Search Results (250)

This comprehensive review investigates the pivotal role of reactive oxygen species (ROS) in cataract formation and evaluates the potential of antioxidant therapies in mitigating this ocular condition. By elucidating the mechanisms of oxidative stress, the article examines how ROS contribute to the deterioration of lens proteins and lipids, leading to the characteristic aggregation, cross-linking, and light scattering observed in cataracts. The review provides a thorough assessment of various antioxidant strategies aimed at preventing and managing cataracts, such as dietary antioxidants (i.e., vitamins C and E, lutein, and zeaxanthin), as well as pharmacological agents with antioxidative properties. Furthermore, the article explores innovative therapeutic approaches, including gene therapy and nanotechnology-based delivery systems, designed to bolster antioxidant defenses in ocular tissues. Concluding with a critical analysis of current research, the review offers evidence-based recommendations for optimizing antioxidant therapies. The current literature on the use of antioxidant therapies to prevent cataract formation is sparse. There is a lack of evidence-based conclusions; further clinical studies are needed to endorse the use of antioxidant strategies in patients to prevent cataractogenesis. However, personalized treatment plans considering individual patient factors and disease stages can be applied. This article serves as a valuable resource, providing insights into the potential of antioxidants to alleviate the burden of cataracts. Full article

In this paper, we proposed Mix-VIO, a monocular and binocular visual-inertial odometry, to address the issue where conventional visual front-end tracking often fails under dynamic lighting and image blur conditions. Mix-VIO adopts a hybrid tracking approach, combining traditional handcrafted tracking techniques with Deep Neural Network (DNN)-based feature extraction and matching pipelines. The system employs deep learning methods for rapid feature point detection, while integrating traditional optical flow methods and deep learning-based sparse feature matching methods to enhance front-end tracking performance under rapid camera motion and environmental illumination changes. In the back-end, we utilize sliding window and bundle adjustment (BA) techniques for local map optimization and pose estimation. We conduct extensive experimental validations of the hybrid feature extraction and matching methods, demonstrating the system’s capability to maintain optimal tracking results under illumination changes and image blur. Full article

In the process of using structured light technology to obtain indoor point clouds, due to the limited field of view of the device, it is necessary to obtain multiple point clouds of different wall surfaces. Therefore, merging the point cloud is necessary to acquire a complete point cloud. However, due to issues such as the sparse geometric features of the wall point clouds and the high similarity of multiple point clouds, the merging effect of point clouds is poor. In this paper, we leverage artificially enhanced features to improve the accuracy of registration in this scenario. Firstly, we design feature markers and present their layout criteria. Then, the feature information of the marker is extracted based on the Color Signature of Histograms of OrienTations (Color-SHOT) descriptor, and coarse registration is realized through the second-order similarity measure matrix. After that, precise registration is achieved using the Iterative Closest Point (ICP) method based on markers and overlapping areas. Finally, the global error of the point cloud registration is optimized by loop error averaging. Our method enables the high-precision reconstruction of integrated home design scenes lacking significant features at a low cost. The accuracy and validity of the method were verified through comparative experiments. Full article

Accurately recognizing apples in complex environments is essential for automating apple picking operations, particularly under challenging natural conditions such as cloudy, snowy, foggy, and rainy weather, as well as low-light situations. To overcome the challenges of reduced apple target detection accuracy due to branch occlusion, apple overlap, and variations between near and far field scales, we propose the Rep-ViG-Apple algorithm, an advanced version of the YOLO model. The Rep-ViG-Apple algorithm features a sophisticated architecture designed to enhance apple detection performance in difficult conditions. To improve feature extraction for occluded and overlapped apple targets, we developed the inverted residual multi-scale structural reparameterized feature extraction block (RepIRD Block) within the backbone network. We also integrated the sparse graph attention mechanism (SVGA) to capture global feature information, concentrate attention on apples, and reduce interference from complex environmental features. Moreover, we designed a feature extraction network with a CNN-GCN architecture, termed Rep-Vision-GCN. This network combines the local multi-scale feature extraction capabilities of a convolutional neural network (CNN) with the global modeling strengths of a graph convolutional network (GCN), enhancing the extraction of apple features. The RepConvsBlock module, embedded in the neck network, forms the Rep-FPN-PAN feature fusion network, which improves the recognition of apple targets across various scales, both near and far. Furthermore, we implemented a channel pruning algorithm based on LAMP scores to balance computational efficiency with model accuracy. Experimental results demonstrate that the Rep-ViG-Apple algorithm achieves precision, recall, and average accuracy of 92.5%, 85.0%, and 93.3%, respectively, marking improvements of 1.5%, 1.5%, and 2.0% over YOLOv8n. Additionally, the Rep-ViG-Apple model benefits from a 22% reduction in size, enhancing its efficiency and suitability for deployment in resource-constrained environments while maintaining high accuracy. Full article

