检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Yang, Ziyuan Yan, Ming Chen, Yingyu Wang, Hui Lu, Zexin Zhang, Yi College of Computer Science Sichuan University China Key Laboratory of Data Protection and Intelligent Management Ministry of Education Sichuan University China Centre for Frontier AI Research Agency for Science Technology and Research

The surge of hate speech on social media platforms poses a significant challenge, with hate speech detection (HSD) becoming increasingly critical. Current HSD methods focus on enriching contextual information to enhance detection performance, but they overlook the inherent uncertainty of hate speech. We propose a novel HSD method, named trustworthy hate speech detection method through visual augmentation (TrusV-HSD), which enhances semantic information through integration with diffused visual images and mitigates uncertainty with trustworthy loss. TrusV-HSD learns semantic representations by effectively extracting trustworthy information through multi-modal connections without paired data. Our experiments on public HSD datasets demonstrate the effectiveness of TrusV-HSD, showing remarkable improvements over conventional methods. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Landslide hazard susceptibility evaluation based on SBAS-InSAR technology and SSA-BP neural network algorithm:A case study of Baihetan Reservoir Area

引用

Journal of Mountain Science 2024年第3期21卷 952-972页

作者： GUO Junqi XI Wenfei YANG Zhiquan SHI Zhengtao HUANG Guangcai YANG Zhengrong YANG Dongqing Faculty of Geography Yunnan Normal UniversityKunming 650500China Key Laboratory of Early Rapid Identification Prevention and Control of Geological Diseases in Traffic Corridor of High Intensity Earthquake Mountainous Area of Yunnan ProvinceKunming 650093China Faculty of Public Safety and Emergency Management Kunming University of Science and TechnologyKunming 650093China Key Laboratory of Geological Disaster Risk Prevention and Control and Emergency Disaster Reduction of Ministry of Emergency Management of the People’s Republic of China Kunming University of Science and TechnologyKunming 650093China Guizhou Geological Survey Institute Guiyang 550081China College of Big Data and Intelligent Engineering Southwest Forestry UniversityKunming 650224China

Landslide hazard susceptibility evaluation takes on critical significance in early warning and disaster prevention and *** order to solve the problems of poor effectiveness of landslide data and complex calculation of weights for multiple evaluation factors in the existing landslide susceptibility evaluation models,in this study,a method of landslide hazard susceptibility evaluation is proposed by combining SBAS-InSAR(Small Baseline Subsets-Interferometric Synthetic Aperture Radar)and SSA-BP(Sparrow Search Algorithm-Back Propagation)neural network *** SBAS-InSAR technology is adopted to identify potential landslide hazards in the study area,update the cataloging data of landslide hazards,and 11 evaluation factors are chosen for constructing the SSA-BP model for training and *** Reservoir area is selected as a case study for *** indicated by the results,the application of SBAS-InSAR technology,combined with both ascending and descending orbit data,effectively addresses the incomplete identification of landslide hazards caused by geometric distortion of single orbit SAR data(e.g.,shadow,overlay,and perspective contraction)in deep canyon areas,thereby enabling the acquisition of up-to-date landslide hazard ***,in comparison to the conventional BP(Back Propagation)algorithm,the accuracy of the model constructed by the SSA-BP algorithm exhibits a significant increase,with mean squared error and mean absolute error reduced by 0.0142 and 0.0607,***,during the process of susceptibility evaluation,the SSA-BP model effectively circumvents the issue of considerable manual interventions in calculating the weight of evaluation *** area under the curve of this model reaches 0.909,surpassing BP(0.835),random forest(0.792),and the information value method(0.699).The risk of landslide occurrence in the Baihetan Reservoir area is positively correlated with slope,surface temperature,and deformation ra

关键词： Baihetan SBAS-InSAR SSA-BP Landslide hazard susceptibility evaluation

来源：评论

学校读者我要写书评

暂无评论

CertRV: an Efficient Certificate Revocation Scheme via Consortium Blockchain, Chameleon Hash and Cuckoo Filter

CertRV: an Efficient Certificate Revocation Scheme via Conso...

