检索结果-内蒙古大学图书馆

Abnormal Traffic Detection for Internet of Things Based on an Improved Residual Network

computers, Materials & Continua 2024年第6期79卷 4433-4448页

作者： Tingting Su Jia Wang Wei Hu Gaoqiang Dong Jeon Gwanggil School of Computer Science and Technology Xinjiang UniversityUrumqi830046China School of Cyber Science and Engineering Jinling Institute of Technology CityNanjing210000China College of Information Technology Incheon National UniversityIncheon22012Korea

Along with the progression of Internet of Things(IoT)technology,network terminals are becoming continuously more *** has been widely applied in various scenarios,including urban infrastructure,transportation,industry,personal life,and other socio-economic *** introduction of deep learning has brought new security challenges,like an increment in abnormal traffic,which threatens network *** feature extraction leads to less accurate classification *** abnormal traffic detection,the data of network traffic is high-dimensional and *** data not only increases the computational burden of model training but also makes information extraction more *** address these issues,this paper proposes an MD-MRD-ResNeXt model for abnormal network traffic *** fully utilize the multi-scale information in network traffic,a Multi-scale Dilated feature extraction(MD)block is *** module can effectively understand and process information at various scales and uses dilated convolution technology to significantly broaden the model’s receptive *** proposed Max-feature-map Residual with Dual-channel pooling(MRD)block integrates the maximum feature map with the residual *** module ensures the model focuses on key information,thereby optimizing computational efficiency and reducing unnecessary information *** results show that compared to the latest methods,the proposed abnormal traffic detection model improves accuracy by about 2%.

关键词： Abnormal network traffic deep learning residual network multi-scale feature extraction max-feature-map

来源：评论

学校读者我要写书评

暂无评论

Hybrid model-driven and data-driven method for predicting concrete creep considering uncertainty quantification

引用

Frontiers of Structural and Civil engineering 2024年第10期18卷 1524-1539页

作者： Yiming YANG Chengkun ZHOU Jianxin PENG Chunsheng CAI Huang TANG Jianren ZHANG School of Civil Engineering Hunan City UniversityYiyang 413000China Hunan Engineering Research Center of Development and Application of Ceramsite Concrete Technology Hunan City UniversityYiyang 413000China School of Civil Engineering Changsha University of Science and TechnologyChangsha 410114China Department of Bridge Engineering School of TransportationSoutheast UniversityNanjing 211189China Department of Civil and Environmental Engineering Louisiana State UniversityBaton RougeLA 70803USA

Reasonable prediction of concrete creep is the basis of studying long-term deflection of concrete *** this paper,a hybrid model-driven and data-driven(HMD)method for predicting concrete creep is proposed by using the sequence integration ***,a novel uncertainty prediction model(UPM)is developed considering uncertainty ***,the effectiveness of the proposed method is validated by using the North-western university(NU)database of creep,and the effect of uncertainty on prediction results are also *** analysis results show that the proposed HMD method outperforms the model-driven and three data-driven methods,including the genetic algorithm-back propagation neural network(GA-BPNN),particle swarm optimization-support vector regression(PSO-SVR)and convolutional neural network only method,in accuracy and time *** proposed UPM of concrete creep not only ensures relatively good prediction accuracy,but also quantifies the model and measurement uncertainties during the prediction ***,although incorporating measurement uncertainty into concrete creep prediction can improve the prediction performance of UPM,the prediction interval of the creep compliance is more sensitive to model uncertainty than to measurement uncertainty,and the mean contribution of variance attributed to the model uncertainty to the total variance is about 90%.

关键词： concrete creep uncertainty prediction hybrid method data-driven model-driven convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

Multi-view GCN for loan default risk prediction

引用

Neural Computing and Applications 2024年第20期36卷 12149-12162页

作者： Li, Zihao Chen, Yakun Wang, Xianzhi Yao, Lina Xu, Guandong School of Computer Science University of Technology Sydney Broadway SydneyNSW2007 Australia School of Computer Science and Engineering University of New South Wales Garden SydneyNSW2052 Australia

