Search Results (8,205)

This study examines how green credit policies, specifically the green credit guidelines (GCGs) implemented in 2012, influence corporate sustainable innovation. This study employs a quasi-natural experiment approach, utilizing data from Chinese listed companies between 2005 and 2023, to examine the differential impact of the GCGs on high-polluting enterprises versus energy-efficient enterprises. The study uses a Difference-in-Differences (DID) methodology to explore how policy-induced changes in financing conditions affect firms’ innovation behaviors, particularly in terms of green patent applications. This study uses a mechanism to understand the role of R&D investment and access to long-term financing in driving these changes. And this study considers heterogeneity across firm ownership types and industry competition to investigate the varying effects of the GCGs. By identifying the causal pathways through which green credit policies influence innovation, this study contributes to the understanding of how environmental policies shape corporate behavior and innovation outcomes. Full article

This paper tackles the challenge of disassembly sequence planning (DSP) in energy-efficient remanufacturing by introducing an innovative hybrid optimization framework. The proposed model integrates a Dynamic Time-Varying CRITIC–Entropy (DTVCE) decision-making framework with an Improved Honey Badger Algorithm (IHBA) to optimize disassembly sequences under key operational criteria, including idle rate, line smoothness, and energy consumption. The DTVCE framework constructs a dynamic composite score by normalizing evaluation criteria across time slices and incorporating temporal discounting to capture the evolving importance of each factor. Meanwhile, by establishing a symmetric disassembly constraint matrix to restrict the disassembly sequence and integrating exploration and exploitation mechanisms to enhance the IHBA, the solution process is empowered to efficiently generate feasible disassembly sequences and fulfill task allocation across workstations while satisfying takt time constraints. Experimental validation demonstrates that the proposed framework significantly outperforms traditional disassembly optimization approaches in both energy efficiency and line balance performance. In a case study involving an automotive drive axle, the method achieved a near-optimal configuration using only eight workstations, leading to a marked reduction in both energy consumption and idle times. Sensitivity analysis further verifies the model’s robustness, showing stable convergence and consistent performance under varying takt times and energy parameters. Overall, this study contributes to the advancement of green remanufacturing by offering a scalable, data-driven, and adaptive solution to disassembly optimization—paving the way toward sustainable and energy-aware production environments. Full article

The rapid growth of e-commerce and the booming online fashion industry are driving growing user demand for sophisticated, compatible fashion outfits. As an emerging multimodal information retrieval technology, fashion compatibility modeling aims to predict the compatibility degree for any given outfit and provide complementary item recommendations for incomplete outfits. Although existing research has made significant progress in exploring fashion compatibility tasks from a multimodal perspective, it has yet to fully exploit the multimodal information and correlations among fashion items. To effectively tackle these challenges, a correlation-aware multimodal fusion network for fashion compatibility modeling is proposed. Long-distance correlated visual features are investigated during multimodal processing to enhance the quality of visual features. An improved dual-interaction mechanism is used to achieve deep multimodal fusion. Furthermore, we explore both negative and multi-scale correlations to obtain complex correlations among items and thereby enhance the accuracy of fashion compatibility assessment. Extensive experiments on real-world fashion datasets demonstrate that our method outperforms existing advanced benchmark models in AUC and ACC metrics. This indicates the efficiency of our model in enhancing fashion compatibility evaluation performance. Full article

Phytoplankton sinking is a pivotal process within the biological carbon pump that drives the vertical transport of organic carbon in the ocean. Its rates and underlying mechanisms directly influence the efficiency of the global carbon cycle and the potential for long-term sequestration. This review synthesizes current knowledge of phytoplankton sinking, encompassing buoyancy regulation mechanisms, environmental and physiological controls, methodological approaches such as settling column (SETCOL), and comparative evidence from laboratory and field studies. The aim is to elucidate the regulatory processes governing sinking and to provide a foundation for improving ecological models and refining estimates of carbon export. Evidence demonstrates that sinking rates vary considerably among phytoplankton groups, with nutrient limitation and aggregation emerging as critical modulators of export efficiency. By integrating results from experimental and in situ research, this review identifies unresolved questions and highlights priority areas: (1) quantitative coupling between aggregation and carbon flux; (2) mechanistic understanding of group-specific sinking responses; (3) integration of novel technologies, including in situ imaging and high-resolution modeling with established methods; and (4) development of interdisciplinary frameworks. Overall, this review consolidates current knowledge and underscores phytoplankton sinking as a crucial yet insufficiently resolved process within the marine carbon cycle. Full article

