检索结果-内蒙古大学图书馆

4th International Conference on Computer science and Management technology, ICCSMT 2023

作者： Xie, Rui Fan, Bo Ma, Jianlin Pan, Meng Southwest Pipeline Ltd. PipeChina ChengDu610213 China School of Computing and Artificial Intelligence Southwest Jiaotong University Chengdu610031 China Chengdu Aerospace Science and Industry Big Data Institute Ltd. Casic Chengdu610213 China National Engineering Laboratory of Industrial Big-Data Application Technology Casic Chengdu610218 China

ISBN: (纸本)9798400709517

Due to challenges such as complex contractor personnel, a large amount of scattered form data, a cumbersome business implementation process, low levels of digitalization and security, and difficult management in the engineering management business of oil and gas storage and transportation stations, this paper proposes a study on business data fusion application in the engineering management of oil and gas storage and transportation stations. Focused on the business processes and data of engineering management in oil and gas storage and transportation stations, this research establishes and analyzes an architecture for engineering management business in these stations. Using an Artifact-centric data fusion method, the research constructs an information model for the engineering management business, identifying the data topics for this area. Finally, the research applies and verifies the study of business data fusion through real-world business management scenarios. As researchers in the field of business data fusion, this study utilizes digital technologies and methods to enhance the overall safety management of engineering operations, thereby promoting the transformation and upgrading of engineering management business in oil and gas storage and transportation stations © 2023 ACM.

关键词： Information management

来源：评论

学校读者我要写书评

暂无评论

Research on Time Series Classification Methods 14th

Research on Time Series Classification Methods

引用

14th International Conference on Computer Engineering and Networks, CENet 2024

作者： Zhang, Qifan Ma, Yimeng Shen, Jie Yan, Qinghua Yang, Houqun School of Computer Science and Technology Hainan University Hainan Haikou570228 China Haikou Key Laboratory of Deep Learning and Big Data Application Technology Hainan University Hainan Haikou570228 China

ISBN: (纸本)9789819640157

Time series classification is a pivotal task in machine learning and data mining and has garnered widespread attention in recent years. With the advent of the significant data era, the application of time series data in finance, healthcare, transportation, energy, and other fields has been increasing, making the research and application of time series classification increasingly significant. This paper summarizes and organizes the relevant research methods from the perspective of traditional time series classification methods and time series classification methods based on deep learning. Traditional methods encompass distance-based, feature-based, interval-based, and dictionary-based approaches. Deep learning-based methods, on the other hand, include convolutional neural networks (CNN), recurrent neural networks (RNN), long short-term memory networks (LSTM), gated recurrent units (GRU), and Transformer models. Furthermore, this paper also introduces the characteristics of time series data and common indicators for evaluating time series classification performance and classifies and organizes public time series datasets. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

A deep convolutional neural network for diabetic retinopathy detection via mining local and long-range dependence

引用

CAAI Transactions on Intelligence technology 2024年第1期9卷 153-166页

作者： Xiaoling Luo Wei Wang Yong Xu Zhihui Lai Xiaopeng Jin Bob Zhang David Zhang Shenzhen Key Laboratory of Visual Object Detection and Recognition Harbin Institute of TechnologyShenzhenChina Peng Cheng Laboratory ShenzhenChina Shenzhen Institute of Artificial Intelligence and Robotics for Society ShenzhenChina College of Big Data and Internet Shenzhen Technology UniversityShenzhenChina The Department of Computer and Information Science University of MacaoMacaoMacaoChina The Chinese University of Hong Kong(Shenzhen) ShenzhenChina

Diabetic retinopathy(DR),the main cause of irreversible blindness,is one of the most common complications of *** present,deep convolutional neural networks have achieved promising performance in automatic DR detection *** convolution operation of methods is a local cross-correlation operation,whose receptive field de-termines the size of the local neighbourhood for ***,for retinal fundus photographs,there is not only the local information but also long-distance dependence between the lesion features(*** and exudates)scattered throughout the whole *** proposed method incorporates correlations between long-range patches into the deep learning framework to improve DR ***-wise re-lationships are used to enhance the local patch features since lesions of DR usually appear as *** Long-Range unit in the proposed network with a residual structure can be flexibly embedded into other trained *** experimental results demon-strate that the proposed approach can achieve higher accuracy than existing state-of-the-art models on Messidor and EyePACS datasets.

关键词： image classification medical image processing pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Finite-time sampled-data control for networked dynamic system

Finite-time sampled-data control for networked dynamic syste...

