检索结果-内蒙古大学图书馆

Remote State Estimation for Complex Networks Under Probabilistic Bit Flips: A Transmission Power Allocation Scheme

IEEE Transactions on Automatic Control 2025年

作者： Song, Jiahao Wang, Zidong Liu, Qinyuan He, Xiao Tsinghua University Department of Automation Beijing100084 China Brunel University London Department of Computer Science UxbridgeUB8 3PH United Kingdom Tongji University Department of Computer Science and Technology Shanghai201804 China Ministry of Education Tongji University Key Laboratory of Embedded System and Service Computing Shanghai200092 China Shanghai Artificial Intelligence Laboratory Shanghai China

In this paper, the problem of remote state estimation is investigated for a class of complex networks with noisy wireless communication channels. The employment of the binary encoding scheme allows for the description of the influence of channel noises as probabilistic bit flips, where the probability of these bit flips is influenced by several factors with the signal-to-noise ratio (SNR) being a crucial one. In engineering practice, the method of adjusting the transmission power for each node in a complex network is commonly applied to modify the SNR so as to reduce the data distortion caused by bit flips. Furthermore, due to restricted communication resources, the total available transmission power is often limited particularly in large-scale systems such as complex networks. Consequently, the allocation of transmission power for all nodes under a total transmission power constraint becomes a concern. Utilizing the ultimately bounded filtering method, we devise a transmission-power-dependent state estimator, by which the combined effect of probabilistic bit flips and transmission power allocation on estimation performance is analyzed. Moreover, the task of co-designing the transmission power allocation scheme and estimator gains is modeled as an optimization problem, which is then addressed through a two-step optimization strategy. The existence of a unique optimal transmission power allocation scheme is also proven. Finally, numerical simulation examples are provided to demonstrate the effectiveness of the proposed co-design approach. © 1963-2012 IEEE.

关键词： Large scale systems

来源：评论

学校读者我要写书评

暂无评论

Handwritten W-Net for High-Frequency Guided Single-Image Super-Resolution

引用

IEEE Access 2025年 13卷 73124-73134页

作者： Yang, Xiang Fang, Chen Xie, Xiaolan Dong, Minggang Guilin University of Technology College of Computer Science and Engineering Guangxi Guilin China Guilin University of Technology Guangxi Key Laboratory of Embedded Technology and Intelligent System Guangxi Guilin China Guilin University of Technology College of Physics and Electronic Information Engineering Guangxi Guilin China

Super-resolution (SR) imaging involves converting low-resolution images into corresponding high-resolution data in specific scenarios. Recent advances in intelligent image reconstruction algorithms have been accompanied by impressive visual outcomes in SR generative adversarial networks (GANs). However, existing research has methodological limitations owing to the constraints posed by the model architecture and loss guidance used for optimization. Consequently, unnatural artifacts often appear in the complex backgrounds of images, leading to unappealing visual results. To address these problems, we propose an enhanced U-Net, known as the handwritten W-Net (HW-Net) architecture, as well as a loss function that uses high-frequency components for guidance. The former improves the best approximate representation of image regions, whereas the latter guides the generation of SR images with more detailed features. We experimentally implemented a biased strategy called parameter transfer, which is suitable for hybrid parameter models. This approach facilitates the blending of weight parameters between similar but different models, significantly improving the peak signal-to-noise ratio and structural similarity index measure metrics without sacrificing the learned perceptual image patch similarity. Across nine SR benchmark datasets, the proposed combinations, with and without parameter transfer, demonstrated excellent performance across multiple evaluation metrics, surpassing the state-of-the-art SRGAN. The code is available at https://***/DaHuaSen/H2SR. © 2013 IEEE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

TDiffSal: Text-Guided Diffusion Saliency Prediction Model for Images 27th

TDiffSal: Text-Guided Diffusion Saliency Prediction Model fo...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Zhang, Nana Xiong, Min Zhu, Dandan Zhu, Kun Zhai, Guangtao School of Computer Science and Technology Donghua University No. 2999 Renmin North Road Songjiang District Shanghai201620 China State Key Laboratory for Novel Software Technology Nanjing University Nanjing210093 China Institute of AI Education Shanghai East China Normal University No. 3663 Zhongshan North Road Putuo District Shanghai200333 China Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University No. 4800 Cao’an Highway Jiading District Shanghai201804 China Institute of Image Communication and Network Engineering Shanghai Jiao Tong University No. 800 Dongchuan Road Minhang District Shanghai200240 China

ISBN: (纸本)9783031781858

Existing visual saliency prediction methods mainly focus on single-modal visual saliency prediction, while ignoring the significant impact of text on visual saliency. To more comprehensively explore the influence of text on human attention in images, we propose a text-guided diffusion saliency prediction model, named TDiffSal. In specific, recent studies on stable diffusion models have shown promising performance in unifying tasks due to their inherent generalization ability. Inspired by this, a novel diffusion model for generalized visual-text saliency prediction is proposed, which formulates the prediction issue as a conditional generative task of the saliency map by employing input visual and text as the conditions. Meanwhile, we introduce a multi-head fusion module to effectively integrate text features and image features, which can efficiently guide the image denoising process and progressively refine the generated saliency map to make it semantically relevant to the text. Additionally, we employ an efficient pre-training strategy to enhance the robustness and generalization of the proposed model. We conduct extensive experiments on benchmark datasets to demonstrate its superior performance compared to other state-of-the-art methods. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Behavioral Unicity: On the Limits of Anonymized Social Behavior Metadata 1st

Behavioral Unicity: On the Limits of Anonymized Social Beh...

