Search Results (5,504)

In China, a single large deep-sea net cage can raise nearly one million fish. If the fish net is damaged and the fish escape, it can lead to significant economic losses and ecological damage. Therefore, the inspection and maintenance of deep-sea aquaculture net cages are very important. Currently, the inspection of fish nets relies primarily on manual remote control, and underwater positioning often uses ultra-short baseline systems, which depend on specialized personnel and have high costs. This paper proposes an autonomous inspection strategy for large aquaculture net cages based on deep visual perception. It utilizes stereo cameras to identify the relative distance and attitude angles between the robot and the sides of fish net as well as the fish net ahead. A PID method is employed to control the underwater autonomous net patrol robot to conduct operations with fixed depth, fixed distance, and attitude holding around the net. By integrating the Gazebo physical simulation platform with the ROS (Robot Operating System), a simulation environment for the underwater autonomous net patrol robot was constructed. The study investigated the inspection performance of the robot under different speed conditions, both in still water and considering current conditions. By comparing the actual operating trajectory with the expected trajectory, the proposed autonomous inspection strategy was validated. Moreover, the study examined the operation state under sudden disturbance forces, where the robot deviated six meters from the net cage and rotated 70 degrees. The simulation results indicate that under this control strategy, the robot can quickly recover its desired pose and continue executing the inspection task. Full article

This paper presents a deep reinforcement learning-based demand response (DR) optimization framework for active distribution networks under uncertainty and user heterogeneity. The proposed model utilizes a Double Deep Q-Network (Double DQN) to learn adaptive, multi-period DR strategies across residential, commercial, and electric vehicle (EV) participants in a 24 h rolling horizon. By incorporating a structured state representation—including forecasted load, photovoltaic (PV) output, dynamic pricing, historical DR actions, and voltage states—the agent autonomously learns control policies that minimize total operational costs while maintaining grid feasibility and voltage stability. The physical system is modeled via detailed constraints, including power flow balance, voltage magnitude bounds, PV curtailment caps, deferrable load recovery windows, and user-specific availability envelopes. A case study based on a modified IEEE 33-bus distribution network with embedded PV and DR nodes demonstrates the framework’s effectiveness. Simulation results show that the proposed method achieves significant cost savings (up to 35% over baseline), enhances PV absorption, reduces load variance by 42%, and maintains voltage profiles within safe operational thresholds. Training curves confirm smooth Q-value convergence and stable policy performance, while spatiotemporal visualizations reveal interpretable DR behavior aligned with both economic and physical system constraints. This work contributes a scalable, model-free approach for intelligent DR coordination in smart grids, integrating learning-based control with physical grid realism. The modular design allows for future extension to multi-agent systems, storage coordination, and market-integrated DR scheduling. The results position Double DQN as a promising architecture for operational decision-making in AI-enabled distribution networks. Full article

Residential courtyards serve as critical mediators between architecture and nature in contemporary high-density urban environments. However, extant scholarship predominantly examines isolated courtyard typologies, lacking comprehensive systemic analysis, while contemporary designs frequently suffer from functional diminishment. This study investigates 72 representative Japanese detached residential projects (2015–2024) to systematically analyze spatial configurations, compositional characteristics, and functional interrelationships between courtyards and interior spaces. The methodological framework incorporates typological classification based on spatial positioning and constituent elements, coupled with analytical examination of aperture connections, interpreted through the lens of pattern language theory. Findings reveal a distinct hierarchical organization and a set of recurrent design patterns: front courtyards predominantly employ “partially walkable” surfaces with symbol trees to reconcile circulatory and esthetic functions, establishing a transitional sequence; central courtyards achieve daylight optimization and spatial extension through compact dimensions and non-paved surfaces, creating intimate outdoor rooms; side courtyards demonstrate scale-dependent adaptive strategies for privacy and microclimate regulation. The predominant living room-courtyard interface configuration features “group-planted trees with large openings,” creating vertically stratified visual experiences. This tripartite system translates traditional nature concepts into evidence-based spatial patterns, providing a transferable design matrix and pattern language for human-centered courtyard design in high-density contexts. Full article

