计算机科学最新文献

筛选
英文 中文
A risk assessment framework for online transactions via Graph Neural Networks and efficient probabilistic prediction 基于图神经网络和高效概率预测的在线交易风险评估框架
IF 8 2区 计算机科学
Engineering Applications of Artificial Intelligence Pub Date : 2025-10-21 DOI: 10.1016/j.engappai.2025.112766
Jicai Chang , Xuejing Fu , Zhen Chen , Li Pan , Shijun Liu
{"title":"A risk assessment framework for online transactions via Graph Neural Networks and efficient probabilistic prediction","authors":"Jicai Chang ,&nbsp;Xuejing Fu ,&nbsp;Zhen Chen ,&nbsp;Li Pan ,&nbsp;Shijun Liu","doi":"10.1016/j.engappai.2025.112766","DOIUrl":"10.1016/j.engappai.2025.112766","url":null,"abstract":"<div><div>Transactions are integral to daily life, but the occurrence of abnormal behaviors can lead to significant risks. Online transaction risk is characterized by the accumulation of abnormal behaviors, where their frequency surpasses a predefined threshold, resulting in measurable probabilities and consequences. Therefore, the assessment of online transaction risk heavily depends on probabilistic predictions of the accumulated frequency of abnormal behaviors, presenting two major challenges. Firstly, abnormal behaviors across different instances (e.g., behavior types, product categories, regions, and platforms) exhibit temporal correlations, such as co-occurrence and concomitance, which most probabilistic models fail to identify and utilize effectively. Additionally, these models do not fully address the real-time demands. To address these challenges, we propose a novel risk assessment framework based on Graph Neural Network (GNN) and probabilistic prediction, named GNN-Probformer. The framework uses Dynamic Time Warping to capture temporal correlations between abnormal behavior frequency sequences and constructs a graph structure through clustering. It then employs Graph Neural Networks to aggregate features and learn representations through a novel embedding module. A sparse self-attention mechanism and an efficient encoder–decoder architecture are incorporated to further enhance performance, while probabilistic predictions are generated through Monte Carlo sampling and cumulative distribution functions. Experimental results on a real-world dataset demonstrate that GNN-Probformer achieves substantial performance gains, with a 15% reduction in normalized deviation. At the 90th percentile, it further reduces normalized quantile loss by 15% and improves the F1-score by 16%, while also reducing training time and inference time by 47% and 38%, respectively.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"163 ","pages":"Article 112766"},"PeriodicalIF":8.0,"publicationDate":"2025-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145335264","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems publication information IEEE集成电路与系统计算机辅助设计汇刊
IF 2.9 3区 计算机科学
IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems Pub Date : 2025-10-21 DOI: 10.1109/TCAD.2025.3613885
{"title":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems publication information","authors":"","doi":"10.1109/TCAD.2025.3613885","DOIUrl":"https://doi.org/10.1109/TCAD.2025.3613885","url":null,"abstract":"","PeriodicalId":13251,"journal":{"name":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems","volume":"44 11","pages":"C3-C3"},"PeriodicalIF":2.9,"publicationDate":"2025-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11211510","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145335299","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
A novel framework for segmenting open-pit mining road 一种新的露天采矿道路分段框架
IF 8 2区 计算机科学
Engineering Applications of Artificial Intelligence Pub Date : 2025-10-21 DOI: 10.1016/j.engappai.2025.112811
Shuo Fan , Yachun Mao , Shuai Zhen , Jing Liu , Liming He , Xinqi Mao
{"title":"A novel framework for segmenting open-pit mining road","authors":"Shuo Fan ,&nbsp;Yachun Mao ,&nbsp;Shuai Zhen ,&nbsp;Jing Liu ,&nbsp;Liming He ,&nbsp;Xinqi Mao","doi":"10.1016/j.engappai.2025.112811","DOIUrl":"10.1016/j.engappai.2025.112811","url":null,"abstract":"<div><div>Accurate segmentation of open-pit mine road networks presents a critical challenge for mine digitization and autonomous driving applications. These roads are prone to mechanical compaction, geological erosion, and coverage by gravel dust, resulting in segmentation outcomes characterized by blurred boundaries, holes, fractures, and geometric deformations, which severely compromise measurement accuracy. To address these challenges, this paper proposes the Mining Road Segmentation Network (MRS-Net), which integrates local features with global semantics. First, a Residual Network Version 2 (ResNetV2)-Transformer cascaded encoder is constructed, employing residual connections to preserve