检索结果-内蒙古大学图书馆

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

作者： Benyuan Meng Qianqian Xu Zitai Wang Xiaochun Cao Qingming Huang Institute of Information Engineering CAS and School of Cyber Security University of Chinese Academy of Sciences Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS and Peng Cheng Laboratory Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS School of Cyber Science and Tech. Shenzhen Campus of Sun Yat-sen University School of Computer Science and Tech. University of Chinese Academy of Sciences and Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS and Key Laboratory of Big Data Mining and Knowledge Management CAS

ISBN: (纸本)9798331314385

Diffusion models are initially designed for image generation. Recent research shows that the internal signals within their backbones, named activations, can also serve as dense features for various discriminative tasks such as semantic segmentation. Given numerous activations, selecting a small yet effective subset poses a fundamental problem. To this end, the early study of this field performs a large-scale quantitative comparison of the discriminative ability of the activations. However, we find that many potential activations have not been evaluated, such as the queries and keys used to compute attention scores. Moreover, recent advancements in diffusion architectures bring many new activations, such as those within embedded ViT modules. Both combined, activation selection remains unresolved but overlooked. To tackle this issue, this paper takes a further step with a much broader range of activations evaluated. Considering the significant increase in activations, a full-scale quantitative comparison is no longer operational. Instead, we seek to understand the properties of these activations, such that the activations that are clearly inferior can be filtered out in advance via simple qualitative evaluation. After careful analysis, we discover three properties universal among diffusion models, enabling this study to go beyond specific models. On top of this, we present effective feature selection solutions for several popular diffusion models. Finally, the experiments across multiple discriminative tasks validate the superiority of our method over the SOTA competitors. Our code is available at https://***/Darkbblue/generic-diffusion-feature.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Modelling and Optimising Process of Micro-Plasma Arc Freeform Fabrication

SSRN

引用

SSRN 2023年

作者： Hong, Bo Qu, Yuanyuan Hong, Yuxiang Li, Menglong Zou, Yeming School of Mechanical Engineering Xiangtan University Xiangtan411105 China Key Laboratory of Intelligent Manufacturing Quality Big Data Tracing and Analysis of Zhejiang Province China Jiliang University Hangzhou310018 China

The main factors limiting the development of wire-based additive manufacturing (w-AM) are deposition process instability and deposition deviation caused by side feed. In this paper, the device tuning accuracy is introduced into the wire-arc deposition model for the first time, a wire-arc stable deposition model in micro-plasma arc directional energy deposition (mPA-DED) was established, and the process of the wire from contacting the micro-plasma arc (mPA) column to conducting stable metal transfer was carefully analyzed. A sensitivity coefficient describing the link between wire size and device adjustment precision in mPA-DED is proposed. The link between the sensitivity coefficient and the maximum meltable wire feeding speed and the threshold value of the maximum stable deposition speed was quantitatively analyzed, and the model was verified by cross-comparison experiments among the design wire size, arc size, and wire-arc position deviation. A well-formed 40-layer curved metal sample with a material area utilization ratio of 90.54 % was steadily deposited by using the proposed model and the optimized deposition parameters. This study offers theoretical guidance for designing an online control system for the deposition process to improve the stability of the fabrication process and deposition accuracy in micro-plasma arc freeform fabrication. © 2023, The Authors. All rights reserved.

关键词： 3D printers

来源：评论

学校读者我要写书评

暂无评论

A Multi-direction Prediction Multi-objective Hybrid Chemical Reaction Optimization Algorithm for Dynamic Multi-objective Optimization 16th

A Multi-direction Prediction Multi-objective Hybrid Chemical...

引用

16th International Conference on Bio-Inspired computing: Theories and Applications, BIC-TA 2021

作者： Li, Hongye Pan, Xiaoying Gan, Wei Wang, Lei School of Computer Science and Technology Xi’an University of Posts and Telecommunications Shaanxi Xi’an710121 China Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Shaanxi Xi’an710121 China Xi’an Key Laboratory of Big Data and Intelligent Computing Shaanxi Xi’an710121 China Xi’an Shiyou University Shaanxi Xi’an710065 China School of Computer Science and Engineering Xi’an University of Technology Xi’an710048 China Shaanxi University of Technology Shaanxi Han Zhong723001 China