Prolonged poor sitting posture increases the risk of musculoskeletal disorders and chronic diseases. We developed a smart cushion system that integrated pressure sensing and machine learning for posture recognition. Nine FSR406 sensors were used to measure pressure distribution on the system. A calibration and normalization process improves data consistency, and a heatmap visualizes the result. Among the five machine learning models evaluated, the narrow neural network achieved the best performance, with a validation accuracy of 97.63% and a test accuracy of 91.73%. When body mass index (BMI) was included as an additional input feature, the test accuracy improved to 95.49%, indicating that BMI positively impacts recognition performance. Full article

Understanding visitors’ outdoor activities in urban public spaces and their relationship with the physical environment is essential for improving the precision of public space design. This study, set in the context of Yangzhou, China, focuses on physical activity and other wellbeing behaviors in meso-scale waterfront public spaces, aiming to explore the characteristics of visitor behavior. A professional behavioral observation protocol was employed, combined with object detection and multi-object tracking algorithms, to systematically code visitor activities in the waterfront area. Subsequently, agent-based modeling (ABM) and three-dimensional isovist analysis (3D isovist) were introduced to construct a quantitative framework for assessing visual accessibility. The results reveal a significant positive correlation between facade Visual Exposure Time (seen from the observer) and isovist field area (seen from the object), providing strong evidence that visual accessibility is a primary causal driver of pedestrian behavior—independent of other causality. Based on these findings, this study proposes actionable design guidelines: “Prioritize small-scale, high-density waterfront building facade layouts to maximize visual efficiency” and “Leverage topographical variation along the waterfront by introducing cross-river visual corridors at intervals of ≤45 m”. The integrated analytical toolkit developed in this study—combining behavioral simulation with spatial–visual analysis—provides not only a theoretical foundation but also clear practical guidance for the fine-grained renewal and design of waterfront public spaces. Full article

Background: The global rise in the aging population presents significant challenges to healthcare systems, especially with increasing rates of chronic illnesses, mental health issues, and functional decline among older adults. In response, holistic and tech-driven approaches, such as telehealth and remote virtual interactive agents (VIAs), are potential emerging solutions to support the physical, cognitive, and emotional well-being of older adults. VIAs are multimodal digital tools that provide interactive and immersive experiences to users. Despite its promise, gaps still exist in the insights that explore ways of delivering geriatric healthcare remotely. Objective: This systematic review examines the existing literature on remote virtual interventions for older adults, focusing on bibliometrics, study purposes, outcomes, and network analysis of studies extracted from major databases using selected keywords and managed using the Covidence application. Methods and Results: Following five stages, namely, problem identification, a literature search, data evaluation, data analysis, and presentation, the review found that the studies on remote VIAs for older adults (2013–2025) were mostly from a positivist perspective, multi-authored, and U.S.-led, mainly showing positive outcomes for most studies (n = 13/15) conducted in home settings with healthy older participants. The dominance of positivist, US-led studies reflect an epistemological stance that emphasizes objectivity, quantification, and generalizability. VIAs, often pre-programmed and internet-based, supported health promotion and utilized visual humanoid avatars on personal devices. Keyword and network analysis additionally revealed four themes resulting from the review: Health and Clinical, Holistic and Cognitive, Home and Caring, and Hybrid and Connection. Conclusion: The review provides innovative insights and illustrations that may serve as a foundation for future research on VIAs and remote healthcare delivery for older adults. Full article

Natural playgrounds have garnered growing attention as supportive environments for children’s mental health. This study develops an analytical framework grounded in affordance theory and incorporates the Pleasure–Arousal–Dominance (PAD) model to examine the relationships between physical environmental features—and their combinations—in natural playgrounds and children’s emotional perceptions. Using the Yunhu Natural Playground in Fuzhou, China, as a case study, we selected seven typical behavior setting units. Environmental features were assessed through UAV imagery and on-site observations, while PAD-based visual questionnaires were employed to collect emotional responses from 159 children. By applying correlation analysis, random forest, and regression tree models, this study identified key environmental predictors of children’s emotional responses and revealed heterogeneous mechanisms across the three emotional dimensions. The results indicated that seasonal flowering/fruiting plants, accessible lawns, and structured play facilities were critical in supporting children’s pleasure, arousal, and dominance. Specifically, pleasure was primarily associated with sensory enjoyment and contextual aesthetics, arousal favored open grassy areas, and dominance was linked to environments with clear structure and manipulability. Based on these findings, this study proposes a spatial configuration strategy characterized by “nature as foundation, play encouraged, and structure clarified” to promote the positive development of children’s multidimensional emotional experiences. This research contributes empirical evidence on the role of physical environmental features in supporting children’s play behaviors and expands the theoretical understanding of the “emotional effects” of green spaces. While the findings are exploratory and context-specific, they emphasize the critical role of the sensory–behavioral–emotional chain in shaping children’s well-being and provide theoretical and practical guidance for the design of emotionally supportive, child-friendly, natural play environments in schools, parks, and residential areas. Full article