sub-pixel-level edge details and multi-head self-attention to establish long-range dependencies, thereby enhancing the representation of weak texture features. Second, the Road Multi-scale Features Fusion Module (RMFF) was designed to extract local geometric features and global continuity features through progressive hollow convolution, enabling the model to extract multi-scale features and effectively suppress interference from gravel dust. Finally, a progressive decoding architecture incorporating bilinear interpolation is adopted to improve edge smoothness. MRS-Net is evaluated on an Unmanned Aerial Vehicle (UAV)-acquired road dataset from the Anshan open-pit iron mine in Liaoning Province, China. Results demonstrate that MRS-Net achieves superior segmentation performance compared to models such as DeepLabV3+ and TransUNet across three distinct scenarios: main roads, temporary roads, and abandoned roads. Specifically, it achieves Intersection over Union (IoU), Dice coefficient(Dice), and Kappa coefficient (Kappa) values of 89.4 % / 94.1 % / 87.2 %, 75.7 % / 83.3 % / 75.1 %, and 83.8 % / 90.0 % / 84.85 % respectively for these scenarios.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"163 ","pages":"Article 112811"},"PeriodicalIF":8.0,"publicationDate":"2025-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145334909","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Task scheduling strategy for mitigating cold start impact in serverless edge computing optical networks 缓解无服务器边缘计算光网络冷启动影响的任务调度策略
IF 4.3 2区 计算机科学
Journal of Optical Communications and Networking Pub Date : 2025-10-21 DOI: 10.1364/JOCN.561045
Shan Yin;Shuyao Wang;Chenyu You;Rongxuan Guo;Mengru Cai;Shanguo Huang
{"title":"Task scheduling strategy for mitigating cold start impact in serverless edge computing optical networks","authors":"Shan Yin;Shuyao Wang;Chenyu You;Rongxuan Guo;Mengru Cai;Shanguo Huang","doi":"10.1364/JOCN.561045","DOIUrl":"https://doi.org/10.1364/JOCN.561045","url":null,"abstract":"As emerging technologies advance, the demand for real-time processing of large-scale data grows increasingly critical. This paper focuses on a scenario of serverless edge computing (SEC) supported by optical networks, which integrates SEC’s key features (e.g., auto-scaling and edge deployment of computing resources) with the transmission advantages of optical networks to enable efficient data processing. However, this scenario brings new challenges beyond the scope of traditional task scheduling strategies. On the one hand, task scheduling needs to consider the resource limitations of computing nodes and dependencies between serverless functions; on the other hand, cold start issues caused by the “scale-to-zero” characteristic of SEC significantly impact latency-sensitive tasks. Moreover, existing container warming strategies for mitigating cold start suffer from resource waste and are disconnected from network scheduling. Therefore, this paper proposes a container warming and task scheduling strategy based on reinforcement learning (CWS-RL), which aims to mitigate the impact of cold start, reduce task latency, and control container warming costs. It makes dynamic container warming decisions based on long short-term memory (LSTM) network prediction results and incorporates the dependency slack characteristics of serverless tasks. Meanwhile, it adopts the Deep Deterministic Policy Gradient (DDPG) algorithm to achieve collaborative optimization of container warming and communication scheduling. Compared to the four baseline algorithms, CWS-RL achieves an average latency reduction of 24.08% and an average container warming costs reduction of 17.48%.","PeriodicalId":50103,"journal":{"name":"Journal of Optical Communications and Networking","volume":"17 12","pages":"D192-D208"},"PeriodicalIF":4.3,"publicationDate":"2025-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145335348","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Inverse compensation and adaptive fuzzy integral sliding-mode control for the underactuated soft massage physiotherapy robot 欠驱动软按摩理疗机器人的逆补偿与自适应模糊积分滑模控制
IF 8 2区 计算机科学
Engineering Applications of Artificial Intelligence Pub Date : 2025-10-21 DOI: 10.1016/j.engappai.2025.112792
Zixin Huang , Chengsong Yu , Junjie Lu , Hao Liu , Peng Huang
