Search Results (25)

Background: Vision is a key sensory system for postural regulation; however, the effects of degraded visual input and complete visual occlusion on static balance are not fully understood. The aim of the present study was to compare postural control during single-leg stance under two reduced-vision conditions (eyes open in darkness vs. complete visual occlusion) in healthy young adults and examine the potential influence of sex and mild visual deficits. Materials and Methods: This within-subject laboratory study included 42 healthy young adults (21 males, 21 females; mean age 20.67 ± 0.48 years). Participants performed three valid 20 s single-leg stance trials on a force platform under two visual conditions: eyes open in darkness and complete visual occlusion using an opaque mask. The order of conditions was randomized and counterbalanced, and the mean value of the three valid trials under each condition was used for analysis. Postural sway outcome variables included CoP Area, Oscillation Width, Oscillation Height, Total Displacement, and Mean Velocity. A two-way mixed-design ANOVA examined the effects of visual condition and sex. Additional mixed ANCOVA analyses were performed using body weight as a covariate to verify whether the sex-related findings remained after adjustment for body weight. Exploratory subgroup analyses based on mild visual deficits were performed using independent-samples t-tests. Results: No significant overall main effect of visual condition was observed for any postural sway variable (all p > 0.05). However, a significant condition × sex interaction was found for CoP Area (F(1,40) = 9.910, p = 0.003, η²p = 0.199), indicating different response patterns between males and females across conditions. Significant main effects of sex were also found for Total Displacement (F(1,40) = 9.212, p = 0.004, η²p = 0.187) and Mean Velocity (F(1,40) = 9.090, p = 0.004, η²p = 0.185), with males showing higher values overall. The sex-related findings for CoP Area, Total Displacement, and Mean Velocity remained significant after adjustment for body weight. No significant sex effects were found for Oscillation Width or Oscillation Height, and no significant differences were observed between participants with and without mild visual deficits in either condition (all p > 0.05). Conclusions: Altered visual input did not produce a uniform overall effect on postural sway during single-leg stance in healthy young adults. Instead, the findings indicate a more differentiated pattern, with a sex-specific response for CoP Area and overall sex-related differences in Total Displacement and Mean Velocity that were not explained by body weight. Mild visual deficits were not associated with significant balance alterations under the present experimental conditions. These findings support a more nuanced interpretation of postural regulation under reduced visual input and highlight the importance of considering individual characteristics, particularly sex, in balance assessment. Full article

Satellite-observed greening in arid regions is often interpreted as ecological restoration success, yet this assessment may conflate natural recovery with agricultural expansion. We developed an Arid Remote Sensing Ecological Index (ARSEI) incorporating a Comprehensive Salinity Index (CSI) to address systematic biases in the traditional RSEI when applied to irrigated drylands. ARSEI scores were validated against MODIS Net Primary Production (NPP) ($R^2>0.75$ at the regional scale), confirming its reliability in capturing ecosystem productivity, while CSI effectively maps the upper-bound of surface salinization potential dictated by intrinsic soil properties. Applied to China’s Mu Us Sandy Land (2000–2024), the ARSEI reveals that 2327 km² of sandy land—54% of current cropland—was converted to agriculture, creating “assessment-induced false greening” signals. While the traditional RSEI increased monotonically (+135%), the ARSEI shows a nuanced pattern with plateau (2010–2015) and decline (2015–2020) phases, reflecting salinization risks masked by high crop NDVI. Optimal Parameters-Based Geographical Detector analysis demonstrates that Land Cover × Precipitation interactions (q = 0.28) drive spatial heterogeneity through irrigation-mediated water redistribution. The ARSEI provides a dialectical evaluation framework: acknowledging agricultural greening’s economic benefits while monitoring subsurface degradation risks. This study offers a critical methodological advance for sustainable land assessment in global drylands undergoing agricultural intensification. Full article