ISBN: (纸本)9789811912559

The challenge of solving dynamic multi-objective optimization problems is to trace the varying Pareto optimal front and/or Pareto optimal set quickly and efficiently. This paper proposes a multi-direction prediction strategy using a hybrid chemical reaction optimization, aimed at finding the dynamic Pareto optimal front and/or Pareto optimal set as quickly and accurately as possible before the next environmental change occurs. The proposed method, multi-direction prediction multi-objective hybrid chemical reaction optimization algorithm which mainly includes a hybrid chemical reaction optimization algorithm is proposed for solving dynamic multi-objective problems, which can guide population trace the optimum. When the environment has changed, the population is divided into several subpopulations. In subpopulation, a center point was found to construct multi-direction prediction model. As a result, this approach enhances the diversity of algorithm. While the environment has not changed, the hybrid chemical reaction algorithm with particle swarm optimization algorithm can efficiency find the optimal solution, it can achieve good diversity as well as guarantee the avoidance of local optimal solutions. The proposed algorithm is measured on several benchmark test suites with various dynamic characteristics and different difficulties. Experimental results show that this algorithm is very competitive in dealing with dynamic multi-objective optimization problems when compared with four state-of-the-art approaches. © 2022, Springer Nature Singapore Pte Ltd.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

SMOG: Accelerating Subgraph Matching on GPUs

SMOG: Accelerating Subgraph Matching on GPUs

引用

IEEE Conference on High Performance Extreme computing (HPEC)

作者： Zhibin Wang Ziheng Meng Xue Li Xi Lin Long Zheng Chen Tian Sheng Zhong State Key Laboratory for Novel Software Technology Nanjing University Alibaba Group“ National Engineering Research Center for Big Data Technology and System/ Services Computing Technology and System Lab/Cluster and Grid Computing Laboratory Huazhong University of Science and Technology Zhejiang Lab

Subgraph matching is a crucial problem in graph theory with diverse applications in fields, such as bioinformatics, social networks and recommendation systems. Accelerating subgraph matching can be greatly facilitated by GPUs, which offer exceptional parallelism and high memory bandwidth. By leveraging the power of multiple GPU cards, subgraph matching can be scaled to achieve unprecedented levels of performance. In this paper, we propose SMOG, an abbreviation for. Subgraph Matching On Multi-Card GPUs. It is a general, high-performance and scalable sub graph matching system that utilizes multi-card GPUs. To address the issue of duplication resulting from subgraph automorphism, SMOG introduces a two-step approach. Firstly, it analyzes the symmetry within the subgraph. Then, it adaptively adjusts the graph preprocessing and generates subgraph-aware GPU codes tailored to the given subgraph. Furthermore, SMOG leverages multi-level parallelism by designing the specific strategy for each level, enabling it to scale from 1 to 1,024 GPU cards, resulting in an extraordinary $553\times$ speedup. We evaluate SMOG on various subgraph queries and datasets. The experimental results demonstrate that SMOG outperforms the triangle-specific system TRUST with an average speedup of $2.94\times$ . And it performs significantly better than the subgraph matching system RPS by $203.55\times$ and the graph processing system Gunrock by 35, $455.52\times$ on average.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Body mass index and survival after cancer diagnosis:A pan-cancer cohort study of 114430 patients with cancer

引用

The Innovation 2022年第6期3卷 159-165页

作者： Huakang Tu Jennifer LMcQuade Michael ADavies Maosheng Huang Kunlin Xie Yuanqing Ye Wong-Ho Chow Alma Rodriguez Xifeng Wu Department of Big Data in Health Science School of Public Health Center of Clinical Big Data and Analytics of The Second Affiliated HospitalZhejiang University School of MedicineHangzhou 310058China Department of Epidemiology The University of Texas MD Anderson Cancer CenterHoustonTX 77030USA The Key Laboratory of Intelligent Preventive Medicine of Zhejiang Province Hangzhou 310058China Department of Melanoma Medical Oncology The University of Texas MD Anderson Cancer CenterHoustonTX 77030USA Department of Liver Surgery&Liver Transplantation West China HospitalSichuan UniversityChengdu 610065China Department of Lymphoma/Myeloma The University of Texas MD Anderson Cancer CenterHoustonTX 77030USA Cancer Center Zhejiang UniversityHangzhou 310058China