Background: This prospective observational study was conducted to systematically assess immediate changes occurring (within one hour) in corneal endothelial cell morphology and anterior segment parameters following Nd:YAG laser posterior capsulotomy in pseudophakic patients and to analyze the correlation between these changes and laser energy parameters. Methods: A single-arm, within-subject pre–post design was employed to evaluate corneal endothelial morphology (cell density, count, area, coefficient of variation and hexagonal percentage) and anterior chamber parameters (depth, angle, volume) before and one hour after the procedure using specular microscopy and Pentacam analysis. Patient demographics (age), clinical parameters (best corrected visual acuity and intraocular pressure), postoperative-YAG laser interval, and laser energy parameters (energy per shot, pulse count, and total applied energy) were also documented. Results: Thirty-two pseudophakic patients (mean age 56.3 ± 19.2 years) underwent Nd:YAG laser posterior capsulotomy with mean energy per shot of 3.15 ± 1.07 mJ and pulse count of 34.3 ± 20.4. Specular microscopy revealed significant post-procedural decreases in endothelial cell density (2184.05 to 2057.2 cells/mm²; p = 0.006) and increases in average cell area (529.25 ± 242.72 to 587.75 ± 281.09 µm²; p = 0.004) and minimum cell area (199.3 ± 170.62 to 248.35 ± 202.7 µm²; p = 0.035). Corneal topography also decreased significantly in the anterior chamber angle (40.07 ± 10.34 to 35.42 ± 6.78 degrees; p = 0.048), with positive correlations between energy per shot and endothelial cell density (r = 0.557; p = 0.011) and average cell area (r = 0.544; p = 0.013). Conclusions: This study demonstrates that Nd:YAG laser capsulotomy causes immediate, energy-dependent alterations in corneal endothelial density and anterior chamber parameters within one hour post-procedurally. The identification of energy per shot as a key determinant represents a preliminary observation for optimizing laser parameters and reducing potential complications in pseudophakic patients. Full article

Aiming at the gas injection technique for maintaining the performance of liquid-propellant rocket engines over a wide throttling range, an experimental study was conducted using the head cavity of a certain type gas generator as the object. White oil and water were selected as the substitute working liquids, while gaseous helium (GHe) and gaseous nitrogen (GN₂) were used as injected gases. Pressures at typical positions were measured, and the phase distribution at the head cavity inlet and nozzle outlets was visually captured. The effects of flow rate, gas type and liquid type were tested and compared. The results indicate that, injecting gas could significantly increase the pressure of head cavity, and improve the nozzle atomization effect at low-thrust conditions. The nozzle pressure drop increases linearly with the gas injection rate at a given liquid flow rate. Across varying liquid flow rates, a fixed amount of gas injection results in nearly constant multiplicative increases in the nozzle pressure drop. GHe is recommended as the preferred injecting gas due to its superior pressurization capability compared to GN₂. This work could provide fundamental data for understanding gas injection mechanisms and promote its mature application in the development of deep-throttling technology. Full article

