检索结果-内蒙古大学图书馆

24th IEEE International Conference on High Performance Computing and Communications, 8th IEEE International Conference on Data science and Systems, 20th IEEE International Conference on Smart City and 8th IEEE International Conference on Dependability in Sensor, Cloud and Big Data Systems and Application, HPCC/DSS/SmartCity/DependSys 2022

作者： Shen, Zhijie Liu, Bowen Xu, Xiaolong Qi, Lianyong Dai, Fei Dou, Wanchun State Key Laboratory for Novel Software Technology Nanjing University Nanjing China Shenzhen China College of Big Data and Intelligent Engineering Southwest Forestry University Kunming China Qingdao China School of Computer Science Nanjing University of Information Science and Technology Nanjing China

ISBN: (纸本)9798350319934

As a standardized and systematic management method, business process management plays an important role in the industrial Internet of Things (IIoT) scenario. With the rapid development of mobile Internet and the increasing amount of data generated by the Internet of Things devices, the traditional storage scheme can no longer meet the requirements of managing the IIoT mobile business data. The cloud-edge collaborative data storage scheme provides mass storage capability by the cloud data center, and meanwhile takes access delay into account by storing data in the edge servers near to user, making it an effective solution to manage mobile business data in the IIoT scenario. However, the storage capacity of edge servers is relatively limited. How to design a reasonable data placement strategy to maximize the speed of data reading and tasks execution in IIoT business process has become an urgent problem to be solved. In order to shorten the overall running time, reduce data transmission costs and enhance users experience, we propose a data placement strategy based on Bayesian optimization algorithm, which can reasonably allocate storage capacity in the edge side, and further determine which edge server the data should be placed on. The results of the experiment show that the strategy based on our proposed algorithm performs better in a variety of different scenarios than the ones that based on other kind of optimization algorithms which have been adopted in similar studies. © 2022 IEEE.

关键词： Edge computing

来源：评论

学校读者我要写书评

暂无评论

Cyclic Sensing: An Orbital Spectrum Sensing Method for Uplink NOMA IoT Systems

Cyclic Sensing: An Orbital Spectrum Sensing Method for Uplin...

引用

IEEE International Conference on Communications (ICC)

作者： Tianheng Xu Yinjun Xu Jingyi Wu Haijun Zhang Ting Zhou Honglin Hu Victor C.M. Leung Shanghai Advanced Research Institute Chinese Academy of Sciences Shanghai China Shanghai Frontier lnnovation Research Institute Shanghai China School of Computer and Communication Engineering University of Science and Technology Beijing Beijing China School of Microelectronics Shanghai University Shanghai China Department of Electrical and Computer Engineering The University of British Columbia Canada College of Computer and Software Engineering Shenzhen University China

ISBN: (数字)9781728190549

ISBN: (纸本)9781728190556

The upcoming sixth-generation (6G) of ubiquitous connectivity communications systems is driven by the next-generation of Internet of Things (IoT) technology. Accordingly, the demand for spectrum resources is growing exponentially. Spectrum sensing, which dynamically explores spectrum holes, is expected to be crucial in the 6G era. In the meantime, Non-Orthogonal Multi-Access (NOMA), an efficient means of reusing resources, can enable multiple users to share the same frequency band stably. The combination of both technologies holds promise for more effective use of spectrum resources in future commu-nications. In this paper, we present a spectrum sensing method for the uplink communication scenario in NOMA with multi-user interference, which aims to make effective use of both static and dynamic gain on spectrum efficiency. Firstly, the sensing criterion and workflow are outlined. The closed-form solution for the sensing threshold configuration is derived thereafter. The simulation results demonstrate the feasibility of the proposed approach, which can increase the system throughput up to 19.7%, when compared to NOMA without spectrum sensing.

关键词： 6G mobile communication NOMA Closed-form solutions Simulation Throughput Orbits Sensors

来源：评论

学校读者我要写书评

暂无评论

MTTM: Metamorphic Testing for Textual Content Moderation software

MTTM: Metamorphic Testing for Textual Content Moderation Sof...