The recommendation encouraging patients with cancer to keep a normal body mass index(BMI)is largely extrapolated from data on risk of developing *** tested the prospective association between peri-diagnostic(within 1 year post-diagnosis)BMI and all-cause mortality in patients with incident *** 7.2 years of follow-up,42%(48,340)of the 114430 patients with cancer *** analysis revealed that compared with a BMI of 22.5,a BMI lower than 22.5 was associated with increased risk of all-cause mortality across 24 cancer types.A BMI higher than 22.5 was associated with reduced all-cause mortality,while a non-linear association was observed;the lowest risk was found at a BMI of 29.6–34.2,and the risk started to return to and above unity at very high BMI *** reduced mortality risk of high BMI was observed in 23 of 24 cancer types and maintained after attempts to remove potential selection bias,confounding by smoking and comorbidities,and reserve causality.

关键词： patients mortality diagnosis

来源：评论

学校读者我要写书评

暂无评论

Fingerprint Presentation Attack Detector Using Global-Local Model

arXiv

引用

arXiv 2024年

作者： Liu, Haozhe Zhang, Wentian Liu, Feng Wu, Haoqian Shen, Linlin The Computer Vision Institute College of Computer Science and Software Engineering SZU Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society The National Engineering Laboratory for Big Data System Computing Technology The Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen518060 China

The vulnerability of automated fingerprint recognition systems (AFRSs) to presentation attacks (PAs) promotes the vigorous development of PA detection (PAD) technology. However, PAD methods have been limited by information loss and poor generalization ability, resulting in new PA materials and fingerprint sensors. This paper thus proposes a global-local model-based PAD (RTK-PAD) method to overcome those limitations to some extent. The proposed method consists of three modules, called: 1) the global module;2) the local module;and 3) the rethinking module. By adopting the cut-out-based global module, a global spoofness score predicted from nonlocal features of the entire fingerprint images can be achieved. While by using the texture in-painting-based local module, a local spoofness score predicted from fingerprint patches is obtained. The two modules are not independent but connected through our proposed rethinking module by localizing two discriminative patches for the local module based on the global spoofness score. Finally, the fusion spoofness score by averaging the global and local spoofness scores is used for PAD. Our experimental results evaluated on LivDet 2017 show that the proposed RTK-PAD can achieve an average classification error (ACE) of 2.28% and a true detection rate (TDR) of 91.19% when the false detection rate (FDR) equals 1.0%, which significantly outperformed the state-of-the-art methods by ∼10% in terms of TDR (91.19% versus 80.74%). Copyright © 2024, The Authors. All rights reserved.

关键词： Supervised learning

来源：评论

学校读者我要写书评

暂无评论

Fed-GAN: Federated Generative Adversarial Network with Privacy-Preserving for Cross-Device Scenarios

引用

IEEE Transactions on Dependable and Secure computing 2025年

作者： Han, Song Ding, Hongxin Zhao, Shuai Ren, Siqi Zeng, Shengke Xue, Mengqi Wang, Ruili Hangzhou City University School of Computer and Computing Science Hangzhou China Zhejiang Gongshang University School of Computer Science and Technology China Zhejiang Key Laboratory of Big Data and Future E-Commerce Technology Hangzhou China Xihua University School of Computer and Software Engineering Chengdu China Massey University School of Mathematical and Computational Science Auckland New Zealand

Huge amounts of data from various sources are substantial to dependable distributed machine learning, especially for trustworthy federated learning (FL). However, existing FL methods are difficult to collect enough data for training the global model more accurately, especially in cross-device scenarios. In this paper, we propose a new federated generative adversarial network empowered by differential privacy and knowledge transfer named Fed-GAN, which can be used to address the problem of data shortage and prevent generator leakage from resource-constrained devices, as well as generate high-quality synthetic data while ensuring strict DP guarantees. Different from other generative model methods, our Fed-GAN framework can achieve efficient and secure generative model training and limited permission for resource-constrained devices to prevent them from leaking or misusing the generator. In addition, we propose a pHash-KT method for our Fed-GAN framework, which selects potentially high-quality data through the knowledge of each client for improving the utility of synthetic data. Our FedGAN framework satisfies (Formula presented)-DP, and also has high resistance when number of adversaries is 10%-70% of the total number of clients. Extensive experiments demonstrate that our Fed-GAN framework not only generates high-quality synthetic data, but also provides strict DP guarantees, compared with other generative model methods. © 2004-2012 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Blockchain-Based Multi-Cloud data Storage System Disaster Recovery

