检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Ding, Youlong Wu, Xueyang Meng, Yining Luo, Yonggang Wang, Hao Pan, Weike College of Computer Science and Software Engineering Shenzhen University Shenzhen China The Hebrew University of Jerusalem Jerusalem Israel Hong Kong University of Science and Technology Hong Kong Changan Automobile Changan Technology Co. Ltd Chongqing China Rutgers University New Jersey United States

Deep learning with differential privacy (DP) has garnered significant attention over the past years, leading to the development of numerous methods aimed at enhancing model accuracy and training efficiency. This paper delves into the problem of training Transformer models with differential privacy. Our treatment is modular: the logic is to ‘reduce’ the problem of training DP Transformer to the more basic problem of training DP vanilla neural nets. The latter is better understood and amenable to many model-agnostic methods. Such ‘reduction’ is done by first identifying the hardness unique to DP Transformer training: the attention distraction phenomenon and a lack of compatibility with existing techniques for efficient gradient clipping. To deal with these two issues, we propose the Re-Attention Mechanism and Phantom Clipping, respectively. We believe that our work not only casts new light on training DP Transformers but also promotes a modular treatment to advance research in the field of differentially private deep learning. Copyright © 2024, The Authors. All rights reserved.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Optimizing machine learning algorithms to enhance blood donation for liver patients: a case study

Optimizing machine learning algorithms to enhance blood dona...

引用

7th IET Smart Cities Symposium (SCS 2023)

作者： Maad M. Mijwil El-Sayed M. El-kenawy Indu Bala Mohammad Aljanabi Mostafa Abotaleb Abdelhameed Ibrahim Computer Techniques Engineering Department Baghdad College of Economic Sciences University Baghdad Iraq Department of Communications and Electronics Delta Higher Institute of Engineering and Technology Egypt School of Electrical and Electronics Engineering Lovely Professional University Punjab India Department of Computer Aliraqia University Baghdad Iraq Department of System Programming South Ural State University Chelyabinsk Russia Computer Engineering and Control Systems Department Faculty of Engineering Mansoura University Mansoura Egypt

Blood is vital for transporting oxygen, nutrients, and hormones to all body parts as it circulates through arteries and veins. It removes carbon dioxide, regulates body temperature, and maintains the body's immune system. Individuals constantly need blood and its derivatives to save their lives and improve their health through medical treatments and surgical operations. Liver diseases are one of the diseases that affects the health of individuals and requires blood to continue living. These diseases cause significant damage to people's health, and early diagnosis plays a crucial role in saving lives. In this paper, machine learning algorithms (support vector machine and random forest) are involved in detecting liver diseases and determining whether donors are suitable to donate blood from blood values. This paper is applied research that found that the performance measures of the random forest algorithm achieved excellent performance in identifying suitable people to donate blood.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Simple Dashboard for OpenStack Horizon 4

A Simple Dashboard for OpenStack Horizon

引用

4th International Conference on Computing and Big Data, ICCBD 2021

作者： Wang, Hongbin Li, Shaoxu Deng, Dan Li, Leixiao Gao, Jing Li, Jie College of Data Science and Application Inner Mongolia University of Technology Hohhot China Inner Mongolia Autonomous Reg. Software Serv. Eng. Technology Research Center Based on Big Data Hohhot China College of Computer and Information Engineering Inner Mongolia Agricultural University Hohhot China

ISBN: (纸本)9781450387194

OpenStack is an open source cloud computing management project, which allows flexible resources applying. The traditional OpenStack dashboard is inflexible, thus a simple dashboard is designed. The simple dashboard integrates keystone, horizon, grace, nova, neutron, swift and other components, communicates with the traditional OpenStack dashboard and runs in the form of docker container. We implemented simple dashboard on a small cloud platform. Compared with the traditional dashboard, the interface of simple dashboard is simpler, more flexible and easy to use. © 2021 ACM.

关键词： Platform as a Service (PaaS)

来源：评论

学校读者我要写书评

暂无评论

A Gait Recognition Method Based on the Combination of Human Body Posture and Human Body Contour 2

A Gait Recognition Method Based on the Combination of Human ...

