检索结果-内蒙古大学图书馆

In an Ocean or a River:Bilinear Auto-Backlund Transformations and Similarity Reductions on an Extended Time-Dependent(3+1)-Dimensional Shallow Water Wave Equation

引用

China Ocean Engineering 2025年第1期39卷 160-165页

作者： GAO Xin-yi College of Science and Beijing Key Laboratory on Integration and Analysis of Large-Scale Stream DataNorth China University of TechnologyBeijing 100144China Beijing Laboratory of New Energy Storage Technology Beijing Municipal Education CommissionBeijing 102206China

With respect to oceanic fluid dynamics,certain models have appeared,e.g.,an extended time-dependent(3+1)-dimensional shallow water wave equation in an ocean or a river,which we investigate in this *** symbolic computation,we find out,on one hand,a set of bilinear auto-Backlund transformations,which could connect certain solutions of that equation with other solutions of that equation itself,and on the other hand,a set of similarity reductions,which could go from that equation to a known ordinary differential *** results in this paper depend on all the oceanic variable coefficients in that equation.

关键词： ocean river extended time-dependent(3+1)-dimensional shallow water wave equation bilinear auto-Bäcklund transformation similarity reduction symbolic computation

来源：评论

学校读者我要写书评

暂无评论

Attack based on data: a novel perspective to attack sensitive points directly

引用

Cybersecurity 2024年第3期7卷 111-123页

作者： Yuyao Ge Zhongguo Yang Lizhe Chen Yiming Wang Chengyang Li School of Information Science and Technology North China University of TechnologyBeijingChina Bejing Key Laboratory on Integration and Analysis of Large-Scale Stream Data North China University of TechnologyBeijingChina School of Computer Science Peking UniversityBeijingChina

Adversarial attack for time-series classification model is widely explored and many attack methods are *** there is not a method of attack based on the data *** this paper,we innovatively proposed a black-box sparse attack method based on data *** method directly attack the sensitive points in the time-series data accord-ing to statistical features extract from the *** frst,we have validated the transferability of sensitive points among DNNs with different ***,we use the statistical features extract from the dataset and the sensi-tive rate of each point as the training set to train the predictive ***,predicting the sensitive rate of test set by predictive ***,perturbing according to the sensitive *** attack is limited by constraining the LO norm to achieve one-point *** conduct experiments on several datasets to validate the effectiveness of this method.

关键词： Black-box adversarial attack Time series classification data mining

来源：评论

学校读者我要写书评

暂无评论

Efficient Range Query Method for Traffic data Using Learning-Based Spatiotemporal Index

Efficient Range Query Method for Traffic Data Using Learning...

引用

International Conference on Artificial Intelligence and Autonomous Transportation, AIAT 2024

作者： Guo, Zhicheng Fang, Jun Zhang, Haibo Beijing Key Laboratory On Integration and Analysis of Large-Scale Stream Data Beijing University of Technology Beijing China North China University of Technology Beijing100144 China

ISBN: (纸本)9789819639601

Traffic data is characterized by complexity in structure, high collection frequency, large volume, and uneven spatiotemporal distribution. Efficient range querying on traffic data poses a significant challenge in intelligent transportation system research. Utilizing spatiotemporal indices to accelerate queries is an effective approach. However, traditional spatiotemporal indices suffer from issues where index efficiency is negatively correlated with data volume, and index storage size is positively correlated with data volume. To address these challenges, this paper proposes an efficient range query method for traffic data based on a learning-based spatiotemporal index. The Flood index is applied and enhanced with the following improvements: Firstly, a fully connected neural network constructs a time-cost model to predict query times and determine the optimal grid layout. Secondly, a recursive model index learns data distribution within each grid for query range prediction and proposes an index updating strategy. Experimental results using real data demonstrate that our method maintains comparable query efficiency to Flood index while reducing index storage space by a factor of 10. Furthermore, compared to baseline methods, our approach improves query speed for traffic spatiotemporal data by 3 to 8 times. © beijing Paike Culture Commu. Co., Ltd. 2025.

关键词： Structured Query Language

来源：评论

学校读者我要写书评

暂无评论

Tour Guide Robot Based on large Language Model and User Behavior analysis 5

Tour Guide Robot Based on Large Language Model and User Beha...