The evolution of non-invasive mechanical ventilation (NIV) from the iron lung of the 1950s to the use of sophisticated ventilators with mask apparatus has allowed for the optimal management of a wide range of respiratory disorders. NIV is now a mainstay in the management of acute, chronic and acute-on-chronic hypoxemic and hypercapnic respiratory failure from diverse etiologies. While NIV offers an effective approach to avoid invasive mechanical ventilation with its inherent risks of lung injury and sedation-related harms, it is a complex modality that requires a nuanced approach to management As the use of NIV has become ubiquitous, complex challenges are faced in the initiation, management and discontinuation of the treatment. We review complex clinical scenarios that present during liberation from non-invasive mechanical ventilation and an approach to successful weaning and liberation in these patient populations. Full article

Accurate classification of tomato ripening stages and quality estimation is pivotal for optimizing post-harvest management and ensuring market value. This study presents a rigorous comparative analysis of morphological and colorimetric features extracted via two state-of-the-art deep learning-based instance segmentation frameworks—Mask R-CNN and YOLOv8n-seg—and their efficacy in machine learning-driven ripening stage classification and quality prediction. Using 216 fresh-market tomato fruits across four defined ripening stages, we extracted 27 image-derived features per model, alongside 12 laboratory-measured physio-morphological traits. Multivariate analyses revealed that R-CNN features capture nuanced colorimetric and structural variations, while YOLOv8 emphasizes morphological characteristics. Machine learning classifiers trained with stratified 10-fold cross-validation achieved up to 95.3% F1-score when combining both feature sets, with R-CNN and YOLOv8 alone attaining 96.9% and 90.8% accuracy, respectively. These findings highlight a trade-off between the superior precision of R-CNN and the real-time scalability of YOLOv8. Our results demonstrate the potential of integrating complementary segmentation-derived features with laboratory metrics to enable robust, non-destructive phenotyping. This work advances the application of vision-based machine learning in precision agriculture, facilitating automated, scalable, and accurate monitoring of fruit maturity and quality. Full article

Online reviews on platforms such as Google Maps strongly influence consumer decisions. However, aggregated ratings mask nuanced opinions about specific aspects such as food, drinks, service, lounge, and price. This study presents a multi-aspect sentiment analysis framework for Arabic café reviews. Specifically, we combine machine learning (Linear SVC, Naïve Bayes, Logistic Regression, Decision Tree, Random Forest) and a Convolutional Neural Network (CNN) to perform aspect identification and sentiment classification. A rigorous preprocessing and feature-engineering with TF-IDF and n-gram was implemented and statistically validated through bootstrap confidence intervals and Friedman–Nemenyi significance tests. Experimental results demonstrate that Linear SVC with optimized TF-IDF tri-grams achieved a macro-F1 of 0.89 for aspect identification and 0.71 for sentiment classification. Meanwhile, the CNN model yielded a comparable F1 of 0.89 for aspect identification and a higher 0.76 for sentiment classification. The findings highlight that effective feature representation and model selection can substantially improve Arabic opinion mining. The proposed framework provides a reliable foundation for analyzing Arabic user feedback on location-based platforms and supports more interpretable and data-driven business insights. These insights are essential to enhance personalized recommendations and business intelligence in the hospitality sector. Full article

Natural elements such as vegetation, water bodies, and sky, together with artificial elements including buildings and paved surfaces, constitute the core of urban visual environments. Their perception at the pedestrian level not only influences city image but also contributes to residents’ well-being and spatial experience. This study develops a hybrid 3D visibility assessment framework that integrates a city-scale LOD1 solid model with high-resolution mobile LiDAR point clouds to quantify five visual exposure indicators. The case study area is Yueya Lake Park in Nanjing, where a voxel-based line-of-sight sampling approach simulated eye-level visibility at 1.6 m along the southern lakeside promenade. Sixteen viewpoints were selected at 50 m intervals to capture spatial variations in visual exposure. Comparative analysis between the solid model (excluding vegetation) and the hybrid model (including vegetation) revealed that vegetation significantly reshaped the pedestrian visual field by reducing the dominance of sky and buildings, enhancing near-field greenery, and reframing water views. Artificial elements such as buildings and ground showed decreased exposure in the hybrid model, reflecting vegetation’s masking effect. The calculation efficiency remains a limitation in this study. Overall, the study demonstrates that integrating natural and artificial elements provides a more realistic and nuanced assessment of pedestrian visual perception, offering valuable support for sustainable landscape planning, canopy management, and the equitable design of urban public spaces. Full article