Object detection for autonomous vehicles under adverse weather conditions—such as rain, fog, snow, and low light—remains a significant challenge due to severe visual distortions that degrade image quality and obscure critical features. This paper presents YOLOv11-TWCS, an enhanced object detection model that integrates TransWeather, the Convolutional Block Attention Module (CBAM), and Spatial-Channel Decoupled Downsampling (SCDown) to improve feature extraction and emphasize critical features in weather-degraded scenes while maintaining real-time performance. Our approach addresses the dual challenges of weather-induced feature degradation and computational efficiency by combining adaptive attention mechanisms with optimized network architecture. Evaluations on DAWN, KITTI, and Udacity datasets show improved accuracy over baseline YOLOv11 and competitive performance against other state-of-the-art methods, achieving mAP@0.5 of 59.1%, 81.9%, and 88.5%, respectively. The model reduces parameters and GFLOPs by approximately 19–21% while sustaining high inference speed (105 FPS), making it suitable for real-time autonomous driving in challenging weather conditions. Full article

This paper reviews recent developments in the design optimization of electrical drive systems for electric vehicles (EVs) and proposes a pathway to develop next-generation AI design platforms that integrate system-level optimization methods and digital twins. First, a comprehensive review is presented to five design optimization models for EV motors, including multiphysics, multiobjective, multimode, robust, and topology optimization, as well as six efficient optimization strategies, such as multilevel optimization and AI-based approaches. Several recommendations on the practical application of these optimization strategies are also presented. Second, representative optimization methods for power converters and control systems of EV drives are summarized. Third, application-oriented and robust system-level design optimization strategies for EV drive systems are discussed. Finally, two proposals are presented and discussed for the design of next-generation EV drive systems and their integration with battery management systems. They are AI-powered automatic design optimization platforms that integrate large language models and a digital-twin-assisted system-level optimization framework. Two case studies on in-wheel motors and drive systems are also included to demonstrate the performance and effectiveness of various optimization methods. Full article

Nowadays, the automotive industry is primarily driven by the CO₂ policy that targets net zero carbon emissions by 2035 from passenger cars and commercial vehicles. The main path to achieve this goal is the implementation of electric powertrains with the energy stored in batteries, as the case for battery electric vehicles (BEV). However, this technology still faces some difficulties in terms of energy density, overall weight, charging time, and vehicle autonomy. From the other point of view, fuel cell electric vehicles (FCEV) offer the same advantages as BEV in terms of CO₂ reduction, providing better autonomy and lower refueling time. The energy demand by the electric powertrain strongly depends on the vehicle driving conditions as it directly affects energy consumption. In that context, the article aims to study the electrical energy demand of an ultra-energy efficient vehicle intended for a Shell eco-marathon competition in order to minimize hydrogen consumption. The study was carried out over a single lap on the racing track in Nogaro, France while applying the race rules from the competition in 2023. It includes a numerical evaluation of the vehicle resistance forces in different driving strategies and experimental validation on the propulsion test bench. Full article

Background/Objectives: Digital transformation is increasingly essential for healthcare organizations to improve operational efficiency and service quality. However, in developing countries such as Indonesia, many lower-middle-class hospitals lag due to limited financial, human, and infrastructural resources. This study examines how environmental dynamism—comprising regulatory changes, market pressures, and technological shifts—affects the digital capabilities of these hospitals. Methods: A quantitative, cross-sectional survey was conducted in Class C and D hospitals across Indonesia. Respondents included hospital directors, deputy directors, and IT heads. Data were collected through structured questionnaires measuring environmental dynamism and digital capability using a six-point Likert scale. Reliability testing yielded Cronbach’s alpha values above 0.96 for both constructs. Correlation analysis was performed to examine the relationship between environmental dynamism and digital capability. Results: Findings reveal a weak positive correlation (r = 0.1816) between environmental dynamism and digital capability. Although external factors such as policy regulations and technological competition encourage digital adoption, hospitals with limited internal resources struggle to translate these pressures into sustainable transformation. Key challenges include low ICT budgets, inconsistent staff training, and insufficient infrastructure. Conclusions: The results suggest that environmental change alone cannot drive digital readiness without internal capacity development. To foster resilient digital healthcare ecosystems, policy interventions should integrate regulatory frameworks with practical support programs that strengthen resources, leadership, and human capital in lower-middle-class hospitals. Full article

The development of sensor technology and deep learning has significantly improved the reliability and practicality of automatic driving technology. In an autonomous driving system, agent trajectory prediction is a complex challenge, which includes the understanding of different and unpredictable behavior patterns of various entities, including vehicles, pedestrians, and other traffic participants, among the data collected by sensors. In this paper, we deeply study two kinds of problems: Single-Agent Trajectory Prediction (SATP) and Multi-Agent Trajectory Prediction (MATP). We propose an innovative model, which combines the attention mechanism and integrates the Liquid Time-Constant (LTC) network with spatio-temporal features and the Mixture of Experts (MoE) framework, termed the Atten-LTC-MoE model. The model is general and extensible to support SATP and MATP problems in different autonomous driving environments. In order to improve computational efficiency and prediction accuracy, lane and agent vectorization, spatio-temporal features, agent data fusion, and trajectory endpoint generation technologies are studied. The effectiveness of our method is verified by comprehensive experiments on Argoverse and Interaction datasets. Our proposed model has been superior to the state-of-the-art models in terms of minADE₆ and minFDE₆ metrics and has shown significant advantages in the accuracy of agent trajectory prediction and computational performance. Full article

