Search Results (21,251)

Hybrid approaches for conversational NLU commonly rely on cascading strategies, where model selection is performed after inference based on output confidence or uncertainty. Although effective, such post-hoc decision processes introduce redundant computation and accumulated latency due to sequential model execution. In this paper, we propose a pre-inference routing framework that selects an appropriate model before executing any candidate NLU model and without relying on candidate-model confidence or uncertainty. Instead of relying on output-dependent signals, we model NLU difficulty as a multi-dimensional representation of the joint intent recognition and slot extraction task, thereby distinguishing the proposed approach from prior post-hoc routing methods that rely primarily on confidence or uncertainty. To further reflect real-world dialogue characteristics, we incorporate temporal conversational factors, including contextual dependency and topic transitions. Based on these features, a lightweight routing mechanism efficiently assigns each utterance to an appropriate model from a pool of domain-specialized and general-purpose models. Experimental results on single-domain turns show that the proposed method maintains competitive Semantic Accuracy while reducing high-capacity model invocation, cost, and latency, thereby improving inference efficiency. These results demonstrate that input-observable difficulty features can provide a practical basis for pre-inference model selection without relying on post-hoc cascading. Full article

With the expansion of urban public spaces and outdoor dining activities, users increasingly demand functional, comfortable, and intelligent outdoor dining facilities, yet traditional design methods rely on subjective manual investigation and struggle to capture real-time user needs. Therefore, this study proposes a product design framework combining online review mining with Artificial Intelligence Generated Content (AIGC). User requirements are first extracted from online reviews through text mining and Latent Dirichlet Allocation (LDA) topic modeling. Subsequently, Quality Function Deployment (QFD) maps these requirements to design features to prioritize key features. A mapping mechanism then translates these elements—such as sunshade and rain protection, shared dining experiences, and multifunctional barbecue facilities—into structured AIGC prompts for concept generation. Taking outdoor dining facilities in parks, scenic areas, and commercial outdoor dining spaces as case studies, the results demonstrate that the proposed framework improves the generated design concepts in terms of functional completeness, environmental adaptability, and structural rationality, leading to concept designs that better satisfy user requirements for outdoor dining facilities. The proposed framework provides a user demand-driven approach for systematically transforming user requirements into structured AIGC prompts for the concept design of public facilities. Full article

To address the difficulty of synergizing multi-source spatial data with geological text and the limited spatial reasoning of large language models (LLMs), this paper proposes an intention-driven hybrid semantic–spatial retrieval–augmented generation (RAG) method and a corresponding GIS visualization system. The method uses intent routing to direct queries to spatial parsing or text retrieval, extracts target entities, attribute constraints, and spatial relations from natural language via an LLM, and dynamically generates parameterized PostGIS (PostgreSQL Spatial Extension) queries through a rule-based parser, achieving deep coupling of semantic understanding and spatial computation. A spatial proximity verification module computes the minimum distances between target and reference entities, producing a verifiable target-reference list that provides precise spatial support for answers. The system implements a multi-source dynamic data management mechanism supporting unified heterogeneous data import, ArcGIS layer style parsing, adaptive point visualization, and user-defined mappings from data tables to geological entity types. It further integrates prospectivity prediction, geochemical association analysis, and intelligent QA into an end-to-end interactive GIS environment. Experimental results show that semantic filtering raises Precision@5 (Precision at rank 5) from 0.171 to 0.829, rule-based ranking improves NDCG@5 (Normalized Discounted Cumulative Gain at rank 5) by about 16%, and the spatial proximity verification module increases the spatial citation rate (distance coverage ratio) from 24.2% to 47.8% when computed over the 17 spatial-relation queries for which distance citations are applicable. Adding textual knowledge further boosts answer relevance to 0.863 while maintaining a comparable spatial citation rate (47.2% vs. 47.8%). To mitigate potential self-preference bias in the LLM-as-Judge setup, an independent evaluation using DeepSeek-V4-Flash was conducted, yielding high inter-evaluator agreement (Pearson r = 0.951 for faithfulness, 0.988 for relevance). These results suggest the method’s potential for query understanding, ranking optimization, and spatial interpretability, while also highlighting the need for larger-scale benchmarks and blinded expert evaluation. Full article