As a significant application of machine learning in financial scenarios, loan default risk prediction aims to evaluate the client’s default probability. However, most existing deep learning solutions treat each application as an independent individual, neglecting the explicit connections among different application records. Besides, these attempts suffer from the problem of missing data and imbalanced distribution (i.e., the default records are small samples against all the applications). We believe similar records could provide some auxiliary signals, which are of critical importance to alleviate the data missing issue and facilitate data argumentation. To this end, we propose multi-view loan application graphs, dubbed MLAGs. By evaluating the similarity between the records, a loan application graph can be constructed. Furthermore, we arrange different similarity thresholds to organize various graph structures for multi-graph constructions;thus, a variety of representations can be generated via information propagation and aggregation for small sample argumentation. Consequently, the imbalanced data distribution and missing values issues can be alleviated effectively. We conduct experiments on three public datasets from real-world home credit and P2P lending platforms, which show that MGCN outperforms both conventional and deep learning models. Ablation studies also illustrated the validity of each module design. © The Author(s) 2024.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Hard-carbon hybrid Li-ion/metal anode enabled by preferred mesoporous uniform lithium growth mechanism

引用

Journal of Energy Chemistry 2024年第1期88卷 252-259,I0006页

作者： Fang Yan Yan Liu Yuan Li Yan Wang Zicen Deng Meng Li Zhenwei Zhu Aohan Zhou Ting Li Jingyi Qiu Gaoping Cao Shaobo Huang Biyan Wang Hao Zhang School of Chemistry and Biological Engineering University of Science and TechnologyBeijing 100083China Research Institute of Chemical Defense Beijing 100191China College of Physics and Engineering Henan University of Science and TechnologyLuoyang 471023HenanChina National Base for International Science&Technology Cooperation School of ChemistryXiangtan UniversityXiangtan 411105HunanChina Materials and Manufacturing Department Beijing University of TechnologyBeijing 100124China

To achieve high energy density in lithium batteries,the construction of lithium-ion/metal hybrid anodes is a promising *** particular,because of the anisotropy of graphite,hybrid anode formed by graphite/Li metal has low transport kinetics and is easy to causes the growth of lithium dendrites and accumulation of dead Li,which seriously affects the cycle life of batteries and even causes safety ***,by comparing graphite with two types of hard carbon,it was found that hybrid anode formed by hard carbon and lithium metal,possessing more disordered mesoporous structure and lithophilic groups,presents better *** indicate that the mesoporous structure provides abundant active site and storage space for dead *** the synergistic effect of this structure and lithophilic functional groups(–COOH),the reversibility of hard carbon/lithium metal hybrid anode is maintained,promoting uniform deposition of lithium metal and alleviating formation of lithium *** hybrid anode maintains a 99.5%Coulombic efficiency(CE)after 260 cycles at a specific capacity of 500 m Ah/*** work provides new insights into the hybrid anodes formed by carbon-based materials and lithium metal with high specific energy and fast charging ability.

关键词： Hard carbon/Li metal hybrid anode Mesoporous structure Surface oxygen functional group Fast charging Lithium batteries

来源：评论

学校读者我要写书评

暂无评论

Multiple object tracking based on appearance and motion graph convolutional neural networks with an explainer

引用

Neural Computing and Applications 2024年第22期36卷 13799-13814页

作者： Zhang, Yubo Huang, Qingming Zheng, Liying School of Computer Science and Technology Harbin Engineering University 145 Nantong Street Heilongjiang Harbin150001 China School of Computer Science and Technology University of Chinese Academy of Sciences Huairou District Beijing100019 China

The tracking performance of Multi-Object Tracking (MOT) has recently been improved by using discriminative appearance and motion features. However, dense crowds and occlusions significantly reduce the reliability of these features, resulting in unsatisfied tracking performance. Thus, we design an end-to-end MOT model based on Graph Convolutional Neural Networks (GCNNs) which fuses four classes of features that characterize objects from their appearances, motions, appearance interactions, and motion interactions. Specifically, a Re-Identification (Re-ID) module is used to extract more discriminative appearance features. The appearance features from object tracklets are then averaged to simplify the proposed tracker. Then, we design two GCNNs to better distinguish objects. One is for extracting interactive appearance features, and the other is for interactive motion features. A fusion module then fuses those features, getting the global feature similarity based on which an association component calculates the MOT matching results. Finally, we semantically visualize relevant structures with the GNNExplainer for insight into the proposed tracker. The evaluation results on MOT16 and MOT17 benchmarks show that our model outperforms the state-of-the-art online tracking methods in terms of Multi-Object Tracking Accuracy and Identification F1 score which is consistent with the results from the GNNExplainer. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Parallel Implementation of the CCSDS Turbo Decoder on GPU