引用

IEEE International Conference on Web Services (ICWS)

作者： Huiying Zhang Yuxian Chen Wei Ren Tao Li School of Computer Science China University of Geosciences Wuhan China Key Laboratory of Data Protection and Intelligent Management Sichuan University Ministry of Education School of Cyber Science and Engineering Sichuan University Chengdu China

ISBN: (数字)9798350368550

ISBN: (纸本)9798350368567

Certificate revocation management is one of the primary tasks of Public key Infrastructure (PKI), and it is crucial to the security of PKI. Existing blockchain-based certificate revocation schemes commonly suffer from time-consuming certificate status verification processes, relatively large storage overhead on the blockchain, and an increasing false positive rate in certificate status as the number of revoked certificates grows. To address these issues, this paper proposes a certificate revocation scheme called CertRV based on blockchain, cuckoo filter, and chameleon hash. Specifically, to improve certificate query efficiency, we construct a "CertRevokedCF" filter to store revoked certificates, and apply the chameleon hash algorithm on the blockchain to modify certificate status information, significantly reducing storage costs while still providing accurate certificate status information even when the filter produces false positive results. Finally, we implement and evaluate CertRV using smart contracts on Hyperledger Fabric. Theoretical analysis and experimental results demonstrate that our scheme outperforms other alternatives in terms of security and performance.

关键词： Costs Web services Distributed ledger Smart contracts Public key Filtering algorithms Information filters Fabrics Blockchains Security

来源：评论

学校读者我要写书评

暂无评论

Preemptive Image protection against Steganography

Preemptive Image Protection against Steganography

引用

Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA)

作者： Yusheng Guo Nan Zhong Zhenxing Qian Xinpeng Zhang Hsunfang Cho School of Computer Science Fudan University Shanghai China Key Laboratory of Digital Culture Protection and Tourism Data Intelligent Computing Shanghai China Shanghai Data Exchange Corporation Shanghai China

Image steganography plays a vital role in the realm of information hiding, involving the discreet embedding of confidential data within an image. However, the misuse of this technology by malicious actors on social media platforms poses a significant threat to public security. Presently, the primary defense against image steganography is steganalysis technology, which effectively distinguishes steganographic images from regular ones by detecting subtle modifications. Nevertheless, there is considerable room for improvement in existing steganalysis techniques, especially when dealing with small payloads. In this paper, we propose a proactive strategy to enhance the detection of steganographic images with small payloads. Specifically, as the image is captured, we apply a meticulous-designed and imperceptible mask to it. This mask is aimed at increasing the success rate of detection. We have developed three convolutional neural networks (CNNs) to facilitate this proactive image processing: preemptive-CNN, steganography network (Stego-CNN), and steganalysis discriminator. During the training process, Stego-CNN remains unaltered, while preemptive-CNN and the discriminator are jointly trained to ensure that the applied mask enhances the detection accuracy. Experimental results demonstrate the effectiveness of our proposed approach in enhancing the detection accuracy, all without compromising the visual quality of the images.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research on the psychological classification of violent crime based on a convolutional neural network

引用

Journal of Ambient Intelligence and Humanized Computing 2023年第12期14卷 16397-16408页

作者： Li, Hui Gao, Guandong Xiao, Ke Song, Shengzun College of Information Science and Technology Hebei Agricultural University Hebei Baoding071001 China Department of Information Management The National Police University for Criminal Justice Hebei Baoding071001 China The Centre of Data Science and Intelligent Correction Technology The National Police University for Criminal Justice Hebei Baoding071001 China Hebei Key Laboratory of Agricultural Big Data Hebei Agricultural University Hebei Baoding071001 China Department of Penology The National Police University for Criminal Justice Hebei Baoding071001 China

This paper uses a text classification algorithm in the context of criminal psychology to scientifically evaluate the correctional effects among offenders in the hopes of preventing recidivism. The proposed algorithm uses an improved convolutional neural network (CNN) and feature fusion to carry out the psychological attribution of violent crime based on criminal fact texts, which are divided into three types: the premeditated type, the impulsive type, and the pathological type. First, a text set of criminal facts with labels was constructed by criminal psychology experts. Then, the numerical features are extracted by the word count and a keyword extraction method based on the criminal feature dictionaries, which are established by criminal psychology experts. The improved CNN model is used to extract the text features by replacing a fully connected layer with the global average pooling layer. Finally, after fusing the numerical features and the text features, softmax function is used to calculate the probability of each category and divide the attribution type. To verify the effect of the algorithm, the proposed model is evaluated and compared with the original CNN, the SVM based on TF-IDF and word count, random forest, and some integration methods. Experimental results show that the proposed algorithm is better in accuracy, recall, precision, and F1 in the micro and macro scopes, with the highest accuracy of 98%. © 2022, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

