Search Results (778)

Self-regulatory foraging behavior in honey bees (Apis mellifera) was investigated using the framework of Perceptual Control Theory (PCT). We developed a PCT-based model to describe how bees maintain goal-directed behavior, specifically targeting a sucrose-rich feeding site while overcoming a wind disturbance. In a controlled experiment, we found that 13 of 14 bees could successfully adjust their flight paths to overcome the disturbance and consistently reach the feeding target. While they demonstrated a great deal of individual variability regarding how they overcame the wind across experimental trials, they did so by finally adopting a headwind (i.e., flying into the wind) approach pattern rather than tailwind or crosswind approach patterns. These results support the application of PCT to the study of behavior in honey bees, which can be regarded as self-regulative (i.e., non-linear and dynamic) rather than as linear sequences of inputs and outputs. Given that such dynamic models are concerned with the functions or purposes of behavior, they may also be classified as teleonomic. Full article

Mobility-as-a-Service (MaaS) represents a transformative shift in transportation, enabling users to plan, book, and pay for diverse mobility services via a unified digital platform. While previous research has explored factors influencing MaaS adoption, few studies have addressed users’ perspectives, particularly concerning data privacy and cyber security. To address this gap, we conducted an online survey with 320 UK-based participants recruited via Prolific. This study examined psychological, demographic, and perceptual factors influencing individuals’ willingness to adopt MaaS, focusing on cyber security and privacy attitudes, as well as perceived benefits and costs. The results of a hierarchical linear regression model revealed that trust in how commercial websites manage personal data positively influenced willingness to use MaaS, highlighting the indirect role of privacy and security concerns. However, when additional predictors were included, this effect diminished, and perceptions of benefits and costs emerged as the primary drivers of MaaS adoption, with the model explaining 54.5% of variance. These findings suggest that privacy concerns are outweighed by users’ cost–benefit evaluations. The minimal role of trust and security concerns underscores the need for MaaS providers to proactively promote cyber security awareness, build user trust, and collaborate with researchers and policymakers to ensure ethical and secure MaaS deployment. Full article

Although SAR systems can provide high-resolution aerial view images all-day, all-weather, the aspect and pose-sensitivity of the SAR target signatures, which defies the Gestalt perceptual principles, sets a frustrating performance upper bound for SAR Automatic Target Recognition (ATR). Therefore, we propose a network to support context-guided ATR by using aligned Electro-Optical (EO)-SAR image pairs. To realize EO-SAR image scene grammar alignment, the stable context features highly correlated to the parking patterns of the vehicle and aircraft targets are extracted from the EO images as prior knowledge, which is used to assist SAR-ATR. The proposed network consists of a Scene Recognition Module (SRM) and an instance-level Cross-modality ATR Module (CATRM). The SRM is based on a novel light-condition-driven adaptive EO-SAR decision weighting scheme, and the Outlier Exposure (OE) approach is employed for SRM training to realize Out-of-Distribution (OOD) scene detection. Once the scene depicted in the cut of interest is identified with the SRM, the image cut is sent to the CATRM for ATR. Considering that the EO-SAR images acquired from diverse observation angles often feature unbalanced quality, a novel class-incremental learning method based on the Context-Guided Re-Identification (ReID)-based Key-view (CGRID-Key) exemplar selection strategy is devised so that the network is capable of continuous learning in the open-world deployment environment. Vehicle ATR experimental results based on the UNICORN dataset, which consists of 360-degree EO-SAR images of an army base, show that the CGRID-Key exemplar strategy offers a classification accuracy 29.3% higher than the baseline model for the incremental vehicle category, SUV. Moreover, aircraft ATR experimental results based on the aligned EO-SAR images collected over several representative airports and the Arizona aircraft boneyard show that the proposed network achieves an F1 score of 0.987, which is 9% higher than YOLOv8. Full article