引用

International Conference on software engineering (ICSE)

作者： Wenxuan Wang Jen-tse Huang Weibin Wu Jianping Zhang Yizhan Huang Shuqing Li Pinjia He Michael R. Lyu Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong China School of Software Engineering Sun Yat-sen University Zhuhai China School of Data Science The Chinese University of Hong Kong Shenzhen Shenzhen China

The exponential growth of social media platforms such as Twitter and Facebook has revolutionized textual communication and textual content publication in human society. However, they have been increasingly exploited to propagate toxic content, such as hate speech, malicious advertisement, and pornography, which can lead to highly negative impacts (e.g., harmful effects on teen mental health). Researchers and practitioners have been enthusiastically developing and extensively deploying textual content moderation software to address this problem. However, we find that malicious users can evade moderation by changing only a few words in the toxic content. Moreover, modern content moderation software's performance against malicious inputs remains underexplored. To this end, we propose MTTM, a Metamorphic Testing framework for Textual content Moderation software. Specifically, we conduct a pilot study on 2, 000 text messages collected from real users and summarize eleven metamorphic relations across three perturbation levels: character, word, and sentence. MTTM employs these metamorphic relations on toxic textual contents to generate test cases, which are still toxic yet likely to evade moderation. In our evaluation, we employ MTTM to test three commercial textual content moderation software and two state-of-the-art moderation algorithms against three kinds of toxic content. The results show that MTTM achieves up to 83.9%, 51%, and 82.5% error finding rates (EFR) when testing commercial moderation software provided by Google, Baidu, and Huawei, respectively, and it obtains up to 91.2% EFR when testing the state-of-the-art algorithms from the academy. In addition, we leverage the test cases generated by MTTM to retrain the model we explored, which largely improves model robustness 0% ~ 5.9% EFR) while maintaining the accuracy on the original test set. A demo can be found in this link 1 .

关键词：

来源：评论

学校读者我要写书评

暂无评论

Disparity Analysis Between the Assembly and Byte Malware Samples with Deep Autoencoders

Disparity Analysis Between the Assembly and Byte Malware Sam...

引用

International Conference on Wavelet Active Media Technology and Information Processing (ICWAMTIP)

作者： Muhammed Amin Abdullah Yongbin Yu Jingye Cai Yakubu Imrana Nartey Obed Tettey Daniel Addo Kwabena Sarpong Bless Lord Y. Agbley Benjamin Appiah School of Information and Software Engineering University of Electronic Science and Technology of China China School of Computer Science and Engineering University of Electronic Science and Technology of China China Department of Computer Science Ho Technical University Ho Ghana

ISBN: (纸本)9781665493901

Malware attacks in the cyber world continue to increase despite the efforts of Malware analysts to combat this problem. Recently, Malware samples have been presented as binary sequences and assembly codes. However, most researchers focus only on the raw Malware sequence in their proposed solutions, ignoring that the assembly codes may contain important details that enable rapid Malware detection. In this work, we leveraged the capabilities of deep autoencoders to investigate the presence of feature disparities in the assembly and raw binary Malware samples. First, we treated the task as outliers to investigate whether the autoencoder would identify and justify features as samples from the same family. Second, we added noise to all samples and used Deep Autoencoder to reconstruct the original samples by denoising. Experiments with the Microsoft Malware dataset showed that the byte samples' features differed from the assembly code samples.

关键词： Training Codes Noise reduction Information processing Media Malware Data models

来源：评论

学校读者我要写书评

暂无评论

Robust Dynamic Broadcasting for Multi-Hop Wireless Networks Under Time-Varying Connectivity and Dynamic SINR

引用

IEEE Transactions on Mobile Computing 2025年

作者： Tian, Xiang Yu, Jiguo Luo, Chuanwen Yu, Dongxiao Wang, Guijuan Feng, Bin Jinan250353 China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Industrial Network and Information System Security Jinan250353 China University of Electronic Science and Technology of China School of Information and Software Engineering Chengdu610054 China Qilu University of Technology Big Data Institute Jinan250353 China Beijing Forestry University School of Information Science and Technology Beijing100083 China Shandong University School of Computer Science and Technology Shandong Qingdao266237 China Taishan University School of Information Science and Technology 271000 China

Throughput-optimal dynamic broadcasting is an essential cornerstone for the efficient operation of Multi-hop Wireless Networks (MWNs). Most existing algorithms for this problem were developed assuming static interference environments and network connectivity. However, wireless interference environments and network connectivity are inherently time-varying in real-world scenarios, primarily due to uncontrollable interference sources and unreliable links. Such time-varying characteristics make these existing algorithms less robust. In this paper, we study the robust throughput-optimal dynamic broadcasting for MWNs with multi-dimensional time-varying characteristics in terms of interference environments, network connectivity, and data arrival. We model the time-varying link existence states using a random process and characterize the time-varying interference environments through a dynamic variant of the classical Signal-to-Interference-plus-Noise-Ratio (SINR) model. In this variant, the SINR model parameters are dynamically adjusted over time by an adversary. Based on this, we first design a Robust Throughput-optimal Dynamic Broadcast (RTDB) algorithm which makes efficient slot-based max-weight link scheduling, power allocation, and data forwarding decisions in each time slot. We then prove its throughput-optimality in time-varying acyclic directed MWNs under the dynamic SINR model. The effectiveness of RTDB is validated via numerous simulations. © 2002-2012 IEEE.