Digital retail is undergoing a paradigm shift driven by the deep integration of artificial intelligence (AI) and augmented reality (AR). Although prior studies have examined the independent effects of AI-based personalized recommendation (cognitive path) and AR-enabled immersion (experiential path), how their integration systematically shapes user behavior through internal psychological mechanisms remains an important unresolved theoretical gap. To address this gap, this study develops an integrated model grounded in the stimulus–organism–response (S-O-R) framework and trust transfer theory. Specifically, the model examines how personalized recommendation, as a dynamic external stimulus, influences users’ cognitive state (perceived usefulness) and experiential state (immersion); how the overall trust of users in the integrated platform can be used as a key boundary condition to adjust the transformation efficiency from the above stimulus to the internal state; and how the above cognitive and experiential states can ultimately drive the continued usage intention through the mediation of positive emotional response. Based on survey data from 400 Chinese consumers with AR shopping experience on Taobao, analyzed using structural equation modeling (SEM), the results indicate that (1) personalized recommendation positively affects both immersion and perceived usefulness; (2) platform trust significantly and positively moderates the effects of personalized recommendation on both immersion and perceived usefulness; (3) both cognitive and experiential states stimulate positive emotions, which in turn enhance continued usage intention, with perceived usefulness exerting a stronger effect; (4) a key theoretical finding is that there is a significant positive correlation between perceived usefulness and immersion, revealing the coupling of psychological paths in an integrated environment; however, immersion does not moderate the effect of personalized recommendation on emotional responses, suggesting that the current integration mode emphasizes the formation of a stable psychological structure rather than real-time interaction. This study makes three contributions to the existing literature. First, it extends the application of S–O–R theory in a complex technological environment by analyzing the “organism” as a parallel and related cognitive-experience dual path and confirming its coupling relationship. Second, it elucidates the enabling role of trust as a moderating mechanism rather than a direct antecedent, thereby enriching micro-level evidence for trust transfer theory in the context of technology integration. Finally, by contrasting path coupling with process regulation, this study provides a more detailed distinction for understanding the theoretical connotations and boundaries of AI–AR technology integration, which may mainly be a kind of structural integration. Full article

Recent advances in deep learning have had a significant impact on biomedical applications, driving precise actions in automated diagnostic processes. However, integrating neural networks into medical devices requires meeting strict requirements regarding computing power, energy efficiency, reconfigurability, and latency, essential conditions for real-time inference. Field-Programmable Gate Array (FPGA) architectures provide a high level of flexibility, performance, and parallel execution, thus making them a suitable option for the real-world implementation of machine learning (ML) and deep learning (DL) models in systems dedicated to the analysis of physiological signals. This paper presents a review of intelligent algorithms for electrocardiogram (ECG) signal classification, including Support Vector Machines (SVMs), Artificial Neural Networks (ANNs), Recurrent Neural Networks (RNNs), Long Short-Term Memory Networks (LSTMs), and Convolutional Neural Networks (CNNs), which have been implemented on FPGA platforms. A comparative evaluation of the performances of these hardware-accelerated solutions is provided, focusing on their classification accuracy. At the same time, the FPGA families used are analyzed, along with the reported performances in terms of operating frequency, power consumption, and latency, as well as the optimization strategies applied in the design of deep learning hardware accelerators. The conclusions emphasize the popularity and efficiency of CNN architectures in the context of ECG signal classification. The study aims to offer a current overview and to support specialists in the field of FPGA design and biomedical engineering in the development of accelerators dedicated to physiological signals analysis. Full article