In complex traffic environments, image degradation due to adverse factors such as haze, low illumination, and occlusion significantly compromises the performance of object detection systems in recognizing vehicles and pedestrians. To address these challenges, this paper proposes a robust visual detection framework that integrates multi-stage image enhancement with a lightweight detection architecture. Specifically, an image preprocessing module incorporating ConvIR and CIDNet is designed to perform defogging and illumination enhancement, thereby substantially improving the perceptual quality of degraded inputs. Furthermore, a novel enhancement strategy based on the Horizontal/Vertical-Intensity color space is introduced to decouple brightness and chromaticity modeling, effectively enhancing structural details and visual consistency in low-light regions. In the detection phase, a lightweight state-space modeling network, Mamba-Driven Lightweight Detection Network with RT-DETR Decoding, is proposed for object detection in complex traffic scenes. This architecture integrates VSSBlock and XSSBlock modules to enhance detection performance, particularly for multi-scale and occluded targets. Additionally, a VisionClueMerge module is incorporated to strengthen the perception of edge structures by effectively fusing multi-scale spatial features. Experimental evaluations on traffic surveillance datasets demonstrate that the proposed method surpasses the mainstream YOLOv12s model in terms of mAP@50–90, achieving a performance gain of approximately 1.0 percentage point (from 0.759 to 0.769). While ensuring competitive detection accuracy, the model exhibits reduced parameter complexity and computational overhead, thereby demonstrating superior deployment adaptability and robustness. This framework offers a practical and effective solution for object detection in intelligent transportation systems operating under visually challenging conditions. Full article

With the growing demand for autonomous robotic operations in complex and unstructured environments, traditional semantic SLAM systems—which rely on closed-set semantic vocabularies—are increasingly limited in their ability to robustly perceive and understand diverse and dynamic scenes. This paper focuses on the paradigm shift toward open-world semantic scene understanding in SLAM and provides a comprehensive review of the technological evolution from closed-world assumptions to open-world frameworks. We survey the current state of research in open-world semantic SLAM, highlighting key challenges and frontiers. In particular, we conduct an in-depth analysis of three critical areas: zero-shot open-vocabulary understanding, dynamic semantic expansion, and multimodal semantic fusion. These capabilities are examined for their crucial roles in unknown class identification, incremental semantic updates, and multisensor perceptual integration. Our main contribution is presenting the first systematic algorithmic benchmarking and performance comparison of representative open-world semantic SLAM systems, revealing the potential of these core techniques to enhance semantic understanding in complex environments. Finally, we propose several promising directions for future research, including lightweight model deployment, real-time performance optimization, and collaborative multimodal perception, and offering a systematic reference and methodological guidance for continued advancements in this emerging field. Full article

Climate change poses significant challenges for viticulture, particularly in regions known for producing high-quality wines. Wine quality results from a complex interaction between climatic factors, regional characteristics, and viticultural practices. Methods: This study integrates statistical analysis, machine learning (ML) algorithms, and systems thinking to assess the extent to which wine quality can be predicted using monthly weather data and regional classification. The dataset includes average wine scores, monthly temperatures and precipitation, and categorical region data for Slovenia between 2011 and 2021. Predictive models tested include Random Forest, Support Vector Machine, Decision Tree, and linear regression. In addition, Causal Loop Diagrams (CLDs) were constructed to explore feedback mechanisms and systemic dynamics. Results: The Random Forest model showed the highest prediction accuracy (R² = 0.779). Regional classification emerged as the most influential variable, followed by temperatures in September and April. Precipitation did not have a statistically significant effect on wine ratings. CLD models revealed time delays in the effects of adaptation measures and highlighted the role of perceptual lags in growers’ responses to climate signals. Conclusions: The combined use of ML, statistical methods, and CLDs enhances understanding of how climate variability influences wine quality. This integrated approach offers practical insights for winegrowers, policymakers, and regional planners aiming to develop climate-resilient viticultural strategies. Future research should include phenological phase modeling and dynamic simulation to further improve predictive accuracy and system-level understanding. Full article

Various low-light image enhancement techniques inevitably introduce noise to varying degrees while improving visibility, leading to a decline in image quality that adversely affects downstream vision tasks. Existing post-processing denoising methods often produce overly smooth results lacking in detail, presenting the challenge of balancing noise suppression and detail preservation. To address this, this paper proposes a conditional diffusion denoising framework based on multi-feature fusion. The framework utilizes a diffusion model to learn the conditional distribution between underexposed and normally exposed images. Complementary features are extracted in parallel through four dedicated branches. These multi-source features are then concatenated and fused to enrich semantic information. Subsequently, redundant information is compressed via 1 × 1 convolutional layers, mitigating the issue of information degradation commonly encountered with U-Net skip connections during multi-scale feature fusion. Experimental results demonstrate the method’s applicability across diverse scenarios and illumination conditions. It outperforms both traditional methods and mainstream deep learning models in qualitative and quantitative evaluations, particularly in terms of perceptual quality. This research provides significant technical support for subsequent image restoration and denoising within low-light enhancement pipelines. Full article

