检索结果-内蒙古大学图书馆

4th International Conference on Innovative Computing, IC 2021

作者： Fan, Ganglong Shen, Jian Henan Key Laboratory for Big Data Processing & Analytics of Electronic Commerce Luoyang Normal University Luoyang China Higher Education Admissions Office of HENAN Province Zhengzhou China

ISBN: (纸本)9789811642579

e-commerce recommendation department is faced with some common problems, such as user cold start problem and data sparsity problem. Solving user cold start problem and data sparsity problem is to improve the accuracy of recommendation results. An effective way is to improve the user experience. Driven by big data collected by e-commerce system and supported by natural language processing technology, a new model of e-commerce recommendation system is designed. This paper puts forward the personalized intelligent recommendation system for electronic commerce, which can effectively alleviate the problems of cold start and sparsity, and provide users with accurate and personalized recommendation results. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

A Task Scheduling Approach based on Particle Swarm Optimization for the Production of Remote Sensing Products

IAENG International Journal of Computer Science

引用

IAeNG International Journal of Computer Science 2023年第1期50卷 23页

作者： Hou, Yan-e He, Wenwen Zuo, Xianyu Dang, Lanxue Han, Hongyu Henan Key Laboratory of Big Data Analysis and Processing Henan University Henan Kaifeng475004 China Computer and Information Engineering Henan University Henan Kaifeng475004 China

The production of remote sensing products is very time-consuming, because it contains a large amount of remote sensing data to be processed. To increase the production efficiency of remote sensing products, a remote sensing processing job is usually divided into multiple tasks that are executed in parallel in the cluster system. So efficient task scheduling is the core problem of remote sensing products production system. This paper issued this problem and proposed a hybrid particle swarm optimization algorithm to improve the production efficiency of the remote sensing products. First, the task scheduling model of remote sensing products was established to minimize the maximum task execution time. Then, in the framework of particle swarm optimization, an inertia weight parameters adjustment strategy based on linear decreasing was adapted. For the solution obtained in each iteration, a local search procedure of task movement between the production nodes was employed to improve the quality of the solution. In addition, a probability acceptance rule was also introduced to allow the acceptance of poor solutions avoid trapping into local optimum prematurely. Finally, we carried out several experiments in the CloudSim simulation platform. The experimental results demonstrate that the proposed algorithm is effective and more competition when compared with the existing scheduling algorithms, such as ant colony optimization, tabu search and other classical scheduling algorithms © 2023, IAeNG International Journal of Computer *** Rights Reserved.

关键词： Remote sensing

来源：评论

学校读者我要写书评

暂无评论

Point-Level and Set-Level Deep Representation Learning for Cross-Modal Person Re-identification 8

Point-Level and Set-Level Deep Representation Learning for C...

引用

8th Ieee International Conference on Computer and Communications, ICCC 2022

作者： Hu, Jihui Ye, Pengfei Li, Danyang Dong, Lingyun Chen, Xiaopan Zhu, Xiaoke School of Computer and Information Engineering Henan University Kaifeng China Henan University Henan Key Laboratory of Big Data Analysis and Processing Kaifeng China Henan University Henan Engineering Research Center of Intelligent Technology and Application China

ISBN: (纸本)9781665450515

In practice, significant modality differences usually exist between visible and infrared images, which makes visible-infrared Person Re-Identification (VI-ReID) a challenging research task. Due to the existing influence of pose variation, background changes, and occlusion, there are often outlier samples within the set of images from the same person. These outlier samples can adversely affect the process of learning the cross-modal matching model. The existing VI-ReID methods mainly focus on learning cross-modal feature representation by using image-level discriminant constraints, i.e., the distance between the truly-matching cross-modal images should be smaller than that between wrong-matching cross-modal images. However, most of these methods ignore the adverse influence caused by outliers. To solve the above problems, we proposed a Point-level and Set-level Deep Representation Learning (PSDRL) approach for VI-ReID in this paper. By using the set-level constraint in the process of deep representation learning, the discrepancy between visible and infrared modalities can be decreased, and the adverse effect of outliers can be weakened. By employing the image-level constraint, the discriminability of the obtained deep feature representations can be improved. extensive experiments are conducted on the publicly available cross-modal Person Re-Identification datasets, including SYSU-MM01 and RegDB. experimental results demonstrate the effectiveness of the proposed approach. © 2022 Ieee.

关键词： Infrared imaging

来源：评论

学校读者我要写书评

暂无评论

Placement of Deep Reinforcement Learning in Service Function Chain of Network Function Virtualization

Placement of Deep Reinforcement Learning in Service Function...

