Sign in to use this feature.

Years

Between: -

Subjects

remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline

Journals

remove_circle_outline
remove_circle_outline
remove_circle_outline

Article Types

Countries / Regions

remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline

Search Results (336)

Search Parameters:
Keywords = neighborhood difference features

Order results
Result details
Results per page
Select all
Export citation of selected articles as:
28 pages, 41726 KiB  
Article
Robust Unsupervised Feature Selection Algorithm Based on Fuzzy Anchor Graph
by Zhouqing Yan, Ziping Ma, Jinlin Ma and Huirong Li
Entropy 2025, 27(8), 827; https://doi.org/10.3390/e27080827 - 4 Aug 2025
Viewed by 29
Abstract
Unsupervised feature selection aims to characterize the cluster structure of original features and select the optimal subset without label guidance. However, existing methods overlook fuzzy information in the data, failing to model cluster structures between data effectively, and rely on squared error for [...] Read more.
Unsupervised feature selection aims to characterize the cluster structure of original features and select the optimal subset without label guidance. However, existing methods overlook fuzzy information in the data, failing to model cluster structures between data effectively, and rely on squared error for data reconstruction, exacerbating noise impact. Therefore, a robust unsupervised feature selection algorithm based on fuzzy anchor graphs (FWFGFS) is proposed. To address the inaccuracies in neighbor assignments, a fuzzy anchor graph learning mechanism is designed. This mechanism models the association between nodes and clusters using fuzzy membership distributions, effectively capturing potential fuzzy neighborhood relationships between nodes and avoiding rigid assignments to specific clusters. This soft cluster assignment mechanism improves clustering accuracy and the robustness of the graph structure while maintaining low computational costs. Additionally, to mitigate the interference of noise in the feature selection process, an adaptive fuzzy weighting mechanism is presented. This mechanism assigns different weights to features based on their contribution to the error, thereby reducing errors caused by redundant features and noise. Orthogonal tri-factorization is applied to the low-dimensional representation matrix. This guarantees that each center represents only one class of features, resulting in more independent cluster centers. Experimental results on 12 public datasets show that FWFGFS improves the average clustering accuracy by 5.68% to 13.79% compared with the state-of-the-art methods. Full article
(This article belongs to the Section Information Theory, Probability and Statistics)
Show Figures

Figure 1

28 pages, 5373 KiB  
Article
Transfer Learning Based on Multi-Branch Architecture Feature Extractor for Airborne LiDAR Point Cloud Semantic Segmentation with Few Samples
by Jialin Yuan, Hongchao Ma, Liang Zhang, Jiwei Deng, Wenjun Luo, Ke Liu and Zhan Cai
Remote Sens. 2025, 17(15), 2618; https://doi.org/10.3390/rs17152618 - 28 Jul 2025
Viewed by 308
Abstract
The existing deep learning-based Airborne Laser Scanning (ALS) point cloud semantic segmentation methods require a large amount of labeled data for training, which is not always feasible in practice. Insufficient training data may lead to over-fitting. To address this issue, we propose a [...] Read more.
The existing deep learning-based Airborne Laser Scanning (ALS) point cloud semantic segmentation methods require a large amount of labeled data for training, which is not always feasible in practice. Insufficient training data may lead to over-fitting. To address this issue, we propose a novel Multi-branch Feature Extractor (MFE) and a three-stage transfer learning strategy that conducts pre-training on multi-source ALS data and transfers the model to another dataset with few samples, thereby improving the model’s generalization ability and reducing the need for manual annotation. The proposed MFE is based on a novel multi-branch architecture integrating Neighborhood Embedding Block (NEB) and Point Transformer Block (PTB); it aims to extract heterogeneous features (e.g., geometric features, reflectance features, and internal structural features) by leveraging the parameters contained in ALS point clouds. To address model transfer, a three-stage strategy was developed: (1) A pre-training subtask was employed to pre-train the proposed MFE if the source domain consisted of multi-source ALS data, overcoming parameter differences. (2) A domain adaptation subtask was employed to align cross-domain feature distributions between source and target domains. (3) An incremental learning subtask was proposed for continuous learning of novel categories in the target domain, avoiding catastrophic forgetting. Experiments conducted on the source domain consisted of DALES and Dublin datasets and the target domain consists of ISPRS benchmark dataset. The experimental results show that the proposed method achieved the highest OA of 85.5% and an average F1 score of 74.0% using only 10% training samples, which means the proposed framework can reduce manual annotation by 90% while keeping competitive classification accuracy. Full article
Show Figures