Hyperspectral image classification is a core task in remote sensing image analysis and understanding. Existing Transformer-based methods have achieved excellent performance but are limited by the quadratic computational complexity of the self-attention mechanism, while the high-dimensional redundancy of hyperspectral data and the difficulty in deeply integrating spatial–spectral features also restrict further performance improvement. To address these issues, we introduce the Mamba architecture based on state-space models into hyperspectral image classification and propose the DFMamba model. The main innovations include (1) constructing a Hyperspectral Spatial Attention Embed (HSAE) to achieve efficient channel compression and feature extraction via adaptive grouped convolution, depth-wise separable convolution, and spatial attention; (2) proposing a spatial–spectral dual-branch collaborative modeling mechanism, EnhancedBothMamba, which separately models global dependencies in the spatial and spectral branches and integrates their outputs through softmax-normalized learnable global weights together with a learnable residual scaling factor; and (3) building an improved classification head, ClsHead, with a multi-scale branch fusion strategy to fully exploit local and global feature information. The experimental results on four standard hyperspectral datasets demonstrate that DFMamba achieves overall accuracy (OA) of 97.41% on the Pavia University dataset, 92.25% on the HanChuan dataset, 95.12% on the HongHu dataset, and 94.98% on the Houston dataset. Under the adopted evaluation protocol, DFMamba obtains higher mean OA than MambaHSI and the other compared methods while retaining favorable computational efficiency. Full article

Lavender essential oil (LEO) possesses broad therapeutic potential, yet translating empirical knowledge into evidence-based medicine is hindered by the descriptive literature that conflates isolated monoterpene mechanisms with whole-oil efficacy. Addressing these critical shortcomings, this review presents a target-centric synthesis that explicitly delineates the molecular pathways of pure constituents (e.g., linalool, linalyl acetate) versus intact LEO matrices and standardized oral preparations (Silexan™). We systematically integrate LEO’s multi-target signaling networks across neuroregulatory, analgesic, anti-inflammatory, and skin-regenerative domains, while critically examining how genetic taxonomy, environmental stress, and green extraction technologies dictate chemotype diversity. Furthermore, we candidly address current evidence limitations, including pre-clinical predominance, publication bias, and clinical trial narrowness. Finally, we outline actionable translational strategies centered on chemotype-driven standardization, smart delivery systems, and a dual pharmacological paradigm that valorizes non-volatile processing byproducts. This synthesis establishes a rigorous theoretical foundation for LEO’s clinical translation and pharmaceutical standardization. Full article

In industrial equipment fault diagnosis, vibration and acoustic signals are highly complementary yet exhibit significant differences in frequency distribution and noise sensitivity. Traditional multimodal methods generally rely on homogeneous feature extractors and direct feature concatenation, which may fail to capture modality-specific characteristics and introduce irrelevant information during fusion. To address this, we propose a novel multimodal heterogeneous convolutional neural network framework. Specifically, separate 1D CNN branches are designed for vibration and acoustic signals. Their architectural differences are determined by the characteristics of each sensing modality. The vibration branch focuses on extracting high-level discriminative fault features, including impulse responses and modulated components from vibration signals, while the acoustic branch is designed to preserve fragile high-frequency details of acoustic signals. Furthermore, an adaptive cross-attention fusion module is introduced to dynamically model cross-modal dependencies, assigning Softmax-based weights to enhance dominant features and suppress noise. Experiments based on bearing fault experimental data demonstrate that the proposed heterogeneous architecture significantly outperforms traditional homogeneous models. The dynamic weighting mechanism effectively prevents inferior noisy modalities from degrading overall performance, achieving high diagnostic accuracy. Although validated on rolling bearing fault diagnosis, the proposed heterogeneous multimodal framework is not restricted to bearings and can be readily extended to other intelligent condition monitoring tasks involving heterogeneous sensor fusion, such as gearboxes, motors, and other rotating machinery. Full article