{"title":"Inverse compensation and adaptive fuzzy integral sliding-mode control for the underactuated soft massage physiotherapy robot","authors":"Zixin Huang ,&nbsp;Chengsong Yu ,&nbsp;Junjie Lu ,&nbsp;Hao Liu ,&nbsp;Peng Huang","doi":"10.1016/j.engappai.2025.112792","DOIUrl":"10.1016/j.engappai.2025.112792","url":null,"abstract":"<div><div>Acupoint massage physiotherapy is a kind of effective method to prevent and remedy diseases. Soft robotics technology is thriving, which has potential applications in the field of acupoint massage physiotherapy. Soft massage physiotherapy robot (SMPR) uses the soft robotics technology to realize the acupoint massage physiotherapy function. In this paper, an SMPR consisting of a wearable armor and several pneumatic physiotherapy actuators (PPAs) is design and fabricated. In order to describe complex hysteresis behavior of SMPR, the dynamic model of its PPA is established and identified, which includes two parts: a linear model and an asymmetric Prandtl–Ishlinskii hysteresis (APIH) model. An inverse compensator is then designed to compensate for the hysteresis behavior of the SMPR based on the APIH model, and an approximately linearized system is obtained. Then, by dint of the artificial intelligence method, a fuzzy approximator is designed to approximate the control system’s lumped uncertainty, which includes external disturbances, modeling errors and parameter perturbations. Further, an adaptive fuzzy integral sliding-mode control (AFISMC) is employed to handle the lump uncertainty. Moreover, based on the back-stepping control method, a nominal controller is designed to realize the control of the approximately linearized system. By combining the inverse compensator, fuzzy approximator, AFISMC and nominal controller, the control of the SMPR is realized and the acupoint massage physiotherapy can be controlled accurately. The stabilization to a control systems is theoretically demonstrated. Finally, the experimental results from multiple test scenarios conclusively demonstrate the efficacy and trajectory tracking capability of the developed control strategy.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"163 ","pages":"Article 112792"},"PeriodicalIF":8.0,"publicationDate":"2025-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145334885","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Accurate multi-step wind and solar power forecasting based on multi-scale convolutional Kolmogorov-Arnold network and improved Lemming-optimized attention fusion 基于多尺度卷积Kolmogorov-Arnold网络和改进的旅鼠优化注意力融合的多步风能和太阳能准确预测
IF 8 2区 计算机科学
Engineering Applications of Artificial Intelligence Pub Date : 2025-10-21 DOI: 10.1016/j.engappai.2025.112832
Siyuan Chen , Hang Wan , Botao Peng , Rui Quan , Yufang Chang , William Derigent
{"title":"Accurate multi-step wind and solar power forecasting based on multi-scale convolutional Kolmogorov-Arnold network and improved Lemming-optimized attention fusion","authors":"Siyuan Chen ,&nbsp;Hang Wan ,&nbsp;Botao Peng ,&nbsp;Rui Quan ,&nbsp;Yufang Chang ,&nbsp;William Derigent","doi":"10.1016/j.engappai.2025.112832","DOIUrl":"10.1016/j.engappai.2025.112832","url":null,"abstract":"<div><div>With the deepening of power market reform, the increasing share of wind and solar energy introduces significant challenges for power system stability due to the high volatility and uncertainty of weather-dependent generation. Accurate multi-step ultra-short-term forecasting is therefore essential for ensuring power balance and effective dispatch coordination in smart grids. To address this issue, we propose a novel hybrid deep learning framework that integrates a multi-scale convolutional Kolmogorov-Arnold network (MCKAN) to improve forecasting performance. This network is specifically designed to capture high-dimensional spatial and temporal features across multiple levels of abstraction. To improve feature selection and scale-specific weight allocation, we integrate an Efficient Additive Attention (EAA) mechanism, which is applied for the first time in the context of renewable energy forecasting. In addition, a Chaotic Quasi-Reverse Artificial Lemming Algorithm (CQALA) is proposed to automatically optimize the complex multivariate hyperparameters, enabling optimal hyperparameter selection and improving the model's overall predictive performance. Extensive experiments on a two-year wind and photovoltaic power dataset from the State Grid of China demonstrate that the proposed method outperforms several state-of-the-art models. For multi-step forecasting, the mean absolute error is reduced by up to 27.6 percent for photovoltaic power and 33.4 percent for wind power, highlighting the practical value of the proposed approach in real-world renewable energy management.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"163 ","pages":"Article 112832"},"PeriodicalIF":8.0,"publicationDate":"2025-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145334911","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
A metaheuristic-driven categorical boosting framework with interpretability for high-precision prediction of mechanical properties in corroded reinforced concrete beams 一个具有解释性的元启发式驱动的分类增强框架,用于腐蚀钢筋混凝土梁的力学性能的高精度预测
IF 8 2区 计算机科学
