检索结果-内蒙古大学图书馆

IEEE International Conference on data Mining (ICDM)

作者： Xiaoyu Zhu Chenyang Bu Bingbing Dong Shengwei Ji Yi He Xindong Wu Key Laboratory of Knowledge Engineering with Big Data (the Ministry of Education of China) Hefei University of Technology School of Computer Science and Information Engineering Hefei University of Technology China School of Artificial Intelligence and Big Data Hefei University China Department of Computer Science Old Dominion University USA Research Center for Knowledge Engineering Zhejiang Lab China

Point-of-Interest (POI) recommendation, pivotal for guiding users to their next interested locale, grapples with the persistent challenge of data sparsity. Whereas knowledge graphs (KGs) have emerged as a favored tool to mitigate the issue, existing KG-based methods tend to overlook two crucial elements: the intention steering users’ location choices and the high-order topological structure within the KG. In this paper, we craft an Intention-aware knowledge Graph (IKG) that harmonizes users’ visit histories, movement trajectories, and location categories to model user intentions. Building upon IKG, our novel Intention-aware knowledge Graph Network (IKGN) delves deeper into the POI recommendation by weighing and propagating node embeddings through an attention mechanism, capturing the unique locational intent of each user. A sequential model like GRU is then employed to ensure a comprehensive representation of users’ short- and long-term location preferences. An empirical study on two real-world datasets validates the effectiveness of our proposed IKGN, with it markedly outshining seven benchmark rival models in both Recall and NDCG metrics. The code of IKGN is available at https://***/Jungle123456/IKGN.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Collaborative Heterogeneous Graph Neural Network for Personalized News Recommendation

A Collaborative Heterogeneous Graph Neural Network for Perso...

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Shi, Chenglong Geng, Haibin Jiang, Wenfeng Li, Jinbao Wu, Chao Liu, Song Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Jinan China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Computer Networks Jinan China

ISBN: (纸本)9781665410205

Personalized news recommendation is the process of predicting the relevance of news to users and recommending news to user to fulfill their information needs. However, existing news recommendation methods extract semantic information from users and candidate news respectively, ignoring semantic interaction information between users and candidate news. Furthermore, previous models only use same node types for message passing, ignoring different characteristics and topology between different node types. In addition, existing methods learn news representations through text representations, ignoring semantic correlation information between entity relationships and texts. To solve these problems, we propose a personalized news recommendation model named CoHG. In our model, we design a collaborative fusion module to obtain semantic interaction information through interacting user history news with candidate news. Furthermore, we design a heterogeneous gated graph neural network that maps different node types into a same space to extract higher-order information in user graphs for message passing. Moreover, we design an enhanced relevant attention module to enhance semantic correlation information of text content by aggregating text representation and entity representation into a unified representation. Finally, we conducted experiments on MIND and Adressa datasets to compare with other baseline models. © 2024 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Injecting Revenue-awareness into Cold-start Recommendation: The Case of Online Insurance 29

Injecting Revenue-awareness into Cold-start Recommendation: ...

引用

29th IEEE International Conference on Parallel and Distributed Systems, ICPADS 2023

作者： Li, Yu Zhang, Yi Chang, Helen He Li, Qiang Jilin University College of Computer Science and Technology China Jilin University Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education China WeSure Inc. Ping An Technology Shenzhen Co. Ltd China

ISBN: (纸本)9798350330717

In online insurance, one of the central challenges is the cold-starting of new insurance products, which means there are no previous samples to refer to. Previous studies have mainly focused on improving the prediction accuracy of new items, but they have failed to consider the revenue generated by existing items. As a result, the total revenue may suffer a loss even if new items get conversions. To address this issue, in this paper we propose RACRec, a Revenue-Aware Cold-start Recommendation framework for online insurance. Unlike previous works, RACRec uses a revenue-based objective function to ensure profitability when cold-starting new items. With this dedicated objective, RACRec orchestrates the cold-start and warm-start model by predicting their expected revenue from each user, thereby preserving the total profit. In order to accurately predict revenue, a double-ranking scheme is designed for the warm-start model to mitigate position bias, while an item embedding alignment algorithm is proposed for the cold-start model to learn the revenue of new items from similar old items. Furthermore, a reinforced orchestrate update scheme is designed to eliminate the impact of sparse conversions and continuously update revenue estimation. Extensive offline and online experiments have been conducted to validate the effectiveness of RACRec. © 2023 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Theoretical analyses of solute concentration-gradient driven water flow and solute concentration variation in solution-saturated semi-permeable materials

