检索结果-内蒙古大学图书馆

2nd IEEE International Conference on Industrial Internet Cloud, ICII 2019

作者： Ma, Rong Chen, Lei Xiong, Jinbo Tian, Youliang Li, Qi Liu, Ximeng Fujian Provincial Key Laboratory of Network Security and Cryptology College of Mathematics and Informatics Fujian Normal University Fuzhou350117 China College of Engineering and Computing Georgia Southern University GA30458 United States Guizhou Provincial Key Laboratory of Public Big Data Guizhou University Guiyang550025 China School of Computer Science Nanjing University of Posts and Telecommunications Nanjing210023 China Fujian Provincial Key Laboratory of Information Security of Network Systems College of Mathematics and Computer Science Fuzhou University Fuzhou350108 China

ISBN: (纸本)9781728129778

Mobile crowdsensing is a typical application of the Industrial Internet of hings and brings a promising opportunity to construct powerful industrial systems and services. The existing privacy protection schemes usually adopt a unified privacy protection policy for all sensing data due to lack of effective privacy metrics, thereby resulting in excessive or insufficient protection of privacy information and low accuracy of sensing data. To tackle these issues, in this paper, we propose a personalized privacy protection data uploading (PPDU) scheme based on game theory and sensing user's historical spatio-temporal data. In PPDU, a personalized privacy measurement algorithm is designed to obtain the personalized privacy degree of user sensing data. Based on the privacy degree, a user uploading behavior game is designed by employing an incomplete information game, and a game-based spatio-temporal sensing data uploading method is proposed for user privacy protection. Simulation experiments with real trajectory data show that the PPDU scheme makes a reasonable balance between retaining high quality of crowdsensing service and protecting user's privacy. © 2019 IEEE.

关键词： Game theory

来源：评论

学校读者我要写书评

暂无评论

A regional industry intelligence business platform based on adaptive clustering

引用

International Journal of Circuits, Systems and Signal Processing 2020年 14卷 656-660页

作者： Liu, Junjie Cai, Danlin Zhu, Daxin Huang, Siyu Network Information Center Quanzhou Normal University Quanzhou China Fujian University Laboratory of Intelligent Computing and Information Processing Quanzhou China Fujian Provincial Key Laboratory of Data-Intensive Computing Quanzhou China College of Mathematics and Computer Science Quanzhou Normal University Quanzhou China

How to grasp comprehensive, timely, effective and accurate business competitive intelligence has become an urgent and critical issue for regional industrial clusters. Therefore, a Industrial Internet Platform for Regional Economic based on Adaptive Clustering called IIPRE is developed. The multi thread oriented extraction technology is used to collect the business intelligence data of specific industries. The data is clustered by rule-based machine learning, and the business information data model is used for analysis. Finally, the visualization report is generated by big data visualization software. The system uses Intelligent Retrieval technology to automatically complete the functions from acquisition to processing automatically, to generate data information to meet the application requirements, uses Automatic Classification Technology to provide automatic classification function combining machine-based automatic learning and rule-based information, and uses Personalized Display Technology to provide customizable personalized display pages for individuals, to organize and adjust the hot information, thematic information, clustering, related words, early warning, statistics and other information released by the system. The construction of the platform provides enterprises with comprehensive, timely, effective and accurate business competitive intelligence services, improves the strategic planning, competitive intelligence acquisition and industrial information sharing capabilities of regional industrial clusters, and will achieve tremendous economic and social benefits. © 2020, North Atlantic University Union NAUN. All rights reserved.

关键词： data visualization

来源：评论

学校读者我要写书评

暂无评论

Correction to: Enhancing cyber defense strategies with discrete multi-dimensional Z-numbers: a multi-attribute decision-making approach

引用

Complex & Intelligent Systems 2025年第7期11卷 1-1页

作者： Yao, Aiting Huang, Chen Zhang, Weiqi Dong, Chengzu Lu, Meiqu Mao, Junjun Liu, Xiao Li, Xuejun Anhui Provincial International Joint Research Center for Advanced Technology in Medical Imaging School of Computer Science and Technology Anhui University Hefei China AI Techplus Pty Ltd Organization Melbourne Australia School of Information Technology Deakin University Geelong Australia School of Data Science Lingnan University Hongkong China School of Artificial Intelligence Guangxi Minzu University Nanning China Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Hefei China

来源：评论

学校读者我要写书评

暂无评论

A Three-party Repeated Game Model for data Privacy in Mobile Edge Crowdsensing of IoT 13

A Three-party Repeated Game Model for Data Privacy in Mobile...