关键词： Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

DarkSAM: fooling segment anything model to segment nothing 24

DarkSAM: fooling segment anything model to segment nothing

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Ziqi Zhou Yufei Song Minghui Li Shengshan Hu Xianlong Wang Leo Yu Zhang Dezhong Yao Hai Jin National Engineering Research Center for Big Data Technology and System and Services Computing Technology and System Lab and Cluster and Grid Computing Lab and School of Computer Science and Technology Huazhong University of Science and Technology School of Cyber Science and Engineering Huazhong University of Science and Technology School of Software Engineering Huazhong University of Science and Technology National Engineering Research Center for Big Data Technology and System and Services Computing Technology and System Lab and Hubei Engineering Research Center on Big Data Security and Hubei Key Laboratory of Distributed System Security and School of Cyber Science and Engineering Huazhong University of Science and Technology School of Information and Communication Technology Griffith University

ISBN: (纸本)9798331314385

Segment Anything Model (SAM) has recently gained much attention for its outstanding generalization to unseen data and tasks. Despite its promising prospect, the vulnerabilities of SAM, especially to universal adversarial perturbation (UAP) have not been thoroughly investigated yet. In this paper, we propose DarkSAM, the first prompt-free universal attack framework against SAM, including a semantic decoupling-based spatial attack and a texture distortion-based frequency attack. We first divide the output of SAM into foreground and background. Then, we design a shadow target strategy to obtain the semantic blueprint of the image as the attack target. DarkSAM is dedicated to fooling SAM by extracting and destroying crucial object features from images in both spatial and frequency domains. In the spatial domain, we disrupt the semantics of both the foreground and background in the image to confuse SAM. In the frequency domain, we further enhance the attack effectiveness by distorting the high-frequency components (i.e., texture information) of the image. Consequently, with a single UAP, DarkSAM renders SAM incapable of segmenting objects across diverse images with varying prompts. Experimental results on four datasets for SAM and its two variant models demonstrate the powerful attack capability and transferability of DarkSAM. Our codes are available at: https://***/CGCL-codes/DarkSAM.

关键词：

来源：评论

学校读者我要写书评

暂无评论

ITSVA: Toward 6G-Enabled Vision Analytics over Integrated Terrestrial-Satellite Network

ITSVA: Toward 6G-Enabled Vision Analytics over Integrated Te...

引用

Satellite Computing (Satellite), IEEE International Conference on

作者： Miao Zhang Jiaxing Li Jianxin Shi Yifei Zhu Lei Zhang Hengzhi Wang School of Computing Science Simon Fraser University Canada College of Computer Science Nankai University China UM-SJTU Joint Institute Shanghai Jiao Tong University China College of Computer Science and Software Engineering Shenzhen University China

The sixth-generation (6G) mobile communications system is expected to integrate the terrestrial and low Earth orbit satellite networks (LSN) to provide seamless global Internet service. This will create new opportunities for edge-assisted mobile vision analytics (MVA), which offloads frames over networks to edge servers for analysis, thereby overcoming the local computational resource constraints. With the integrated terrestrial and LSN (ITLSN), edge-assisted MVA can reach its full potential in remote and maritime areas. Nevertheless, the proximity of LEO satellites to the Earth is a double-edged sword. It offers benefits in latency and data rates but also brings challenges like frequent satellite handovers and volatile channel conditions. To demystify the in-the-wild performance of ITLSN, we carry out large-scale measurements with a major LSN service provider. The measurement results confirm the highly asymmetric and dynamic network performance of today's ITLSN, which can present non-trivial challenges for MVA frame offloading. We thus propose an ITLSN -adaptive MVA offloading framework, IT SVA, to address the inherent dynamics brought by network conditions, video content, and the offloading strategy. Extensive trace-driven simulation experiments are further conducted to verify the effectiveness of ITSVA.

