检索结果-内蒙古大学图书馆

IEEE International Conference on Systems, Man and Cybernetics

作者： Xin Zhang Mengning Yang Haiyang Chai School of Big Data and Software Engineering Chongqing University Chongqing China

ISBN: (纸本)9781665442084

Among the major remaining challenges in image-to-image translation is the capacity to generate multi-domain High-Definition images. Recently, the StarGAN is proposed to solve the multi-domain image translation problem. However, the StarGAN focuses on the low-resolution facial image synthesis, leaving some high-frequency information and unsuitable for HD image translation tasks. To address the issue, we propose the Enhanced StarGAN (called EStarGAN), aiming to generate multi-style High-Definition images with fine-grained details simultaneously. Specifically, we propose the Channel-and-Spatial Residual-in-Residual (CSRIR) module to learn high-frequency information in the deep network more effectively. Furthermore, we propose a new reconstruction loss, which consists of mean squared error and Structural Similarity loss to enhance the quality of the generated images. Extensive experiments on real-world datasets prove that our EStarGAN excels baselines with respect to both subjective and objective evaluations.

关键词： Social networking (online) Image synthesis Conferences Task analysis Image reconstruction Cybernetics

来源：评论

学校读者我要写书评

暂无评论

GCD-Sampling: A General Cross-scale Decoupled Sampling for Point Cloud 39

GCD-Sampling: A General Cross-scale Decoupled Sampling for P...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Dai, Tao Wang, Yanzi Xiong, Jianyu Zha, Yaohua Xia, Shu-Tao Zhu, Zexuan College of Computer Science and Software Engineering Shenzhen University China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Tsinghua Shenzhen International Graduate School Tsinghua University China Shenzhen City Key Laboratory of Embedded System Design Shenzhen China

ISBN: (纸本)157735897X

Sampling strategy (e.g., fixed farthest point sampling) of point cloud has been an essential step for developing practical solutions in 3D computer vision tasks. Previous fixed sampling is simple, but suffer from suboptimal performance for downstream tasks. To adapt to target networks properly, adaptive sampling methods with trainable parameters have been recently developed to enhance the performance. However, existing adaptive sampling methods still suffer from the over-coupling problem of target network, and thus become model-specific, which limits their practical applications. To address this issue, we propose a novel general cross-scale decoupled sampling method (GCD-sampling) for point cloud, which consists of original feature cache, cross-scale feature fusion and convex combination learning for better feature extraction. To reduce the coupling relationship with the target task network, our method only utilizes the point cloud coordinates as the input and output of itself. Besides, we introduce an arbitrary scale structure to enable parameter sharing across multi-scale sampling in point cloud networks. Extensive experiments on different architectures demonstrate the effectiveness of our method over other existing adaptive sampling methods. © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Sequence-to-Sequence Multi-Hop Knowledge Reasoning Based on Retentive Network

Sequence-to-Sequence Multi-Hop Knowledge Reasoning Based on ...

引用

Computer Information Science and Application Technology (CISAT), International Conference on

作者： Ruilin Su Wanshan Zhang Dunhui Yu Hubei University Wuhan China Wuhan China School of Computer Science and Information Engineering Hubei University Wuhan China Hubei Key Laboratory of Big Data Intelligent Analysis and Application Hubei University Wuhan China Engineering and Technical Research Center of Hubei Province in Software Engineering Wuhan China

