavior across multiple scenarios. Simulation outcomes highlight the critical role of hysteresis, aquifer dynamics, and producer well placement in enhancing CO₂ trapping efficiency and maintaining long-term storage stability. To support the credibility of the model, a qualitative validation framework was implemented by comparing simulation results with benchmarked field studies and peer-reviewed numerical models. These comparisons confirm that the modeled mechanisms and trends align with established CCS behavior in real-world systems. Overall, the study demonstrates the value of combining traditional reservoir engineering with data-driven approaches to optimize CCS performance, offering scalable, reliable, and secure solutions for long-term carbon sequestration. Full article

Despite rapid advances in robot learning, the coordination of closed-loop manipulation in cluttered environments remains a challenging and relatively underexplored problem. We present a novel two-level hierarchical architecture for a depth vision-equipped robotic arm that integrates pushing, grasping, and high-level decision making. Central to our approach is a prioritised action–selection mechanism that facilitates efficient early-stage learning via behaviour cloning (BC), while enabling scalable exploration through reinforcement learning (RL). A high-level decision neural network (DNN) selects between grasping and pushing actions, and two low-level action neural networks (ANNs) execute the selected primitive. The DNN is trained with RL, while the ANNs follow a hybrid learning scheme combining BC and RL. Notably, we introduce an automated demonstration generator based on oriented bounding boxes, eliminating the need for manual data collection and enabling precise, reproducible BC training signals. We evaluate our method on a challenging manipulation task involving five closely packed cubic objects. Our system achieves a completion rate (CR) of 100%, an average grasping success (AGS) of 93.1% per completion, and only 7.8 average decisions taken for completion (DTC). Comparative analysis against three baselines—a grasping-only policy, a fixed grasp-then-push sequence, and a cloned demonstration policy—highlights the necessity of dynamic decision making and the efficiency of our hierarchical design. In particular, the baselines yield lower AGS (86.6%) and higher DTC (10.6 and 11.4) scores, underscoring the advantages of content-aware, closed-loop control. These results demonstrate that our architecture supports robust, adaptive manipulation and scalable learning, offering a promising direction for autonomous skill coordination in complex environments. Full article

Accurate estimation of biomass higher heating value (HHV) is crucial for designing efficient bioenergy systems. In this study, we developed a Backpropagation artificial neural network (ANN) that predicts HHV from routine proximate/ultimate composition data. The network (9-6-6-1 architecture, trained for 15,000 epochs with learning rate 0.3 and momentum 0.4) was calibrated on 99 diverse Spanish biomass samples (inputs: moisture, ash, volatile matter, fixed carbon, C, H, O, N, S). The optimized ANN achieved strong predictive accuracy (validation R² ≈ 0.81; mean squared error ≈ 1.33 MJ/kg; MAE ≈ 0.77 MJ/kg), representing a substantial improvement over 54 analytical models despite the known complexity and variability of biomass composition. Importantly, in direct comparisons it significantly outperformed 54 published analytical HHV correlations—the ANN achieved substantially higher R² and lower prediction error than any fixed-form formula in the literature. A sensitivity analysis confirmed chemically intuitive trends (higher C/H/FC increase HHV; higher moisture/ash/O reduce it), indicating the model learned meaningful fuel-property relationships. The ANN thus provided a computationally efficient and robust tool for rapid, accurate HHV estimation from compositional data. Future work will expand the dataset, incorporate thermal pretreatment effects, and integrate the model into a user-friendly decision-support platform for bioenergy applications. Full article