检索结果-内蒙古大学图书馆

International Conference on Computer Supported Cooperative Work in Design

作者： Ruiying Zhou Keke Tian Hanjiang Lai Jian Yin Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou P.R.China School of Artificial Intelligence Sun Yat-sen University

ISBN: (纸本)9781728165981

Commonsense question answering (CSQA) aims to answer questions which require the system to understand related commonsense knowledge that is not explicitly expressed in the given context. Recent advance in neural language models (e.g., BERT) that are pre-trained on a large-scale text corpus and fine-tuned on downstream tasks has boosted the performance on CSQA. However, due to the lack of domain knowledge (e.g., in social situations), these models fail to reason about specific tasks. In this work, we propose an approach to incorporate domain knowledge and semantic information into language model based approaches for better understanding the related commonsense knowledge. Firstly, we extract the knowledge from existing resources by jointly learning to ask and answer as well as semantic role labeling based answering. These two tasks are correlated and can reinforce each other to discover the domain knowledge. Then, we utilize Semantic Role Labeling to enable the system to gain a better understanding of relations among relevant entities. Experimental results on several CSQA benchmarks demonstrate the effectiveness of the proposed approach.

关键词： Computational modeling Conferences Semantics Bit error rate Benchmark testing Knowledge discovery Collaborative work

来源：评论

学校读者我要写书评

暂无评论

An Algorithm of data Classification Based on PCA and K-Means++

An Algorithm of Data Classification Based on PCA and K-Means...

引用

Telecommunications, Optics and Computer Science (TOCS), IEEE Conference on

作者： Ruirui Huang Qianshuai Cheng Zhengquan Chen Henan Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng China School of Computer and Information Engineering Henan University Kaifeng China

ISBN: (纸本)9781665424998

Principal component analysis (PCA) and K-means++ algorithm are used to classify and analyze eight main variables of the average annual consumption expenditure of urban households in 31 Provinces and cities in China in a given year, so as to better build the reasonable consumption level of each area. In this paper, a data classification method based on PCA and improved K-means++ is proposed. In this method, PCA was used to extract eight variable characteristics of consumer expenditure, and K-means++ algorithm was used to classify the data. The experimental results show that this method reduces the dependence of the characteristic dimension of variable data and the k-means++ algorithm on the initial classification center of gravity, and improves the accuracy and stability of data classification results.

关键词： Dimensionality reduction Conferences Urban areas Optics Stability analysis Classification algorithms Telecommunications

来源：评论

学校读者我要写书评

暂无评论

Graph Structure-Aware Bi-directional Graph Convolution Model for Semantic Role Labeling

Graph Structure-Aware Bi-directional Graph Convolution Model...

引用

IEEE International Conference on Big data

作者： Wenke Ding Congcong Zhang Gaofei Xie Xiaojie Hu Xiajiong Shen Yatian Shen School of Computer and Information Engineering Henan University Kaifeng China Henan Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng China

ISBN: (纸本)9781665445993

Dependency tree contains rich syntactic structure information, which is very effective for semantic role labeling. Semantic role labeling is a task with strong syntactic dependence. How to effectively use subgraphs to predict surrounding graph structures for context of dependency tree and encode the dependency relationships between predicates and arguments in the sentence which to be annotated is still a challenging problem. In this paper, we propose a bidirectional graph convolution model based on distribution of graph structure and the attention mechanism, which is used to make better use of all syntactic information in the sentence dependency tree and the dependencies between predicates and arguments, so as to improve the accuracy of semantic role labeling. Without heavy feature engineering and extra knowledge of a particular language, our model obtained 88.9% F1 value on the WSJ test set of public dataset CoNLL2005, and 0.7% improvement compared with the existing best model.

关键词： Knowledge engineering Convolution Conferences Semantics Bidirectional control Syntactics Big data

来源：评论

学校读者我要写书评

暂无评论

key-Point Based Distribution Probability Optimization for Object Detection in Remote Sensing images

Key-Point Based Distribution Probability Optimization for Ob...

引用

International Conference on Computer and Communications (ICCC)

作者： Xiaoke Zhu Yufei Wang Xiaopan Chen Danyang Li Jitong Zhang Yulong Cai School of Computer and Information Engineering Henan University Kaifeng China Henan Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng China

ISBN: (纸本)9781665409513

Recently, object detection in remote sensing images has been an important topic in computer vision. As a mainstream approach to detectors, single-stage detectors usually compute the important points of the bounding box to get the location of the target, and optimize them by Focal Loss. One of the development trends for one-stage detectors is to combine with Localization Quality Estimation (LQE), which can provide accurate ranking scores, and thus bring benefits to the Non-Maximum Suppression as well as the following detection results. In this paper, we propose a one-stage detector, named key-point based Distribution Probability Optimization (KDPO), for remote sensing object detection. Specially, we first classify and locate the object through five key points. Then, we merge the quality estimation into the class prediction vector to form a joint representation of localization quality and classification. Next, we utilize a vector to represent arbitrary distribution of box locations. The improved representations avoid the inconsistency risk and accurately describe the flexible distribution of the data. Meanwhile, we use the improved Focal Loss for the succeed optimization. The proposed method is tested on two popular aerial image datasets, including HRSC2016 and DOTA. In all experiments, our approach achieves promising performance comparing to the state-of-the-art detectors.

