Search Results (633)

Background/Objectives: Emotion classification based on eye-movement features has become a widely adopted approach due to the simplicity of data acquisition and the strong association between ocular responses and emotional states. However, several challenges remain with regard to existing emotion recognition methods, including the relatively weak correlation between eye-movement features and emotional labels and the fact that the key features are not prominently presented. Methods: To address abovelimitations, this study proposes an improved CNN-transformer combined with enhanced deep canonical correlation analysis network (ICTD). The proposed method first performs preprocessing and reconstruction of raw eye-movement signals to extract informative features. Subsequently, convolutional neural networks (CNNs) and transformer architectures are employed to capture local and global feature, respectively. In addition, an incremental feature feedforward network is incorporated to enhance the transformer, enabling the model to assign higher importance to salient feature information. Finally, the extracted representations are processed through deep canonical correlation analysis based on cosine similarity in order to generate classification outcomes. Results: Experiments conducted on the SEED-IV, SEED-V, and eSEE-d datasets demonstrate that the proposed ICTD framework consistently outperforms baseline approaches and attains optimal classification results. (1) On the eSEE-d dataset, the results of three-category arousal and valence classification reach 81.8% and 85.2%, respectively; (2) on the SEED-IV dataset, the emotion four-category classification result reaches 91.2%; (3) finally, on the SEED-V dataset, the emotion five-category classification result reaches 85.1%. Conclusions: The proposed ICTD framework effectively improves feature representation and classification performance, showing strong potential for practical emotion recognition and physiological signal analysis. Full article

In frequency division duplex (FDD) massive multiple-input multiple-output orthogonal frequency division multiplexing (MIMO-OFDM) systems, the sub-array multi-user (MU) hybrid beamforming architecture is highly attractive because of its low hardware cost and high energy efficiency. However, downlink channel state information (CSI) acquisition and hybrid beamformer optimization remain challenging due to the large feedback overhead and the non-convexity of the beamforming design. To address these issues, we propose an end-to-end deep learning (DL) framework that jointly optimizes pilot training, CSI feedback, and hybrid beamforming, overcoming the limitations of conventional independently designed modules. At the core of the network, we introduce the star efficient location attention (StarELA) module, which combines the implicit high-dimensional representation capability of star operations (element-wise multiplication) with the fine-grained feature localization of efficient location attention (ELA). In addition, for wideband digital beamformer generation, we exploit inter-subcarrier correlation and design a frequency–domain seed generation and interpolation upsampling strategy, which significantly reduces network parameters. Experimental results show that the proposed method approaches the upper-bound performance of conventional hybrid beamforming with ideal CSI, while consistently outperforming existing benchmark methods. Full article

Music popularity prediction is a fundamental problem in music information retrieval, with important implications for digital content dissemination and creative decision-making on streaming platforms. In this study, music popularity prediction is formulated as a supervised regression problem, and six widely-used tree ensemble models (Random Forest, XGBoost, CatBoost, LightGBM, Extra Trees, and Decision Tree) are systematically evaluated using large-scale Spotify data. Among these models, Random Forest achieves the best predictive performance on this dataset (RMSE = 6.79, MAE = 5.10, and $R^2$ = 0.6658), followed by Extra Trees ($R^2$ = 0.6378) and Decision Tree ($R^2$ = 0.6328). Bayesian hyperparameter optimization based on a Tree-structured Parzen Estimator with an Expected Improvement acquisition function is conducted over 50 trials with 5-fold cross-validation to ensure robust model selection. Shapley value decomposition via SHAP analysis reveals that temporal recency dominates feature importance, far surpassing traditional musical attributes, while acoustic intensity (loudness) exhibits a U-shaped contribution pattern with optimal values at moderate intensity levels. Further SHAP dependence analysis uncovers non-linear relationships, indicating substantial popularity advantages for recent releases and optimal loudness levels around $-5$ to 0 dB. These findings suggest that streaming popularity is primarily governed by temporal exposure dynamics and production-related characteristics rather than intrinsic musical structure, offering both theoretical insights for music information retrieval research and suggestive empirical patterns that may inform future investigations into digital music ecosystems. Full article