The hard bottom layer in paddy fields significantly impacts the driving stability, operational quality, and efficiency of agricultural machinery. Continuously improving the precision and efficiency of unmanned, precision operations for paddy field machinery is essential for realizing unmanned smart rice farms. Addressing the unclear influence patterns of hard bottom contours on typical scenarios of agricultural machinery motion and posture changes, this paper employs a rice transplanter chassis equipped with GNSS and AHRS. It proposes methods for acquiring motion state information and hard bottom contour data during agricultural operations, establishing motion state expression models for key points on the machinery antenna, bottom of the wheel, and rear axle center. A correlation analysis method between motion state and hard bottom contour parameters was established, revealing the influence mechanisms of typical hard bottom contours on machinery trajectory deviation, attitude response, and wheel trapping. Results indicate that hard bottom contour height and local roughness exert extremely significant effects on agricultural machinery heading deviation and lateral movement. Heading variation positively correlates with ridge height and negatively with wheel diameter. The constructed mathematical model for heading variation based on hard bottom contour height difference and wheel diameter achieves a coefficient of determination R² of 0.92. The roll attitude variation in agricultural machinery is primarily influenced by the terrain characteristics encountered by rear wheels. A theoretical model was developed for the offset displacement of the antenna position relative to the horizontal plane during roll motion. The accuracy of lateral deviation detection using the posture-corrected rear axle center and bottom of the wheel center improved by 40.7% and 39.0%, respectively, compared to direct measurement using the positioning antenna. During typical vehicle-trapping events, a segmented discrimination function for trapping states is developed when the terrain profile steeply declines within 5 s and roughness increases from 0.008 to 0.012. This method for analyzing how hard bottom terrain contours affect the position and attitude changes in agricultural machinery provides theoretical foundations and technical support for designing wheeled agricultural robots, path-tracking control for unmanned precision operations, and vehicle-trapping early warning systems. It holds significant importance for enhancing the intelligence and operational efficiency of paddy field machinery. Full article

Automated driving technologies have the capability to significantly increase road safety by decreasing accidents and increasing travel efficiency. This research presents a decision-making strategy for automated vehicles that models both lane changing and double lane changing maneuvers and is supported by a Deep Reinforcement Learning (DRL) algorithm. To capture realistic driving challenges, a highway driving scenario was designed using the professional multi-body simulation tool IPG Carmaker software, version 11 with realistic weather simulations to include aspects of rainy weather by incorporating vehicles with explicitly reduced tire–road friction while the ego vehicle is attempting to safely and perform efficient maneuvers in highway and merged merges. The hierarchical control system both creates an operational structure for planning and decision-making processes in highway maneuvers and articulates between higher-level driving decisions and lower-level autonomous motion control processes. As a result, a Duel Deep Deterministic Policy Gradient (Duel-DDPG) agent was created as the DRL approach to achieving decision-making in adverse driving conditions, which was built in MATLAB version 2021, designed, and tested. The study thoroughly explains both the Duel-DDPG and standard Deep Deterministic Policy Gradient (DDPG) algorithms, and we provide a direct performance comparative analysis. The discussion continues with simulation experiments of traffic complexity with uncertainty relating to weather conditions, which demonstrate the effectiveness of the Duel-DDPG algorithm. Full article

This study examines the psychological mechanisms underlying service stickiness during the mature phase of the AI subscription economy, with particular attention to the paradox of subscription fatigue. To enhance conceptual clarity, AI-driven stimuli—specifically Algorithmic Curation and Technological Fluidity—are defined as perceived attributes at the individual level. Employing the Stimulus–Organism–Response (S-O-R) framework, the research explores how these perceived stimuli influence consumers’ internal states (Cognitive Efficiency and Serendipity) and subsequent behavioral responses (Service Stickiness). Empirical analysis using partial least squares structural equation modeling (PLS-SEM) on data from U.S. subscription service users yields several theoretical insights. Cognitive Efficiency is identified as the primary driver of stickiness, indicating that, in the context of subscription fatigue, the utilitarian benefit of reduced cognitive effort surpasses hedonic enjoyment. Additionally, the study identifies a “Frictionless Trap,” in which excessive Technological Fluidity negatively affects Serendipity (β = −0.195), suggesting that an entirely seamless experience may create a filter bubble that limits unexpected discovery. As a result, Serendipity does not significantly affect stickiness in the aggregate model. However, post hoc analysis demonstrates that Serendipity remains significant for high-income users, while Cognitive Efficiency is most influential in high-frequency utilitarian contexts, such as food services. These findings indicate that sustainable retention depends on reducing cognitive load while intentionally introducing friction to preserve opportunities for discovery. Full article

Small-object semantic segmentation remains challenging in urban driving scenes due to limited pixel occupancy, blurred boundaries, and the constraints imposed by lightweight deployment. To address these issues, this paper presents a lightweight semantic segmentation framework that enhances boundary awareness and contextual representation while maintaining computational efficiency. The proposed method integrates an edge-supervised boundary gating module to emphasize object boundaries, an efficient multi-scale context aggregation strategy to mitigate scale variation, and a lightweight feature enhancement mechanism for effective feature fusion. Edge supervision is introduced as an auxiliary regularization signal and does not require additional manual annotations. Extensive experiments conducted on multiple benchmark datasets, including Cityscapes, CamVid, PASCAL VOC 2012, and IDDA, demonstrate that the proposed framework consistently improves segmentation performance, particularly for small-object categories, while preserving a favorable balance between accuracy and efficiency. Full article