检索结果-内蒙古大学图书馆

International Conference on Advances in Social Network Analysis and Mining, ASONAM

作者： Ke-Jia Chen Shijun Xue Yun Li Bin Liu Jiangsu Key Laboratory of Big Data Security & Intelligent Processing Nanjing University of Posts and Telecommunications Nanjing Jiangsu China College of Computer Science Nanjing University of Posts and Telecommunications Nanjing Jiangsu China

ISBN: (数字)9781450349932

ISBN: (纸本)9781450349932

This paper studies the problem of relationship prediction in heterogeneous information networks. Our goal is not only to predict links/relationships more accurately but also to provide more viable paths to facilitate the formation of new links/relationships. A relationship prediction method based on multi-label learning named ML 3 P is proposed. In ML 3 P, each meta-path between nodes is regarded as a type of relationship and is given a label. Under the framework of multi-label learning, any potential relationship including the target relationship can be predicted. The results of comparative experiments in DBLP and Twitter datasets show that ML 3 P better uses heterogeneous information in supervised learning process and thus achieves better performance. Moreover, our method can output the correlation between relationships.

关键词： Twitter Task analysis Feature extraction Training Measurement Correlation

来源：评论

学校读者我要写书评

暂无评论

Deep representation learning for road detection using siamese network

arXiv

引用

arXiv 2019年

作者： Liu, Huafeng Han, Xiaofeng Li, Xiangrui Yao, Yazhou Huang, Pu Tang, Zhenming School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China Jiangsu Key Laboratory of Big Data Security & Intelligent Processing Nanjing University of Posts and Telecommunications Nanjing210023 China

Robust road detection is a key challenge in safe autonomous driving. Recently, with the rapid development of 3D sensors, more and more researchers are trying to fuse information across different sensors to improve the performance of road detection. Although many successful works have been achieved in this field, methods for data fusion under deep learning framework is still an open problem. In this paper, we propose a Siamese deep neural network based on FCN-8s to detect road region. Our method uses data collected from a monocular color camera and a Velodyne-64 LiDAR sensor. We project the LiDAR point clouds onto the image plane to generate LiDAR images and feed them into one of the branches of the network. The RGB images are fed into another branch of our proposed network. The feature maps that these two branches extract in multiple scales are fused before each pooling layer, via padding additional fusion layers. Extensive experimental results on public dataset KITTI ROAD demonstrate the effectiveness of our proposed approach. Copyright © 2019, The Authors. All rights reserved.

关键词： Roads and streets

来源：评论

学校读者我要写书评

暂无评论

A Privacy-Preserving and Verifiable Federated Learning Scheme

A Privacy-Preserving and Verifiable Federated Learning Schem...

引用

IEEE International Conference on Communications (ICC)

作者： Xianglong Zhang Anmin Fu Huaqun Wang Chunyi Zhou Zhenzhu Chen School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing PR China Jiangsu Key Laboratory of Big Data Security and Intelligent Processing Nanjing University of Posts and Telecommunications Nanjing PR China

ISBN: (数字)9781728150895

ISBN: (纸本)9781728150901

Due to the complexity of the data environment, many organizations prefer to train deep learning models together by sharing training sets. However, this process is always accompanied by the restriction of distributed storage and privacy. Federated learning addresses this challenge by only sharing gradients with the server without revealing training sets. Unfortunately, existing research has shown that the server could extract information of the training sets from shared gradients. Besides, the server may falsify the calculated result to affect the accuracy of the trained model. To solve the above problems, we propose a privacy-preserving and verifiable federated learning scheme. Our scheme focuses on processing shared gradients by combining the Chinese Remainder Theorem and the Paillier homomorphic encryption, which can realize privacy-preserving federated learning with low computation and communication costs. In addition, we introduce the bilinear aggregate signature technology into federated learning, which effectively verifies the correctness of aggregated gradient. Moreover, the experiment shows that even with the added verification function, our scheme still has high accuracy and efficiency.

关键词： Servers Machine learning Training Encryption Aggregates Computational modeling Privacy

来源：评论

学校读者我要写书评

暂无评论

Temporal data fusion at the edge

arXiv

引用

arXiv 2019年

作者： Yang, Linfu Liu, Bin School of Computer Science Nanjing University of Posts and Telecommunications Nanjing China School of Computer Science Jiangsu Key Lab of Big Data Security & Intelligent Processing Nanjing University of Posts and Telecommunications Nanjing China

