检索结果-内蒙古大学图书馆

Attention-augmented and depthwise separable convolutional message passing for robust fraud detection in large-scale graphs

引用

Journal of Advanced Research 2025年

作者： Ijeoma A. Chikwendu Xiaoling Zhang Chiagoziem C. Ukwuoma Chibueze D. Ukwuoma Isaac Adjei-Mensah Chinedu I. Otuka Chukwuebuka Joseph Ejiyi Yeong Hyeon Gu Mugahed A. Al-antari School of Information and Communication Engineering University of Electronic Science and Technology of China 611731 Chengdu China College of Nuclear Technology and Automation Engineering Chengdu University of Technology Sichuan 610059 China Sichuan Engineering Technology Research Center for Industrial Internet Intelligent Monitoring and Application Chengdu University of Technology Sichuan 610059 China School of Information and Software Engineering University of Electronic Science and Technology of China Sichuan 610059 China Network and Data Security Key Laboratory of Sichuan Province University of Electronic Science and Technology of China Chengdu Sichuan China Department of Artificial Intelligence and Data Science College of AI Convergence Daeyang AI Center Sejong University Seoul 05006 Republic of Korea

Introduction Graph Neural Networks (GNNs) have shown great promise in fraud detection tasks on graph-structured data. However, they struggle with challenges such as label imbalance and the presence of heterophilic neighbours, which can obscure fraudulent behaviour by embedding fraudsters among benign users. Objectives Existing GNN-based models often address these issues by modifying the graph structure to favour homophily, frequently ignoring heterophilic neighbours during message passing. This approach weakens their capacity to detect fraud in real-world graphs. Addressing this gap is crucial to enhance the effectiveness of fraud detection in large-scale graph. Methods This study proposes Attention-Augmented and Depthwise Separable Convolutional Message Passing (ADSCMP), a novel GNN framework. ADSCMP actively partitions neighbours into homophilic, heterophilic, and unknown groups during message passing. It integrates lightweight attention mechanisms to highlight critical nodes and employ depthwise separable convolutions to reduce computational overhead. Furthermore, this study dynamically generates root-specific weight matrices and incorporate both spectral and spatial features to better handle complex graph topologies. Results This study evaluated ADSCMP on four benchmark datasets Amazon, YelpChi, T-Finance, and T-Social. In supervised experiments (40 % labelled data), ADSCMP achieved AUC scores of 97.91 %, 94.17 %, 97.51 %, and 99.75 %, respectively. Even with only 1 % labelled data in semi-supervised settings, the model maintained strong performance with AUCs of 93.15 %, 84.53 %, 94.92 %, and 98.59 %. Our ablation study confirmed that each model component contributed meaningfully to its overall performance. Additionally, ADSCMP reduced inference time compared to competitive baselines, making it suitable for real-time fraud detection. Conclusion By actively learning from both homophilic and heterophilic neighbours and optimizing message passing with efficient con

关键词： Attention mechanism Depthwise separable convolution Graph fraud detection Graph neural networks Message passing

来源：评论

学校读者我要写书评

暂无评论

Effect of thermal-hydraulic parameters and pH on the corrosion product deposition in steam generator based on CFD

引用

Annals of nuclear Energy 2025年 223卷

作者： Yunchen Lai Haiyan Xie Shiyu Tan Ke Wang Dongyun Li Xuesong Li Yang Gao Hongguo Hou Nan Chao Caishan Jiao Yu Zhou Fundamental Science on Nuclear Safety and Simulation Technology Laboratory College of Nuclear Science and Technology Harbin Engineering University Harbin 150001 Heilongjiang Province China Science and Technology on Reactor System Design Technology Laboratory Nuclear Power Institute of China Chengdu 610041 Sichuan Province China