Background/Objectives: Romania’s National Health Insurance House (CNAS) reimbursement basket is the principal public financial-protection mechanism, yet whether it reflects the therapeutic services patients actually seek has not been tested against private-market offerings. This study compared the public basket with the private dental service portfolio, using the latter as an indirect, supply-side signal of expressed need rather than a direct measure of demand. Methods: In this cross-sectional study (November 2024–February 2025), the publicly listed portfolios of 420 private dental practices in Bucharest (n = 256), Cluj-Napoca (n = 104), and Iași (n = 60) were analyzed, stratified by size (0–3 vs. >3 employees). Practices were identified from CAEN 8623 records on listafirme.ro; portfolios were extracted from official websites displaying prices. Services were classified as functional or aesthetic by two independent raters (Cohen’s κ = 0.91), with disagreements resolved by consensus. Results: Across all municipalities and strata, approximately 53–68% of private services fell outside the CNAS basket. Critically, about 95–96% of private services were functional rather than aesthetic (4–5%), indicating that the gap reflects functional treatments patients seek and providers offer yet that remain unfunded—not elective demand. No statistically significant geographic differences emerged. Geographic location was not associated with portfolio breadth, whereas in multivariable models larger practices (>3 employees) independently offered approximately 33% more services. Conclusions: Because the analysis reflects advertised portfolio breadth rather than utilization, and a documented Romanian orientation toward reactive over preventive care, these hypothesis-generating findings make private supply a pragmatic, supply-side reference point for evidence-based revision of the CNAS basket, pointing to two directions directly supported by the data—aligning coverage with observed demand and administrative simplification of contracting. To our knowledge, this is the first benchmarking of the CNAS basket against private supply, relevant to other predominantly private European dental systems. Full article

For final-state quality inspection of three-dimensional stamped hairpin windings, existing studies still lack multimodal methods that integrate mechanical geometric constraints, prior-guided fusion, and decision interpretability. This study proposes a span-prior-guided explainable multimodal neural network method and develops SPIMA-Net. The final-state images were acquired at a fixed inspection station with a fixed camera position and imaging angle under a CCD vision light source. Final-state images are used as visual inputs, while geometric priors are constructed from span measurements and model-type information. A visual branch and a span branch extract image and prior features, and a span-prior-assisted gating mechanism modulates visual features to enable collaborative fusion. Experimental results show that SPIMA-Net achieves an accuracy of 98.14%, an F1-score of 96.55%, and an AUC of 0.9983 on the test set. Its nonconforming-class F1-score is improved by 10.44, 3.04, 6.27, 1.38, and 0.66 percentage points over the image-only, span-only, direct-fusion, SE-fusion, and CBAM-fusion models, respectively, while the total number of misclassifications decreases to five. Interpretability analysis shows that the model mainly focuses on span openings, end profiles, and local abnormal regions. Relative and absolute span deviations are identified as the main mechanical geometric factors affecting final-state quality classification. The proposed method provides a neuro-mechanical fusion approach that demonstrates high discriminative performance and engineering interpretability for hairpin winding quality inspection on the investigated industrial dataset. Full article

In rotating machinery monitoring, obtaining highly discriminative fault features from complex vibration signals remains a significant challenge for deep learning-based diagnostic models. In this paper, a novel intelligent fault diagnosis method named MSFormer is proposed. The MSFormer incorporates a parallel multi-scale Convolutional Neural Network (CNN) architecture and hierarchical Transformer modules to comprehensively process 1D vibration signals. By utilizing varying kernel sizes, the multi-scale CNN extracts both high-frequency local transient impulses and low-frequency global degradation trends. Subsequently, the Transformer modules are employed to model the long-range dependencies within the extracted feature sequences, effectively mitigating the interference of environmental noise. Extensive experiments are conducted on bearing fault experimental data to evaluate the proposed method. Four state-of-the-art models are compared under the same experimental settings. Quantitative metrics and qualitative tools are utilized for comprehensive evaluation. Experimental results indicate that MSFormer achieves a 92.67% accuracy, 92.54% F1-score, and 93.22% precision, demonstrating significant superiority. MSFormer provides a powerful and precise intelligent solution for mechanical fault diagnosis. Full article