Figure 1

23 pages, 24301 KiB  
Article
Robust Optical and SAR Image Registration Using Weighted Feature Fusion
by Ao Luo, Anxi Yu, Yongsheng Zhang, Wenhao Tong and Huatao Yu
Remote Sens. 2025, 17(15), 2544; https://doi.org/10.3390/rs17152544 - 22 Jul 2025
Viewed by 315
Abstract
Image registration constitutes the fundamental basis for the joint interpretation of synthetic aperture radar (SAR) and optical images. However, robust image registration remains challenging due to significant regional heterogeneity in remote sensing scenes (e.g., co-existing urban and marine areas within a single image). [...] Read more.
Image registration constitutes the fundamental basis for the joint interpretation of synthetic aperture radar (SAR) and optical images. However, robust image registration remains challenging due to significant regional heterogeneity in remote sensing scenes (e.g., co-existing urban and marine areas within a single image). To overcome this challenge, this article proposes a novel optical–SAR image registration method named Gradient and Standard Deviation Feature Weighted Fusion (GDWF). First, a Block-local standard deviation (Block-LSD) operator is proposed to extract block-based feature points with regional adaptability. Subsequently, a dual-modal feature description is developed, constructing both gradient-based descriptors and local standard deviation (LSD) descriptors for the neighborhoods surrounding the detected feature points. To further enhance matching robustness, a confidence-weighted feature fusion strategy is proposed. By establishing a reliability evaluation model for similarity measurement maps, the contribution weights of gradient features and LSD features are dynamically optimized, ensuring adaptive performance under varying conditions. To verify the effectiveness of the method, different optical and SAR datasets are used to compare it with the currently advanced algorithms MOGF, CFOG, and FED-HOPC. The experimental results demonstrate that the proposed GDWF algorithm achieves the best performance in terms of registration accuracy and robustness among all compared methods, effectively handling optical–SAR image pairs with significant regional heterogeneity. Full article
Show Figures

Figure 1

22 pages, 2652 KiB  
Article
Niching-Driven Divide-and-Conquer Hill Exploration
by Junchen Wang, Changhe Li and Yiya Diao
Appl. Syst. Innov. 2025, 8(4), 101; https://doi.org/10.3390/asi8040101 - 22 Jul 2025
Viewed by 305
Abstract
Optimization problems often feature local optima with a significant difference in the basin of attraction (BoA), making evolutionary computation methods prone to discarding solutions located in less-attractive BoAs, thereby posing challenges to the search for optima in these BoAs. To enhance the ability [...] Read more.
Optimization problems often feature local optima with a significant difference in the basin of attraction (BoA), making evolutionary computation methods prone to discarding solutions located in less-attractive BoAs, thereby posing challenges to the search for optima in these BoAs. To enhance the ability to find these optima, various niching methods have been proposed to restrict the competition scope of individuals to their specific neighborhoods. However, redundant searches in more-attractive BoAs as well as necessary searches in less-attractive BoAs can only be promoted simultaneously by these methods. To address this issue, we propose a general framework for niching methods named niching-driven divide-and-conquer hill exploration (NDDCHE). Through gradually learning BoAs from the search results of a niching method and dividing the problem into subproblems with a much smaller number of optima, NDDCHE aims to bring a more balanced distribution of searches in the BoAs of optima found so far, and thus enhance the niching method’s ability to find optima in less-attractive BoAs. Through experiments where niching methods with different categories of niching techniques are integrated with NDDCHE and tested on problems with significant differences in the size of the BoA, the effectiveness and the generalization ability of NDDCHE are proven. Full article
Show Figures