引用

第42届中国控制会议

作者： Dan Zhang Hui Wang Xuefeng Chen Xiaojuan Xue School of Science Yanshan University Aliyun School of Big Data Changzhou University College of Data Science Taiyuan University of Technology

This paper studies the finite-time stability of the networked dynamic system under sampled-data control. By taking the interconnected structure into consideration and employing input-delay approach, tractable conditions that only depend on individual subsystem are proposed to ensure the finite-time stability of the networked dynamic system. By utilizing the Finsler's lemma, the existence conditions of the decentralized state feedback controller are derived. An example of interconnected seesawcart system is given to illustrate the effectiveness of the proposed method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Threshold Attention Network for Semantic Segmentation of Remote Sensing Images

arXiv

引用

arXiv 2025年

作者： Long, Wei Zhang, Yongjun Cui, Zhongwei Xu, Yujie Zhang, Xuexue State Key Laboratory of Public Big Data College of Computer Science and Technology Guizhou University Guizhou Guiyang550025 China School of Mathematics and Big Data Guizhou Education University Guiyang550018 China

Semantic segmentation of remote sensing images is essential for various applications, including vegetation monitoring, disaster management, and urban planning. Previous studies have demonstrated that the self-attention mechanism (SA) is an effective approach for designing segmentation networks that can capture long-range pixel dependencies. SA enables the network to model the global dependencies between the input features, resulting in improved segmentation outcomes. However, the high density of attentional feature maps used in this mechanism causes exponential increases in computational complexity. Additionally, it introduces redundant information that negatively impacts the feature representation. Inspired by traditional threshold segmentation algorithms, we propose a novel threshold attention mechanism (TAM). This mechanism significantly reduces computational effort while also better modeling the correlation between different regions of the feature map. Based on TAM, we present a threshold attention network (TANet) for semantic segmentation. TANet consists of an attentional feature enhancement module (AFEM) for global feature enhancement of shallow features and a threshold attention pyramid pooling module (TAPP) for acquiring feature information at different scales for deep features. We have conducted extensive experiments on the ISPRS Vaihingen and Potsdam datasets. The results demonstrate the validity and superiority of our proposed TANet compared to the most state-of-the-art models. Copyright © 2025, The Authors. All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

An API Field Design Method Based on Pre-trained Model 14

An API Field Design Method Based on Pre-trained Model

引用

14th International Conference on Software technology and Engineering, ICSTE 2024

作者： Wang, Hai Lou, Yihua Yang, Yi Xu, Ranbin Yang, Jingbo Liao, Xingchuang Center of Civil Aviation Big Data TravelSky Technology Limited Beijing Engineering Research Beijing China School of Computer Science and Engineering Beihang University Beijing China School of Artificial Intelligence Beihang University Beijing China

ISBN: (纸本)9798350378955

Application programming interface (API) plays an important role in modern software development, a well designed API can provide tremendous convenience for developers. However, designing an excellent API is not a trivial task, each field in the API should avoid any ambiguity. Besides, in some special cases, for instance, a Chinese developer might not accurately translate the meaning of a Chinese API field into its English counterpart. Therefore, there exists a tremendous requirement in designing high quality API field. In this paper, a fine-tuning pre-trained model based method is proposed for API field design task. Firstly, we consider the design of API fields as a translation task, converting the fields from another language into English. Secondly, we fine-tune a pre-trained model for API field design task. In the end, we curate two datasets to illustrate our method and the experiment results demonstrate that our method has a better performance in designing API field. © 2024 IEEE.

关键词： Application programs

来源：评论

学校读者我要写书评

暂无评论

Action Recognition for Solo-Militant Based on ResNet and Rule Matching 7th

Action Recognition for Solo-Militant Based on ResNet and Rul...

引用

7th International Conference on data Mining and big data, DMBD 2022

作者： Tong, Lijing Feng, Jinzhi Zhao, Huiqun Liu, Kun School of Information Science and Technology North China University of Technology Beingjing100144 China Advanced Institute of Big Data Beijing100195 China

ISBN: (纸本)9789811992964

To solve the problem of low accuracy of solo-militant action recognition under small sample data set, a new method of solo-militant behavior analysis based on ResNet and rule matching is proposed in this paper. The militant's action classification is done by 2 levels of classification. Firstly, the skeleton key points are extracted from the militant's combat video frames by OpenPose. Then, the first level classification of militant's action is performed by the ResNet deep learning network based on RGB images and combined with the skeleton key point rule set of militant's action. Next, the second level classification of militant's action is performed by the CNN network based on skeleton map. At last, the final classification of militant's action is output according to the 2 levels of classification. The experimental results show that the proposed method in this paper can achieve more effective recognition rate of solo-militant action under small sample data set. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Research on expressway traffic flow prediction model based on MSTA-GCN

引用

Journal of Ambient Intelligence and Humanized Computing 2023年第7期14卷 9317-9328页

作者： Ning, Tao Wang, Jiayu Duan, Xiaodong Institute of Computer Science and Engineering Dalian Minzu University Dalian116000 China Big Data Application Technology Key Laboratory of State Ethnic Affairs Commission Dalian Minzu University Dalian116000 China Institute of Information Dalian Maritime University Dalian116021 China