Precise underwater object detectors can provide Autonomous Underwater Vehicles (AUVs) with good situational awareness in underwater environments, supporting a wide range of unmanned exploration missions. However, the quality of optical imaging is often insufficient to support high detector accuracy due to poor lighting and the complexity of underwater environments. Therefore, this paper develops an efficient and precise object detector that maintains high recognition accuracy on degraded underwater images. We design a Cross Spatial Global Perceptual Attention (CSGPA) mechanism to achieve accurate recognition of target and background information. We then construct an Efficient Multi-Scale Weighting Feature Pyramid Network (EMWFPN) to eliminate computational redundancy and increase the model’s feature-representation ability. The proposed Occlusion-Robust Wavelet Network (ORWNet) enables the model to handle fine-grained frequency-domain information, enhancing robustness to occluded objects. Finally, EMASlideloss is introduced to alleviate sample-distribution imbalance in underwater datasets. Our architecture achieves 81.8% and 83.8% mAP on the DUO and UW6C datasets, respectively, with only 7.2 GFLOPs, outperforming baseline models and balancing detection precision with computational efficiency. Full article

Image dehazing is an effective approach for enhancing the quality of images captured under foggy or hazy conditions. Although existing methods have achieved certain success in dehazing performance, many rely on deep network architectures, leading to high model complexity and computational costs. To address this issue, this study aims to compare and optimize existing algorithms to improve dehazing performance. For this purpose, we innovatively propose a multi-scale feature-coordinated composite loss mechanism, integrating perceptual loss, Mean Squared Error, and L1 regularization to optimize two dehazing methods: AOD-Net and DehazeFormer. Extensive experiments demonstrate significant performance improvements under the multi-objective loss mechanism. For AOD-Net, the PSNR increased by 22.40% (+4.17 dB), SSIM by 3.62% (+0.0318), VSNR by 43% (+1.54 dB), and LPIPS decreased by 56.30% (−0.1161). Similarly, DehazeFormer showed notable enhancements: the PSNR improved by 11.43% (+2.45 dB), SSIM by 0.8% (+0.008), VSNR by 2.6% (+0.23 dB), and LPIPS decreased by 5.5% (−0.0104). These results fully validate the effectiveness of the composite loss mechanism in enhancing the feature representation capability of the models. Full article

Visual search is a core component of map reading, influenced by both cartographic design and human perceptual processes. This study investigates whether the location of a target cartographic symbol—central or peripheral—can be predicted using eye-tracking data and machine learning techniques. Two datasets were analyzed, each derived from separate studies involving visual search tasks with varying map characteristics. A comprehensive set of eye movement features, including fixation duration, saccade amplitude, and gaze dispersion, were extracted and standardized. Feature selection and polynomial interaction terms were applied to enhance model performance. Twelve supervised classification algorithms were tested, including Random Forest, Gradient Boosting, and Support Vector Machines. The models were evaluated using accuracy, precision, recall, F1-score, and ROC-AUC. Results show that models trained on the first dataset achieved higher accuracy and class separation, with AdaBoost and Gradient Boosting performing best (accuracy = 0.822; ROC-AUC > 0.86). In contrast, the second dataset presented greater classification challenges, despite high recall in some models. Feature importance analysis revealed that fixation standard deviation as a proxy for gaze dispersion, particularly along the vertical axis, was the most predictive metric. These findings suggest that gaze behavior can reliably indicate the spatial focus of visual search, providing valuable insight for the development of adaptive, gaze-aware cartographic interfaces. Full article

Underwater image enhancement is crucial for fields like marine exploration, underwater photography, and environmental monitoring, as underwater images often suffer from reduced visibility, color distortion, and contrast loss due to light absorption and scattering. Despite recent progress, existing methods struggle to generalize across diverse underwater conditions, such as varying turbidity levels and lighting. This paper proposes a novel hybrid UNet–Transformer architecture based on MaxViT blocks, which effectively combines local feature extraction with global contextual modeling to address challenges including low contrast, color distortion, and detail degradation. Extensive experiments on two benchmark datasets, UIEB and EUVP, demonstrate the superior performance of our method. On UIEB, our model achieves a PSNR of 22.91, SSIM of 0.9020, and CCF of 37.93—surpassing prior methods such as URSCT-SESR and PhISH-Net. On EUVP, it attains a PSNR of 26.12 and PCQI of 1.1203, outperforming several state-of-the-art baselines in both visual fidelity and perceptual quality. These results validate the effectiveness and robustness of our approach under complex underwater degradation, offering a reliable solution for real-world underwater image enhancement tasks. Full article