The deposition of corrosion products in the primary circuit of a pressurized water reactors is known to have an adverse impact on reactor system’s performance, which can cause localized corrosion. They can also impede the flow of coolant, or in severe cases block the tube channels. Besides, the deposits have a lower thermal conductivity than the structural materials, which may increase the thermal resistance, thus reducing heat transfer efficiency. Despite the presence of a considerable amount of corrosion products in steam generators, research on the deposition of corrosion products within is still insufficient. A comprehensive 3-D model of thermal–hydraulic and chemical processes was used to investigate the factors affecting the deposition of corrosion products in a steam generator. For the purpose of determine the deposition distribution along the heat transfer tube, the tube was separated into 11 main nodes based on the equal temperature differences according to the thermal–hydraulic data calculated. The simulation results indicate that the deposition thickness is sensitive to coolant temperature, flow velocity and pH value, and it was shown that higher temperature(from 560 K to 600 K decreasing 9.31 %), pH value (from 6.5 to 8.0 decreasing 9.92 %) and lower flow velocity (from 5 m/s to 20 m/s increasing 8.13 %)was effective for reducing the corrosion product deposition due to the physicochemical properties of the coolant and the turbulent flow, while working pressure has less influence on it(from 6 MPa to 15 MPa increasing only 1.03 %).

关键词： Computational fluid dynamics

来源：评论

学校读者我要写书评

暂无评论

A multimodal deep learning approach for very short-term solar forecasts using sky images and historical numerical data

引用

Renewable Energy 2025年 255卷

作者： Anto Leoba Jonathan Olusola Bamisile Dongsheng Cai Chukwuebuka Joseph Ejiyi Joseph Junior Nkou Nkou Kombou Victor Chiagoziem C. Ukwuoma Liu Wei Qi Huang College of Nuclear Technology and Automation Engineering Chengdu University of Technology Sichuan P.R. 610059 China Sichuan Engineering Technology Research Center for Industrial Internet Intelligent Monitoring and Application Chengdu University of Technology Sichuan P.R. 610059 China Energy Environment and Society Division University of Dundee United Kingdom School of Computer Science and Engineering (School of Cyber Security) Shenzhen Institute for Advanced Study University of Electronic Science and Technology of China (UESTC) Chengdu 611731 China

The increased solar energy integration into the power system introduces various issues due to its intermittent nature. As solar power penetration increases, grid management becomes increasingly complex, highlighting the importance of precise solar power forecasts. This paper addresses a critical challenge in solar power integration, highlighting the significance of very short-term solar forecasting (VSTSF) for grid operators. We propose a novel MULSKIN hybrid framework that combines a custom ResNet and a novel targeted feature attention mechanism (TFAM), which dynamically focuses on the most relevant regions in sky images, improving the model's ability to capture essential cloud dynamics and spatiotemporal patterns. Unlike existing methods in literature that either use image (sky images) or numerical (meteorological) data, the proposed MULSKIN approach integrates both data types, allowing for a more holistic understanding of atmospheric conditions. This paper contributes to advancing the field of solar forecasting by presenting a new, effective, and scalable solution suitable for operational deployment in modern energy systems. With six years of high-resolution data, the model outperforms traditional machine learning (ML), deep learning (DL) models, and baseline reference models, achieving a forecast skill score of 32.84 % and a root mean square error (RMSE) of 54.36W/m 2 . Our Results indicate that incorporating sky images alongside numerical meteorological data significantly enhances forecasting accuracy, with the MULSKIN model demonstrating its superiority in capturing dynamic cloud movements and weather patterns over short time horizons. The findings underscore the potential of combining multimodal data sources to address the challenges of VSTSF, offering promising improvements in solar irradiance prediction for real-time grid operations.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Interaction of H2+ molecular beam with thin layer graphene foils

引用

Chinese Physics B 2019年第9期28卷 164-168页

作者： Min Li Guo-Feng Qu Yi-Zhou Wang Zhou-Sen Zhu Mian-Gong Shi Mao-Lei Zhou Dong Liu Zi-Xu Xu Ming-Jiang Song Jun Zhang Fan Bai Xiao-Dong Liao Ji-Feng Han Key Laboratory of Radiation Physics and Technology of the Ministry of Education Institute of Nuclear Science and TechnologySichuan UniversityChengdu 610064China College of Physics and Electronic Engineering Sichuan Normal UniversityChengdu 610066China