Background: Extracting radiomic features from volumetric imaging data for lung cancer classification is limited by high dimensionality and the black-box nature of deep learning models. Traditional methods may overlook dependencies between slices, leading to the loss of sequential spatial information. Even when classification is correct, the model’s explanatory power may remain insufficient. Objective: This study proposes SpecAtt-Net, which processes spectral representations of slice-level radiomic data from computed tomography (CT) scans of lung cancer patients. A slice-based explainability approach is also presented to identify the slice groups used in model decision-making. Methods: Slice-level radiomic data were preprocessed, and slice-position–frequency representations were generated using the Short-Time Fourier Transform (STFT). This enables the model to capture spectral textures and spatial transitions from 720 × 288 feature maps. SpecAtt-Net employs a dual-attention mechanism to focus on distinctive radiomic features. To address the lack of slice-level labels, Slice-Wise Activation Mapping (SWAM), a post hoc interpretability technique, was developed. SWAM converts two-dimensional (2D) activation maps into one-dimensional (1D) importance vectors and provides a weakly supervised indication of the slice groups most relevant to the model’s decision. Results: SpecAtt-Net achieved competitive performance in accuracy, precision, recall, and F1-score compared with the evaluated reference architectures. SWAM highlighted slice-sequence regions contributing strongly to model predictions, providing preliminary evidence for interpretability. Conclusion: SpecAtt-Net provides a compact and interpretable approach for lung cancer subtype classification using attention-based feature modeling. SWAM offers an exploratory visualization of decision-relevant sequence regions and may support future radiological interpretation and validation studies. Full article

Background: The increasing prevalence of antifungal resistance among Candida albicans isolates necessitates the exploration of alternative antifungal strategies and novel molecular targets. Plant-derived bioactive compounds represent a promising source of antifungal agents; however, their chemical composition and mechanisms of action remain insufficiently characterized. Methods: Ethanolic extracts of Azadirachta indica leaves and Ficus benghalensis aerial roots were subjected to qualitative phytochemical screening, gas chromatography–mass spectrometry (GC–MS), and Fourier transform infrared (FTIR) analysis to characterize their bioactive constituents. Molecular docking studies were performed to evaluate the interaction of selected phytochemicals with C. albicans N-myristoyltransferase (PDB ID: 1IYK), a validated antifungal drug target. Results: Phytochemical screening revealed the presence of alkaloids, carbohydrates, and phenolic compounds in both extracts, while saponins were detected only in A. indica. GC–MS analysis demonstrated greater chemical diversity in A. indica, including fatty acids and phenolic derivatives, compared with F. benghalensis, which was dominated by terpenoids and long-chain hydrocarbons. FTIR analysis confirmed functional groups relevant to protein–ligand interactions. Molecular docking showed favorable binding interactions between several A. indica–derived compounds and N-myristoyltransferase, whereas compounds from F. benghalensis did not exhibit detectable binding under the conditions tested. Conclusions: The integrated phytochemical and in silico analyses provide insight into the antifungal potential of A. indica, suggesting possible interactions between identified phytochemicals and the selected drug target protein. This study highlights the value of combining chemical characterization with target-based computational screening in the rational exploration of plant-derived antifungal agents. Full article

Timely and accurate identification of fish diseases, along with the provision of corresponding treatment plans, is crucial for improving fish welfare and reducing economic losses in aquaculture facilities. To address issues such as low detection efficiency and excessive reliance on manual experience in aquaculture, this paper proposes an innovative diagnostic and treatment method based on the Octopus framework for model optimization. The CBAM (Convolutional Block Attention Module) attention mechanism is introduced into the YOLOv11n backbone to enhance feature extraction, while the Focus-CIoU (Focus-Complete Intersection over Union) loss function is adopted to improve the detection performance for small-target lesions and dense fish schools. Additionally, by integrating wireless sensor networks and the OTDA (Octopus-inspired Therapeutic Decision Agent) bionic agent, an integrated ‘detection-identification-perception-recommendation’ framework is constructed. The results showed that the optimized YOLOv11n model achieved a detection precision of 98.00%, a recall of 94.86%, and an F1 score of 96.40% in detecting ulcer disease, tail rot disease, and red skin disease. Furthermore, the mAP@50 was 97.58%, and the mAP@50–95 was 85.68%. Compared with the traditional YOLOv11n model, the optimized model achieved improvements of 1.39%, 1.48%, 1.43%, 1.4%, and 2.74% in precision, recall, F1 score, mAP@50, and mAP@50–95, respectively. The treatment recommendations produced by means of the Octopus bionic intelligent agent resulted in an average system response time of no more than 53 s, with the maximum observed response time not exceeding 60 s. The identification accuracy of OTDA remained above 87.1%. Full article