Teledermatology relies on digital transfer of dermatological images, but compression and resolution differences compromise diagnostic quality. Image enhancement techniques are crucial to compensate for these differences and improve quality for both clinical assessment and AI-based analysis. We developed a customized image degradation pipeline simulating common artifacts in dermatological images, including blur, noise, downsampling, and compression. This synthetic degradation approach enabled effective training of DermaSR-GAN, a super-resolution generative adversarial network tailored for dermoscopic images. The model was trained on 30,000 high-quality ISIC images and evaluated on three independent datasets (ISIC Test, Novara Dermoscopic, PH²) using structural similarity and no-reference quality metrics. DermaSR-GAN achieved statistically significant improvements in quality scores across all datasets, with up to 23% enhancement in perceptual quality metrics (MANIQA). The model preserved diagnostic details while doubling resolution and surpassed existing approaches, including traditional interpolation methods and state-of-the-art deep learning techniques. Integration with downstream classification systems demonstrated up to 14.6% improvement in class-specific accuracy for keratosis-like lesions compared to original images. Synthetic degradation represents a promising approach for training effective super-resolution models in medical imaging, with significant potential for enhancing teledermatology applications and computer-aided diagnosis systems. Full article

Background: Persistent Postural-Perceptual Dizziness (PPPD) is a chronic vestibular disorder characterized by dizziness, instability, and visual hypersensitivity. Vestibular Physical Therapy (VPT) is commonly used, but its efficacy remains uncertain due to limited and heterogeneous evidence. Objective: This systematic review and meta-analysis aimed to evaluate the effectiveness of VPT in reducing dizziness and improving balance in individuals with PPPD. Methods: A systematic search of MEDLINE and PEDro was conducted in January 2025. Studies were selected following PRISMA guidelines and included if they assessed VPT interventions in patients diagnosed with PPPD. Risk of bias was assessed using the PEDro scale and the modified Newcastle–Ottawa Scale. The meta-analysis focused on pre- and post-intervention changes in Dizziness Handicap Inventory (DHI) scores using a random-effects model. Results: Six studies met the inclusion criteria. VPT significantly reduced DHI scores (pooled Hedges’ g = 1.60; 95% CI: 0.75–2.45), indicating a moderate to large improvement. Additional outcomes included improvements in postural control (e.g., mini-BESTest and posturography) and psychological well-being (anxiety and depression questionnaires). However, high heterogeneity (I² = 92%) was present across studies. Conclusions: VPT may improve dizziness and balance in PPPD, though evidence is limited. Further high-quality trials with standardized protocols are needed. Full article

Recent advancements in generative artificial intelligence have significantly progressed the field of text-to-music generation, enabling users to create music from natural language descriptions. Despite the success of various models, such as MusicLM, MusicGen, and AudioLDM, the current approaches struggle to capture fine-grained genre-specific characteristics, precisely control musical attributes, and handle underrepresented cultural data. This paper introduces a novel, lightweight fine-tuning method for the AudioLDM framework using low-rank adaptation (LoRA). By updating only selected attention and projection layers, the proposed method enables efficient adaptation to musical genres with limited data and computational cost. The proposed method enhances controllability over key musical parameters such as rhythm, emotion, and timbre. At the same time, it maintains the overall quality of music generation. This paper represents the first application of LoRA in AudioLDM, offering a scalable solution for fine-grained, genre-aware music generation and customization. The experimental results demonstrate that the proposed method improves the semantic alignment and statistical similarity compared with the baseline. The contrastive language–audio pretraining score increased by 0.0498, indicating enhanced text-music consistency. The kernel audio distance score decreased by 0.8349, reflecting improved similarity to real music distributions. The mean opinion score ranged from 3.5 to 3.8, confirming the perceptual quality of the generated music. Full article

This study presents a reanalysis of existing data to clarify how the visual system processes simple dynamic Glass patterns (GPs), with a particular focus on translational configurations. By combining datasets from previous studies, we apply a mixed-effects modeling approach—which offers advantages over the statistical methods used in previous studies—to investigate the contributions of pattern update rate and number of unique frames to perceptual sensitivity. Our findings indicate that the number of unique frames is the most robust predictor of discrimination thresholds, supporting the idea that the visual system integrates global form information across multiple frames—a process consistent with spatiotemporal summation. In contrast, the pattern update rate showed a weaker, though statistically significant, effect. This suggests that faster updates help preserve temporal consistency between frames, facilitating global form extraction. These results align with previous observations on complex dynamic GPs, where discrimination thresholds decrease with more unique frames, suggesting that the summation of form signals across time plays a key role in form–motion perception. By adopting a mixed-effects modeling approach, our reanalysis provides new insights into the mechanisms underlying global form perception in dynamic GPs. Full article