引用

China Communications 2024年第10期21卷 70-77页

作者： Liu Zhanxian Liu Rongke Zhang Haijun Wang Ning Sun Lei Wang Jianquan School of Computer&Communication Engineering University of Science and Technology BeijingBeijing 100083China School of Electronic and Information Engineering Beihang UniversityBeijing 100191China Beijing Engineering and Technology Research Center for Convergence Networks and Ubiquitous Services Institute of Artificial IntelligenceUniversity of Science and Technology BeijingBeijing 100083China School of Information Engineering Zhengzhou UniversityZhengzhou 450001China School of Automation and Electrical Engineering University of Science and Technology BeijingBeijing 100083China

This paper presents a software turbo decoder on graphics processing units(GPU).Unlike previous works,the proposed decoding architecture for turbo codes mainly focuses on the Consultative Committee for Space Data Systems(CCSDS)***,the information frame lengths of the CCSDS turbo codes are not suitable for flexible sub-frame parallelism *** mitigate this issue,we propose a padding method that inserts several bits before the information frame *** obtain low-latency performance and high resource utilization,two-level intra-frame parallelisms and an efficient data structure are *** presented Max-Log-Map decoder can be adopted to decode the Long Term Evolution(LTE)turbo codes with only small *** proposed CCSDS turbo decoder at 10 iterations on NVIDIA RTX3070 achieves about 150 Mbps and 50Mbps throughputs for the code rates 1/6 and 1/2,respectively.

关键词： CCSDS CUDA GPU parallel decoding turbo codes

来源：评论

学校读者我要写书评

暂无评论

Multi-scale feature fusion for facial expression recognition

引用

Neural Computing and Applications 2025年第17期37卷 11399-11420页

作者： Guo, Jiatao Peng, Junjie Huang, Yansong Chen, Gan Cai, Zesu Tan, Shuhua School of Computer Engineering and Science Shanghai University Shanghai China Shanghai Institute for Advanced Communication and Data Science Shanghai University Shanghai China School of Computer Science and Technology Harbin Institute of Technology Harbin China National Engineering Laboratory for Logistics Information Technology YTO Express Co. Ltd. Shanghai China

As an important computer vision task that can be used in many areas, facial expression recognition (FER) has been widely studied which much progress has been obtained especially when deep learning (DL) approaches have been introduced in FER. However, existing methods are restricted to extracting localized information or utilizing attention mechanism to focus on the region most relevant to the emotion, possibly resulting in errors in facial expression interpretation. Moreover, the inconsistency of image sizes in the wild FER datasets further increases the difficulty of the FER task. To address these issues, we propose a multi-scale feature fusion (MSFF) for FER. Specifically, our method first extracts features from facial images using multi-scale feature extraction to obtain rich multi-dimensional information. Meanwhile, extensive feature extraction at different scales is achieved by expanding the receptive field of the model, which provides the basis for more detailed analysis of facial expressions. Eventually, features at different scales are fused to enhance their synergistic effect. Subsequently, the adaptive extraction of comprehensive and valuable information from the fused features is performed, optimizing the performance of expression recognition. Extensive experimental results demonstrate that the proposed method outperforms the state-of-the-art methods on in-the-wild datasets. It is promising for FER in realistic and complex scenarios. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

SMART AGRICULTURE: INTEGRATING AIR QUALITY MONITORING WITH DEEP LEARNING FOR PROCESS OPTIMIZATION*

引用

Scalable Computing 2025年第3期26卷 1005-1016页

作者： Shobana, J. Subramanian, A Venkata Balamurugan, P. Perumal, Sivakumar Sankari, V. Eldho, K.J. Nareshkumar, R. Department of Data Science and Business Systems School of Computing College of Engineering and Technology SRM Institute of Science and Technology Tamilnadu Kattankulathur India Department of Computer Science and Engineering GITAM University Bengaluru India Department of Computer Science and Engineering J N N Institute of Enginering India Saveetha university Chennai India Department of Computer Science and Engineering Sasi Institute of Technology and Engineering Andhra Pradesh Tadepalligudem India Department of Artificial Intelligence and Data Science K.Ramakrishnan College of Engineering Kariyamanickam Rd Tamil Nadu Samayapuram India PG and Research Department of Computer Science Mary Matha Arts and Science College Kerala Mananthavady India Department of Networking and Communications School of Computing College of Engineering and Technology SRM Institute of Science and Technology Tamilnadu Kattankulathur India