High-fidelity acquisition of canopy phenotypic data is critical for the advancement of orchard Artificial Intelligence (AI). Yet, an improper Light Detection and Ranging (LiDAR) installation height (IH) frequently induces data occlusion and substantial measurement errors. To address this limitation, this study developed an information collection vehicle (ICV) integrated with a 16-channel three-dimensional (3D) LiDAR to determine the optimal LiDAR IH. Three representative LiDAR IHs (1.4 m, 2.0 m, and 2.6 m) were evaluated on spindle-shaped cherry trees under both forward and reverse driving strategies. Subsequently, a novel 12-zone refined evaluation framework was introduced to quantify localized errors that are conventionally obscured by traditional whole-canopy metrics. Results demonstrated a profound nonlinear relationship between IH and measurement accuracy. Specifically, the 2.0 m IH (approximating the canopy’s geometric center) emerged as the optimal setup, maintaining relative errors (REs) below 5% with minimal dispersion. Conversely, the 2.6 m IH caused lower-canopy volume REs to surge beyond 16% owing to restricted downward viewing angles. Additionally, reverse driving at higher IHs exacerbated mechanical vibrations via the “lever arm effect”, thereby significantly degrading point cloud registration accuracy. Ultimately, these findings underscore the critical necessity of aligning sensors with the canopy geometric center, supplying essential theoretical guidelines for the hardware design of future orchard robots. Full article

This retrospective study evaluated patient radiation dose during fluoroscopy-guided peripherally inserted central catheter (PICC) placement. A total of 1240 consecutive adult patients who underwent PICC placement between January 2023 and December 2024 were analyzed. Patient radiation dose indices, including air kerma (AK) and dose–area product (DAP), as well as fluoroscopy time and number of radiographic acquisitions, were obtained from the radiology information system. The mean and median AK were 2.47 mGy and 1.54 mGy, respectively, and the median DAP was 901.9 mGy·cm². The median fluoroscopy time was 1.9 min, and the median number of radiographic acquisitions was 1. Patient radiation dose during PICC placement was lower than the Japanese Diagnostic Reference Levels (Japan DRLs 2025). AK showed a strong positive correlation with fluoroscopy time (Spearman’s rank correlation, $\rho$ = 0.77), whereas correlations between AK and BMI or the number of radiographic acquisitions were weak. In some patients with high BMI, AK values exceeding 40 mGy were observed. These findings indicate that patient radiation dose during PICC placement is generally low but remains closely associated with fluoroscopy time. Optimization of the patient radiation dose should be considered, particularly for patients with high BMIs or those undergoing repeated PICC placements. Full article

Atractylodes macrocephala Rhizoma (AMR) is a frequently used medicinal herb for treating gastrointestinal disorders, with its quality influenced by factors such as origin and cultivation duration. Traditional quality control methods for AMR are time-consuming and invasive, making the development of faster and more efficient alternatives urgently needed. This study aims to utilize electronic nose (E-nose) and electronic tongue (E-tongue) to achieve the acquisition of odor–taste two-dimensional information of AMR. Integrating this approach with machine learning (ML) enables intelligent transformation from “experience-driven” to “data-driven” quality assessment, thereby developing a rapid and cost-effective quality control strategy for AMR. Feature-extraction and feature-selection techniques were employed to optimize back-propagation neural network (BPNN) classification and regression models for eight key quality markers, selecting the optimal feature subset. Additionally, nine machine-learning algorithms were applied with the optimal feature subset to establish classification models for different AMR grades and quantitative regression models for eight components based on E-nose and E-tongue data. The results demonstrated that the E-tongue combined with the k-nearest neighbors (KNN) algorithm could achieve a rapid classification of AMR grades with an accuracy of 95.56%. It also successfully predicted the contents of the extract, volatile oil, polysaccharides, atractylenolide I, atractylenolide II, atractylenolide III, bis-atractylenolide, and atractylone, with the test set’s coefficient of determination (R²) values of 0.8874, 0.8313, 0.9628, 0.8406, 0.8736, 0.8532, 0.7758, and 0.8101, respectively. In conclusion, this study provides a comprehensive and rapid solution for AMR grade classification and quality evaluation, significantly improving efficiency compared with traditional methods. This strategy holds substantial promise for real-world applications, as it enables a high-throughput, non-destructive screening of AMR in settings such as post-harvest processing and market quality surveillance, thereby supporting the sustainable and intelligent development of the herbal medicine industry. Full article