Blockchain-Based Multi-Cloud Data Storage System Disaster Re...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Feiyu Wang Jian-tao Zhou College of Computer Science Inner Mongolia University Hohhot Inner Mongolia China Inner Mongolia Engineering Laboratory for Cloud Computing and Service Software Inner Mongolia Key Laboratory of Social Computing and Data Processing Inner Mongolia Engineering Laboratory for Big Data Analysis Technology Engineering Research Center of Ecological Big Data Ministry of Education National & Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian China

Cloud storage services have been used by most businesses and individual users. However, data loss, service interruptions and cyber attacks often lead to cloud storage services not being provided properly, and these incidents have caused financial losses to users. Second, traditional and single-cloud model disaster recovery services are no longer suitable for the current complex cloud storage systems. Therefore, a scheme to provide disaster recovery for cloud storage services in a multi-cloud storage environment is needed in real production. In this paper, we propose a disaster recovery scheme based on blockchain technology. The proposed scheme outlined in this study aims to address the issue of data availability within the cloud storage landscape. The proposed scheme achieves this goal by dividing data into hot and cold categories, verifying the integrity of copy data via blockchain technology, and utilizing blockchain networks to manage multi-cloud storage systems. Experimental findings demonstrate that the proposed scheme yields superior results in terms of computation and time overheads.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Uniformly Spaced Double-Latent Variable Probabilistic Model for Monitoring of Dynamic Processes with Multiple Sampling Rates

SSRN

引用

SSRN 2024年

作者： Ying, Ze Chang, Yuqing He, Yuchen Wang, Fuli College of Information Science and Engineering Northeastern University Shenyang110819 China Northeastern University State Key Laboratory of Synthetical Automation for Process Industries Shenyang110819 China Key Laboratory of Intelligent Manufacturing Quality Big Data Tracing and Analysis of Zhejiang Province China Jiliang University Hangzhou310018 China

The collections and statistical analysis of production data are essential for process monitoring in modern industries, yet often faces challenges such as multi-sample rates and dynamics. In this paper, we propose a uniformly spaced double-latent variable probabilistic (USDLVP) model that can obtain the measurement correlations within diverse sampling rates (SR). The model utilizes the greatest common divisors of the SR to construct a latent variable structure, effectively addressing the challenges encountered by conventional methods in handling practical multi-sampling rate data. Moreover, to gain a comprehensive understanding of the dynamics in multi-sampling rate processes, a Markov-enhanced double latent variable structure is presented to extract data autocorrelation features from both quality-correlated and uncorrelated perspectives. The expectation maximization (EM) algorithm is employed for model training. Finally, the model is adopted to develop a fault detection method, which is subsequently applied in two industrial plants. The experimental results demonstrate the superiority of the proposed model in handling multi-sampling rate issues. © 2024, The Authors. All rights reserved.

关键词： Process monitoring

来源：评论

学校读者我要写书评

暂无评论

BMDP:Blockchain-Based Multi-Cloud Storage data Provenance

BMDP:Blockchain-Based Multi-Cloud Storage Data Provenance

引用

International Conference on Computer Supported Cooperative Work in Design

作者： Feiyu Wang Jian-Tao Zhou Xu Guo College of Computer Science Inner Mongolia University Hohhot Inner Mongolia China Inner Mongolia Engineering Laboratory for Cloud Computing and Service Software Engineering Research Center of Ecological Big Data Ministry of Education National & Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian Inner Mongolia Key Laboratory of Social Computing and Data Processing Inner Mongolia Engineering Laboratory for Big Data Analysis Technology China

In a multi-cloud storage system, provenance data records all operations and ownership during its lifecycle, which is critical for data security and audibility. However, recording provenance data also poses some challenging security and storage issues. In this paper, we present a secure and efficient multi-cloud storage data source scheme, BMDP. We use blockchain technology to ensure the secure storage of provenance data and design a smart contract to utilize the provenance data to ensure the proper operation of the multi-cloud storage system. Finally, we analyze the scheme’s safety and do simulation experiments to show that the scheme has practicality.

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：