引用

data Science and Information System (ICDSIS), Ieee International Conference on

作者： Hongsheng Xu Kaifeng Huang College of Electronic and Commerce Luoyang Normal University Luoyang China Henan key Laboratory for Big Data Processing & Analytics of Electronic Commerce Luoyang Normal University Luoyang China

ISBN: (数字)9798350381665

ISBN: (纸本)9798350381672

Reinforcement learning is a goal-oriented algorithm. The core goal of the algorithm is to learn to make decisions during the interaction between intelligent agents and the environment. Deep Reinforcement Learning is an algorithm that combines the perception ability of deep learning and the powerful decision-making ability of reinforcement learning. It can directly understand the network and task from experience, thus improving the accuracy and reducing repeated modeling, and is widely used to solve complex problems. A Network Service in NFV can be represented as a Service Function Chain (SFC), which consists of a series of Virtual network functions (VNF) in a given order. In order to provide efficient services, SFCS are deployed in a number of different servers and direct traffic through a set of VNFS in a specific order. This paper proposes SFC placement in NFV based on deep reinforcement learning model. Finally, it is found that the deep learning model can effectively improve the efficiency of SFC placement.

关键词： Service function chaining Decision making Deep reinforcement learning Stability analysis Reproducibility of results Network function virtualization Servers

来源：评论

学校读者我要写书评

暂无评论

e-commerce Personalized Recommendation System in big data Based on Three-Way Concept Lattices

E-Commerce Personalized Recommendation System in Big Data Ba...

引用

Artificial Intelligence and Autonomous Robot Systems (AIARS), International Conference on

作者： Hongsheng Xu Jing Gu College of Electronic and Commerce Luoyang Normal University Luoyang China Henan key Laboratory for Big Data Processing & Analytics of Electronic Commerce Luoyang Normal University Luoyang China

ISBN: (数字)9798350376173

ISBN: (纸本)9798350376180

The e-commerce recommendation system can automatically judge the preferences of users according to the browsing situation, and recommend relevant products to customers based on this basis to reduce the time wasted by customers in looking for products. The e-commerce recommendation system is to use the e-commerce big data platform to provide consumers with product information and relevant suggestions, to recommend consumers to buy their favorite types of products, and to imitate the salesman to help consumers to complete the purchase behavior. The paper presents e-commerce personalized recommendation system in big data based on three-way concept lattices. Finally, the method experimentally proves that the proposed method achieves accurate personalized recommendation results and showing better prediction accuracy, which has strong scalability.

关键词： Accuracy Filtering electricity Scalability Lattices Psychology big data Knowledge discovery electronic commerce Recommender systems

来源：评论

学校读者我要写书评

暂无评论

YOLO-FNC: An Improved Method for Small Object Detection in Remote Sensing Images Based on YOLOv7

IAENG International Journal of Computer Science

引用

IAeNG International Journal of Computer Science 2024年第9期51卷 1281-1290页

作者： Dang, Lanxue Liu, Gang Hou, Yan-e Han, Hongyu Henan Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng475004 China School of Computer and Information Engineering Henan University Kaifeng475004 China School of Computer and Information Engineering Henan University Kaifeng475004 China

The detection algorithms of small objects in remote sensing images is often challenging due to the complex background and limited pixels. This can lead to reduced accuracy in detection and an increased number of missed small objects. So this paper introduces YOLOFNC, an enhanced network based on YOLOv7. To improve the model’s ability to capture features of small objects, an enhanced C3-Faster module based on the C3 module is designed and integrated into the YOLOv7 network. This module helps extract more features related to small objects. Additionally, we employ Normalized Wasserstein Distance (NWD) fusion GIoU as a novel loss function to refine the accuracy of network optimization weights and the small object regression framework. Furthermore, a coordinated attention (CA) mechanism is incorporated at strategic locations in the model to reduce redundant information in the feature layer and prevent the loss of important small object features. we conduct comparison experiments between YOLO-FNC and other commonly used object detection algorithms on DIOR, AITOD, and VisDrone datasets. The experimental results show that YOLO-FNC achieves 84.4% mAP on the DIOR dataset, 35.9% mAP on the AI-TOD dataset, and 52.6% mAP on the VisDrone dataset. Compared to YOLOv7 and other remote sensing object detection models, YOLO-FNC demonstrates better performance in object detection. © (2024), (International Association of engineers). All Rights Reserved.

关键词： Proximity sensors

来源：评论

学校读者我要写书评

暂无评论

Graph-enhanced Multi-Scale Contrastive Learning for Graph Anomaly Detection with Adaptive Diffusion Models

引用

Ieee Transactions on big data 2025年

作者： Xiao, Chunjing Tong, Yao Lu, Jiahui Xue, Yuxia Tai, Wenxin Cheng, Zhangtao Zhou, Fan The Henan Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng475004 China The University of Electronic Science and Technology of China Chengdu610054 China