关键词： Location awareness Heating systems Computer vision Estimation Detectors Object detection Prediction algorithms

来源：评论

学校读者我要写书评

暂无评论

Base Station handover Based on User Trajectory Prediction in 5G Networks

Base Station handover Based on User Trajectory Prediction in...

引用

IEEE International Conference on Big data and Cloud Computing (BdCloud)

作者： Yuxiang Ma Xuefei Chen Lei Zhang School of Computer and Information Engineering Henan University Kaifeng China Henan Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng China

In the 5G era, user equipment connected to 5G base stations can obtain better communication services. However, due to the limited coverage of base stations, the movement of users may cause frequent handover of base stations. With the widespread deployment of 5G base stations, how to reduce unnecessary handover times when users connect to the base station becomes particularly important. In recent years, user trajectory data has been mined and applied to many scenarios. In the 5G network, by judging the user’s movement trajectory, the number of handovers required for the user to connect to the 5G base station can be effectively reduced. In this paper, we propose a 5G base station handover method based on trajectory prediction. A CNN-LSTM neural network, which combines a Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) has been proposed to predict the user’s trajectory. The evaluation results show that our mechanism can effectively reduce the number of base station handovers and improve the efficiency of users using the network. In addition, the stability of 5G networks can be improved by reducing inefficient base station handover.

关键词： Base stations 5G mobile communication Time series analysis Handover Predictive models Prediction algorithms Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Design and Research of Remote Sensing Process Language based on XML

Design and Research of Remote Sensing Process Language based...

引用

Information Technology,Big data and Artificial Intelligence (ICIBA), International Conference on IEEE International Conference on

作者： Xianyu Zuo Heng Li Liming Zhou Henan Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng China School of Computer and Information Engineering Henan University Kaifeng China

ISBN: (纸本)9781665428781

In the era of rapid development of remote sensing technology, in order to improve the production efficiency of remote sensing data processing flow and further optimize the editing of remote sensing processes in the visual interface. In this paper we have analyzed the characteristics and attributes of remote sensing processes and algorithms. We made the production of processes and algorithms into scripts, and realizes to create remote sensing processes by inputting scripting language in the visual interface. A remote sensing language based on XML is designed to read and store key information. This language will use XML to drive the production of remote sensing process. With the language we design, a remote sensing process customization system has been implemented. It can improve the editing and production efficiency of remote sensing data processing flow.

关键词： Visualization Flowcharts XML Production Programming data processing Sensors

来源：评论

学校读者我要写书评

暂无评论

Access control of blockchain based on dual-policy attribute-based encryption 22

Access control of blockchain based on dual-policy attribute-...

引用

22nd IEEE International Conference on High Performance Computing and Communications, 18th IEEE International Conference on Smart City and 6th IEEE International Conference on data Science and Systems, HPCC-SmartCity-DSS 2020

作者： Han, Daojun Chen, Jinyu Zhang, Lei Shen, Yatian Wang, Xueheng Gao, Yihua Institute of Data and Knowledge Engineering School of Computer and Information Engineering Henan University Kaifeng China Henan University Henan Key Laboratory of Big Data Analysis and Processing School of Computer and Information Engineering Kaifeng China

ISBN: (纸本)9781728176499

In scenarios where multiple parties such as the Internet of Things and Supply Chains participate in data sharing and computing, when accessing data, users not only need to accept the forward access control of the data owner, but also needs to perform reverse access control on the data, so as to realize two-way access control. In the traditional blockchain, all users can participate in accounting and view transaction data, and only protect user privacy through 'pseudo-Anonymity'. The access rights of different users cannot be distinguished, which cannot meet the user's two-way access control needs. However, most of the existing blockchain-based access control schemes are one-way access control, which cannot meet the needs of users for two-way access control in scenarios such as the Internet of Things and Supply Chains. Therefore, it is particularly important to design a two-way access control mechanism suitable for application in the blockchain. On this basis, this paper proposes a dual strategy attribute-based encryption (ABE) scheme for distributed outsourcing. This scheme combines two existing schemes, ciphertext-policy ABE and key-policy ABE, and proposes two access structures and a structure of attribute sets. The primary access structure and the secondary attributes are stored in the ciphertext, and the secondary access structure and the primary attributes are stored in the user's private key. Only when the primary attribute set satisfies the primary access structure and the secondary attribute set satisfies the secondary access structure can the user unlock the ciphertext. This scheme has no single authorization center;instead, blockchain nodes jointly participate in authorization. In addition, the proposed scheme outsources the encryption and decryption of the ciphertext to blockchain nodes to reduce the computing pressure on users and can adapt to the decentralized environment of the blockchain and provide users with two-way access control services. Finally,