Figure 1

22 pages, 4636 KiB  
Article
SP-GEM: Spatial Pattern-Aware Graph Embedding for Matching Multisource Road Networks
by Chenghao Zheng, Yunfei Qiu, Jian Yang, Bianying Zhang, Zeyuan Li, Zhangxiang Lin, Xianglin Zhang, Yang Hou and Li Fang
ISPRS Int. J. Geo-Inf. 2025, 14(7), 275; https://doi.org/10.3390/ijgi14070275 - 15 Jul 2025
Viewed by 286
Abstract
Identifying correspondences of road segments in different road networks, namely road-network matching, is an essential task for road network-centric data processing such as data integration of road networks and data quality assessment of crowd-sourced road networks. Traditional road-network matching usually relies on feature [...] Read more.
Identifying correspondences of road segments in different road networks, namely road-network matching, is an essential task for road network-centric data processing such as data integration of road networks and data quality assessment of crowd-sourced road networks. Traditional road-network matching usually relies on feature engineering and parameter selection of the geometry and topology of road networks for similarity measurement, resulting in poor performance when dealing with dense and irregular road network structures. Recent development of graph neural networks (GNNs) has demonstrated unsupervised modeling power on road network data, which learn the embedded vector representation of road networks through spatial feature induction and topology-based neighbor aggregation. However, weighting spatial information on the node feature alone fails to give full play to the expressive power of GNNs. To this end, this paper proposes a Spatial Pattern-aware Graph EMbedding learning method for road-network matching, named SP-GEM, which explores the idea of spatially-explicit modeling by identifying spatial patterns in neighbor aggregation. Firstly, a road graph is constructed from the road network data, and geometric, topological features are extracted as node features of the road graph. Then, four spatial patterns, including grid, high branching degree, irregular grid, and circuitous, are modelled in a sector-based road neighborhood for road embedding. Finally, the similarity of road embedding is used to find data correspondences between road networks. We conduct an algorithmic accuracy test to verify the effectiveness of SP-GEM on OSM and Tele Atlas data. The algorithmic accuracy experiments show that SP-GEM improves the matching accuracy and recall by at least 6.7% and 10.2% among the baselines, with high matching success rate (>70%), and improves the matching accuracy and recall by at least 17.7% and 17.0%, compared to the baseline GNNs, without spatially-explicit modeling. Further embedding analysis also verifies the effectiveness of the induction of spatial patterns. This study not only provides an effective and practical algorithm for road-network matching, but also serves as a test bed in exploring the role of spatially-explicit modeling in GNN-based road network modeling. The experimental performances of SP-GEM illuminate the path to develop GeoEmbedding services for geospatial applications. Full article
Show Figures

Figure 1

27 pages, 3553 KiB  
Article
Mitigating Selection Bias in Local Optima: A Meta-Analysis of Niching Methods in Continuous Optimization
by Junchen Wang, Changhe Li and Yiya Diao
Information 2025, 16(7), 583; https://doi.org/10.3390/info16070583 - 7 Jul 2025
Cited by 1 | Viewed by 209
Abstract
As mainstream solvers for black-box optimization problems, evolutionary computation (EC) methods struggle with finding desired optima of lower attractiveness. Researchers have designed benchmark problems for simulating this scenario and proposed a large number of niching methods for solving those problems. However, factors causing [...] Read more.
As mainstream solvers for black-box optimization problems, evolutionary computation (EC) methods struggle with finding desired optima of lower attractiveness. Researchers have designed benchmark problems for simulating this scenario and proposed a large number of niching methods for solving those problems. However, factors causing the difference in attractiveness between local optima are often coupled in existing benchmark problems, which makes it hard to clarify the primary contributors. In addition, niching methods are carried out using a combination of several niching techniques and reproduction operators, which enhances the difficulty of identifying the essential effects of different niching techniques. To obtain an in-depth understanding of the above issue, thus offering actionable insights for optimization tasks challenged by the multimodality, this paper uses continuous optimization as an entry point and focuses on analyzing differential behaviors of EC methods across different basins of attraction. Specifically, we quantitatively investigate the independent impacts of three features of basins of attraction via corresponding benchmark scenarios generated by Free Peaks. The results show that the convergence biases induced by the difference in distribution only occur in EC methods with less uniform reproduction operators. On the other hand, convergence biases induced by differences in size and average fitness, both of which equate to the difference in size of superior region, pose a challenge to any EC method driven by objective functions. As niching methods limit survivor selection to specified neighborhoods to mitigate the latter biases, we abstract five niching techniques from these methods by their definitions of neighborhood for restricted competition, thus identifying key parameters that govern their efficacy. Experiments confirm these parameters’ critical roles in reducing convergence biases. Full article
Show Figures