引用

5th International Conference on Artificial Intelligence and Computer Engineering, ICAICE 2024

作者： Lin, Haoran Wang, Jing Zhan, Yutong Zhang, Yuan School of Information Science and Technology North China University of Technology Beijing Key Laboratory on Integration and Analysis of Large-Scale Stream Data Beijing China

ISBN: (纸本)9798331528911

With the continuous development of human-computer interaction technology, the applications of tour guide robots in scenarios such as museums and exhibition halls are becoming increasingly widespread. However, traditional tour guide robots primarily rely on predefined content and texts, as well as pre-planned routes, making it difficult to adjust in real-time based on the diverse needs and interests of different visitors. This limitation restricts interactivity and engagement. To address this issue, this paper proposes an intelligent tour guide robot system that integrates large language model and user behavior analysis technology, aimed at dynamically adjusting tour content by real-time perception of visitors' interests. This system leverages the natural language processing capabilities of large language model, along with user behavior analysis techniques, to provide visitors with a more personalized and interactive tour experience. Experimental validation shows that the proposed tour guide robot system can enhance the accuracy and proactivity of tour presentations, thereby increasing user engagement and the overall effectiveness of the tour. © 2024 IEEE.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

A survey on graph neural network-based next POI recommendation for smart cities

引用

Journal of Reliable Intelligent Environments 2024年第3期10卷 299-318页

作者： Yu, Jian Guo, Lucas Zhang, Jiayu Wang, Guiling Department of Computer Science and Soft Engineering Auckland University of Technology Auckland New Zealand School of Information Science and Technology Beijing Key Laboratory on Integration and Analysis of Large-Scale Stream Data North China University of Technology Beijing China

Amid the rise of mobile technologies and Location-Based Social Networks (LBSNs), there’s an escalating demand for personalized Point-of-Interest (POI) recommendations. Especially pivotal in smart cities, these systems aim to enhance user experiences by offering location recommendations tailored to past check-ins and visited POIs. Distinguishing itself from traditional POI recommendations, the next POI approach emphasizes predicting the immediate subsequent location, factoring in both geographical attributes and temporal patterns. This approach, while promising, faces with challenges like capturing evolving user preferences and navigating data biases. The introduction of Graph Neural Networks (GNNs) brings forth a transformative solution, particularly in their ability to capture high-order dependencies between POIs, understanding deeper relationships and patterns beyond immediate connections. This survey presents a comprehensive exploration of GNN-based next POI recommendation approaches, delving into their unique characteristics, inherent challenges, and potential avenues for future research. © The Author(s) 2024.

关键词： Location based services

来源：评论

学校读者我要写书评

暂无评论

Research on Construction Method of Science and Technology Service Domain Knowledge Map 7

Research on Construction Method of Science and Technology Se...

引用

7th IEEE Advanced Information Technology, Electronic and Automation Control Conference, IAEAC 2024

作者： Qian, Jiaqi North China University of Technology School of Information Science and Technology Beijing China Beijing Key Laboratory on Integration and Analysis of Large-Scale Stream Data Beijing China

ISBN: (纸本)9798350339161

With the development of the science and technology service industry, there is an urgent need to effectively organize multi-source and heterogeneous science and technology resources to meet the personalized needs of science and technology services in different industrial fields, that is, to provide various services to different industrial fields according to industry perspectives. Required scientific and technological resources, including scientific and technological project resources and scientific and technological consulting resources, etc. Effective organization and management of scientific and technological resources can be completed by building a domain knowledge map for industrial industry scientific and technological services. However, these resource fields have a large number of data types, are highly professional, and have complex businesses. How to obtain useful data, information, and business knowledge from massive data and store it in a graph database to complete the construction of a knowledge graph is the subject of this article. Concerns. Therefore, this article proposes a set of methods that integrate data preprocessing and knowledge modeling based on structured data processing and ontology technology to complete the construction of domain knowledge graphs. © 2024 IEEE.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Verification of IoT-Aware Business Processes Based on Extended Petri Nets 16th

Verification of IoT-Aware Business Processes Based on Exte...

引用

16th International Conference on Service Science, ICSS 2023

作者： Cao, Jiachen Wang, Jing Yang, Shiyi Gong, Huilong Beijing Key Laboratory on Integration and Analysis of Large-scale Stream Data North China University of Technology Beijing100144 China

ISBN: (纸本)9789819944019

With the rapid development of cloud computing and Internet of Things (IoT)technology, the convergence of BPM (Business Process Management) and IoT big data has attracted more and more attention. Integrating IoT services into BPM enables BPM to perceive changes in the physical world more quickly and accurately, but also brings challenges to process verification. The verification method that supports IoT-aware business processes is required. This paper proposes a method to formally represent the Business Process Modeling Notation (BPMN) model with IoT services integrated based on extended Petri nets, and a deadlock detection algorithm for this formaliza-tion method. The case study shows that the method proposed in this paper can effectively detect the deadlock structures in IoT-aware business process-es, and reduce process errors for process modelers. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

IoT Service Runtime Fault Tolerance Mechanism Based on Flink Dynamic Checkpoint 16th

IoT Service Runtime Fault Tolerance Mechanism Based on Flin...