Background: Copy number variations (CNVs), also referred to as large genomic rearrangements (LGRs), represent a crucial component of BRCA1/2 (BRCA) testing. Next-generation sequencing (NGS) has become an established approach for detecting LGRs by combining sequencing data with dedicated bioinformatics pipelines. However, CNV detection in formalin-fixed paraffin-embedded (FFPE) samples remains technically challenging, and there is the need to implement a robust and optimized analysis strategy for routine clinical practice. Methods: This study evaluated 40 FFPE ovarian cancer (OC) samples from patients undergoing BRCA testing. The performance of the amplicon-based NGS Diatech Myriapod^® NGS BRCA1/2 panel (Diatech Pharmacogenetics, Jesi, Italy) was assessed for its ability to detect BRCA CNVs and results were compared to two hybrid capture-based reference assays. Results: Among the 40 analyzed samples (17 CNV-positive and 23 CNV-negative for BRCA genes), the Diatech pipeline showed a good concordance with the reference method—all CNVs were correctly identified in 16 cases with good enough sequencing quality. Only one result was inconclusive due to low sequencing quality. Conclusions: These findings support the clinical utility of NGS-based CNV analysis in FFPE samples when combined with appropriate bioinformatics tools. Integrating visual inspection of CNV plots with automated CNV calling improves the reliability of CNV detection and enhances the interpretation of results from tumor tissue. Accurate CNV detection directly from tumor tissue may reduce the need for additional germline testing, thus shortening turnaround times. Nevertheless, blood-based testing remains mandatory to determine whether detected BRCA CNVs are of hereditary or somatic origin, particularly in cases with a strong clinical suspicion of inherited predisposition due to young age and a personal and/or family history of OC. Full article

The increasing sophistication of malware and the use of evasive techniques such as obfuscation pose significant challenges to traditional detection methods. This paper presents a deep convolutional neural network (CNN) framework that integrates static and dynamic analysis for malware classification using RGB image representations. Binary and memory dump files are transformed into images to capture structural and behavioural patterns often missed in raw formats. The proposed system comprises two tailored CNN architectures: a static model with four convolutional blocks designed for binary-derived images and a dynamic model with three blocks optimised for noisy memory dump data. To enhance generalisation, we employed Cycle-Consistent Generative Adversarial Networks (CycleGANs) for cross-domain image augmentation, expanding the dataset to over 74,000 RGB images sourced from benchmark repositories (MaleVis and Dumpware10). The static model achieved 99.45% accuracy and perfect recall, demonstrating high sensitivity with minimal false positives. The dynamic model achieved 99.21% accuracy. Experimental results demonstrate that the fused approach effectively detects malware variants by learning discriminative visual patterns from both structural and runtime perspectives. This research contributes to a scalable and robust solution for malware classification unlike a single approach. Full article

Background and Objectives: Early gastric cancer (EGC) has an excellent prognosis when detected, yet miss rates during endoscopy remain high. Narrow-band imaging (NBI) enhances mucosal and vascular visualization and is increasingly used, but its benefit over white-light imaging (WLI) in high-risk patients is uncertain. This study aimed to compare NBI with WLI for the detection of gastric neoplasia in patients undergoing gastroscopy. Materials and Methods: We conducted a systematic review and meta-analysis of randomized controlled trials (RCTs), registered in PROSPERO (CRD42025649908) and reported according to PRISMA 2020 guidelines. PubMed, Scopus, and CENTRAL were searched up to October 2024. Eligible RCTs randomized adults undergoing gastroscopy for cancer surveillance or red-flag symptoms to NBI or WLI. Data extraction and risk of bias assessment were performed independently by two reviewers. Pooled relative risks (RRs) with 95% confidence intervals (CIs) were calculated using a random-effects model, and certainty of evidence was graded with GRADE. Results: From 21 records, 3 RCTs comprising 6003 patients were included. NBI did not significantly increase gastric neoplasm detection compared with WLI (2.79% vs. 2.74%; RR = 0.98; 95% CI: 0.66–1.45; I² = 22%). Focal gastric lesion detection rates (14.73% vs. 15.50%; RR = 1.05; 95% CI: 0.72–1.52; I² = 87%) and positive predictive value (29.56% vs. 20.56%; RR = 1.29; 95% CI: 0.84–1.99; I² = 61%) also showed no significant differences. Risk of bias was high for blinding, and overall evidence certainty was low. In practical terms, both NBI and WLI detected gastric cancers at similar rates, indicating that while NBI enhances visualization, it does not increase the likelihood of finding additional cancers in high-risk patients. Conclusions: NBI did not significantly improve gastric neoplasm detection compared with WLI in high-risk patients, though it remains valuable for mucosal and vascular assessment. Larger, multicenter RCTs across diverse populations are required to establish its role in surveillance strategies. Full article