Engineering Applications of Artificial Intelligence Pub Date : 2025-10-21 DOI: 10.1016/j.engappai.2025.112804
Yuzhuo Zhang , Zheng Wang , Jinlong Liu , Yalin Li , Zhenqin Huang , Xiaohu Yu
{"title":"A metaheuristic-driven categorical boosting framework with interpretability for high-precision prediction of mechanical properties in corroded reinforced concrete beams","authors":"Yuzhuo Zhang ,&nbsp;Zheng Wang ,&nbsp;Jinlong Liu ,&nbsp;Yalin Li ,&nbsp;Zhenqin Huang ,&nbsp;Xiaohu Yu","doi":"10.1016/j.engappai.2025.112804","DOIUrl":"10.1016/j.engappai.2025.112804","url":null,"abstract":"<div><div>The degradation of mechanical properties in corroded reinforced concrete (RC) beams presents a major challenge for assessing structural durability. To address this issue, this study proposes an integrated machine learning (ML) framework to predict the mechanical properties of such beams. First, a database of 464 samples was established, including 12 input parameters and 2 output parameters, followed by correlation analysis of the inputs. On this basis, the applicability of existing design codes and empirical models was evaluated. Subsequently, eight ML models were trained, with their hyperparameters optimized via Bayesian optimization (BO) to enhance prediction accuracy. The Categorical Boosting (CatBoost) model was identified as the most accurate, and its hyperparameters were further optimized using Particle Swarm Optimization (PSO) and Genetic Algorithm (GA) for improved performance. Results show the PSO-optimized CatBoost model achieves the highest prediction accuracy to date: for the flexural strength test set, the coefficient of determination (<em>R</em><sup><em>2</em></sup>) is 0.984 and root mean square error (<em>RMSE</em>) is 3.1602; for the deflection test set, <em>R</em><sup><em>2</em></sup> is 0.975 and <em>RMSE</em> is 0.6259. Compared with design codes, flexural strength test set <em>R</em><sup><em>2</em></sup> increases by 27.3 % and <em>RMSE</em> decreases by 72.8 %; versus traditional models like Support Vector Regression (SVR), <em>R</em><sup><em>2</em></sup> rises by 5.4 % and <em>RMSE</em> drops by 43.5 %. Additionally, SHapley Additive exPlanations (SHAP) analysis reveals geometric parameters (beam height, beam width) dominate flexural strength, while elastic stiffness and beam length drive deflection. Finally, a user-friendly graphical user interface (GUI) was developed for rapid mechanical property assessment of corroded RC beams.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"163 ","pages":"Article 112804"},"PeriodicalIF":8.0,"publicationDate":"2025-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145334915","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Deep learning-based on-site identification and volume measurement of bulk material in construction industry 基于深度学习的建筑行业散体材料现场识别与体积测量
IF 8 2区 计算机科学
Engineering Applications of Artificial Intelligence Pub Date : 2025-10-21 DOI: 10.1016/j.engappai.2025.112797
Zhen Cai , Ghaith Allah Chebil , Yuan Tan , Stephan Kessler , Johannes Fottner
{"title":"Deep learning-based on-site identification and volume measurement of bulk material in construction industry","authors":"Zhen Cai ,&nbsp;Ghaith Allah Chebil ,&nbsp;Yuan Tan ,&nbsp;Stephan Kessler ,&nbsp;Johannes Fottner","doi":"10.1016/j.engappai.2025.112797","DOIUrl":"10.1016/j.engappai.2025.112797","url":null,"abstract":"<div><div>Bulk materials are important raw construction materials, the adequate and precise supply of which enables a smooth construction process. Two conventional techniques for controlling the quantity of bulk materials on-site along the supply chain are: 1) estimation based on the cone-shape of the material pile, but the accuracy is low; 2) calculation by using bulk density and weighing stations, which are not available in all facilities. To address this issue, we propose a novel hybrid camera-based method combining a red-green-blue (RGB) camera and a light detection and ranging (LiDAR) sensor for automatic material type identification and volume measurement. The data from two-dimensional pictures and three-dimensional point cloud were segmented and extracted with two Deep Learning models: “You Only Look Once“ (YOLO) v5 and PointNet++for the identification of material type and volume measurement. This novel hybrid camera-based method was developed as an Industry 4.0 solution to enable the automatic and accurate evaluation of the volume of bulk materials. With a precision of 81.6 % in object recognition and a volume estimation deviation of less than 8 %, it provides a reliable and efficient alternative to conventional, labour-intensive measurement techniques.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"163 ","pages":"Article 112797"},"PeriodicalIF":8.0,"publicationDate":"2025-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145334890","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Predicting tourism demand using data based on a two-stage feature selection: A hybrid deep learning approach incorporating Time2Vec 基于两阶段特征选择的数据预测旅游需求:结合Time2Vec的混合深度学习方法