引用

16th International Conference on Service Science, ICSS 2023

作者： Bai, Wentao Fang, Jun Chang, Wei Beijing Key Laboratory on Integration and Analysis of Large-scale Stream Data Beijing China North China University of Technology Beijing100144 China

ISBN: (纸本)9789819944019

By integrating Internet of Things (IoT) capabilities to sense real-time conditions in the physical environment, traditional Business Process Management (BPM) has the potential to become more flexible and adaptive. However, the integration of BPM and IoT faces challenges such as programming mechanism mismatches, resource management mechanism mismatches, and adaptive mechanism mismatches. This research considers IoT service-based technology as an effective approach to integrate BPM and IoT. The IoT service must be calculable, composable, bindable, and fault-tolerant. When IoT services run on Apache Flink, the native fault tolerance mechanism may not meet the fault tolerance needs of IoT services due to high-speed fluctuation characteristics of IoT service data sources. Additionally, traditional static checkpoint fault-tolerant mechanisms may not balance runtime overhead and recovery delay optimally. This paper proposes an on-demand dynamic checkpoint fault-tolerant method that calculates the recovery delay in real-time based on data fluctuation rates and actively triggers the checkpoint operation when the user threshold is reached. Experiments show that the proposed method improves system efficiency by up to 11.9% compared to the static checkpoint mechanism. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Dynamics

来源：评论

学校读者我要写书评

暂无评论

An Intent Understanding and Entity Extraction Method Based on Intent-Slot Attention Mechanism 3

An Intent Understanding and Entity Extraction Method Based o...

引用

3rd International Conference on Electronic Information Engineering and Computer Science, EIECS 2023

作者： Cao, Sheng-Yuan Liu, Chen North China University of Technology Beijing Key Laboratory on Integration and Analysis of Large-Scale Stream Data School of Information Beijing100144 China

ISBN: (纸本)9798350316674

In the realm of chronic disease health dialog, natural language understanding plays a pivotal role. It encompasses two vital subtasks: recognizing user intentions and populating relevant data slots. To establish a symbiotic relationship between these intentions and slots, fostering semantic-level modeling, we present an innovative algorithm for comprehending medical consultation intentions and extracting pertinent entities. This algorithm leverages an intention-slot attention mechanism. Our approach introduces a slot pick-through mechanism, which effectively captures the explicit connection between user intent and data slots. Furthermore, we have designed an intent-slot attention mechanism layer and devised a method for embedding contextual intent information into data slots in the form of intent label vectors. In conclusion, our experimental results, evaluated on the MedDG dataset, demonstrate the superiority of our proposed algorithm over other comparative methods. We achieve an accuracy rate of 78.1% for medical intent recognition, an F1 value of 94.9% for semantic slot-filling, and a sentence-level semantic framing accuracy of 73.2%. © 2023 IEEE.

关键词： attention mechanism chronic disease intent-slot

来源：评论

学校读者我要写书评

暂无评论

Multi-source Autoregressive Entity Linking Based on Generative Method 18th

Multi-source Autoregressive Entity Linking Based on Generati...

引用

18th CCF Conference on Computer Supported Cooperative Work and Social Computing, ChineseCSCW 2023

作者： Yang, Dongju Lan, Weishui Beijing Municipal Key Laboratory on Integration and Analysis of Large-Scale Stream Beijing100144 China Data Research Center for Cloud Computing North China University of Technology Beijing100144 China

ISBN: (纸本)9789819996360

The task of entity linking aims to map the entity reference in the text with the unambiguous entity in the knowledge base. However, under the background of the continuous growth of science and technology service platform services, the complexity and diversity of domain semantic information, and the vagueness and ambiguity of natural language, the task of linking industrial chain knowledge graphs and technology service resources faces the following problems: (1) The increase in the types of semantic information in the do-main will lead to the lack of cognition and ambiguity in the entity linking process, which will affect the accuracy of entity linking;(2) the context and interaction of corpus information Dependencies become more complex, making insufficient consideration of the mapping relationship between linked entities. To address the above issues, this paper proposes a generative method and multiple sources of information Autoregressive Entity Linking (GMoAEL), which uses data sets such as unstructured textual descriptions, related reference links, and fine-grained structured types Information and other sources of information are used to build a unified dense representation for entity learning, and an autoregressive model in the form of encoder-decoder is used to adjust the link generation process to handle the complex mapping relationship between in-put and output. This paper uses the AIDA CoNLL-YAGO data set to conduct experiments. Compared with other methods, the Micro-F1 value is 1.6% points ahead, which verifies the feasibility and effectiveness of this method. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Knowledge graph

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：