Dual-emission photoluminescence (PL) nanoprobes provide improved analytical performance to develop a reliable and sensitive sensing platform for quantifying chloramphenicol in pharmaceutical samples, thereby ensuring therapeutic efficacy and patient safety. In this work, a dual-emission PL sensing platform combining carbon dots (CDs) and AgInS₂ quantum dots (QDs) capped with mercaptopropionic acid (MPA) was developed for the quantitative determination of chloramphenicol, resorting to chemometric methods for data analysis. CDs, CdTe QDs, and AgInS₂ QDs were synthesized and individually evaluated considering their photostability, PL response and kinetics of their interaction with the antibiotic. After this, two dual-emission probes, CDs/MPA-CdTe and CDs/MPA-AgInS₂, were prepared and assessed based on the complementarity of their individual emission features. The obtained kinetic PL dataset was processed using unfolded partial least squares (U-PLS) in order to explore the multidimensional information of the dual-emission systems and to evaluate the performance of both sensing platforms. CDs/MPA-AgInS₂ probe was demonstrated to be the most efficient sensing platform due to its better compromise between sensitivity and photostability, as well as its cadmium-free composition, allowing the implementation of a more environmentally friendly analytical methodology. The optimization of the U-PLS models involved the assessment of the kinetic acquisition time and different spectral regions. The results showed that reliable, sensitive and efficient quantification could be achieved within the first 5 min of interaction and using the full emission spectrum of the sensing probe. Additionally, different interaction mechanisms were observed for each nanomaterial in the combined probe, being static for the CDs/chloramphenicol interaction and dynamic for MPA-AgInS₂/chloramphenicol interaction, which supports the synergetic behavior of the combined probe. The proposed methodology was effectively applied to commercial pharmaceutical formulations, yielding accurate results with good figures of merit. Therefore, this approach can be used as a relevant alternative to existing methodologies for a rapid, robust, and environmentally friendly method for chloramphenicol quantification. Full article

Geometallurgical modeling is pivotal for optimizing mining projects, yet the selection of an appropriate modeling strategy often relies on empirical experience rather than a systematic methodology. This paper introduces a novel systems-theoretic framework that formalizes geometallurgical modeling as an information acquisition problem under cost and uncertainty constraints. We propose a taxonomy of four fundamental strategies (S₀–S₃) defined by their use of direct measurement, interpolation, and regression to populate the key target variable geometallurgical ore type in a spatial block model. A generalized decision algorithm is developed to select the optimal strategy by evaluating economic feasibility and predictive accuracy against system characteristics such as deposit complexity, cost structure, and internal variable correlations. The framework demonstrates that the proxy-based strategy (S₂) generally offers the most robust balance between cost and accuracy for complex deposits. This work provides a scalable and generalizable approach applicable not only to geometallurgy but also to other domains involving spatial resource characterization under uncertainty, such as environmental monitoring and petroleum engineering. Full article

With the sharp increase in winter heating demand in northern China, the carbon emissions of combined heat and power (CHP) units remain high. This paper proposes a low-carbon optimal scheduling model for the system, considering the dynamic carbon-green certificate coupling and the multi-source energy supply of carbon capture and storage (CCS). Firstly, we analyze the thermal and electrical demand characteristics of the installed CCS and optimize its supply mode, and propose the corresponding low-carbon operation strategy for the CHP-CCS unit. Secondly, a dynamic coupling mechanism of carbon-green certificates with the acquisition volume of green certificates and the trading volume of carbon emission rights as the interaction medium should be constructed. The transmission effect of the historical trading volume on the current period should be achieved through dynamic prices, and a low-carbon economic scheduling model with the goal of minimizing operating costs should be established. Again, for the source-load uncertainty, by integrating the entropy weight method and the information gap decision theory, an IES optimization scheduling model based on the information gap decision theory method (IGDT) is established. Finally, through multi-scenario case simulation verification, the results confirmed that the proposed model can effectively improve the economy and low-carbon performance of the system. Full article