—As an enabler technique, data fusion has gained great attention in the context of Internet of things (IoT). In traditional settings, data fusion is done at the cloud server. So the data to be fused should be transferred from the sensor nodes to the cloud server before data fusion. Such an application mode of data fusion inherits disturbing concerns from the cloud computing framework, e.g., privacy-leaking, large latency between data capture and computation, excessive ingress bandwidth consumption. We take into account how to do temporal data fusion at the edge to bypass the above issues. We present a Gaussian process based temporal data fusion (GPTDF) method targeted for the problem of sequential online prediction at the edge. The GPTDF method fits the edge computing framework and thus inherits desirable properties from edge computing, such as privacy-preserving, low latency between data capture and computation, and tiny bandwidth consumption. Through a real-data experiment using archived traffic datasets from the Caltrans Performance Measurement System (PeMS), we demonstrate that the application of GPTDF can provide more timely and accurate real-time predictions at the network edge. Copyright © 2019, The Authors. All rights reserved.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Proxy Re-Encryption Scheme For Complicated Access Control Factors Description in Hybrid Cloud

Proxy Re-Encryption Scheme For Complicated Access Control Fa...

引用

IEEE International Conference on Communications (ICC)

作者： Zheng Lian Mang Su Anmin Fu Huaqun Wang Chunyi Zhou School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing PR China Jiangsu Key Laboratory of Big Data Security and Intelligent Processing Nanjing University of Posts and Telecommunications Nanjing PR China

ISBN: (数字)9781728150895

ISBN: (纸本)9781728150901

Hybrid cloud has both the strong computing power of public cloud and easy control of private cloud. It provides users with robust services and convenience, meanwhile faces numerous security challenges. How to implement the effective access control is one of them, the purpose of which is deploying policy in private cloud to protect the ciphertext in public cloud. Furthermore, it becomes more and more difficult to describe the access control policy, which is suitable for multi-factor and dynamic updating. Considering the issues above, we propose a proxy re-encryption (PRE) scheme for complicated access control factors description in hybrid cloud. Firstly, we build the system model combining PRE with access control in hybrid cloud. Secondly, we design the algorithm for our scheme including the key construction with multi-factor and its weight, which achieve the target of dynamic updating. Finally, we analyze the security of this scheme by the mathematical method and performance by theory, experiment and comparisons with some other works. Our scheme has made the deployment of access control in hybrid cloud more reliable and scalable.

关键词： Cloud computing Access control Cryptography XML Reliability Privacy

来源：评论

学校读者我要写书评

暂无评论

Temporal data Fusion at the Edge

Temporal Data Fusion at the Edge

引用

IEEE International Symposium on Parallel and Distributed processing with Applications and IEEE International Conference on Ubiquitous Computing and Communications (ISPA/IUCC)

作者： Linfu Yang Bin Liu School of Computer Science Nanjing University of Posts and Telecommunications Nanjing China School of Computer Science Jiangsu Key Lab of Big Data Security & Intelligent Processing Nanjing University of Posts and Telecommunications Nanjing China

ISBN: (纸本)9781728152103

As an enabler technique, data fusion has gained great attention in the context of Internet of things (IoT). In traditional settings, data fusion is done at the cloud server. So the data to be fused should be transferred from the sensor nodes to the cloud server before data fusion. Such an application mode of data fusion inherits disturbing concerns from the cloud computing framework, e.g., privacy-leaking, large latency between data capture and computation, excessive ingress bandwidth consumption. We take into account how to do temporal data fusion at the edge to bypass the above issues. We present a Gaussian process based temporal data fusion (GPTDF) method targeted for the problem of sequential online prediction at the edge. The GPTDF method fits the edge computing framework and thus inherits desirable properties from edge computing, such as privacy-preserving, low latency between data capture and computation, and tiny bandwidth consumption. Through a real-data experiment using archived traffic datasets from the Caltrans Performance Measurement System (PeMS), we demonstrate that the application of GPTDF can provide more timely and accurate real-time predictions at the network edge.

关键词： data privacy Gaussian processes Internet of Things sensor fusion data fusion Gaussian processes Internet of things data integration data privacy Sensor fusion Edge of a figure or solid data capture Privacy

来源：评论

学校读者我要写书评

暂无评论

Incentivizing the workers for truth discovery in crowdsourcing with copiers

arXiv

引用

arXiv 2019年

作者： Jiang, Lingyun Niu, Xiaofu Xu, Jia Yang, Dejun Xu, Lijie Jiangsu Key Laboratory of Big Data Security and Intelligent Processing Nanjing University of Posts and Telecommunications Nanjing Jiangsu210023 China Department of Computer Science Colorado School of Mines GoldenCO80401 United States