ISBN: (数字)9798350375107

ISBN: (纸本)9798350375114

Multi-hop Knowledge Reasoning is a task that involves generating an answer given a query and a knowledge graph. Existing sequence-to-sequence reasoning models use the Transformer to encode and decode sequences, but these models have some flaws, such as the inability to effectively handle long-sequence reasoning and susceptibility to exposure bias. To address these issues, we provides a sequence-to-sequence reasoning model named STSR, which is based on Retentive Network. Aiming at improving training efficiency through parallel training, this model leverages the advantages in Retentive Network, reduce time overhead, and enhance reasoning efficiency through iterative reasoning. It effectively mitigates the problems of high spatial overhead and low efficiency in long-sequence reasoning faced by the Transformer. Moreover, it retains and updates historical information during the encoding and decoding process, enhancing the model’s memory and generalization capabilities. Additionally, the Scheduled Sampling method is adopted to alleviate the exposure bias introduced during reasoning, which involves using the model’s own output as the input for the next moment with a certain probability during training, instead of using the true label. We conduct the experiment on six public datasets, with the results showing that the proposed model outperforms existing baseline models in terms of precision and generation quality. This paper provides a new solution for the task of sequence-to-sequence multihop knowledge reasoning and also demonstrates the potential application of the Retentive Network in natural language processing.

关键词： Training Knowledge engineering Accuracy Spread spectrum communication Knowledge graphs Transformers Sampling methods Cognition Natural language processing Iterative decoding

来源：评论

学校读者我要写书评

暂无评论

Global Feature Enhancing and Fusion Framework for Strain Gauge Status Recognition 25

Global Feature Enhancing and Fusion Framework for Strain Gau...

引用

Companion Proceedings of the ACM on Web Conference 2025

作者： Xu Zhang Peng Wang Chen Wang Zhe Xu Xiaohua Nie Wei Wang Shanghai Key Laboratory of Data Science School of Computer Science and Technology Fudan University Shang Hai China Shanghai Key Laboratory of Data Science School of Computer Science and Technology Fudan University Shanghai China National Engineering Research Center for Big Data Software Tsinghua University Beijing China School of Software Tsinghua University Beijing China National Key Laboratory of Strength and Structural Integrity Aircraft Strength Research Institute of China Xi'an Shaanxi China

ISBN: (纸本)9798400713316

Strain Gauge Status (SGS) recognition is crucial in the field of intelligent manufacturing based on the Internet of Things, as accurate identification helps timely detection of failed mechanical components, avoiding accidents. The loading and unloading sequences generated by strain gauges can be identified through time series classification (TSC) algorithms. Recently, deep learning models, e.g., convolutional neural networks (CNNs) have shown remarkable success in the TSC task, as they can extract discriminative local features from the subsequences to identify the time series. However, we observe only the local features may not be sufficient for expressing the time series, especially when the local sub-sequences between different time series are very similar, e.g., SGS data of aircraft wings in static strength experiments. Nevertheless, CNNs suffer from the limitation in extracting global features due to the nature of convolution operations. For extracting global features to more comprehensively represent the SGS time series, we propose two insights: (i) Constructing global features through feature engineering. (ii) Learning high-order relationships between local features to capture global features. To realize and utilize them, we propose a hypergraph-based global feature learning and fusion framework, which learns and fuses global features for semantic consistency to enhance the representation of SGS time series, thereby improving recognition accuracy. Our method designs are validated on industrial SGS and public UCR datasets, showing better generalization for unseen data in SGS recognition.

关键词： deep learning models

来源：评论

学校读者我要写书评

暂无评论

Enhancing Consistency in Container Migration via TEE: A Secure Architecture

Enhancing Consistency in Container Migration via TEE: A Secu...

引用

IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom)

作者： Qingyu Gao Liantao Song Yan Lei Feng Wang Lei Wang Shize Zong Yan Ding College of Computer Science National University of Defense Technology Changsha China School of Big Data and Software Engineering Chongqing University Chongqing China College of Computer Science and Electronic Engineering Hunan University Changsha China National Innovation Institution of Defense Technology AMS China