Figure 1

25 pages, 67703 KiB  
Article
Robust Feature Matching of Multi-Illumination Lunar Orbiter Images Based on Crater Neighborhood Structure
by Bin Xie, Bin Liu, Kaichang Di, Wai-Chung Liu, Yuke Kou, Yutong Jia and Yifan Zhang
Remote Sens. 2025, 17(13), 2302; https://doi.org/10.3390/rs17132302 - 4 Jul 2025
Viewed by 267
Abstract
Lunar orbiter image matching is a critical process for achieving high-precision lunar mapping, positioning, and navigation. However, with the Moon’s weak-texture surface and rugged terrain, lunar orbiter images generally suffer from inconsistent lighting conditions and exhibit varying degrees of non-linear intensity distortion, which [...] Read more.
Lunar orbiter image matching is a critical process for achieving high-precision lunar mapping, positioning, and navigation. However, with the Moon’s weak-texture surface and rugged terrain, lunar orbiter images generally suffer from inconsistent lighting conditions and exhibit varying degrees of non-linear intensity distortion, which pose significant challenges to image traditional matching. This paper presents a robust feature matching method based on crater neighborhood structure, which is particularly robust to changes in illumination. The method integrates deep-learning based crater detection, Crater Neighborhood Structure features (CNSFs) construction, CNSF similarity-based matching, and outlier removal. To evaluate the effectiveness of the proposed method, we created an evaluation dataset, comprising Multi-illumination Lunar Orbiter Images (MiLOIs) from different latitudes (a total of 321 image pairs). And comparative experiments have been conducted using the proposed method and state-of-the-art image matching methods. The experimental results indicate that the proposed approach exhibits greater robustness and accuracy against variations in illumination. Full article
(This article belongs to the Special Issue Remote Sensing and Photogrammetry Applied to Deep Space Exploration)
Show Figures

Graphical abstract

28 pages, 8102 KiB  
Article
Multi-Neighborhood Sparse Feature Selection for Semantic Segmentation of LiDAR Point Clouds
by Rui Zhang, Guanlong Huang, Fengpu Bao and Xin Guo
Remote Sens. 2025, 17(13), 2288; https://doi.org/10.3390/rs17132288 - 3 Jul 2025
Viewed by 354
Abstract
LiDAR point clouds, as direct carriers of 3D spatial information, comprehensively record the geometric features and spatial topological relationships of object surfaces, providing intelligent systems with rich 3D scene representation capability. However, current point cloud semantic segmentation methods primarily extract features through operations [...] Read more.
LiDAR point clouds, as direct carriers of 3D spatial information, comprehensively record the geometric features and spatial topological relationships of object surfaces, providing intelligent systems with rich 3D scene representation capability. However, current point cloud semantic segmentation methods primarily extract features through operations such as convolution and pooling, yet fail to adequately consider sparse features that significantly influence the final results of point cloud-based scene perception, resulting in insufficient feature representation capability. To address these problems, a sparse feature dynamic graph convolutional neural network, abbreviated as SFDGNet, is constructed in this paper for LiDAR point clouds of complex scenes. In the context of this paper, sparse features refer to feature representations in which only a small number of activation units or channels exhibit significant responses during the forward pass of the model. First, a sparse feature regularization method was used to motivate the network model to learn the sparsified feature weight matrix. Next, a split edge convolution module, abbreviated as SEConv, was designed to extract the local features of the point cloud from multiple neighborhoods by dividing the input feature channels, and to effectively learn sparse features to avoid feature redundancy. Finally, a multi-neighborhood feature fusion strategy was developed that combines the attention mechanism to fuse the local features of different neighborhoods and obtain global features with fine-grained information. Taking S3DIS and ScanNet v2 datasets, we evaluated the feasibility and effectiveness of SFDGNet by comparing it with six typical semantic segmentation models. Compared with the benchmark model DGCNN, SFDGNet improved overall accuracy (OA), mean accuracy (mAcc), mean intersection over union (mIoU), and sparsity by 1.8%, 3.7%, 3.5%, and 85.5% on the S3DIS dataset, respectively. The mIoU on the ScanNet v2 validation set, mIoU on the test set, and sparsity were improved by 3.2%, 7.0%, and 54.5%, respectively. Full article
(This article belongs to the Special Issue Remote Sensing for 2D/3D Mapping)
Show Figures