引用

Science China(Technological Sciences) 2025年第5期68卷 243-253页

作者： Yao LIU Chongbin ZHAO Bruce HOBBS Alison ORD Xiangtao ZHANG School of Tourism Data Guilin Tourism UniversityGuilin 541006China Guangxi Key Laboratory of Culture and Tourism Smart Technology Guilin Tourism UniversityGuilin 541006China Computational Geosciences Research Centre Central South UniversityChangsha 410083China School of Earth and Environment the University of Western AustraliaCrawleyWA 6009Australia Department of Hydraulic Engineering Tsinghua UniversityBeijing 100084China

Based on the commonly-used definition of the semi-permeable material(SPM),in which the solvent(such as water)can pass through but the solute cannot move freely,a novel constitutive equation is presented,in this paper,to theoretically express the intrinsic constitutive relationship between the porosity variation rate with time and the solute concentration variation rate with *** this theoretical finding,a mathematical model is established to describe the solute concentrationgradient driven water flow and solute concentration variation problem in solution-saturated semi-permeable materials(SSSPMs).In particular,the solute concentration variation in the considered problem can be mathematically described as a linear homogeneous second-order partial differential equation with a variable coefficient in the front of the time term.A special mathematical transform is presented and used to solve this equation,so that the analytical solution for the solute concentration variation in the considered problem has been derived in a purely mathematical *** derived analytical solution is then used to provide some theoretical understanding of solute concentration variations in the SSSPM layer.

关键词： water flow concentration gradient semi-permeable material theoretical analyses analytical solution mathematical proof

来源：评论

学校读者我要写书评

暂无评论

Dynamic multi-objective optimization algorithm based on weighted differential prediction model 4

Dynamic multi-objective optimization algorithm based on weig...

引用

4th International Conference on Industrial Artificial Intelligence, IAI 2022

作者： Zhao, Yumeng Wang, Xianpeng Dong, Zhiming Wang, Yao Lou, Hangyu Hu, Tenghui Fu, Kai Tang, Lixin Northeastern University Key Laboratory of Data Analytics and Optimization for Smart Industry Ministry of Education Shenyang110819 China Northeastern University Liaoning Engineering Laboratory of Operation Analytics and Optimization for Smart Industry Liaoning Key Laboratory of Manufacturing System and Logistics Ministry of Education Shenyang110819 China Liaoning Engineering Laboratory of Data Analytics and Optimization for Smart Industry Shenyang110819 China

ISBN: (数字)9781665451208

ISBN: (纸本)9781665451208

In this paper, a new algorithm for solving dynamic multi-objective optimization problems(DMOPs) is proposed. Most of the traditional dynamic multi-objective optimization algorithms will make predictions based on the overall average evolutionary direction of the population, which is hardly applicable to problems where the solution set and frontier do not vary with the environmental rules. In this paper, a dynamic multi-objective optimization algorithm based on weight difference prediction model is designed to solve such problems. The algorithm contains a weighted differential prediction strategy, and a differential model is built for each individual using the weights to predict the initial population after environmental changes. With this approach, each individual in the population can be made to respond quickly to environmental changes. We used three classical comparison algorithms to conduct experiments on a series of test problems. The experimental results show that the WD-MOEA/D algorithm can significantly improve the dynamic optimization performance and is effective in solving different types of dynamic problems. © 2022 IEEE.

关键词： Evolutionary algorithms

来源：评论

学校读者我要写书评

暂无评论

Multi-Server Cooperative Video Caching Strategy Based on Deep Reinforcement Learning in Cloud-Edge Computing 10

Multi-Server Cooperative Video Caching Strategy Based on Dee...