Background/Objectives: Previous research has demonstrated that the initial letters of a word likely play a privileged role in visual word recognition, such that reading and visual recognition errors reflecting changes in this position are much less likely. For example, prior case studies of attentional dyslexia reported that participants were most accurate at rejecting nonwords formed by transposing a word’s first two letters (e.g., WONER from OWNER) compared to transpositions in later positions. The current study aimed to replicate and extend this finding in patients with posterior cortical atrophy (PCA), a neurodegenerative condition associated with visuospatial and attentional impairments. Methods: Two PCA patients completed lexical decision tasks involving five-letter real words and nonwords created either by transposing adjacent letters (in positions 1 + 2, 2 + 3, 3 + 4, or 4 + 5) or using matched nonword controls. To assess robustness, tasks were repeated across test–retest sessions. Stimuli were presented in both canonical horizontal and non-canonical vertical (marquee) formats. Accuracy, response bias, and sensitivity (d′) were estimated, with 95% confidence intervals derived from a nonparametric bootstrap procedure. Within-case logistic regressions were also conducted to illustrate the findings. Results: Both patients showed significantly higher accuracy and lower response bias for 1 + 2 transposition nonwords relative to other positions. This early-letter advantage persisted across test–retest observations and was maintained when words were presented in the vertical format, suggesting orientation-invariant effects. The bootstrap and regression analyses provided convergent support for these results. Conclusions: The findings provide novel evidence in PCA that the encoding of early letter positions operates independently of visual orientation and persists despite attentional deficits. This supports models in which the initial letters serve as a key anchor point in orthographic processing, highlighting the privileged and resilient status of early letter encoding in visual word recognition. Full article

Small object detection in UAV imagery remains challenging due to complex aerial perspectives and the presence of dense, small targets with blurred boundaries. To address these challenges, we propose ACD-DETR, an adaptive end-to-end Transformer detector tailored for UAV-based small object detection. The framework introduces three core modules: the Multi-Scale Edge-Enhanced Feature Fusion Module (MSEFM) to preserve fine-grained details; the Omni-Grained Boundary Calibrator (OG-BC) for boundary-aware semantic fusion; and the Dynamic Position Bias Attention-based Intra-scale Feature Interaction (DPB-AIFI) to enhance spatial reasoning. Furthermore, we introduce ACD-DETR-SBA+, a fusion-enhanced variant that removes OG-BC and DPB-AIFI while deploying densely connected Semantic–Boundary Aggregation (SBA) modules to intensify boundary–semantic fusion. This design sacrifices computational efficiency in exchange for higher detection precision, making it suitable for resource-rich deployment scenarios. On the VisDrone2019 dataset, ACD-DETR achieves 50.9% mAP@0.5, outperforming the RT-DETR-R18 baseline by 3.6 percentage points, while reducing parameters by 18.5%. ACD-DETR-SBA+ further improves accuracy to 52.0% mAP@0.5, demonstrating the benefit of SBA-based fusion. Extensive experiments on the VisDrone2019 and DOTA datasets demonstrate that ACD-DETR achieves a state-of-the-art trade-off between accuracy and efficiency, while ACD-DETR-SBA+ achieves further performance improvements at higher computational cost. Ablation studies and visual analyses validate the effectiveness of the proposed modules and design strategies. Full article

Focusing on the discovery of new $\delta$ Scuti and $\gamma$ Doradus stars, we analyzed the Transiting Exoplanet Survey Satellite (TESS) light curves for 193,940 A-F stars selected from four legacy catalogs—the Henry Draper Catalogue (HD), the Smithsonian Astrophysical Observatory (SAO) Star Catalog, the Positions and Proper Motions Catalog (PPM), and the Bonner Durchmusterung (BD, including its extensions). Through visual inspection of light curve morphologies and periodograms, combined with evaluation of stellar parameters, we identified over 51,850 previously unreported variable stars. These include 15,380 $\delta$ Scuti, 18,560 $\gamma$ Doradus, 28 RR Lyrae stars, 260 heartbeat candidates, and 2645 eclipsing binaries, along with thousands of other variable types. Notably, over 4145 variables exhibit hybrid $\delta$ Scuti-$\gamma$ Doradus pulsations, and more than 380 eclipsing binaries feature pulsating primary components. This study reveals a substantial population of bright, previously undetected variables, providing a valuable resource for ensemble asteroseismology, binary evolution studies, and Galactic structure research. Our results also highlight the surprising richness in variability still hidden within well-known stellar catalogs and the continued importance of high-precision, time-domain surveys such as TESS. Full article