ISBN: (数字)9798331506209

ISBN: (纸本)9798331506216

Secure migration of multi-tenant containerized cloud servers is critical to maintaining the stability and security of cloud services. However, migrating applications across servers owned by different platforms introduces a range of security challenges. Recent research indicates that Trusted Execution Environments (TEEs) provide effective hardware-based isolation for containers, significantly enhancing data confidentiality and integrity. Despite these advancements, existing technologies still struggle to ensure consistency during the migration of container data. To address these issues, we propose a comprehensive security migration framework that defines the security properties required for container migration and introduces a software-based solution. This solution integrates several technologies, including a secure removal mechanism utilizing monotonic counters to prevent potential fork/rollback attacks and ensure the single-instance nature of migrated containers. Additionally, a two-phase commit-based pre-migration check mechanism is employed to maintain consistency among tightly coupled containers being migrated simultaneously on the same host. Safety analysis confirms the effectiveness of our proposed design, and performance evaluation indicates an additional overhead of approximately 7%.

关键词： Cloud computing Privacy Runtime Scalability Containers Stability analysis Safety Security Servers Virtualization

来源：评论

学校读者我要写书评

暂无评论

An adaptive coordinator for multi-variable controller via dynamic belief assignment

An adaptive coordinator for multi-variable controller via dy...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Yongchuan Tang School of Big Data and Software Engineering Chongqing University Chongqing China

ISBN: (纸本)9781665442084

The stability of a humanoid robot is the base of other complex gestures in different and complicated tasks. Each gesture for different joints needs many controllers. To address the outputs from different controller, an adaptive coordinator for multi-variable controller via dynamic basic belief assignment strategy is proposed in this work. The planar inverted pendulum (PIP) platform, which is a very typical, simplify, cheap and an effective system for verification of a multi-variable controller, can generally imitate the stability of a robot as a whole. For each axis of PIP, there are two control variables. One is the angle of the rod, and the other is the displacement for the base cart. We propose an adaptive coordinator for the fuzzy controller in each axis to construct the final output value of control variable from the only motor in different axes. The adaptive coordinator has a dynamic value represented as the belief degree in the framework of belief functions. For different control areas and moment, the coordinator has an adaptive and dynamic basic belief assignment for the corresponding controller. The control strategy for controller design is based on classical and efficient fuzzy control. Simulation experiment verifies the rationality of the adaptive coordinator as well as the effectiveness of the multi-variable controller.

关键词： Fuzzy control Adaptation models Evidence theory Robot kinematics Design methodology Force Humanoid robots

来源：评论

学校读者我要写书评

暂无评论

One-Bit Reconfigurable Reflective Metasurface Based on Electromagnetically Wideband Element

SSRN

引用

SSRN 2023年

作者： Wu, Yuhan Yu, Shixing Kou, Na Ding, Zhao Zhang, Zhengping Key Laboratory of Micro-Nano-Electronics and Software Technology of Guizhou Province Engineering Research Center of Semiconductor Power Device Reliability the Ministry of Education College of Big Data and Information Engineering Guizhou University Guiyang550025 China

In this paper, a one-bit reconfigurable reflective metasurface is proposed by electromagnetically wideband elements is proposed. The element has a double-layer structure, the lower dielectric plate is driven by a electromagnetically push-pull solenoid to adjust the air layer thickness between top layer. The element has a wideband characteristic, the phase difference between 1bit and 0bit in 9.3GHz-16GHz is 180°±10°and the bandwidth of the unit reaches 53.6%. A 12x12 prototype was then designed, simulated and measured at 10GHz, 12.5GHz and 15GHz. The maximum gain is 18.4 dBi, 19.08 dBi, 18.8 dBi. The aperture efficiency is 13.51% at 12.5GHz. The 3dB bandwidth is 16%, and the main beam can scan range of ±40° at the centre frequency. © 2023, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhancing Consistency in Container Migration via TEE: A Secure Architecture 23

Enhancing Consistency in Container Migration via TEE: A Secu...