Domain adaptation of pre-trained language models remains challenging, especially for specialized text collections that include distinct vocabularies and unique semantic structures. Existing contrastive learning methods frequently rely on generic masking techniques and coarse-grained similarity measures, which limit their ability to capture fine-grained, domain-specific linguistic nuances. This paper proposes an enhanced domain adaptation framework by integrating weighted contrastive learning guided by large language model (LLM) feedback and a novel topic-aware masking strategy. Specifically, topic modeling is utilized to systematically identify semantically crucial domain-specific terms, enabling the creation of meaningful contrastive pairs through three targeted masking strategies: single-keyword, multiple-keyword, and partial-keyword masking. Each masked sentence undergoes LLM-guided reconstruction, accompanied by graduated similarity assessments that serve as continuous, fine-grained supervision signals. Experiments conducted on an early 20th-century science fiction corpus demonstrate that the proposed approach consistently outperforms existing baselines, such as SimCSE and DiffCSE, across multiple linguistic probing tasks within the newly introduced SF-ProbeEval benchmark. Furthermore, the proposed method achieves these performance improvements with significantly reduced computational requirements, highlighting its practical applicability for efficient and interpretable adaptation of language models to specialized domains. Full article

Human Action Recognition has seen significant advances through transformer-based architectures, yet achieving a nuanced understanding often requires fusing multiple data modalities. Standard models relying solely on RGB video can struggle with actions defined by subtle motion cues rather than appearance. This paper introduces TransMODAL, a novel dual-stream transformer that synergistically fuses spatiotemporal appearance features from a pre-trained VideoMAE(Video Masked AutoEncoders) backbone with explicit skeletal kinematics from a state-of-the-art pose estimation pipeline (RT-DETR(Real-Time DEtection Transformer) + ViTPose++). We propose two key architectural innovations to enable effective and efficient fusion: a CoAttentionFusion module that facilitates deep, iterative cross-modal feature exchange between the RGB and pose streams, and an efficient AdaptiveSelector mechanism that dynamically prunes less informative spatiotemporal tokens to reduce computational overhead. Evaluated on three challenging benchmarks, TransMODAL demonstrates robust generalization, achieving accuracies of 98.5% on KTH, 96.9% on UCF101, and 84.2% on HMDB51. These results significantly outperform a strong VideoMAE-only baseline and are competitive with state-of-the-art methods, demonstrating the profound impact of explicit pose guidance. TransMODAL presents a powerful and efficient paradigm for composing pre-trained foundation models to tackle complex video understanding tasks by providing a fully reproducible implementation and strong benchmark results. Full article

This study analyzes the decision making that underlies the choice of terms we use to refer to companion animals. Three focus groups were developed, including participants from different demographic backgrounds who answered questions about their experience cohabitating with companion animals. The interviews were transcribed and analyzed using Thematic Analysis, carrying out a progressive refinement of the semantic contents until abstracting general themes. This study organizes the results based on three themes: (1) What you mean to me, contemplating human–animal relationships such as multispecies family, pet–owner relationship, human-like relationship, and objectivization; (2) Others’ surveillance, encompassing the role of social pressure in decision making; and (3) A good solution (here and now), focused on the strategic decisions made to balance the prior questions. The analysis shows that companion animals are usually considered part of the family, but that importance is not always freely communicated outside of the household. Often, participants try to nuance the importance of their companion animals, mask this relationship behind jokes, or tend to isolate themselves to avoid hostile social attention. These findings show the dilemmas faced by people who live with animals and point to the urgency of revising hegemonic discourses to improve the integration of these new family models in Spanish society. Full article