Crowdsourcing has become an efficient paradigm for performing large scale tasks. Truth discovery and incentive mechanism are fundamentally important for the crowdsourcing system. Many truth discovery methods and incentive mechanisms for crowdsourcing have been proposed. However, most of them cannot be applied to deal with the crowdsourcing with copiers. To address the issue, we formulate the problem of maximizing the social welfare such that all tasks can be completed with the least confidence for truth discovery. We design an incentive mechanism consisting truth discovery stage and reverse auction stage. In truth discovery stage, we estimate the truth for each task based on both the dependence and accuracy of workers. In reverse auction stage, we design a greedy algorithm to select the winners and determine the payment. Through both rigorous theoretical analysis and extensive simulations, we demonstrate that the proposed mechanisms achieve computational efficiency, individual rationality, truthfulness, and guaranteed approximation. Moreover, our truth discovery method shows prominent advantage in terms of precision when there are copiers in the crowdsourcing systems. Copyright © 2019, The Authors. All rights reserved.

关键词： Crowdsourcing

来源：评论

学校读者我要写书评

暂无评论

Darkfight: A Detection Method of Violent Behavior in Dark Place for intelligent Monitoring System

SSRN

引用

SSRN 2022年

作者： Wang, Jun Xu, Xiaolong Nanjing University of Posts & Telecommunications Jiangsu Key Laboratory of Big Data Security & Intelligent Processing Nanjing210023 China Nanjing University of Posts & Telecommunications School of Computer Science Nanjing210023 China

With the continuous development of deep learning, the use of deep learning methods for intelligent violent behavior recognition has become an active research field in computer vision. However, there are relatively few studies on violent behavior recognition in dark light environment. In this paper, we propose the DarkFight network model for violent behavior recognition in dark light environment. In the proposed DarkFight model, Resnet50 is used as the basic network model to extract features. In order to obtain multi-scale spatiotemporal features, DarkFight adds a multi-scale attention module PSA to the network. The DarkFight model uses Zero-DCE for low-light image enhancement. In order not to lose the spatiotemporal characteristics of the low-light environment, DarkFight uses the initial dark-light data and the enhanced data as the input to the two paths of the model. In addition, this paper researches the replacement of the traditional temporal global average pooling layer of the network with the BERT module to better utilize the temporal information when fusing the two path features. We construct a violent behavior dataset VDID (Violence Detection in Dark) in a dark-light environment, and conduct experimental verification on this dataset. The verification results show that the recognition precision of the DarkFight model increases by 2.51%, the accuracy increases by 3.4%, and the F1-score improves by 0.032. © 2022, The Authors. All rights reserved.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Image representation based on multi-features

Image representation based on multi-features

引用

International Conference on intelligent System and Knowledge Engineering, ISKE

作者： Xianzhong Long Lei Chen Qun Li College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing China Jiangsu Key Laboratory of Big Data Security & Intelligent Processing Nanjing Jiangsu China School of Computer Science & Technology Nanjing University of Posts and Telecommunications Nanjing China

As one kind of popular application in computer vision, image clustering has attracted many attentions. Some machine learning algorithms have been widely employed, such as K-Means, Non-negative Matrix Factorization (NMF), Graph regularized Non-negative Matrix Factorization (GNMF) and Locally Consistent Concept Factorization (LCCF). These methods possess respective strength and weakness. The common problem existing in these clustering algorithms is that they only use one kind of feature. However, different kinds of features complement each other and can be used to improve performance results. In this paper, in order to make use of the complementarity between different features, we propose an image representation method based on multi-features. Clustering results on several benchmark image data sets show that the proposed scheme outperforms some classical methods.

关键词： Clustering algorithms Image representation Feature extraction Optimization Symmetric matrices Machine learning algorithms Signal processing algorithms

来源：评论

学校读者我要写书评

暂无评论

Flight Path Optimization for UAVs to Provide Location Service to Ground Targets

Flight Path Optimization for UAVs to Provide Location Servic...

引用

IEEE Conference on Wireless Communications and Networking

作者： Youpeng Wang Xiaojun Zhu Lijie Xu College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing China Jiangsu Key Laboratory of Big Data Security & Intelligent Processing Nanjing University of Posts and Telecommunications China

ISBN: (数字)9781728131061

ISBN: (纸本)9781728131078

We consider using UAVs to provide location service to ground targets. UAVs fly over the target area and broadcast their locations periodically via wireless signals. When a UAV flies along a straight line, a target will observe the strongest signal when the UAV is at the closest location, based on which it can infer its location. The problem is to minimize the flight length subject to the constraint that the transmission range of a UAV is limited and all targets in the area should be located. We formulate the problem and give an optimal flight path to cover a square with side length no greater than a certain value. In the general case when the given area cannot be covered by the square, we propose to divide UAVs into two groups, whose flight paths are either parallel or orthogonal. We conduct simulations to compare our approach with existing approaches. Results verify the superiority of our approach in terms of flight length and localization error.

关键词：

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：