引用

13th EAI International Conference on Mobile Multimedia Communications, Mobimedia 2020

作者： Zhao, Mingfeng Chen, Lei Xiong, Jinbo Tian, Youliang Fujian Provincial Key Laboratory of Network Security and Cryptology College of Mathematics and Informatics Fujian Normal University Fuzhou350117 China College of Engineering and Computing Georgia Southern University GA30458 United States State Key Laboratory of Public Big Data College of Computer Science and Technology Guizhou University Guiyang550025 China

ISBN: (纸本)9781631902710

The low request response delay of mobile edge crowdsensing (MECS) paradigm allows quick interactions among entities in practical scenarios. However, there often exist dishonest behaviors in such interactions, and the personal information leakage involved seriously threatens the privacy and security of sensing users. To tackle this problem, previously we had proposed a non-repeated three-party game model, without the consideration of multiple interactions in the actual scenario. Based on game theory, this research therefore proposes a three-party repeated game model. Specifically, we propose the corresponding social norms for different phases of sensing data. It analyzes all possible behaviors deviating from rationality, calculates the change of corresponding payoff function, and explores the influencing factors and constraints of players' honest behaviors based on the premise of maximizing interests. Finally, a significant number of simulations and numerical analyse indicate that the proposed model is feasible and effective in maximizing the benefits of game participants. Copyright © 2020 EAI.

关键词： Game theory

来源：评论

学校读者我要写书评

暂无评论

Deep learning SPECT lung perfusion image classification method based on attention mechanism 5

Deep learning SPECT lung perfusion image classification meth...

引用

2020 5th International Seminar on Computer Technology, Mechanical and Electrical Engineering, ISCME 2020

作者： Zeng, Sitao Cao, Yongchun Lin, Qiang Man, Zhengxing Deng, Tao Wang, Rong Key Laboratory of China's Ethnic Languages and Information Technology of Ministry of Education Northwest Minzu University Lanzhou Gansu730030 China Key Laboratory of Streaming Data Computing Technologies and Application Northwest Minzu University Lanzhou Gansu730030 China Department of Nuclear Medicine Gansu Provincial Hospital Lanzhou Gansu730030 China

SPECT lung perfusion is an important functional imaging technology. It can capture the functional lesions of the lung in a non-invasive manner and has become an important clinical detection method for diseases such as pulmonary embolism. In order to realize the automatic detection of the degree of pulmonary embolism, this paper studies and constructs a deep classification model based on the attention mechanism. First, the normalization technique is used to convert the original lung perfusion file into a SPECT image;secondly, in view of the over-fitting phenomenon of the deep learning model caused by the small amount of medical image data and the unbalanced data, the image translation and rotation techniques are used to perform effective expansion;then, in order to improve the model's feature extraction ability, the attention mechanism is combined with the depth classification model to build a SPECT lung perfusion image classification model;finally, a set of real SPECT lung perfusion images were used to carry out comparative experiments on various depth classification models. The experimental results show that the model proposed in this paper can effectively detect the extent of lung disease lesions, and the classification accuracy rate exceeds 88%, which verifies the effectiveness and reliability of the classification model. © Published under licence by IOP Publishing Ltd.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Forest Mapping from Hyperspectral Image Using Deep Belief Network

Forest Mapping from Hyperspectral Image Using Deep Belief Ne...

引用

International Conference on Mobile Ad-hoc and Sensor Networks, MSN

作者： Xianxian Luo Songya Xu Faculty of Mathematics and Computer Science Quanzhou Normal University Fujian Provincial Key Laboratory of Data Intensive Computing Quanzhou China Faculty of Educational Science Quanzhou Normal University Quanzhou China

ISBN: (数字)9781728152127

ISBN: (纸本)9781728152134

Forest type is very important in the management of the forest ecosystem. Previous literatures demonstrate that deep belief network (DBN) gain the excellent classification performance. This research attempts to classify the forest type from hyperspectral image using DBN. To begin with, the Restricted Boltzmann Machines and deep belief networks are briefly reviewed. Then, the effect of network depth and the number of hidden units on the accuracy and Kappa efficient is discussed. Furthermore, forest type is classified using DBN by Python language, comparing with typical classification methods, such as support vector machine (SVM). The experimental results show that the number of layers is 3 and the number of nodes is 256 are the optimal network structure for forest type identification. The overall accuracy is 85.8% and the coefficient is 0.785, which is better than the classification performance of support vector machine. In general, deep belief network has the potential to be the dominant method of forest mapping by hyperspectral image.

关键词： Forestry Support vector machines Hyperspectral imaging Feature extraction Machine learning Training

来源：评论

学校读者我要写书评

暂无评论

Breast mass classification method based on convolutional neural networks

Breast mass classification method based on convolutional neu...