A Multi-Stream Structure-Enhanced Network for Mesh Denoising

A Multi-Stream Structure-Enhanced Network for Mesh Denoising

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Yutian Yang Lingyu Liang Jie Yan Yong Xu South China University of Technology Guangzhou China Henan Key Laboratory of Chronic Disease Prevention and Therapy & Intelligent Health Management Henan China Guangdong Provincial Key Laboratory of Multimodal Big Data Intelligent Analysis China

ISBN: (数字)9781665410205

ISBN: (纸本)9781665410212

Triangular meshes provide an efficient representation of 3D shapes. Various applications such as 3D simulation suffer from degradation in geometric quality. This paper proposes a novel Multi-stream Structure-Enhanced Network (MSE-Net) based on graph convolutional networks. The network uses multi-scale features besides vertex position to guide face normal filtering, which can better preserve the geometric feature during the denoising process. In contrast to former methods that focus on filtering vertex coordinate and face normal apart, MSE-Net innovatively fuses more structure features like face area, inner product between face normal and vertex normals, and the interior angles of face to guide the face normal and vertex position updating, utilizing the inherent structural characteristic of Mesh. Our method achieves state-of-the-art performance on several publicly available datasets, demonstrating its effectiveness.

关键词： Degradation Three-dimensional displays Filtering Shape Graph convolutional networks Fuses Noise reduction Faces Cybernetics

来源：评论

学校读者我要写书评

暂无评论

SE-Chain:A Scalable Storage and Efficient Retrieval Model for Blockchain

引用

Journal of Computer Science & Technology 2021年第3期36卷 693-706页

作者： Da-Yu Jia Jun-Chang Xin Zhi-Qiong Wang Han Lei Guo-Ren Wang School of Computer Science and Engineering Northeastern UniversityShenyang 110819China Key Laboratory of Big Data Management and Analytics of Liaoning Province Shenyang 110819China College of Medicine and Biological Information Engineering Northeastern UniversityShenyang 110169China Neusoft Institute of Intelligent Healthcare Technology Co.Ltd. Shenyang 110179China School of Electrical and Electronic Engineering Nanyang Technological UniversitySingapore 639798Singapore School of Computer Science and Technology Beijing Institute of TechnologyBeijing 100081China

Massive data is written to blockchain systems for the destination of keeping safe. However, existing blockchain protocols still demand that each full node has to contain the entire chain. Most nodes quit because they are unable to grow their storage space with the size of data. As the number of nodes decreases, the security of blockchains would significantly reduce. We present SE-Chain, a novel scale-out blockchain model that improves storage scalability under the premise of ensuring safety and achieves efficient retrieval. The SE-Chain consists of three parts:the data layer, the processing layer and the storage layer. In the data layer, each transaction is stored in the AB-M tree (Adaptive Balanced Merkle tree), which adaptively combines the advantages of balanced binary tree (quick retrieval) and Merkle tree (quick verification). In the processing layer, the full nodes store the part of the complete chain selected by the duplicate ratio regulation algorithm. Meanwhile, the node reliability verification method is used for increasing the stability of full nodes and reducing the risk of imperfect data recovering caused by the reduction of duplicate number in the storage layer. The experimental results on real datasets show that the query time of SE-Chain based on the AB-M tree is reduced by 17% when 16 nodes exist. Overall, SE-Chain improves the storage scalability extremely and implements efficient querying of transactions.

关键词： SE-Chain AB-M(adaptive balanced Merkle)tree efficient retrieval scale-out blockchain

来源：评论

学校读者我要写书评

暂无评论

Target detection method based on deep learning applied in integrity evaluation of explosion proof electrical equipment

Target detection method based on deep learning applied in in...