Graphical abstract

22 pages, 3237 KiB  
Article
Local Polar Coordinate Feature Representation and Heterogeneous Fusion Framework for Accurate Leaf Image Retrieval
by Mengjie Ye, Yong Cheng, Yongqi Yuan, De Yu and Ge Jin
Symmetry 2025, 17(7), 1049; https://doi.org/10.3390/sym17071049 - 3 Jul 2025
Viewed by 234
Abstract
Leaf shape is a crucial visual cue for plant recognition. However, distinguishing among plants with high inter-class shape similarity remains a significant challenge, especially among cultivars within the same species where shape differences can be extremely subtle. To address this issue, we propose [...] Read more.
Leaf shape is a crucial visual cue for plant recognition. However, distinguishing among plants with high inter-class shape similarity remains a significant challenge, especially among cultivars within the same species where shape differences can be extremely subtle. To address this issue, we propose a novel shape representation and an advanced heterogeneous fusion framework for accurate leaf image retrieval. Specifically, based on the local polar coordinate system, multiscale analysis, and statistical histograms, we first propose local polar coordinate feature representation (LPCFR), which captures spatial distribution from two orthogonal directions while encoding local curvature characteristics. Next, we present heterogeneous feature fusion with exponential weighting and Ranking (HFER), which enhances the compatibility and robustness of fused features by applying exponential weighted normalization and ranking-based encoding within neighborhood distance measures. Extensive experiments on both species-level and cultivar-level leaf datasets demonstrate that the proposed representation effectively captures shape features, and the fusion framework successfully integrates heterogeneous features, outperforming state-of-the-art (SOTA) methods. Full article
(This article belongs to the Section Computer)
Show Figures

Figure 1

19 pages, 25047 KiB  
Article
Hash-Guided Adaptive Matching and Progressive Multi-Scale Aggregation for Reference-Based Image Super-Resolution
by Lin Wang, Jiaqi Zhang, Huan Kang, Haonan Su and Minghua Zhao
Appl. Sci. 2025, 15(12), 6821; https://doi.org/10.3390/app15126821 - 17 Jun 2025
Viewed by 322
Abstract
Reference-based super-resolution (RefSR) enhances the detail restoration capability of low-resolution images (LR) by utilizing the details and texture information of external reference images (Ref). This study proposes a RefSR method based on hash adaptive matching and progressive multi-scale dynamic aggregation to improve the [...] Read more.
Reference-based super-resolution (RefSR) enhances the detail restoration capability of low-resolution images (LR) by utilizing the details and texture information of external reference images (Ref). This study proposes a RefSR method based on hash adaptive matching and progressive multi-scale dynamic aggregation to improve the super-resolution reconstruction capability. Firstly, to address the issue of feature matching, this chapter proposes a hash adaptive matching module. On the basis of similarity calculation between traditional LR images and Ref images, self-similarity information of LR images is added to assist in super-resolution reconstruction. By dividing the feature space into multiple hash buckets through spherical hashing, the matching range is narrowed down from global search to local neighborhoods, enabling efficient matching in more informative regions. This not only retains global modeling capabilities, but also significantly reduces computational costs. In addition, a learnable similarity scoring function has been designed to adaptively optimize the similarity score between LR images and Ref images, improving matching accuracy. Secondly, in the process of feature transfer, this chapter proposes a progressive multi-scale dynamic aggregation module. This module utilizes dynamic decoupling filters to simultaneously perceive texture information in both spatial and channel domains, extracting key information more accurately and effectively suppressing irrelevant texture interference. In addition, this module enhances the robustness of the model to large-scale biases by gradually adjusting features at different scales, ensuring the accuracy of texture transfer. The experimental results show that this method achieves superior super-resolution reconstruction performance on multiple benchmark datasets. Full article
Show Figures