引用

3rd Asian Conference on Artificial Intelligence Technology, ACAIT 2019

作者： Sun, Lilei Wang, Junqian Xu, Yong Guizhou Provincial Key Laboratory of Public Big Data Guizhou University Guiyang China College of Computer Science and Technology Guizhou University Guiyang China Bio-Computing Research Centre Harbin Institute of Technology Shenzhen China

To classify the X-ray mammograms images as benign or malignant is a long-standing unresolved problem, due to the high similarity of different between the mammograms images. In this study, a novel convolutional neural network based X-ray breast mass classification method is proposed. The method receives original breast mass image and its transformed image simultaneously, and extracts more abundant features from the breast mass images. Though the transformed image is a simple inverse of the original image, it allows another side of the thing to be perceived by the network at a very low cost. Experiment results demonstrate that the proposed method significantly outperforms the compared state-of-the-art classification methods for breast mass. © 2020 Institution of Engineering and Technology. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

HairDiffusion: Vivid Multi-Colored Hair Editing via Latent Diffusion 38

HairDiffusion: Vivid Multi-Colored Hair Editing via Latent D...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Zeng, Yu Zhang, Yang Liu, Jiachen Shen, Linlin Deng, Kaijun He, Weizhao Wang, Jinbao Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University China Shenzhen Institute of Artificial Intelligence and Robotics for Society China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Guangdong Provincial Key Laboratory of Intelligent Information Processing China

Hair editing is a critical image synthesis task that aims to edit hair color and hairstyle using text descriptions or reference images, while preserving irrelevant attributes (e.g., identity, background, cloth). Many existing methods are based on StyleGAN to address this task. However, due to the limited spatial distribution of StyleGAN, it struggles with multiple hair color editing and facial preservation. Considering the advancements in diffusion models, we utilize Latent Diffusion Models (LDMs) for hairstyle editing. Our approach introduces Multi-stage Hairstyle Blend (MHB), effectively separating control of hair color and hairstyle in diffusion latent space. Additionally, we train a warping module to align the hair color with the target region. To further enhance multi-color hairstyle editing, we fine-tuned a CLIP model using a multi-color hairstyle dataset. Our method not only tackles the complexity of multi-color hairstyles but also addresses the challenge of preserving original colors during diffusion editing. Extensive experiments showcase the superiority of our method in editing multi-color hairstyles while preserving facial attributes given textual descriptions and reference images. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Few-Shot Class-Incremental Semantic Segmentation via Pseudo-Labeling and Knowledge Distillation 4

Few-Shot Class-Incremental Semantic Segmentation via Pseudo-...

引用

4th International Conference on Information Science, Parallel and Distributed Systems, ISPDS 2023

作者： Jiang, Chengjia Wang, Tao Li, Sien Wang, Jinyang Wang, Shirui Antoniou, Antonios Minjiang University Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Fuzhou China Fujian Education Institutions Wuyi University The Key Laboratory of Cognitive Computing and Intelligent Information Processing Wuyishan China College of Computer and Data Science Fuzhou University Fuzhou China European University Cyprus Department of Computer Science and Engineering Nicosia Cyprus

ISBN: (纸本)9798350337181

We address the problem of learning new classes for semantic segmentation models from few examples, which is challenging because of the following two reasons. Firstly, it is difficult to learn from limited novel data to capture the underlying class distribution. Secondly, it is challenging to retain knowledge for existing classes and to avoid catastrophic forgetting. For learning from limited data, we propose a pseudo-labeling strategy to augment the few-shot training annotations in order to learn novel classes more effectively. Given only one or a few images labeled with the novel classes and a much larger set of unlabeled images, we transfer the knowledge from labeled images to unlabeled images with a coarse-to-fine pseudo-labeling approach in two steps. Specifically, we first match each labeled image to its nearest neighbors in the unlabeled image set at the scene level, in order to obtain images with a similar scene layout. This is followed by obtaining pseudo-labels within this neighborhood by applying classifiers learned on the few-shot annotations. In addition, we use knowledge distillation on both labeled and unlabeled data to retain knowledge on existing classes. We integrate the above steps into a single convolutional neural network with a unified learning objective. Extensive experiments on the Cityscapes and KITTI datasets validate the efficacy of the proposed approach in the self-driving domain. Code is available from https://***/ChasonJiang/FSCILSS. © 2023 IEEE.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

GA-Net: Gated Attention Mechanism Based Global Refinement Network for Image Inpainting 29

GA-Net: Gated Attention Mechanism Based Global Refinement Ne...

引用

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

作者： Qiu, Ran Zhao, Shengrong Liang, Hu Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center 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)9798350330717

Underwater images are often affected by problems such as light attenuation, color distortion, noise and scattering, resulting in image defects. A novel image inpainting method is proposed to intelligently predict and fill damaged areas for complete and continuous visualization of the image. First, in order to effectively solve the problem of color distortion caused by light refraction in underwater environments, the improved gated attention mechanism is used. This mechanism improves the local details by learning and weighting the important features of the image. Second, gated convolution automatically determines the degree of restoration for each pixel based on local features of the original image. It eliminates distractions such as low contrast and scattering, retaining more original detailed information. By doing so, image inpainting techniques improve the quality and visualization of underwater images. © 2023 IEEE.

关键词： Gated convolution Image inpainting Underwater images

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：