Efficient RFID spatial exploration in dynamic warehouse environments is challenging due to occlusions, sensing geometry constraints, and the weak coupling between information acquisition and navigation decisions. Many existing inventory robots treat RFID sensing as a passive data source during exploration, without explicitly optimizing sensing pose or prioritizing inventory-driven frontiers, which can result in incomplete coverage and redundant traversal. This paper presents ArmTenna, an articulated mobile robotic platform that formulates RFID inventory exploration as an active perception problem. The system integrates dual 4-DOF robotic arms carrying directional UHF RFID antennas and a 2-DOF neck-mounted RGB-D camera, enabling adaptive interrogation of candidate regions. We propose a multi-modal frontier exploration framework that combines newly detected EPC tags, average RSSI values, and vision-based product detections into a composite utility function for goal selection. By embedding articulated antenna control directly into the frontier evaluation loop, the robot tightly couples sensing geometry with exploration decisions. Experimental validation with 150 tagged items across three separated warehouse zones shows that ArmTenna achieves up to 97% map coverage, compared to 72% for a baseline platform, while reducing missed-tag regions. These results demonstrate that integrating active sensing pose control with multi-modal frontier evaluation provides an effective and scalable solution for RFID-driven warehouse inventory automation. Full article

Introduction: Rapid and reliable neurovascular imaging is critical for time-sensitive diagnosis in acute cerebrovascular disorders, yet conventional magnetic resonance imaging (MRI) workflows remain constrained by acquisition speed, motion sensitivity, and limited integration of physiological context. We introduce the Intelligent Neurovascular Imaging Engine (INIE), a sensor-informed, topology-aware framework that jointly optimizes accelerated data acquisition, physics-grounded reconstruction, and cross-scale physiological consistency. Methods: INIE combines adaptive sampling, structured low-rank (Hankel) priors, and topology-preserving objectives with multimodal physiological sensors and scanner telemetry, enabling phase-consistent gating and confidence-weighted reconstruction under realistic operating conditions. The framework was evaluated using synthetic phantoms, a translational porcine stroke recanalization model with repeated measures, and retrospective human datasets. Across $N_{\mathrm{runs}}=120$ acquisition–reconstruction runs derived from $N_{\mathrm{animals}}=18$ pigs with animal-level train/validation/test separation, performance was assessed using image quality, topological fidelity, and cross-modal consistency metrics. Multiple-comparison control was performed using Bonferroni/Holm–Bonferroni procedures. Results: INIE achieved acquisition acceleration exceeding 70% while maintaining high reconstruction fidelity (PSNR $\approx 35$–36 dB, SSIM $\approx 0.90$–0.92). Topology-aware analysis showed an approximately twofold reduction in Betti number deviation relative to baseline accelerated methods. Cross-modal validation in a PET subset demonstrated strong agreement between MRI-derived perfusion parameters and metabolic markers (Pearson $r\approx 0.9$). INIE improved large-vessel occlusion detection accuracy to approximately 93% and reduced automated time-to-decision to under three minutes. Conclusions: These results indicate that sensor-informed, topology-aware, closed-loop imaging improves the reliability and physiological consistency of accelerated neurovascular MRI and supports faster, more robust decision-making in acute cerebrovascular imaging workflows. Full article

Green building rating systems (GBRS) (e.g., LEED and BREEAM) assess sustainability in the built environment but require extensive data collection and processing. In this context, digitalization strategies, such as building information Modeling (BIM), enable centralized data management throughout the building’s life cycle. This study presents a PRISMA-based systematic literature review (SLR) of BIM-GBRS integration methods, identifying 83 articles and 13 reviews. The analysis is structured around three key phases defined to enable a systematic comparison of the existing approaches. Phase 1, “Data acquisition”, involves collecting the values of the investigated parameters either from the BIM model or through analysis software (e.g., Insight, One Click LCA) grouped into eight categories. Phase 2, “compliance verification”, focuses on comparing collected data with GBRS requirements using manual or automated tools (e.g., Dynamo). Phase 3, “optimization”, involves improving alternative design scenarios using tools such as plug-ins and MATLAB-based algorithms (e.g., NSGA-II, DWKNN). Emerging digital technologies (e.g., AI, digital twins, IoT) are analyzed to enable automated workflows, while interoperability is examined by distinguishing format-based (e.g., gbXML, IFC) and tool-based (e.g., APIs, VPL) approaches. The study identifies fragmented and limited interoperability in BIM-GBRS integration, highlighting the need for an automated end-to-end framework to support sustainability in the construction sector. Full article