引用

10th International Conference on Big data Computing and Communications, BIGCOM 2024

作者： Li, Guanyu Mao, Yingchi Peng, Xinxin Zheng, Haotian Wang, Zibo College of Computer Science and Software Engineering Hohai University Nanjing China Hohai University Key Laboratory of Water Big Data Technology of Ministry of Water Resources Nanjing China Huaneng Hydro Lancang Xiaowan Hydropower Plant Dali China

ISBN: (纸本)9798331509538

The soaring number of mobile devices has led the innovation of the edge caching in edge computing, which relieves the heavy pressure of cloud computing. However, with the escalating popularity of short video services, the prevalence of video content in edge server caches has seen a marked increase. Previous work ignored the impact of edge server performance on video caching and failed to automatically adjust the optimal video bit rate in response to users' demand. To improve users' evaluation for watching videos on devices with different display sizes, we propose a novel edge caching strategy called Gate Self-attention Recurrent Network-Multi Agent Reinforcement Learning(GSRN-MARL). GSRN-MARL utilizes leverages Gate Recurrent Unit(GRU) and attention mechanisms to predict cache content based on user historical request information and device details, consequently improving edge server caching performance and users' evaluation of video. Experiment demonstrates that GSRN-MARL surpasses LRU, DRL, and MAAC across two critical metrics: video cache hit rate and users' QoE (Quality of Experience). © 2024 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Combined Particle Filter and Its Application on Human Pose Estimation 20th

Combined Particle Filter and Its Application on Human Pose...

引用

20th International Forum on Digital TV and Wireless Multimedia Communications, IFTC 2023

作者： Liu, Xinyang Ye, Long Yang, Yinghao School of Information and Communication Engineering Communication University of China Beijing China State Key Laboratory of Media Convergence and Communication Communication University of China Beijing China School of Data Science and Media Intelligence Communication University of China Beijing China

ISBN: (纸本)9789819736225

Time series analysis has a wide range of applications in various domains. When addressing this task, tracking and identification are usually solved as two separate problems. However, it introduces a lot of computational redundancy and makes it difficult to guarantee synchronization and real-time performance. We propose a joint problem combining recognition and tracking and use particle filtering to solve the state estimation problem. However, the general particle filter cannot accurately estimate the state of the system in the time series state estimation task, because the system is time-varying and the prediction model of the particle filter is fixed. To address this issue, we assume that the system transition space is a set of finite prediction modes, and then propose a new Combined Particle Filter (CPF) framework that jointly achieves prediction mode recognition and state tracking. In the CPF, the prediction mode is regarded as a variable to be estimated, along with the system state variables. As a result, the resampled particle state set forms the global estimation of the system state, while the resampled mode variables indicate the optimal transition mode of the current frame. We construct an evaluation index system and conduct several evaluation tests to demonstrate the excellent performance of the CPF. Finally, we apply the CPF to the articulated human pose estimation task and obtain satisfactory results. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： State estimation

来源：评论

学校读者我要写书评

暂无评论

Bayesian network-based risk evaluation model for the operational requirements of the China Railway Express under the Belt and Road initiative

引用

Transportation Safety and Environment 2022年第3期4卷 18-31页

作者： Fenling Feng Junjie Jia Ailan Liang Chengguang Liu School of Traffic and Transportation Engineering Central South UniversityChangsha 410075HunanChina Rail Data Research and Application Key Laboratory of Hunan Province Central South UniversityChangsha 410075HunanChina.