In this study, we propose a novel framework for time-series representation learning that integrates a learnable masking-augmentation strategy into a contrastive learning framework. Time-series data pose challenges due to their temporal dependencies and feature-extraction complexities. To address these challenges, we introduce a masking-based reconstruction approach within a contrastive learning context, aiming to enhance the model’s ability to learn discriminative temporal features. Our method leverages self-supervised learning to effectively capture both global and local patterns by strategically masking segments of the time-series data and reconstructing them, which aids in revealing nuanced temporal dependencies. We utilize learnable masking as a dynamic augmentation technique, which enables the model to optimize contextual relationships in the data and extract meaningful representations that are both context-aware and robust. Extensive experiments were conducted on multiple time-series datasets, including SleepEDF-78, 20, UCI-HAR, achieving improvements of 2%, 2.55%, and 3.89% each and similar performance on Epilepsy in accuracy over baseline methods. Our results show significant performance gains compared to existing methods, highlighting the potential of our framework to advance the field of time-series analysis by improving the quality of learned representations and enhancing downstream task performance. Full article

This investigation investigates the influence of a variety of data augmentation techniques on sentiment analysis in low-resource languages, with a particular emphasis on Bulgarian, Croatian, Slovak, and Slovene. The following primary research topic is addressed: is it possible to improve sentiment analysis efficacy in low-resource languages through data augmentation? Our sub-questions look at how different augmentation methods affect performance, how effective WordNet-based augmentation is compared to other methods, and whether lemma-based augmentation techniques can be used, especially for Croatian sentiment tasks. The sentiment-labelled evaluations in the selected languages are included in our data sources, which were curated with additional annotations to standardise labels and mitigate ambiguities. Our findings show that techniques like replacing words with synonyms, masked language model (MLM)-based generation, and permuting and combining sentences can only make training datasets slightly bigger. However, they provide limited improvements in model accuracy for low-resource language sentiment classification. WordNet-based techniques, in particular, exhibit a marginally superior performance compared to other methods; however, they fail to substantially improve classification scores. From a practical perspective, this study emphasises that conventional augmentation techniques may require refinement to address the complex linguistic features that are inherent to low-resource languages, particularly in mixed-sentiment and context-rich instances. Theoretically, our results indicate that future research should concentrate on the development of augmentation strategies that introduce novel syntactic structures rather than solely relying on lexical variations, as current models may not effectively leverage synonymic or lemmatised data. These insights emphasise the nuanced requirements for meaningful data augmentation in low-resource linguistic settings and contribute to the advancement of sentiment analysis approaches. Full article

Symbolic music understanding is a critical challenge in artificial intelligence. While traditional symbolic music representations like MIDI capture essential musical elements, they often lack the nuanced expression in music scores. Leveraging the advancements in multimodal pre-training, particularly in visual-language pre-training, we propose a groundbreaking approach: the Score Images as a Modality (SIM) model. This model integrates music score images alongside MIDI data for enhanced symbolic music understanding. We also introduce novel pre-training tasks, including masked bar-attribute modeling and score-MIDI matching. These tasks enable the SIM model to capture music structures and align visual and symbolic representations effectively. Additionally, we present a meticulously curated dataset of matched score images and MIDI representations optimized for training the SIM model. Through experimental validation, we demonstrate the efficacy of our approach in advancing symbolic music understanding. Full article