关键词：

来源：评论

学校读者我要写书评

暂无评论

OldVisOnline: Curating a Dataset of Historical Visualizations

arXiv

引用

arXiv 2023年

作者： Zhang, Yu Jiang, Ruike Xie, Liwenhan Zhao, Yuheng Liu, Can Ding, Tianhong Chen, Siming Yuan, Xiaoru The Department of Computer Science University of Oxford United Kingdom the School of Intelligence Science and Technology Peking University China The School of Data Science Fudan University China The Department of Computer Science and Engineering The Hong Kong University of Science and Technology Hong Kong The Fundamental Software Innovation Lab Huawei Technologies China

With the increasing adoption of digitization, more and more historical visualizations created hundreds of years ago are accessible in digital libraries online. It provides a unique opportunity for visualization and history research. Meanwhile, there is no large-scale digital collection dedicated to historical visualizations. The visualizations are scattered in various collections, which hinders retrieval. In this study, we curate the first large-scale dataset dedicated to historical visualizations. Our dataset comprises 13K historical visualization images with corresponding processed metadata from seven digital libraries. In curating the dataset, we propose a workflow to scrape and process heterogeneous metadata. We develop a semi-automatic labeling approach to distinguish visualizations from other artifacts. Our dataset can be accessed with OldVisOnline, a system we have built to browse and label historical visualizations. We discuss our vision of usage scenarios and research opportunities with our dataset, such as textual criticism for historical visualizations. Drawing upon our experience, we summarize recommendations for future efforts to improve our dataset. Copyright © 2023, The Authors. All rights reserved.

关键词： Digital libraries

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Rail Surface Defect Detection Method

Unsupervised Rail Surface Defect Detection Method

引用

International Symposium on Environmentally Conscious Design and Inverse Manufacturing (EcoDesign)

作者： ChenYu Zhao Yi Han Ningkang Ouyang YiFan Zhao School of Artificial Intelligence Zhengzhou Software Vocational and Technical College Zhengzhou China Department of Computer Science and Information Anyang Institute of Technology Engineering Anyang China School of Information Engineering North China University of Water Resources and Electric Power Zhengzhou China

ISBN: (数字)9798350363043

ISBN: (纸本)9798350363050

Railroad travel has become an essential part of modern life, therefore, rail surface defect detection has become a problem that cannot be ignored. However, most of the currently existing methods often require a large number of defect samples for learning, which are labor-intensive and very difficult to obtain. In order to alleviate the data dependence of the detection model, this paper proposes an unsupervised method. Specifically, we use Transformer’s attention mechanism to construct the encoder-decoder structure and train it only on normal samples with the purpose of reconstruction, so that those regions that cannot be reconstructed will be regarded as defects at the time of detection. To prevent the model from generalizing its generalization ability to those unknown defective samples, i.e., to avoid overgeneralization, we introduce a noise perturbation in the training so that the model focuses on the reconstruction of normal features. Experiments show that the proposed unsupervised approach outperforms a host of supervised models with low data requirements and can effectively address the current challenges of track defect detection.

关键词： Rails Surface reconstruction Perturbation methods Noise Transformers Data models Decoding Image reconstruction Unsupervised learning Defect detection

来源：评论

学校读者我要写书评

暂无评论

A Fast Line Density Visualization Plugin for Geographic Information Systems 25

A Fast Line Density Visualization Plugin for Geographic Info...

引用

Companion of the 2025 International Conference on Management of Data

作者： Tsz Nam Chan Bojian Zhu Dingming Wu Yun Peng Leong Hou U Wei Tu Ruisheng Wang College of Computer Science and Software Engineering Shenzhen University Shenzhen China Department of Computer Science Hong Kong Baptist University Hong Kong SAR China Institute of Artificial Intelligence and Blockchain Guangzhou University Guangzhou China Department of Computer and Information Science University of Macau Macao SAR China School of Architecture and Urban Planning Shenzhen University Shenzhen China

ISBN: (纸本)9798400715648

Line Density Visualization (LDV) has been widely used in different domains, e.g., transportation science, urban planning, and criminology. Therefore, various geographic information systems, e.g., ArcGIS and QGIS, can also support this tool. However, all these GIS platforms mainly adopt the naïve algorithm for generating LDV, which cannot be scalable to high resolution sizes and large-scale line-segment datasets. To tackle this issue, we have developed a new QGIS plugin, called Fast Line Density Analysis, for efficiently supporting two types of accurate approximation, namely (1) generating LDV with an ε-relative error guarantee (εLDV) and (2) generating LDV with multiple thresholds (τLDV). In this demonstration, we have prepared three large-scale datasets (with up to 15.7 million line segments) for participants to compare our plugin with QGIS and ArcGIS in terms of accuracy and efficiency. In particular, participants can also tune different parameters in our plugin for understanding how they can affect the visualization quality and efficiency. The demonstration video is available in the YouTube and Bilibili links, which are https://***/watch?v=EYl3Wieb-2I and https://***/video/BV1aJwaeMEHr, respectively.

关键词： GIS

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：