Figure 1

16 pages, 3228 KiB  
Article
Symbolic Regression-Based Modeling for Aerodynamic Ground-to-Flight Deviation Laws of Aerospace Vehicles
by Di Ding, Qing Wang, Qin Chen and Lei He
Aerospace 2025, 12(6), 455; https://doi.org/10.3390/aerospace12060455 - 22 May 2025
Viewed by 420
Abstract
The correlation between aerodynamic data obtained from ground and flight tests is crucial in developing aerospace vehicles. This paper proposes methods for modelling this correlation that combine feature extraction and symbolic regression. The neighborhood component analysis (NCA) method is utilized to extract features [...] Read more.
The correlation between aerodynamic data obtained from ground and flight tests is crucial in developing aerospace vehicles. This paper proposes methods for modelling this correlation that combine feature extraction and symbolic regression. The neighborhood component analysis (NCA) method is utilized to extract features from the high-dimensional state space and then symbolic regression (SR) is applied to find the concise optimal expression. First, a simulation example of the NASA Twin Otter aircraft is used to validate the NCA and the SR tool developed by the research team in modeling the aerodynamic coefficient deviation between ground and flight due to an unpredictable inflight icing failure. Then, the method and tool are applied to real flight tests of two types of aerospace vehicles with different configurations. The final optimized mathematical models show that the two vehicles’ pitching moment coefficient deviations are related to the angle of attack (AOA) only. The mathematical model built using NCA and the SR tool demonstrates higher fitting accuracy and better generalization performance for flight test data than other typical data-driven methods. The mathematical model delivers a multi-fold enhancement in fitting accuracy over data-driven methods for all fight cases. For UAV flight test data, the average root mean square error (RMSE) of the mathematical model demonstrates a maximum improvement of 37% in accuracy compared to three data-driven methods. For XRLV flight test data, the prediction accuracy of the mathematical model shows an enhancement exceeding 80% relative to Gaussian kernel SVM and Gaussian process data-driven models. The research verifies the feasibility and effectiveness of the data feature extraction combined with the symbolic regression method in mining the correlation law between ground and flight deviations of aerodynamic characteristics. This study provides valuable insight for modeling problems with finite data samples and explicit physical meanings. Full article
(This article belongs to the Special Issue Flight Dynamics, Control & Simulation (2nd Edition))
Show Figures

Figure 1

17 pages, 4722 KiB  
Article
Research on Bearing Fault Diagnosis Based on Vibration Signals and Deep Learning Models
by Bin Yuan, Lingkai Lu and Suifan Chen
Electronics 2025, 14(10), 2090; https://doi.org/10.3390/electronics14102090 - 21 May 2025
Viewed by 437
Abstract
To overcome the limitations of characteristic parameter identification and inadequate fault recognition rates in bearings, a bearing fault diagnosis method combining the improved whale optimization algorithm (IWOA), variational mode decomposition (VMD), and kernel extreme learning machine (KELM) is proposed. Firstly, to improve the [...] Read more.
To overcome the limitations of characteristic parameter identification and inadequate fault recognition rates in bearings, a bearing fault diagnosis method combining the improved whale optimization algorithm (IWOA), variational mode decomposition (VMD), and kernel extreme learning machine (KELM) is proposed. Firstly, to improve the convergence behavior and global search capability of the WOA, we introduced adaptive weight, a variable spiral shape parameter, and a Cauchy neighborhood perturbation strategy to improve the performance of the original algorithm. Secondly, to enhance the effectiveness of feature extraction, the IWOA was used to optimize the number of modal components and penalty coefficients in the VMD algorithm; then, we could obtain the optimal modal components and construct feature vectors based on the optimal modal components. Next, we used the IWOA to optimize the two key parameters, the regularization coefficient C and kernel parameter γ of KELM, and the feature vector was used as the input of KELM to achieve fault diagnosis. Finally, data collected from different experimental platforms were used for experimental analysis. The results indicate that the IWOA-VMD-KELM bearing fault diagnosis model significantly improved its accuracy compared to other models, achieving accuracies of 98.8% and 98.4% on the CWRU dataset and Southeast University dataset, respectively. Full article
Show Figures