The interaction of MeV H2^+ molecular ions with thin layer graphene and graphite foils was studied by using a highresolution electrostatic analyzer.A large number of fragment protons were observed at zero degree(along the beam direction) when the H2^+ beam was passing through the monolayer graphene foil, which indicates that the electron of the H2^+ molecular ions can be stripped easily even by the monolayer graphene *** trailing than leading protons were found in the energy spectrum, which means significant wake effect was observed in the monolayer graphene *** ratio of the numbers of trailing protons over leading protons first increased with the thickness for the much thinner graphene foils, and then decreased with the thickness for the much thicker graphite foils, which indicates that the bending effect of the wake field on the trailing proton varied with the foil thickness.

关键词： H2^+ molecular ions graphene electron stripping wake effect

来源：评论

学校读者我要写书评

暂无评论

Forecasting of Vessel Traffic Flow Using BPNN Based on Genetic Algorithm Optimization

Forecasting of Vessel Traffic Flow Using BPNN Based on Genet...

引用

International Wireless Communications and Mobile Computing Conference, IWCMC

作者： Qihang Yi Yi Zuo Tieshan Li Yuhao Mao Yang Xiao Navigation College Dalian Maritime University Dalian China College of Automation Engineering University of Electronic Science and Technology of China Chengdu China The University of Alabama Tuscaloosa USA

Accurate prediction of vessel traffic flow plays a significant role in the field of modern intelligent transportation system. In order to enhance the prediction accuracy of vessel traffic flow, this paper combines genetic algorithm (GA) and Back Propagation neural network (BPNN) to build a prediction model. Based on the vessel traffic flow data of The Wuhan Yangtze River Bridge, the simulation experiments were carried out from 2013 to 2018. The average relative error of BPNN optimized by GA is 4.03%, which is better than the average relative error of direct BPNN prediction is 5.57%. The results show that accuracy of the prediction model using BPNN with GA optimization is higher than the traditional BPNN. The BPNN optimized by GA has achieved more ideal results in the forecast of vessel traffic flow. This paper provides the theoretical basis for the relevant decision-making of the water safety authorities so as to guarantee the water traffic safety.

关键词： Wireless communication Computational modeling Neural networks Predictive models Prediction algorithms Data models Safety

来源：评论

学校读者我要写书评

暂无评论

Monte Carlo Simulation of Angular Response of GRID Detectors for GRID Mission

arXiv

引用

arXiv 2024年

作者： Liu, Qize Pan, Xiaofan Zheng, Xutao Gao, Huaizhong Li, Longhao Wang, Qidong Yang, Zirui Tang, Chenchong Wu, Wenxuan Cheng, Jianping Zeng, Zhi Zeng, Ming Feng, Hua Zhang, Binbin Wang, Zhonghai Zhou, Rong Liu, Yuanyuan Lin, Lin Zhong, Jiayong Jiang, Jianyong Han, Wentao Tian, Yang Xu, Benda Department of Engineering Physics Tsinghua University Beijing100084 China Department of Astronomy Beijing Normal University Beijing100875 China Beijing Normal University Beijing100875 China Institute of High Energy Physics CAS Beijing100049 China Department of Astronomy Tsinghua University Beijing100084 China School of Astronomy and Space Science Nanjing University Nanjing210093 China College of Physics Sichuan University Chengdu610064 China College of Nuclear Science and Technology Beijing Normal University Beijing100875 China Department of Computer Science and Technology Tsinghua University Beijing100084 China

The Gamma-Ray Integrated Detectors (GRID) are a space science mission that employs compact gamma-ray detectors mounted on NanoSats in low Earth orbit (LEO) to monitor the transient gamma-ray sky. Owing to the unpredictability of the time and location of gamma-ray bursts (GRBs), obtaining the photon responses of gamma-ray detectors at various incident angles is important for the scientific analysis of GRB data captured by GRID detectors. For this purpose, a dedicated Monte Carlo simulation framework has been developed for GRID detectors. By simulating each GRID detector and the NanoSat carrying it, the spectral energy response, detection efficiency, and other angular responses of each detector for photons with different incident angles and energies can be obtained within this framework. The accuracy of these simulations has been corroborated through on-ground calibration, and the derived angular responses have been successfully applied to the data analysis of recorded GRBs. Copyright © 2024, The Authors. All rights reserved.