With LiDAR (Light Detection and Ranging) time series being used for various applications, the optimal realization of a common geodetic datum over many epochs is a highly important prerequisite with a direct impact on the accuracy and reliability of derived measures. In our work, we develop and define several approaches to the adjustment of multi-temporal LiDAR data in a given software framework. These approaches, ranging from pragmatic to more rigorous solutions, are applied to an 8-year time series with 21 individual epochs. The analysis of the respective results suggests that a sequence of bi-temporal adjustments of each individual epoch and a designated reference epoch brings the best results while being more flexible and computationally viable than the most extensive approach of using all epochs in one single multi-temporal adjustment. With a combination of sparse control patches measured in the field and one selected reference block, the negative impacts of changing surfaces on orientation quality are more effectively avoided than in any other approach. We obtain relative discrepancies in the range of 1–2 cm between epoch-wise DSMs for the complete time series and mean offsets from independent checkpoints in the range of 3–5 cm. Based on our findings, we formulate design criteria for setting up and adjusting future time series with the proposed method. Full article

Classifieds pose numerous challenges for recommendation methods, including the temporary visibility of ads, the anonymity of most users, and the fact that typically only one user can consume an advertised item. In this work, we address these challenges by choosing models and evaluation procedures that are considered accurate, diverse, and efficient (in terms of memory and time consumption during training and prediction). This paper aims to benchmark various recommendation methods for job classifieds, using OLX Jobs as an example, to enhance the conversion rate of advertisements and user satisfaction. In our research, we implement scalable methods and represent different approaches to the recommendations: Alternating Least Square (ALS), LightFM, Prod2Vec, RP3Beta, and Sparse Linear Methods (SLIM). We conducted A/B tests by sending millions of messages with recommendations to perform online evaluations of selected methods. In addition, we have published the dataset created for our research. To the best of our knowledge, this is the first dataset of its kind. It contains 65,502,201 events performed on OLX Jobs by 3,295,942 users who interacted with (displayed, replied to, or bookmarked) 185,395 job ads over two weeks in 2020. We demonstrate that RP3Beta, SLIM, and ALS perform significantly better than Prod2Vec and LightFM when tested in a laboratory setting. Online A/B tests also show that sending messages with recommendations generated by the ALS and RP3Beta models increases the number of users contacting advertisers. Additionally, RP3Beta had a 20% more significant impact on this metric than ALS. Full article

The Auckland Harbour Bridge (AHB) utilises a movable concrete barrier (MCB) to regulate the uneven bidirectional flow of daily traffic. In addition to the risk of human error during regular visual inspections, staff members inspecting the MCB work in diverse weather and light conditions, exerting themselves in ergonomically unhealthy inspection postures with the added weight of protection gear to mitigate risks, e.g., flying debris. To augment visual inspections of an MCB using computer vision technology, this study introduces a hybrid deep learning solution that combines kernel manipulation with custom transfer learning strategies. The video data recordings were captured in diverse light and weather conditions (under the safety supervision of industry experts) involving a high-speed (120 fps) camera system attached to an MCB transfer vehicle. Before identifying a safety hazard, e.g., the unsafe position of a pin connecting two 750 kg concrete segments of the MCB, a multi-stage preprocessing of the spatiotemporal region of interest (ROI) involves a rolling window before identifying the video frames containing diagnostic information. This study utilises the ResNet-50 architecture, enhanced with 3D convolutions, within the STENet framework to capture and analyse spatiotemporal data, facilitating real-time surveillance of the Auckland Harbour Bridge (AHB). Considering the sparse nature of safety anomalies, the initial peer-reviewed binary classification results (82.6%) for safe and unsafe (intervention-required) scenarios were improved to 93.6% by incorporating synthetic data, expert feedback, and retraining the model. This adaptation allowed for the optimised detection of false positives and false negatives. In the future, we aim to extend anomaly detection methods to various infrastructure inspections, enhancing urban resilience, transport efficiency and safety. Full article