Graph anomaly detection has gained significant research interest across various domains. Due to the lack of labeled data, contrastive learning has been applied in detecting anomalies and various contrastive strategies have been initiated. However, these methods might force two instances (e.g., node-level and subgraph-level representations) with different category labels to be consistent during model training, which can adversely impact the model robustness. Also, they extract node-level representations only based on node attributes, which are inadequate in reflecting the information of the structural anomaly. To tackle this problem, we present a Graph-enhanced multi-scale Contrastive Learning framework for Anomaly Detection, GCLAD. In this framework, we design a diffusion probabilistic model-based graph enhancement module to adaptively manipulate neighbors to generate enhanced graphs, which can efficiently enhance subgraph-level representations and alleviate the inconsistent problem. Further, we present a multi-scale contrastive module where we introduce meta-paths to exploit a few relevant neighbors to boost node-level representations, and build the multi-scale contrastive losses to promote anomaly detection performance. experimental results demonstrate the superiority of GCLAD compared with state-of-the-art baselines. © 2015 Ieee. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

A Two-stage Selection Hyper-heuristic Algorithm for the Capacitated Vehicle Routing Problem

引用

IAeNG International Journal of Applied Mathematics 2022年第4期52卷 1页

作者： Hou, Yan-e He, Wenwen Wang, Congran Ren, Xinhui Henan Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng475004 China College of Computer and Information Engineering Henan University Kaifeng475004 China

As a classical combinatorial optimization problem, capacitated vehicle routing problem (CVRP) has been continuously studied. However, developing effective approaches for CVRP remains very challengeable. This article presented a two-stage selection hyper-heuristic algorithm for CVRP. The proposed algorithm used the multi-armed bandit algorithm as the high-level selection strategy, which selected a low-level heuristic at each step in the iterative local search framework according to the rewards that it had obtained. For the new neighborhood solution that was found by the selected lowlevel heuristic, a hybrid acceptance strategy was employed to decide whether to accept it. In addition, we also designed a low-level heuristic based on the ruin-and-recreate principle to expand the search space of neighborhood solutions except for the regular neighborhood operators widely used in CVRP. Moreover, the routes of better solutions were also put into a pool of routes. Then a set partitioning procedure model was built based on these routes and then solved by CPLeX to obtain better solution. Computational results on 82 instances demonstrate that the presented algorithm is a satisfactory and competitive approach for CVRP. © 2022, IAeNG International Journal of Applied Mathematics. All Rights Reserved.

关键词： Vehicle routing

来源：评论

学校读者我要写书评

暂无评论

A Selection Hyper-heuristic based on Q-learning for School Bus Routing Problem

引用

IAeNG International Journal of Applied Mathematics 2022年第4期52卷 1页

作者： Hou, Yan-e Gu, Wenbo Wang, Chunxiao Yang, Kang Wang, Yujing Henan Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng475004 China College of Computer and Information Engineering Henan University Kaifeng475004 China

School bus routing problem (SBRP) has been studied for decades. Many successful approaches based on heuristics or metaheuristics have been developed for various SBRP problems. However, developing an effective algorithm for SBRP is still a very challenging task. This paper developed a Q-learning-based selection hyper-heuristic to solve basic and open single-school SBRP problems, which both aim to minimize the total travel distance. The proposed algorithm took a Qlearning algorithm as the high-level strategy to select a lowlevel heuristic from a set of low-level heuristics, which are dependent on the problem domain. The selected low-level heuristic was regarded as an action and then executed to improve the current solution. In each stage of the optimization process, the best action with the best cumulative rewards will be chosen to get better results. The presented algorithm was implemented and some experiments were carried out on some Capacitated vehicle routing problem (CVRP) instances and SBRP benchmark instances. experiment results on two types of instances demonstrate that our proposed hyper-heuristic algorithm is more competition than existing approaches. © 2022, IAeNG International Journal of Applied Mathematics. All Rights Reserved.

关键词： Vehicle routing

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Max-Min Ant System Algorithm for electric Capacitated Vehicle Routing Problem

IAENG International Journal of Computer Science

引用

IAeNG International Journal of Computer Science 2024年第3期51卷 195-203页

作者： Hou, Yan-e Wang, Congran Zhang, Chunyang Dang, Lanxue Xiao, Chunjing Henan Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng475004 China College of Computer and Information Engineering Henan University Kaifeng475004 China College of Computer and Information Engineering Henan University Kaifeng475004 China College of Computer and Information Engineering Henan University Kaifeng475004 China School of Computer and Information Engineering Henan University Kaifeng475004 China

electric vehicles have become the first choice for products delivery in logistics, due to their environmental friendliness and low cost compared to the traditional fuel vehicles. This paper deals with an electric capacitated vehicle routing problem with variable energy consumption rate (e-CVRP), which aims to minimize the total cost including vehicle fixed cost, traveled distance cost and energy cost. First, a mixed integer linear programming model is constructed based on the fact that the energy consumption is affected by the vehicle load. Second, a hybrid Max-Min Ant System (HMMAS) algorithm is proposed to solve this problem. Three neighborhood structures are introduced and executed in a Variable Neighborhood Descent (VND) algorithm to improve the current solution. In addition, an effective charging station adjustment strategy is adopted to further improve the solution obtained by the local search process. Finally, some experiments have been conducted on public instances, and the results demonstrate the effectiveness and stability of the algorithm. © (2024), (International Association of engineers). All Rights Reserved.

关键词： energy utilization

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：