关键词： Gamma rays

来源：评论

学校读者我要写书评

暂无评论

Safety Analysis of Automatic Crane Trolley Running System Based on STAMP/STPA

Safety Analysis of Automatic Crane Trolley Running System Ba...

引用

International Conference on Informative and Cybernetics for Computational Social Systems (ICCSS)

作者： Wenbo Zhang Xiangkun Meng Jianyuan Wang Tieshan Li Qihe Shan Fei Teng College of Navigation Dalian Maritime University Dalian China Marine Electrical Engineering College Dalian Maritime University Dalian China College of Automation Engineering University of Electronic Science and Technology Chengdu China

ISBN: (纸本)9781665402460

Automatic crane is a complex system affected by the external environment and the internal components of the system, information fusion, software and hardware combination, and man-machine integration. The improvement of its automation and informatization proposes various challenges in the accident model construction and safety analysis. However, the safety analysis methods based on fault types consider that the occurrence of accidents is linear and ignore the correlation among components of the system. This paper adopts the system-theoretic accident model and process (STAMP) and system-theoretic process analysis (STPA) mode is to implement safety analysis of the automatic crane trolley running system (ACTRs). The paper starts from the identification of system-level losses and hazards, clarifies the function and internal logical control relationships of the system’s components, and then finds potential unsafe control actions (UCAs) and loss scenarios during the trolley running. The results show that the control requirements for the regular operation of the trolley running system can be analyzed in detail. Therefore, the STAMP/STPA can apply to the safety investigation of automatic cranes.

关键词： Analytical models Cranes Correlation automation Manuals Software Safety

来源：评论

学校读者我要写书评

暂无评论

Research on Wind Turbine Gearbox Fault Diagnosis Based on CEEMDAN and CVFDT

Research on Wind Turbine Gearbox Fault Diagnosis Based on CE...

引用

IEEE International Conference on Power and Energy Systems (ICPES)

作者： Fangzhou Shi Jianghao Yu Min Gu Kai Lei Jian He Dongfang Electric Co. Ltd Chengdu China College of Automation Engineering University of Electronic Science and Technology of China Chengdu China Intelligent Terminal Key Laboratory of Sichuan Province University of Electronic Science and Technology of China Chengdu China

ISBN: (纸本)9781665413268

Gearbox fault diagnosis has always been a hot topic in the field of mechanical fault diagnosis and has great research value and significance. But at present, it is mainly based on offline data for fault diagnosis, which is not real-time and slow to find. In this paper, the real-time diagnosis of gearbox bearing fault is realized based on flow data. Aiming at the problems of nonstationary and weak fault characteristics of gearbox bearing vibration signals collected in real time, an energy entropy feature extraction method based on sliding window is proposed for adaptive noise complete set empirical mode decomposition (SWCEEMDAN), which not only effectively solves the problem of end-point effect of CEEMDAN, The feature vectors containing rich fault features can also be extracted; Then, the incremental training and adaptive update of the model are carried out by combining the incremental classification method CVFDT, and then the gearbox fault diagnosis can be realized in real time. Finally, the validity of the improved method was proved by the bearing data set of Case Western reserve university.