Aiming at addressing the problems of complex geometric features, high inter-class similarity, and insufficient single-scale information in semantic segmentation of point clouds for ancient building interior components, this paper takes the Ba Wang Academy of Shenyang Jianzhu University as the research object and proposes a Geometric Feature Multi-scale Network (GFMN). First, a point cloud dataset containing five types of components—windows, beams, walls, roofs, and columns—was collected and constructed using a FARO Focus3D X330 terrestrial laser scanner (FARO Technologies, Lake Mary, Florida, USA). Second, 46-dimensional handcrafted geometric descriptors were extracted for each discrete point from four aspects: basic point attributes, local geometric features, density and scale features, and multi-scale fusion. On this basis, features were grouped according to semantics and fed into independent encoding branches, where a gated adaptive fusion mechanism was employed to dynamically adjust the contribution of each branch, and optimization was performed in combination with a prototype classification head and a joint loss function. Experimental results show that the proposed method achieved an overall accuracy of 93.17% on the test set, significantly outperforming state-of-the-art methods such as PointNet, PointNet++, Point Transformer, and Point Cloud Transformer. This study provides an effective solution for high-precision semantic segmentation of ancient building interior components. Full article

Plant-derived natural products are essential and prominent contributors to drug discovery, especially as anticancer agents. Medicinal plants used in alternative therapy are often obscured by poor definitions of the underlying mechanisms behind their bioactivity. In this study, we investigated the cytotoxic and mechanistic effects of an enriched bioactive fraction derived from Mondia whitei. Bioactivity-guided fractionation was performed using C18 solid-phase extraction. The cytotoxic effects were evaluated using the MTT assay, while cellular morphology and mechanistic pathways were examined through microscopy, acridine orange staining, cathepsin-based assay, and immunoblotting of apoptosis- and autophagy-related proteins. Chemical profiling of the fraction was conducted using GC–MS analysis. The enriched fraction exhibited enhanced cytotoxicity at low microgram concentrations. Morphological assessment revealed prominent cytoplasmic vacuolation, while acridine orange staining indicated the accumulation of acidic vesicles. Cathepsin-based assays and immunoblot analysis of LC3-I/II confirmed lysosomal involvement and autophagy perturbation, whereas increased p62 levels suggested disruption of the autophagy–lysosome perturbation. In parallel, activation of intrinsic apoptosis was evidenced by the increased expression of caspase-9 and caspase-3. GC–MS profiling tentatively identified lupeol and cis-vaccenic acid as the major constituents of the fraction. The results from these studies demonstrate that the enriched fraction of Mondia whitei induced vacuolation-associated cytotoxicity through autophagy–lysosome perturbation and caspase-dependent apoptosis, providing mechanistic insight into its anticancer potential. Full article

The increasing accumulation of industrial solid waste and worsening groundwater pollution pose significant environmental challenges. This study introduces a Si-Ca-Fe-based ceramsite from solid wastes with exceptional Cd adsorption capacity. A comprehensive investigation was conducted on the phase evolution, adsorption properties, and underlying mechanisms of the synthesized ceramsite. The findings revealed that the optimum sintering temperature for the ceramsite, characterized by austenite and pyroxene, was 1140 °C, which balanced mechanical strength and Cd adsorption capacity. Remarkably, the ceramsite (6.0 g) was immersed in 5 L of a Cd(NO₃)₂ solution for 21 h under initial conditions (pH = 7 and temperature = 20 °C), and the ceramsite exhibited a notable Cd adsorption capacity of 5.47 mg/g (initial Cd concentration: 53.42 mg/L), with a maximum theoretical capacity of 9.32 mg/g according to the Langmuir isotherm. An in-depth analysis of adsorption kinetics, phase composition, and EDS data indicated that the primary adsorption mechanism was the zero-valent iron (ZVI) corrosion-driven reaction. This ZVI formed in situ under reducing conditions during the ceramsite’s preparation and subsequently aided in the precipitation of Cd(OH)₂. Additionally, the honeycomb structure of the ceramsite, containing fine pores (approximately 2–5 μm), enhanced physical adsorption via capillary action, further improving Cd removal. These insights offer a robust foundation for crafting efficient, solid waste-derived ceramsite tailored for heavy metal extraction from polluted water, presenting a compelling approach to concurrent waste recycling and environmental remediation. Full article