The operation of the China Railway Express features numerous links across several regions and countries. Effectively controlling therisks involved in the operation of the China Railway Express is crucial for ensuring safety and efficiency and promoting the sustainabledevelopment of the China Railway Express. The Bayesian network-based risk-management model was built corresponding to theactual operation of the China Railway Express;the model used an advanced risk-management theory. The sensitivity analysis of riskfactors and Bayesian network inference were realized using the expectation-maximization and clique-tree propagation *** the risk-checklistmethod, 17 risk-related factors were analysed on 17 nodes of the Bayesian network fromthree perspectives—safety, efficiency and effectiveness—based on expert opinions and the actual operating conditions of the China Railway *** from a sensitivity analysis and evidence inference of the Bayesian network model indicated that the sensitivity coefficients ofnodes N01, N04, N07, N08 and N17 of the network were high. Moreover, the risk-occurrence probabilities for nodes N01, N04, N06,N07 and N09 were higher in the case of reverse inference. Our results revealed the crucial factors influencing the risk. The identifiedrisk factors included the stability of the political environment in countries along the route, conditions of station infrastructures andthe complexity of the process of changing rails and reloading. Further, risk-management suggestions were provided. By establishinga sound risk-management framework, reliable assessment and management could be realized in accordance with changes in theoperating conditions of the China Railway Express.

关键词： Risk evaluation Bayesian network China railway express risk-management suggestion

来源：评论

学校读者我要写书评

暂无评论

ATPRINPM: A single-source domain generalization method for the remaining useful life prediction of unknown bearings

ATPRINPM: A single-source domain generalization method for t...

引用

Sensing, Measurement & data Analytics in the era of Artificial Intelligence (ICSMD), International Conference on

作者： Juan Xu Bin Ma Yuqi Fan Xu Ding Key Laboratory of Knowledge Engineering with Big Data School of Computer and Information Hefei University of Technology Hefei China

The remaining useful life (RUL) of bearings is critical to the proper operation of mechanical equipment, maintenance of equipment costs and availability. The existing domain adaptation methods have had great success in RUL prediction. However, when the target bearing data are unavailable or unknown to be involved in model training, the domain adaptation approaches also incapable. To solve the problem, we propose a parallel reversible instance normalization method based on adaptive threshold stage division for remaining useful life prediction of unknown bearings. First, we design an adaptive threshold method to find degradation points to divide the healthy and degradation stages. Then according to time series, we merge the original vibration data and its instance normalized data to increase the data distribution diversity. Finally, we combine instance normalization and parallel reversible normalization of the source bearing data into unified RUL learning framework to solve the uncertainty of counterfactual data and improve RUL prediction performance. The results show that the method is superior to the state-of-the-art methods for RUL prediction of unknown bearings.

关键词： Degradation Vibrations Training Adaptation models Uncertainty data analysis Time series analysis

来源：评论

学校读者我要写书评

暂无评论

PEDTrans: A Fine-Grained Visual Classification Model for Self-attention Patch Enhancement and Dropout 16th

PEDTrans: A Fine-Grained Visual Classification Model for Se...

引用

16th Asian Conference on Computer Vision, ACCV 2022

作者： Lin, Xuhong Yan, Qian Wu, Caicong Chen, Yifei College of Information and Electrical Engineering China Agricultural University Beijing100083 China Key Laboratory of Agricultural Machinery Monitoring and Big Data Applications Ministry of Agriculture and Rural Affairs Beijing100083 China

ISBN: (纸本)9783031263507

Fine-grained visual classification (FGVC) is an essential and challenging classification task in computer visual classification, aiming to identify different cars and birds. Recently, most studies use a convolutional neural network combined with an attention mechanism to find discriminant regions to improve algorithm accuracy automatically. However, the discriminant regions selected by the convolutional neural network are extensive. Vision Transformer divides the image into patches and relies on self-attention to select more accurate discriminant regions. However, the Vision Transformer model ignores the response between local patches before patch embedding. In addition, patches usually have high similarity, and they are considered redundant. Therefore, we propose a PEDTrans model based on Vision Transformer. The model has a patch enhancement module based on attention mechanism and a random similar group patch discarding module based on similarity. These two modules can establish patch local feature relationships and select patches that are easier to distinguish between images. Combining these two modules with the Vision Transformer backbone network can improve the fine-grained visual classification accuracy. We employ commonly used fine-grained visual classification datasets CUB-200-2011, Stanford Cars, Stanford Dogs and NABirds to get advanced results. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Convolution

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：