关键词： Fault diagnosis Vibrations Training Adaptation models Empirical mode decomposition Feature extraction Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Temporal Correlation Meets Embedding: Towards a 2nd Generation of JDE-based Real-Time Multi-Object Tracking

arXiv

引用

arXiv 2024年

作者： Zhang, Yunfei Liang, Chao Gao, Jin Zhang, Zhipeng Hu, Weiming Maybank, Stephen Zhou, Xue Li, Liang School of Information Science and Technology Shanghaitech University Shanghai201210 China State Key Laboratory of Multimodal Artificial Intelligence System Institute of Automation Chinese Academy of Sciences Beijing100190 China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing101408 China Shenzhen Institute for Advanced Study University of Electronic Science and Technology of China Shenzhen518110 China KargoBot China Department of Computer Science and Information Systems Birkbeck College LondonWC1E 7HX United Kingdom School of Automation Engineering University of Electronic Science and Technology of China Chengdu611731 China Beijing Institute of Basic Medical Sciences Beijing100850 China

Joint Detection and Embedding (JDE) trackers have demonstrated excellent performance in Multi-Object Tracking (MOT) tasks by incorporating the extraction of appearance features as auxiliary tasks through embedding Re-Identification task (ReID) into the detector, achieving a balance between inference speed and tracking performance. However, solving the competition between the detector and the feature extractor has always been a challenge. Meanwhile, the issue of directly embedding the ReID task into MOT has remained unresolved. The lack of high discriminability in appearance features results in their limited utility. In this paper, a new learning approach using cross-correlation to capture temporal information of objects is proposed. The feature extraction network is no longer trained solely on appearance features from each frame but learns richer motion features by utilizing feature heatmaps from consecutive frames, which addresses the challenge of inter-class feature similarity. Furthermore, our learning approach is applied to a more lightweight feature extraction network, and treat the feature matching scores as strong cues rather than auxiliary cues, with an appropriate weight calculation to reflect the compatibility between our obtained features and the MOT task. Our tracker, named TCBTrack, achieves state-of-the-art performance on multiple public benchmarks, i.e., MOT17, MOT20, and DanceTrack datasets. Specifically, on the DanceTrack test set, we achieve 56.8 HOTA, 58.1 IDF1 and 92.5 MOTA, making it the best online tracker capable of achieving real-time performance. Comparative evaluations with other trackers prove that our tracker achieves the best balance between speed, robustness and accuracy. Code is available at https://***/yfzhang1214/TCBTrack. Copyright © 2024, The Authors. All rights reserved.

关键词： HTTP

来源：评论

学校读者我要写书评

暂无评论

Research and Application of Query Optimization Based on HBase

Research and Application of Query Optimization Based on HBas...

引用

International Conference on Computer and Communications (ICCC)

作者： Kai Lei Xiaoyu Xiong Zengzhou Wang Fangzhou Shi Jian He Dongfang Electric Co. Ltd Chengdu China College of Automation Engineering University of Electronic Science and Technology of China Chengdu China University of Electronic Science and Technology of China Intelligent Terminal Key Laboratory of Sichuan Province Chengdu China

ISBN: (纸本)9781665409513

With the advent of the big data era, higher technical requirements have been put forward for the management and retrieval of massive data. As a distributed NoSQL database under the Hadoop framework, HBase has been chosen by many companies as the storage medium for big data due to its strong scalability, excellent storage capabilities, and good read and write capabilities. However, HBase uses the Map-Reduce framework to process aggregate queries, which requires Calculate in real time and cannot keep the calculated result. This paper is dedicated to the research of query optimization technology based on HBase. In order to improve the efficiency of HBase for time series data aggregation and query, an index structure based on time split tree is proposed. The query overhead of tree index stored on disk is high and the query time is high. For problems affected by the amount of data, the time division tree structure is improved, and the query algorithm is optimized at the same time to avoid the disk I/O overhead of traversing the index tree layer by layer. First, save the time summary information, that is, the fixed-length data aggregation information, by constructing a time split tree; then persist the time split tree index into HBase according to the set time, add the corresponding timing information, and construct the sequence number, timing number, The HBase primary key of time range information; using time sequence information, through optimized index query algorithms, it can effectively narrow the data table retrieval range and improve the efficiency of aggregated information query. The effectiveness of the improved method is proved by a large number of wind farm wind turbine operating data.

关键词： Technical requirements Query processing Scalability Time series analysis Data aggregation Big Data Wind farms

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：