Figure 1

21 pages, 11194 KiB  
Article
A Dynamic Regional-Aggregation-Based Heterogeneous Graph Neural Network for Traffic Prediction
by Xiangting Liu, Chengyuan Qian and Xueyang Zhao
Mathematics 2025, 13(9), 1458; https://doi.org/10.3390/math13091458 - 29 Apr 2025
Viewed by 627
Abstract
Traffic flow prediction, crucial for intelligent transportation systems, has seen advancements with graph neural networks (GNNs), yet existing methods often fail to distinguish between the importance of different intersections. These methods usually model all intersections uniformly, overlooking significant differences in traffic flow characteristics [...] Read more.
Traffic flow prediction, crucial for intelligent transportation systems, has seen advancements with graph neural networks (GNNs), yet existing methods often fail to distinguish between the importance of different intersections. These methods usually model all intersections uniformly, overlooking significant differences in traffic flow characteristics and influence ranges between ordinary and important nodes. To tackle this, this study introduces a dynamic regional-aggregation-based heterogeneous graph neural network (DR-HGNN). This model categorizes intersections into two types—ordinary and important—to apply tailored feature aggregation strategies. Ordinary intersections aggregate features based on local neighborhood information, whereas important intersections utilize deeper neighborhood diffusion and multi-hop dependencies to capture broader traffic influences. The DR-HGNN model also employs a dynamic graph structure to reflect temporal changes in traffic flows, alongside an attention mechanism for adaptive regional feature aggregation, enhancing the identification of critical traffic nodes. Demonstrating its efficacy, the DR-HGNN achieved 19.2% and 15.4% improvements in the RMSE over 50 min predictions in the METR-LA and PEMS-BAY datasets, respectively, offering a more precise prediction method for traffic management. Full article
(This article belongs to the Special Issue Modern Methods and Applications Related to Integrable Systems)
Show Figures

Figure 1

15 pages, 8846 KiB  
Article
An Effective Mixed-Precision Quantization Method for Joint Image Deblurring and Edge Detection
by Luo Tian and Peng Wang
Electronics 2025, 14(9), 1767; https://doi.org/10.3390/electronics14091767 - 27 Apr 2025
Viewed by 664
Abstract
Deploying deep neural networks (DNNs) for joint image deblurring and edge detection often faces challenges due to large model size, which restricts practical applicability. Although quantization has emerged as an effective solution to this issue, conventional quantization methods frequently struggle to optimize for [...] Read more.
Deploying deep neural networks (DNNs) for joint image deblurring and edge detection often faces challenges due to large model size, which restricts practical applicability. Although quantization has emerged as an effective solution to this issue, conventional quantization methods frequently struggle to optimize for the unique characteristics of the targeted model. This paper introduces a mixed-precision quantization method that dynamically adjusts quantization precision based on the edge regions of the input image. High-precision quantization is applied to edge neighborhoods to preserve critical details, while low-precision quantization is employed in other areas to reduce computational overhead. In addition, a zero-skipping computation strategy is designed for model deployment, thereby enhancing computational efficiency when processing sparse input feature maps. The experimental results demonstrate that the proposed method significantly outperforms existing quantization methods in model accuracy across different edge neighborhood settings (achieving 97.54% to 98.23%) while also attaining optimal computational efficiency under both 3 × 3 and 5 × 5 edge neighborhood configurations. Full article
Show Figures

Figure 1

20 pages, 6782 KiB  
Article
Validating Pedestrian Infrastructure Data: How Well Do Street-View Imagery Audits Compare to Government Field Data?
by Sajad Askari, Devon Snyder, Chu Li, Michael Saugstad, Jon E. Froehlich and Yochai Eisenberg
Urban Sci. 2025, 9(4), 130; https://doi.org/10.3390/urbansci9040130 - 17 Apr 2025
Viewed by 1192
Abstract
Data on pedestrian infrastructure is essential for improving the mobility environment and for planning efficiency. Although governmental agencies are responsible for capturing data on pedestrian infrastructure mostly by field audits, most have not completed such audits. In recent years, virtual auditing based on [...] Read more.
Data on pedestrian infrastructure is essential for improving the mobility environment and for planning efficiency. Although governmental agencies are responsible for capturing data on pedestrian infrastructure mostly by field audits, most have not completed such audits. In recent years, virtual auditing based on street view imagery (SVI), specifically through geo-crowdsourcing platforms, offers a more inclusive approach to pedestrian movement planning, but concerns about the quality and reliability of opensource geospatial data pose barriers to use by governments. Limited research has compared opensource data in relation to traditional government approaches. In this study, we compare pedestrian infrastructure data from an opensource virtual sidewalk audit platform (Project Sidewalk) with government data. We focus on neighborhoods with diverse walkability and income levels in the city of Seattle, Washington and in DuPage County, Illinois. Our analysis shows that Project Sidewalk data can be a reliable alternative to government data for most pedestrian infrastructure features. The agreement for different features ranges from 75% for pedestrian signals to complete agreement (100%) for missing sidewalks. However, variations in measuring the severity of barriers challenges dataset comparisons. Full article
Show Figures

Figure 1

Back to TopTop