Vegetation plays a key role in trapping sediments and further controlling pollutants. However, few studies were conducted to clarify the erosion and deposition laws of sediments and the influence factors caused by vegetation patch properties, which is not conducive to the revelation of riverbank protection and erosion prevention. Therefore, this study investigated the change in scouring and deposition characteristics around submerged vegetation patches of nine kinds of typical configurations and their influencing factors. Vegetation patches were assembled from three vegetation densities (G/d = 0.83, 1.3, and 1.77, representing dense, medium, and sparse, respectively), and three vegetation patch thicknesses (dn = 170, 400, and 630, representing narrow, usual, and wide, respectively), to measure vegetation patch property influences. Flow velocity, scouring, and deposition characteristics under nine patches were determined by a hydraulic flume experiment, three-dimensional acoustic Doppler velocimetry (ADV), and three-dimensional laser scanner, and then ten geometry and morphology indices were measured and calculated based on the results of laser scanning. Results showed that both vegetation patch density and thickness were positively related to the turbulence kinetic energy (TKE) above the vegetation canopy, and only vegetation patch density was negatively related to the flow velocity above the vegetation canopy. The relation between the product of density and vegetation patch thickness and erosion area in planform (EA) showed a power function (R² = 0.644). Both density and vegetation patch thickness determined the scouring degree, but deposition location and amount did not rely on each one simply. On average, medium density showed the smallest maximum erosion length (MEL), EA, deposition area in planform (DA), and average deposition length (ADL) and a minimum of the above parameters also occurred at narrow vegetation patch thickness. The shape factor of the erosion volume (SFEV), the shape factor of the deposition volume (SFDV), ADL, and MEL of medium density and narrow thickness vegetation patch (G/d = 1.3, dn = 170) were significantly smaller than that of other types of patches. DA and equivalent prismatic erosion depth on the erosion area (EPED) were significantly linearly related (R² = 0.766). Consequently, most sediment was deposited close to the vegetation patch edge. It is suggested that vegetation patch thickness and density should be given to control sediment transport. In particular, natural vegetation growth changes vegetation patch density and then alters vegetation patch thickness. Management and repair need to be first considered. The results of this study shed light on riparian zone recovery and vegetation filter strip mechanism. Full article

When a camera lens is directly faced with a strong light source, image flare commonly occurs, significantly reducing the clarity and texture of the photo and interfering with image processing tasks that rely on visual sensors, such as image segmentation and feature extraction. A novel flare removal network, the Sparse-UFormer neural network, has been developed. The network integrates two core components onto the UFormer architecture: the mixed-scale feed-forward network (MSFN) and top-k sparse attention (TKSA), creating the sparse-transformer module. The MSFN module captures rich multi-scale information, enabling the more effective addressing of flare interference in images. The TKSA module, designed with a sparsity strategy, focuses on key features within the image, thereby significantly enhancing the precision and efficiency of flare removal. Furthermore, in the design of the loss function, besides the conventional flare, background, and reconstruction losses, a structural similarity index loss has been incorporated to ensure the preservation of image details and structure while removing the flare. Ensuring the minimal loss of image information is a fundamental premise for effective image restoration. The proposed method has been demonstrated to achieve state-of-the-art performance on the Flare7K++ test dataset and in challenging real-world scenarios, proving its effectiveness in removing flare artefacts from images. Full article

Detecting small dark targets underwater, such as fishing nets, is critical to the operation of underwater robots. Existing techniques often require more computational resources and operate under harsh underwater imaging conditions when handling such tasks. This study aims to develop a model with low computational resource consumption and high efficiency to improve the detection accuracy of fishing nets for safe and efficient underwater operations. The Light-YOLO model proposed in this paper introduces an attention mechanism based on sparse connectivity and deformable convolution optimized for complex underwater lighting and visual conditions. This novel attention mechanism enhances the detection performance by focusing on the key visual features of fishing nets, while the introduced CoTAttention and SEAM modules further improve the model’s recognition accuracy of fishing nets through deeper feature interactions. The results demonstrate that the proposed Light-YOLO model achieves a precision of 89.3%, a recall of 80.7%, and an [email protected] of 86.7%. Compared to other models, our model has the highest precision for its computational size and is the lightest while maintaining similar accuracy, providing an effective solution for fishing net detection and identification. Full article

In light of the issue that the vibration signal from an axle-box bearing collected during the operation of an electric multiple unit (EMU) is seriously polluted by background noise, which leads to difficulty in identifying fault characteristic frequency, this paper proposes a resonance-based sparse signal decomposition (RSSD) and variational mode decomposition (VMD) method based on sparrow search algorithm (SSA) optimization to extract the fault characteristic frequency of the bearing. Firstly, the RSSD method is utilized to decompose the signal based on the obtained optimal combination of quality factors, resulting in the optimal low-resonance component with periodic fault information. Then, the VMD method is performed on this low-resonance component. The parameter combinations for both methods are optimized utilizing the SSA method. Subsequently, envelope demodulation is applied to the intrinsic mode function (IMF) with maximum kurtosis, and fault diagnosis is achieved by comparing it with the theoretical fault characteristic frequency. Finally, experimental validation and comparison are conducted by utilizing simulated signals and example signals. The results demonstrate that the proposed method extracts more obvious periodic fault impact components. It effectively filters out the interference of complex noise and reduces the blindness of setting weights on parameters due to human experience, indicating excellent adaptability and robustness. Full article