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Contrastive Continual Learning with Importance Sampling and Prototype-Instance Relation Distillation

arXiv

引用

arXiv 2024年

作者： Li, Jiyong Azizov, Dilshod Li, Yang Liang, Shangsong School of Computer Science and Engineering Sun Yat-sen University China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China Department of Machine Learning Mohamed bin Zayed University of Artificial Intelligence United Arab Emirates AI Thrust Information Hub The Hong Kong University of Science and Technology Guangzhou China Department of CSE The Hong Kong University of Science and Technology China

Recently, because of the high-quality representations of contrastive learning methods, rehearsal-based contrastive continual learning has been proposed to explore how to continually learn transferable representation embeddings to avoid the catastrophic forgetting issue in traditional continual settings. Based on this framework, we propose Contrastive Continual Learning via Importance Sampling (CCLIS) to preserve knowledge by recovering previous data distributions with a new strategy for Replay Buffer Selection (RBS), which minimize estimated variance to save hard negative samples for representation learning with high quality. Furthermore, we present the Prototype-instance Relation Distillation (PRD) loss, a technique designed to maintain the relationship between prototypes and sample representations using a self-distillation process. Experiments on standard continual learning benchmarks reveal that our method notably outperforms existing baselines in terms of knowledge preservation and thereby effectively counteracts catastrophic forgetting in online contexts. The code is available at https://***/lijy373/CCLIS. Copyright © 2024, The Authors. All rights reserved.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

FF-KGAT: Feature Fusion Based Knowledge Graph Attention Network for Recommendation 5

FF-KGAT: Feature Fusion Based Knowledge Graph Attention Netw...

引用

5th International Conference on Artificial Intelligence and Pattern Recognition, AIPR 2022

作者： Tao, Li Xiaoge, Li Chaodong, Wang Xianliang, Li Shuai, Gao Dan, Han Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Xian University of Posts and Telecommunications Shaanxi Xi'an710121 China School of Computer Xian University of Posts and Telecommunications Shaanxi Xi'an710121 China Inspur Software Technology Co Ltd Software Development Project Management China Xian University of Posts and Telecommunications Shaanxi Xi'an710121 China School of Communication and Information Engineering Xian University of Posts and Telecommunications Shaanxi Xi'an710121 China

ISBN: (纸本)9781450396899

It is commonly agreed that a recommender system based on knowledge graph (KG) should not only use user-item interactions, but also take side information into account to deal with the problem of data sparsity. However, existing KG-based models present unique challenges that have the shortcoming of cold start and redundant iterations. To address the issue, we propose a Feature Fusion-based Knowledge Graph Attention Network (FF-KGAT) for the recommendation. FF-KGAT handles the cold-start problem through introducing user characteristics to fully explore the information of users. Additionally, FF-KGAT introduces the feature fusion graph, which removes slight nodes to obtain fewer iterations. Experimental results show that the proposed model significantly outperforms baseline methods. Particularly, the ndcg is increased by 9.83% and 10.25% on two public datasets, compared with the best performance of existing methods. © 2022 ACM.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Appformer: A Novel Framework for Mobile App Usage Prediction Leveraging Progressive Multi-Modal data Fusion and Feature Extraction

arXiv

引用

arXiv 2024年

作者： Sun, Chuike Chen, Junzhou Zhao, Yue Han, Hao Jing, Ruihai Tan, Guang Wu, Di School of Intelligent Systems Engineering Shenzhen Campus of Sun Yat-sen University No. 66 Gongchang Road Guangming District Guangdong Shenzhen518107 China Transsion Holdings Co. Ltd Shanghai201203 China The School of Computer Science and Engineering Sun Yat-sen University Guangzhou510006 China The Guangdong Key Laboratory of Big Data Analysis and Processing Guangdong510006 China

This article presents Appformer, a novel mobile application prediction framework inspired by the efficiency of Transformer-like architectures in processing sequential data through self-attention mechanisms. Combining a Multi-Modal data Progressive Fusion Module with a sophisticated Feature Extraction Module, Appformer leverages the synergies of multimodal data fusion and data mining techniques while maintaining user privacy. The framework employs Points of Interest (POIs) associated with base stations, optimizing them through comprehensive comparative experiments to identify the most effective clustering method. These refined inputs are seamlessly integrated into the initial phases of cross-modal data fusion, where temporal units are encoded via word embeddings and subsequently merged in later stages. The Feature Extraction Module, employing Transformer-like architectures specialized for time series analysis, adeptly distils comprehensive features. It meticulously fine-tunes the outputs from the fusion module, facilitating the extraction of high-calibre, multi-modal features, thus guaranteeing a robust and efficient extraction process. Extensive experimental validation confirms Appformer’s effectiveness, attaining state-of-the-art (SOTA) metrics in mobile app usage prediction, thereby signifying a notable progression in this field. © 2024, CC BY-NC-SA.

关键词： Spatio-temporal data

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：