Modernization and intense industrialization have led to a substantial improvement in people’s quality of life. However, the aspiration for achieving an improved quality of life results in environmental contamination. A primary consequence of environmental degradation is air pollution, resulting from rising levels of poisonous chemicals in the atmosphere, which may induce detrimental health conditions in humans. It is harmful to both humans and agriculture. Given that the effects of air pollution on plants may not be readily apparent, it is important to analyse the necessary data and compute the outcomes. Farmers prioritise on pests and plant diseases, frequently neglecting the detrimental impacts of air pollution. Some plant species can withstand high amounts of pollution from suspended particulate matter and accumulated gases, while others are more susceptible to harm. Therefore, plants’ reaction to air pollution is influenced by the kind of harmful compounds, their levels, and the plant’s susceptibility to them. The LSTM +CNN Proposed Ensemble method may be used to analyse the impact of air pollution on agriculture by examining trends in crop production over time and predicting which crop is more resistant based on the pollution data. The initiative created for this aim may assist farmers in determining the most suitable crop to cultivate in their fields to minimize the impact of air pollution on agricultural yield. The findings show deep learning algorithms correctly predict hourly pollutant concentrations such as carbon monoxide, sulphur dioxide, nitrogen dioxide, ground-level ozone, and particulate matter 2.5, along with the hourly Air Quality Index (AQI) for California. A proposed model used test RMSE values as a measure to evaluate prediction performance, achieving the best possible results. © 2025 SCPE.

关键词： Nitrogen oxides

来源：评论

学校读者我要写书评

暂无评论

Event-Triggered Optimized Anti-Disturbance Dynamic Positioning for Marine Intelligent Vehicles Via Reinforcement Learning

IEEE Transactions on Intelligent Vehicles

引用

IEEE Transactions on Intelligent Vehicles 2024年 1-12页

作者： Gao, Xiaoyang Li, Tieshan Li, Meilin Chen, C.L.P. School of Maritime Economics and Management Dalian Maritime University Dalian China School of Automation Engineering University of Electronic Science and Technology of China Chengdu China School of Computer Science and Engineering South China University of Technology Guangzhou China

The dynamic positioning of marine intelligent vehicles is gradually becoming the core technique to perform herculean tasks in complex sea conditions. To cope with the composite ocean disturbances and the constraint of communication resources, this paper proposes an event-triggered anti-disturbance dynamic positioning control strategy with performance optimization via reinforcement learning. Firstly, to overcome the composite disturbances caused by external environmental disturbance and internal uncertainties, the disturbance estimator with a fuzzy logic system is established. By constructing an event-triggered mechanism that relies on position and heading information, an event-triggered optimized dynamic positioning controller is designed by combining modified backstepping and reinforcement learning methods. The designed controller consists of a composite anti-disturbance controller and an optimized compensator. Thus, unnecessary communication can be avoided and the performance index is minimized simultaneously. Furthermore, the errors of the closed-loop system are rigorously proved to be bounded. At last, the validity of the proposed control scheme for a marine intelligent vehicle is illustrated by simulation and comparison studies. IEEE

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A comprehensive survey of visible infrared person re-identification from an application perspective

引用

Multimedia Tools and Applications 2024年第42期83卷 90243-90270页

作者： Chang, Hua Xu, Xin Liu, Wei Lu, Lingyi Li, Weigang School of Computer Science and Technology Wuhan University of Science and Technology Wuhan China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan University of Science and Technology Wuhan430065 China School of Information Science and Engineering Wuhan University of Science and Technology Wuhan China

Person re-identification (ReID) is a significant issue in computer vision, aiming to match the same pedestrian across various cameras. Recent research on this issue has successfully reached a satisfactory performance level in the daytime scenario. However, the performance of ReID in low illumination scenarios suffers a dramatic degradation due to the insufficient personal information captured by visible cameras in low or no light scenarios. To address this challenge, the adoption of novel camera technologies for more effective pedestrian data is imperative. Owing to the constraints of distance and usage scenarios in deploying depth cameras, practical infrared cameras are frequently utilized, spurring research in visible infrared person re-identification (VI-ReID). Significant progress has been made in the field of VI-ReID in recent years, but only a few reviews have categorized this problem based on methodology. This article offers a novel perspective by classifying VI-ReID according to application scenarios. Following our categorization scheme, the main advancements in deep learning for VI-ReID over the past five years have been grouped into three categories as follows: retrieval of infrared images using visible images (V→IR), retrieval of visible images using infrared images (IR→V), and joint retrieval of infrared and visible images (V→IR and IR→V). Next, this survey outlines the available datasets and evaluation metrics. After that, we categorize diverse methodologies under the proposed classification and assess their performance metrics across common datasets. Finally, we present two prospective avenues for future research in this domain, informed by the current state of advancement. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Infrared imaging

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：