Stargardt disease (STGD1), associated with biallelic variants in the ABCA4 gene, is the most common heritable macular dystrophy and is currently untreatable. To identify potential treatment targets, we characterized surviving STGD1 photoreceptors. We used clinical data to identify macular regions with surviving STGD1 photoreceptors. We compared the hyperreflective bands in the optical coherence tomographic (OCT) images that correspond to structures in the STGD1 photoreceptor inner segments to those in controls. We used adaptive optics scanning light ophthalmoscopy (AO-SLO) to study the distribution of cones and AO-OCT to evaluate the interface of photoreceptors and retinal pigment epithelium (RPE). We found that the profile of the hyperreflective bands differed dramatically between patients with STGD1 and controls. AO-SLOs showed patches in which cone densities were similar to those in healthy retinas and others in which the cone population was sparse. In regions replete with cones, there was no debris at the photoreceptor-RPE interface. In regions with sparse cones, there was abundant debris. Our results raise the possibility that pharmaceutical means may protect surviving photoreceptors and so mitigate vision loss in patients with STGD1. Full article

Enhancing corporate accountability in areas such as environment, social, and governance (ESG) has solidified its role in the discussion on improving corporate resilience and growth. ESG management activities not only augment corporate sustainability and risk control but also influence the professional roles and personal lives of members through their perceived ESG. Historically, most ESG research has centered on the interrelation of corporate ESG endeavors and outcomes, while studies focusing on the influence of perceived ESG on members have been sparse. In this light, our investigation, rooted in the conservation of resources theory, aimed to delineate the mechanistic link between perceived ESG and members’ psychological well-being. This study employed a stratified random sampling technique and collected data across three waves, each spaced four weeks apart. Our sample comprised 325 Korean employees working in administrative, technical, service, and sales roles. This study recruited 325 Korean employees across three time-lagged phases and found that ESG comprehension enhances job meaningfulness, subsequently amplifying psychological wellness. Intriguingly, as pay satisfaction escalates, the mediating role of job meaningfulness between perceived ESG and well-being intensifies. Our study underscores that for organizations to harness perceived ESG to boost psychological well-being via job meaningfulness, managing pay satisfaction is imperative. These findings highlight a crucial policy implication: policymakers must actively promote ESG awareness and incorporate it into employee compensation strategies. This integration is essential to cultivating a healthier, more engaged workforce and driving long-term organizational success. Full article

Depth estimation represents a prevalent research focus within the realm of computer vision. Existing depth estimation methodologies utilizing LiDAR (Light Detection and Ranging) technology typically obtain sparse depth data and are associated with elevated hardware expenses. Multi-view image-matching techniques necessitate prior knowledge of camera intrinsic parameters and frequently encounter challenges such as depth inconsistency, loss of details, and the blurring of edges. To tackle these challenges, the present study introduces a monocular depth estimation approach based on an end-to-end convolutional neural network. Specifically, a DNET backbone has been developed, incorporating dilated convolution and feature fusion mechanisms within the network architecture. By integrating semantic information from various receptive fields and levels, the model’s capacity for feature extraction is augmented, thereby enhancing its sensitivity to nuanced depth variations within the image. Furthermore, we introduce a loss function optimization algorithm specifically designed to address class imbalance, thereby enhancing the overall predictive accuracy of the model. Training and validation conducted on the NYU Depth-v2 (New York University Depth Dataset Version 2) and KITTI (Karlsruhe Institute of Technology and Toyota Technological Institute) datasets demonstrate that our approach outperforms other algorithms in terms of various evaluation metrics. Full article

Illegal dumping is one of the major issues to be addressed by public managers in both developed and developing countries. The adequate tackling and enforcement of such unlawful activities require continuous territory monitoring, the lack of which is the principal cause of the failure of traditional systems based on patrolling, eventually triggered by sparse crowdsourced data. This work proposes the digitalization of the entire illegal waste management monitoring process through an innovative decision support system based on multiscale remote sensing data. These data enable the assessment of the risk level of specific areas, thus determining inspection priorities in line with the available patrolling resources. The proposed methodology provides a tool to assess the impact of diverse monitoring system parameters on overall the performance in light of the expected operating costs and to understand whether remote sensing can help a better management of illegal waste in a specific operational scenario, thus helping in the determination of the best cost–benefit trade-off. Simulation results over a demonstration scenario, based on realistic dumping/restoration dynamics and the typical performance of satellite detection systems, show that the adoption of remote sensing technologies in the monitoring process can increase the restoration capacity by about 10% compared to traditional patrolling. Full article