引用

1st Conference on Blockchain and Web3.0 Technology Innovation and Application, BWTAC 2024

作者： Tang, Hao Wang, Cheng Tongji University Shanghai201804 China The Key Laboratory of Embedded System and Service Computing Ministry of Education Shanghai201804 China Shanghai Artificial Intelligence Laboratory Shanghai200030 China Shanghai Institute of Intelligent Science and Technology Tongji University Shanghai200092 China

ISBN: (纸本)9789819794119

Social behavior metadata has altered business models and human lifestyles. However, the inclusion of personal information in social behavior metadata poses risks of identity exposure for users. Under the requirements of modern data management laws, service providers now employ anonymization techniques when collecting user behavior metadata, which aims to break the link between personal identifiers and behavioral attributes for privacy protection. This paper conducts experiments on an open-source dataset of anonymized social behavior metadata and finds that even with privacy protection techniques such as data generalization, there remains a high risk of reidentification. Specifically, four social behavior metadata records are sufficient to reidentify users from the anonymized social behavior metadata, achieving a unicity of 90.10%. This indicates that the current widespread collection of social behavior metadata brings a high risk of privacy breaches. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Anonymity

来源：评论

学校读者我要写书评

暂无评论

E2DAS: An Efficient Equivariant Dynamic Aggregation Saliency Model for Omnidirectional Images 27th

E2DAS: An Efficient Equivariant Dynamic Aggregation Saliency...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Zhang, Nana Liu, Qian Zhu, Dandan Zhu, Kun Zhai, Guangtao Yang, Xiaokang School of Computer Science and Technology Donghua University No.2999 Renmin North Road Songjiang District Shanghai201620 China Institute of AI Education Shanghai East China Normal University No.3663 Zhongshan North Road Putuo District Shanghai200333 China Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University No.4800 Cao’an Highway Jiading District Shanghai201804 China Institute of Image Communication and Network Engineering Shanghai Jiao Tong University No. 800 Dongchuan Road Minhang District Shanghai200240 China

ISBN: (纸本)9783031781216

Recent years have witnessed rapid progress of convolutional neural networks (CNNs) and their successful application in the task of saliency prediction for omnidirectional images (ODIs). Albeit achieving tremendous performance improvements, these CNNs-based saliency models are plagued by two major shortcomings: spatial content-agnostic and computationally intensive. Inspired by the effectiveness of equivariant network in the majority of computer vision tasks, we propose a novel efficient equivariant dynamic aggregation saliency (E2DAS) model to efficiently tackle the issue of human fixation prediction in ODIs. To be specific, our proposed model consists of an efficient equivariant module, a dynamic convolutional aggregation module, and an optimization computation module. Different from existing saliency models for ODIs, we are the first attempt to introduce an efficient equivariant dynamic convolutional aggregation operation into the saliency prediction task, which can fundamentally alleviate the projection distortion problem and can effectively learn spatial content-adaptive features. Moreover, we clearly observe a considerable decrease in the number of parameters resulting from the replacement of standard convolution with dynamic convolution aggregation. Extensive experiments on several benchmark datasets show the proposed model’s superiority over other state-of-the-art methods in terms of performance. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Equivariant dynamic aggregation light-weight model omnidirectional images saliency prediction spatial content-adaptive

来源：评论

学校读者我要写书评

暂无评论

Convex Hull-based Algebraic Constraint for Visual Quadric SLAM

arXiv

引用

arXiv 2025年

作者： Yu, Xiaolong Zhao, Junqiao Song, Shuangfu Zhu, Zhongyang Yuan, Zihan Ye, Chen Feng, Tiantian School of Computer Science and Technology Tongji University Shanghai China The MOE Key Lab of Embedded System and Service Computing Tongji University Shanghai China Institute of Intelligent Vehicles Tongji University Shanghai China School of Surveying and Geo-Informatics Tongji University Shanghai China

Using Quadrics as the object representation has the benefits of both generality and closed-form projection derivation between image and world spaces. Although numerous constraints have been proposed for dual quadric reconstruction, we found that many of them are imprecise and provide minimal improvements to localization. After scrutinizing the existing constraints, we introduce a concise yet more precise convex hull-based algebraic constraint for object landmarks, which is applied to object reconstruction, frontend pose estimation, and backend bundle adjustment. This constraint is designed to fully leverage precise semantic segmentation, effectively mitigating mismatches between complex-shaped object contours and dual quadrics. Experiments on public datasets demonstrate that our approach is applicable to both monocular and RGB-D SLAM and achieves improved object mapping and localization than existing quadric SLAM methods. The implementation of our method is available at https://***/tievtongji/convexhull-based-algebraic-constraint. © 2025, CC BY.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Net-structure-based conditions to decide compatibility and weak compatibility for a class of inter-organizational workflow nets