Change detection (CD) is the main task in the remote sensing field. Binary change detection (BCD), which only focuses on the region of change, cannot meet current needs. Semantic change detection (SCD) is pivotal for identifying regions of change in sequential remote sensing imagery, focusing on discerning “from-to” transitions in land cover. The emphasis on features within these regions of change is critical for SCD efficacy. Traditional methodologies, however, often overlook this aspect. In order to address this gap, we introduce a change-aware guided multi-task network (CGMNet). This innovative network integrates a change-aware mask branch, leveraging prior knowledge of regions of change to enhance land cover classification in dual temporal remote sensing images. This strategic focus allows for the more accurate identification of altered regions. Furthermore, to navigate the complexities of remote sensing environments, we develop a global and local attention mechanism (GLAM). This mechanism adeptly captures both overarching and fine-grained spatial details, facilitating more nuanced analysis. Our rigorous testing on two public datasets using state-of-the-art methods yielded impressive results. CGMNet achieved Overall Score metrics of 58.77% on the Landsat-SCD dataset and 37.06% on the SECOND dataset. These outcomes not only demonstrate the exceptional performance of the method but also signify its superiority over other comparative algorithms. Full article

Vehicle re-identification (vehicle ReID) is designed to recognize all instances of a specific vehicle across various camera viewpoints, facing significant challenges such as high similarity among different vehicles from the same viewpoint and substantial variance for the same vehicle across different viewpoints. In this paper, we introduce the RAND network, which is equipped with relation attention mechanisms, nuance, and disparity masks to tackle these issues effectively. The disparity mask specifically targets the automatic suppression of irrelevant foreground and background noise, while the nuance mask reveals less obvious, sub-discriminative regions to enhance the overall feature robustness. Additionally, our relation attention module, which incorporates an advanced transformer architecture, significantly reduces intra-class distances, thereby improving the accuracy of vehicle identification across diverse viewpoints. The performance of our approach has been thoroughly evaluated on widely recognized datasets such as VeRi-776 and VehicleID, where it demonstrates superior effectiveness and competes robustly with other leading methods. Full article

Leaf abnormalities pose a significant threat to agricultural productivity, particularly in medicinal plants such as Centella asiatica (Linn.) Urban (CAU), where they can severely impact both the yield and the quality of leaf-derived substances. In this study, we focus on the early detection of such leaf diseases in CAU, a critical intervention for minimizing crop damage and ensuring plant health. We propose a novel parallel-Variable Neighborhood Strategy Adaptive Search (parallel-VaNSAS) ensemble deep learning method specifically designed for this purpose. Our approach is distinguished by a two-stage ensemble model, which combines the strengths of advanced image segmentation and Convolutional Neural Networks (CNNs) to detect leaf diseases with high accuracy and efficiency. In the first stage, we employ U-net, Mask-R-CNN, and DeepNetV3++ for the precise image segmentation of leaf abnormalities. This step is crucial for accurately identifying diseased regions, thereby facilitating a focused and effective analysis in the subsequent stage. The second stage utilizes ShuffleNetV2, SqueezeNetV2, and MobileNetV3, which are robust CNN architectures, to classify the segmented images into different categories of leaf diseases. This two-stage methodology significantly improves the quality of disease detection over traditional methods. By employing a combination of ensemble segmentation and diverse CNN models, we achieve a comprehensive and nuanced analysis of leaf diseases. Our model’s efficacy is further enhanced through the integration of four decision fusion strategies: unweighted average (UWA), differential evolution (DE), particle swarm optimization (PSO), and Variable Neighborhood Strategy Adaptive Search (VaNSAS). Through extensive evaluations of the ABL-1 and ABL-2 datasets, which include a total of 14,860 images encompassing eight types of leaf abnormalities, our model demonstrates its superiority. The ensemble segmentation method outperforms single-method approaches by 7.34%, and our heterogeneous ensemble model excels by 8.43% and 14.59% compared to the homogeneous ensemble and single models, respectively. Additionally, image augmentation contributes to a 5.37% improvement in model performance, and the VaNSAS strategy enhances solution quality significantly over other decision fusion methods. Overall, our novel parallel-VaNSAS ensemble deep learning method represents a significant advancement in the detection of leaf diseases in CAU, promising a more effective approach to maintaining crop health and productivity. Full article