引用

23rd IEEE International Conference on Trust, Security and Privacy in Computing and Communications, TrustCom 2024

作者： Gao, Qingyu Song, Liantao Lei, Yan Wang, Feng Wang, Lei Zong, Shize Ding, Yan National University of Defense Technology College of Computer Science Changsha China Chongqing University School of Big Data and Software Engineering Chongqing China Hunan University College of Computer Science and Electronic Engineering Changsha China Ams National Innovation Institution of Defense Technology China

关键词： consistency Container Migration fork/rollback attack TEE

来源：评论

学校读者我要写书评

暂无评论

Joint Node Selection and Resource Allocation Optimization for Cooperative Sensing with a Shared Wireless Backhaul

arXiv

引用

arXiv 2024年

作者： Chen, Mingxin Zhao, Ming-Min Liu, An Li, Min Shi, Qingjiang College of Information Science and Electronic Engineering Zhejiang University Zhejiang Provincial Key Laboratory of Information Processing Communication and Networking Hangzhou310027 China School of Software Engineering Tongji University Shanghai201804 China Shenzhen Research Institute of Big Data Shenzhen518172 China

In this paper, we consider a cooperative sensing framework in the context of future multi-functional network with both communication and sensing ability, where one base station (BS) serves as a sensing transmitter and several nearby BSs serve as sensing receivers. Each receiver receives the sensing signal reflected by the target and communicates with the fusion center (FC) through a wireless multiple access channel (MAC) for cooperative target localization. To improve the localization performance, we present a hybrid information-signal domain cooperative sensing (HISDCS) design, where each sensing receiver transmits both the estimated time delay/effective reflecting coefficient and the received sensing signal sampled around the estimated time delay to the FC. Then, we propose to minimize the number of channel uses by utilizing an efficient Karhunen-Loéve transformation (KLT) encoding scheme for signal quantization and proper node selection, under the Cramér-Rao lower bound (CRLB) constraint and the capacity limits of MAC. A novel matrix-inequality constrained successive convex approximation (MCSCA) algorithm is proposed to optimize the wireless backhaul resource allocation, together with a greedy strategy for node selection. Despite the high non-convexness of the considered problem, we prove that the proposed MCSCA algorithm is able to converge to the set of Karush-Kuhn-Tucker (KKT) solutions of a relaxed problem obtained by relaxing the discrete variables. Besides, a low-complexity quantization bit reallocation algorithm is designed, which does not perform explicit node selection, and is able to harvest most of the performance gain brought by HISDCS. Finally, numerical simulations are presented to show that the proposed HISDCS design is able to significantly outperform the baseline schemes. Copyright © 2024, The Authors. All rights reserved.

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

Distributed Energy Management for Carbon Neutral data Centers

Distributed Energy Management for Carbon Neutral Data Center...

引用

International Symposium on Parallel and Distributed Processing with Applications, ISPA

作者： Chuyi Liu Jianxiong Wan Leixiao Li Guanyu Ren Xiaolei Wang Inner Mongolia University of Technology Huhhot China Inner Mongolia Autonomous Region Engineering & Technology Research Center of Big Data Based Software Service Huhhot China Research Center of Large-Scale Energy Storage Technologies Huhhot China

ISBN: (数字)9798331509712

ISBN: (纸本)9798331509729

With the continuous expansion of data centers, their carbon emission becomes a serious issue. A number of studies are committing to reduce the carbon emission of data centers. Carbon trading is a promising emission reduction technique which is, however, seldom applied to data centers. To bridge this gap, we propose a carbon-neutral architecture DC 2 for distributed data centers, where each data center consists of three subsystems, i.e., energy subsystem for energy supply, thermal subsystem for data center cooling and the carbon subsystem for carbon trading. Then, we formulate the energy management problem as a Decentralized Partially Observable Markov Decision Processe (Dec-POMDP) and develop a distributed solution framework using Multi-Agent Deep Deterministic Policy Gradient (MAD-DPG). Finally, simulations on real-world data shows that the DC 2 provides a cost saving of 8.16%, and applying MADDPG saves 10.04% of the overall cost compared to Independent MADDPG.

关键词： data centers Distributed processing Costs Markov decision processes Emissions trading Carbon neutral Energy efficiency data models Service-oriented architecture Carbon

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：