The traffic flow prediction of expressway is highly nonlinear and complex, so it is technically and operationally difficult to predict it accurately. In order to predict the traffic flow of expressway and alleviate its traffic congestion, a multi-component spatial–temporal graph convolution network model based on attention mechanism (MSTA-GCN) is proposed, which combines GCN, standard CNN and attention mechanism. Firstly, near period, daily period and weekly period are modeled to capture the nonlinear correlation characteristics in multivariable urban spatial–temporal series. Then input the sample data into the integrated model for training and extract the characteristics of traffic flow data. Finally, the model is tested on California Expressway PeMS D7 dataset. The experimental results show that MSTA-GCN is superior to classical shallow learning model, benchmark deep learning model and other traffic flow deep learning models, and has lower prediction error. © 2022, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Feature fusion-based weighted broad learning system for imbalanced data 8

Feature fusion-based weighted broad learning system for imba...

引用

8th IEEE Information technology and Mechatronics Engineering Conference, ITOEC 2025

作者： Li, Yanting Wang, Yusha Jin, Junwei Philip Chen, C.L. Zhengzhou University of Light Industry College of Computer Science and Technology Zhengzhou China Henan University of Technology College of Artificial Intelligence and Big Data Zhengzhou China South China University of Technology School of Computer Science and Engineering Guangzhou China

ISBN: (纸本)9798331517915

Broad Learning System (BLS), characterized by its flat architecture as an efficient neural network, has garnered significant interest for its benefits in terms of training velocity and network scalability. However, BLS does not perform well when dealing with imbalanced classification problems. First, conventional BLS neglects the intrinsic logical information contained in the original input data, which may be critical for classification and prediction. Second, BLS fails to emphasize the significance of minority classes in imbalanced data scenarios. In this paper, we propose a feature fusion-based weighted broad learning system. Unlike traditional BLS, we combine the original features and broad features as fused features for training. Additionally, we introduce a weight generation mechanism that assigns higher weights to minority classes, enhancing the model's focus on these classes. A closed solution is available for the issue, and the transformation matrix can be effectively resolved. The experimental results on multiple imbalanced datasets show that our method is superior to other imbalanced methods. © 2025 IEEE.

关键词： Calibration

来源：评论

学校读者我要写书评

暂无评论

Logic-Aware Knowledge Graph Reasoning for Structural Sparsity under Large Language Model Supervision 25

Logic-Aware Knowledge Graph Reasoning for Structural Sparsit...

引用

34th ACM Web Conference, WWW 2025

作者： Pan, Yudai Hong, Jiajie Zhao, Tianzhe Song, Lingyun Liu, Jun Shang, Xuequn School of Computer Science Northwest Polytechnical University Shaanxi Xi’an China Key Laboratory of Big Data Storage and Management Northwestern Polytechnical University Shaanxi Xi’an China School of Computer Science and Technology Xi’an Jiaotong University Shaanxi Xi’an China Research & Development Institute of Northwestern Polytechnical University in Shenzhen Shenzhen China National Engineering Lab for Big Data Analytics Xi’an Jiaotong University Shaanxi Xi’an China

ISBN: (纸本)9798400712746

Knowledge Graph (KG) reasoning aims to predict missing entities in incomplete triples, which requires adequate structural information to derive accurate embeddings. However, KGs in the real world are not as dense as the idealized benchmarks, where sparse graph structures restrict the comprehensive structural information for superior performance. Although the logical semantics in KGs shows its potential in alleviating the impact of structural sparsity, there still exist some challenges. The deficient supervision and the semantic gap of logic make it difficult to introduce logical semantics in sparse KG reasoning. To this end, we propose a novel KG reasoning approach LoLLM injecting logic with the supervised information supplied by the Large Language Model (LLM), which is proved to be effective in evaluating and scoring. Firstly, LoLLM derives structural embeddings employing a graph convolutional network (GCN) with relation-aware and triple-aware attention. LoLLM secondly constructs reasoning paths instantiated from the first-order logic rules extracted from sparse KGs, and injects the logical semantics by a designed LLM-enhanced tuning strategy. We propose a textual loss (TL) and a logical loss (LL) in the optimization and obtain logical tuning embeddings of KG in this process. Finally, LoLLM fuses structural embeddings from the GCN and logical tuning embeddings from the LLM-enhanced tuning for scoring and incomplete triple prediction. Extensive experiments on two sparse KGs and a benchmark show that LoLLM outperforms state-of-the-art structure-based and Language Model (LM)-augmented baselines. Moreover, the logic rules with corresponding confidences provide explicit explanations as an interpretable paradigm. © 2025 Copyright held by the owner/author(s).

关键词： Structural analysis

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：