IF 8 2区 计算机科学
Engineering Applications of Artificial Intelligence Pub Date : 2025-10-21 DOI: 10.1016/j.engappai.2025.112768
Jinghui Wei , Sheng Wu , Qiangwen Zheng
{"title":"Predicting tourism demand using data based on a two-stage feature selection: A hybrid deep learning approach incorporating Time2Vec","authors":"Jinghui Wei ,&nbsp;Sheng Wu ,&nbsp;Qiangwen Zheng","doi":"10.1016/j.engappai.2025.112768","DOIUrl":"10.1016/j.engappai.2025.112768","url":null,"abstract":"<div><div>Accurate tourism demand forecasting is important for regional tourism planning, management, and industry development. However, existing models often struggle with the complexity of external variables or fail to capture essential temporal patterns and multi-scale temporal correlations, directly limiting their accuracy and robustness. Therefore, we propose a predictor with Two-Stage Feature Selection and Time2Vec-enhanced Extraction Mechanisms (TFS-T2VEM). The model employs a two-stage feature selection strategy to refine predictive variables and integrates a Time2Vec-driven temporal pattern extraction module to effectively capture key temporal patterns across multiple scales. By leveraging multi-scale features from intermediate layers of Convolutional Neural Networks (CNN), it captures both mid-short-term fluctuations and long-term trends. Time2Vec further serves as an implicit temporal decomposition module, replacing traditional methods by embedding temporal information directly into the network. This enables dynamic attention adjustment based on intrinsic periodicity and external disturbances, enhancing the temporal attention mechanism by focusing on critical time points and reducing noise from irrelevant features. These improvements ultimately contribute to higher predictive accuracy and robustness. Extensive experiments on three datasets show that our model consistently outperforms baseline methods, confirming its effectiveness in tourism demand forecasting.</div></div>","PeriodicalId":50523,"journal":{"name":"Engineering Applications of Artificial Intelligence","volume":"163 ","pages":"Article 112768"},"PeriodicalIF":8.0,"publicationDate":"2025-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145334913","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Window normalization: Enhancing point cloud understanding by unifying inconsistent point densities 窗口归一化:通过统一不一致的点密度来增强对点云的理解
IF 4.2 3区 计算机科学
Image and Vision Computing Pub Date : 2025-10-21 DOI: 10.1016/j.imavis.2025.105789
Qi Wang , Sheng Shi , Jiahui Li , Wuming Jiang , Xiangde Zhang
{"title":"Window normalization: Enhancing point cloud understanding by unifying inconsistent point densities","authors":"Qi Wang ,&nbsp;Sheng Shi ,&nbsp;Jiahui Li ,&nbsp;Wuming Jiang ,&nbsp;Xiangde Zhang","doi":"10.1016/j.imavis.2025.105789","DOIUrl":"10.1016/j.imavis.2025.105789","url":null,"abstract":"<div><div>Downsampling and feature extraction are essential procedures for 3D point cloud understanding. Existing methods are limited by the inconsistent point densities of different parts in the point cloud. In this work, we analyze the limitation of the downsampling stage and propose the pre-abstraction group-wise window-normalization module. In particular, the window-normalization method is leveraged to unify the point densities in different parts. Furthermore, the group-wise strategy is proposed to obtain multi-type features, including texture and spatial information. We also propose the pre-abstraction module to balance local and global features. Extensive experiments show that our module performs better on several tasks. In segmentation tasks on S3DIS (Area 5), the proposed module performs better on small object recognition, and the results have more precise boundaries than others. The recognition of the sofa and the column is improved from 69.2% to 84.4% and from 42.7% to 48.7%, respectively. The benchmarks are improved from 71.7%/77.6%/91.9% (mIoU/mAcc/OA) to 72.2%/78.2%/91.4%. The accuracies of 6-fold cross-validation on S3DIS are 77.6%/85.8%/91.7% (mIoU/mAcc/OA). It outperforms the best model PointNeXt-XL (74.9%/83.0%/90.3% (mIoU/mAcc/OA)) by 2.7% on mIoU and achieves state-of-the-art performance.</div></div>","PeriodicalId":50374,"journal":{"name":"Image and Vision Computing","volume":"164 ","pages":"Article 105789"},"PeriodicalIF":4.2,"publicationDate":"2025-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145335055","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信