引用

Science China(Information Sciences) 2015年第7期58卷 128-143页

作者： LIU GuanJun JIANG ChangJun Department of Computer Science Tongji University Key Laboratory of the Ministry of Education for Embedded System and Service Computing Tongji University

Inter-organizational workflow nets(IWF-nets) can well model the interactions among multiple processes by sending/receiving messages. Compatibility and weak compatibility are crucial properties for *** latter guarantees that a system is deadlock-free and livelock-free while the former also guarantees that it has no dead tasks. Our previous work proved that the(weak) compatibility problem is PSPACE-complete for safe IWF-nets. This paper defines a class of IWF-nets in which some simple circuits are allowed. Necessary and sufficient conditions are presented to decide compatibility and weak compatibility for this class, and they are dependent on the net structures only. Algorithms are developed based on these conditions. In addition, we show that the traditional net structures like siphon cannot be easily used to decide the(weak) compatibility of IWF-nets.

关键词： formal method workflow nets compatibility business process model web services composition

来源：评论

学校读者我要写书评

暂无评论

Partition-based Collaborative Tensor Factorization for POI Recommendation

引用

IEEE/CAA Journal of Automatica Sinica 2017年第3期4卷 437-446页

作者： Wenjing Luan Guanjun Liu Changjun Jiang Liang Qi Department of Computer Science and Technology Tongji University IEEE Key Laboratory of Embedded System and Service Computing Tongji University

The rapid development of location-based social networks(LBSNs) provides people with an opportunity of better understanding their mobility behavior which enables them to decide their next *** example,it can help travelers to choose where to go next,or recommend salesmen the most potential places to deliver advertisements or sell *** this paper,a method for recommending points of interest(POIs)is proposed based on a collaborative tensor factorization(CTF)***,a generalized objective function is constructed for collaboratively factorizing a tensor with several feature ***,a 3-mode tensor is used to model all users' check-in behaviors,and three feature matrices are extracted to characterize the time distribution,category distribution and POI correlation,***,each user's preference to a POI at a specific time can be estimated by using *** order to further improve the recommendation accuracy,PCTF(Partitionbased CTF) is proposed to fill the missing entries of a tensor after clustering its every *** on a real checkin database show that the proposed method can provide more accurate location recommendation.

关键词： Clustering context feature extraction point of interest(POI) recommendation tensor factorization

来源：评论

学校读者我要写书评

暂无评论

Behavior Consistency Computation for Workflow Nets With Unknown Correspondence

引用

IEEE/CAA Journal of Automatica Sinica 2018年第1期5卷 281-291页

作者： Mimi Wang Guanjun Liu Peihai Zhao Chungang Yan Changjun Jiang Department of Computer Science and Technology the Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University Shanghai 200092 China IEEE

Consistency degree calculation is established on the basis of known correspondence, but in real life, the correspondence is generally unknown, so how to calculate consistency of two models under unknown correspondence has become a problem. For this condition, we should analyze unknown correspondence due to the influence of different *** this paper we obtain the relations of transitions based on event relations using branching processes, and build a behavioral matrix of relations. Based on the permutation of behavioral matrix, we express different correspondences, and define a new formula to compute the maximal consistency degree of two workflow nets. Additionally, this paper utilizes an example to show these definitions, computation as well as the advantages.

关键词： Behavioral matrix branching process consistency degree unknown correspondence workflow net(WF-nets)

来源：评论

学校读者我要写书评

暂无评论

Impact of the Next-Nearest-Neighbor Interaction on Traffic Flow of Highway with Slopes

引用

Communications in Theoretical Physics 2012年第10期58卷 590-598页

作者：李志鹏周盈 The Key Laboratory of Embedded System and Service Computing supported by Ministry of Education Tongji University

In this paper,we study the motion course of traffic flow on the slopes of a highway by applying a microscopic traffic model,which takes into account the next-nearest-neighbor interaction in an intelligent transportation system *** common gradients of the highway,which are sag terrain,uphill terrain,and downhill terrain on a single-lane roadway,are selected to clarify the impact on the traffic flow by the next-nearest-neighbor interaction in relative *** obtain the current-density relation for traffic flow on the sag,the uphill and the downhill under the next-nearest-neighbor interaction *** is observed that the current saturates when the density is greater than a critical value and the current decreases when the density is greater than another critical *** the density falls into the intermediate range between the two critical densities it is also found that the oscillatory jam,easily leads to traffic accidents,often appears in the downhill stage,and the next-nearest-neighbor interaction in relative velocity has a strong suppressing effect on this kind of dangerous congestion.A theoretical analysis is also presented to explain this important conclusion.

关键词： traffic flow traffic jam next-nearest-neighbor interaction

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：