引用

2022 International Conference on Cyber Security, Artificial Intelligence, and Digital Economy, CSAIDE 2022

作者： Li, Bohan Liu, Weijing Lin, Yuchen Lin, Tao School of Artificial Intelligence and Data Sciences Hebei University of Technology Tianjin300130 China Tianjin Key Laboratory of Aerospace Intelligent Equipment Technology Tianjin Institute of Aerospace Mechanical and Electrical Equipment Tianjin300130 China School of Economics and Management Hebei University of Technology Tianjin300130 China

ISBN: (纸本)9781510657304

There are many types of explosion-proof equipment, so the problems in use are not the same. In view of these situations, this project takes the explosion-proof electrical equipment as the research object, and develops a set of integrity evaluation system of explosion-proof electrical equipment. This paper presents a defect detection method applied in the integrity evaluation system of explosion-proof electrical equipment. The proposed method first designs a lightweight network capable of achieving high-definition image detection under the YOLOV4 detection framework. Then, according to the specific data set, a priori box corresponding to the data distribution is generated. Finally, the distance-based K-means clustering method is used to extract the anchor block. The STN-OCR detects and identifies the defects from the natural images, thus applying the defect detection method in the explosion-proof electrical integrity evaluation system. This method improves the traditional evaluation process of traditional explosion-proof electrical equipment, which is cumbersome and inefficient, and has a certain impact on the application in some other fields in the future. © 2022 SPIE.

关键词： K-means clustering

来源：评论

学校读者我要写书评

暂无评论

Reconfiguration of the brain during aesthetic experience on Chinese calligraphy—Using brain complex networks

引用

Visual Informatics 2022年第1期6卷 35-46页

作者： Rui Li Xiaofei Jia Changle Zhou Junsong Zhang National Engineering Laboratory for Educational Big Data Central China Normal UniversityWuhanHubeiChina Mind Art&Computation GroupDepartment of Artificial IntelligenceSchool of InformaticsXiamen UniversityChina Key Laboratory of Digital Protection and Intelligent Processing of Intangible Cultural Heritage of Fujian and Taiwan Ministry of Culture and TourismChina Center for the Study of Brain and Language Qufu Normal UniversityRizhaoChina Faculty of Education The Edmond J.Safra Brain Research Center for the Study of Learning DisabilitiesUniversity of HaifaHaifaIsrael

Chinese calligraphy,as a well-known performing art form,occupies an important role in the intangible cultural heritage of *** studies focused on the psychophysiological benefits of Chinese *** attention has been paid to its aesthetic attributes and effectiveness on the cognitive *** complement our understanding of Chinese calligraphy,this study investigated the aesthetic experience of Chinese cursive-style calligraphy using brain functional network *** stayed on the coach and rested for several ***,they were requested to appreciate artwork of cursive-style *** showed that(1)changes in functional connectivity between frontooccipital,fronto-parietal,bilateral parietal,and central–occipital areas are prominent for calligraphy condition,(2)brain functional network showed an increased normalized cluster coefficient for calligraphy condition in alpha2 and gamma *** results demonstrate that the brain functional network undergoes a dynamic reconfiguration during the aesthetic experience of Chinese *** evidence that the aesthetic experience of Chinese calligraphy has several similarities with western art while retaining its unique characters as an eastern traditional art form.

关键词： Chinese calligraphy Aesthetic experience Electroencephalogram Brain functional connectivity Complex network

来源：评论

学校读者我要写书评

暂无评论

Learning Representation for Clustering via Dual Correlation 6

Learning Representation for Clustering via Dual Correlation

引用

6th IEEE Information Technology, Networking, Electronic and Automation Control Conference, ITNEC 2023

作者： Zhang, Tao Hu, Mingming Shenyang Institute of Automation Chinese Academy of Sciences State Key Laboratory of Robotics Shenyang China University of Chinese Academy of Sciences Chinese Academy of Sciences Institutes for Robotics and Intelligent Manufacturing Shenyang Institute of Automation Shenyang China Center for Clinical Studies Data Management Department Beijing China

ISBN: (纸本)9781665460033

Contrastive learning is a self-supervised learning method used to learn the general features of a dataset without labels by letting the model learn which data points are similar or different. It constructs labeled samples through data augmentation. Therefore, the core and difficulty of self-supervised contrastive learning are to construct high-quality contrastive samples, especially negative sample pairs. In this paper, a cluster-based contrast sample selection method is proposed, which selects the positive contrast samples from the same cluster and the negative contrast samples from different clusters. By minimizing the forward contrast sample loss and maximizing the reverse sample loss, the deep representation clustering result of the image is obtained. The experimental results show the excellence and adaptability of the algorithm. © 2023 IEEE.

关键词： Deep learning

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：