Arable land quality is of the essence for the sustenance of grain production and food security. The continuous monitoring of the physical and chemical properties of arable land is instrumental in facilitating a comprehensive understanding of the evolution patterns of soil quality. This, in turn, provides fundamental evidence that is crucial for the optimization of cultivation practices, the establishment of appropriate plough layers, and the enhancement of soil quality. The near-surface sensing methodologies facilitate the acquisition of soil data at reduced scales, thus signifying a pivotal research trajectory for the procurement of soil-related information. The present study undertakes an examination of the current state of research on acquiring key parameters of farmland soil and provides an overview of the fundamental ground-level techniques employed for the assessment of farmland soil parameters. These techniques encompass single-parameter fixed-point detection, encompassing Soil Moisture Content (SMC), Soil Electrical Conductivity (EC), and nutrient analysis, multi-parameter fusion detection, and dynamic parameter monitoring. The study systematically reviews field sensing methods for major soil physicochemical parameters (such as SMC, Soil Penetration Resistance (SPR), EC, and nutrients) while analyzing the current application of Artificial Intelligence (AI) in soil parameter detection. The present paper proposes a developmental trajectory that shifts from “single-parameter static” to “multi-parameter dynamic” monitoring. This trajectory is proposed as a building upon the analysis of existing research. This evolution emphasizes intelligent algorithm-driven data enhancement to improve detection accuracy, forming a closed-loop progression of “dynamic detection—precise modeling—decision support”. This framework provides a reference for the advancement of soil sensing monitoring technologies and the scaling of precision agriculture applications. Full article

As global climate change intensifies and economic transformation progresses, the agro-pastoral ecotone of northern China faces dual challenges of stopping ecological degradation and enhancing farmers’ livelihoods. Yunzhou District in Shanxi Province represents a typical ecologically fragile area, where the daylily industry contributes significantly to improving livelihood resilience. This study categorized farmers into three types based on their dependence on daylily income: major-job farmers (50–90% income from daylily), sole agriculture farmers (≥90%), and side-job farmers (<50%). Using questionnaire survey data and the optimal parameter-based geographical detector method, we evaluated and compared the livelihood resilience levels of these farmer types and identified their key explanatory factors. The results showed that (1) major-job farmers exhibited the highest livelihood resilience index (0.165), followed by sole agriculture farmers (0.152), whereas side-job farmers exhibited the lowest (0.138); (2) significant differences in livelihood resilience existed across farmer types (p < 0.05); and (3) health status was a common key factor across all types, while factors such as traffic accessibility, policy awareness, social security, and information acquisition capability exhibited differential effects among groups. These findings provide empirical evidence to guide targeted livelihood interventions and sustainable transitions in the agro-pastoral ecotone. Full article

Compared with conventional financing approaches, supply chain financing demonstrates superior adaptability in risk management, greater cost-effectiveness in financial control, and enhanced efficiency in approval processes, owing to its deep integration with industrial chains. This investigation explores the intrinsic relationship between digital innovation and corporate supply chain financing. To ensure the rigor and reliability of the research conclusions, we adopt an empirical research method based on the OLS econometric regression model to systematically examine the relationship between digital innovation and supply chain financing. Our findings reveal that digital innovation positively influences corporate operations and information disclosure quality, thereby facilitating supply chain financing acquisition. Specifically, digital innovation enhances both Tobin’s Q and information transparency, which consequently improves firms’ access to supply chain financing. Furthermore, we observe pronounced heterogeneity in digital innovation’s impact on supply chain financing accessibility, with more pronounced effects observed in state-owned enterprises, mature firms, and regions with less developed legal frameworks. From the perspective of theoretical contributions, this study enriches the application scenario of signal transmission theory. We verify that operational improvement driven by digital innovation can serve as an effective signal to alleviate information asymmetry in supply chain financing. Meanwhile, we supplement the research on information asymmetry theory by providing a digital solution to mitigate information frictions between supply chain partners. In terms of practical contributions, we provide actionable insights for firms. Specifically, our findings guide firms to leverage digital innovation to improve supply chain financing accessibility. Additionally, these findings offer references for supply chain stakeholders and relevant authorities to optimize financing support mechanisms. Full article