引用

2nd International Conference on Artificial Intelligence and computer Science, AICS 2020

作者： Ma, Yue Wei, Chenghao Long, Hao Ministry of Public Security China Big Data Institute College of Computer Science and Software Engineering Shenzhen University China

Aiming at the issues that affect the gait recognition, such as outfit changes and carry-on-objects during gait recognition, this paper proposes a gait recognition method based on the improved GaitSet network, which relies on the fusion of human posture and human contour. This method introduces key points of human posture, and improves the precision of human contour extraction by introducing the key points of human posture. At the same time, the human posture map composed of the key points of human posture is used as the synchronous attribute of the contour map to extract gait features. Because key points focus on the inherent walking characteristics of human body, they are not affected by the external information such as clothing and carrying objects. Combined with the rich gait change attributes of human contour, it can effectively improve the accuracy and robustness of the gait recognition model. In scenes of human body wearing coats, our experimental results show that the accuracy of the proposed method in CASIA-B gait data set and self-built database can reach over 73.5% accuracy. © Published under licence by IOP Publishing Ltd.

关键词： Gait analysis

来源：评论

学校读者我要写书评

暂无评论

Symmetrical Supervision with Transformer for Few-shot Medical Image Segmentation

Symmetrical Supervision with Transformer for Few-shot Medica...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Yao Niu Zhiming Luo Sheng Lian Lei Li Shaozi Li Haixin Song Department of Artificial Intelligence Xiamen University Fujian China College of Computer and Data Science Fuzhou University Fujian China Department of Software Engineering Xiamen University Fujian China

ISBN: (数字)9781665468190

ISBN: (纸本)9781665468206

Few-shot learning can potentially learn the target knowledge in extremely few data regimes. Existing few-shot medical image segmentation methods fail to consider the global anatomy correlation between the support and query sets. They generally adopt a weak one-way information transmission that can not fully explore the knowledge to segment query data. To address this problem, we propose a novel Symmetrical Supervision network based on traditional two-branch methods. We raise two main contributions: (1) The Symmetrical Supervision Mechanism is leveraged to strengthen the supervision of network training; (2) A transformer-based Global Feature Alignment module is introduced to increase the global consistency between the two branches. Experimental results on two challenging datasets (abdominal segmentation dataset CHAOS and cardiac segmentation dataset MS-CMRSeg) show a remarkable performance compared to other comparing methods.

关键词： Training Chaos Image segmentation Correlation Biological system modeling Information processing Transformers

来源：评论

学校读者我要写书评

暂无评论

FCloudless: A Performance-Aware Collaborative Mechanism for JointCloud Serverless

FCloudless: A Performance-Aware Collaborative Mechanism for ...

引用

IEEE International Conference on Joint Cloud Computing (JCC)

作者： Jianfei Liu Huaimin Wang Peichang Shi Yaojie Li Penghui Ma Guodong Yi National Key Laboratory of Parallel and Distributed Computing College of Computer Science National University of Defense Technology Changsha 410073 China Key Laboratory of Software Engineering for Complex Systems College of Computer Science National University of Defense Technology Changsha 410073 China Xiangjiang Lab Changsha 410073 China School of Advanced Interdisciplinary Studies Hunan University Of Technology and Business Changsha 410073 China

As a new stage in the development of the cloud computing paradigm, serverless computing has the high-level abstraction characteristic of shielding underlying details. This makes it extremely challenging for users to choose a suitable serverless platform. To address this, targeting the jointcloud computing scenario of heterogeneous serverless platforms across multiple clouds, this paper presents a jointcloud collaborative mechanism called FCloudless with cross-cloud detection of the full lifecycle performance of serverless platforms. Based on the benchmark metrics set that probe performance critical stages of the full lifecycle, this paper proposes a performance optimization algorithm based on detected performance data that takes into account all key stages that affect the performance during the lifecycle of a function and predicts the overall performance by combining the scores of local stages and dynamic weights. We evaluate FCloudless on AWS, AliYun, and Azure. The experimental results show that FCloudless can detect the underlying performance of serverless platforms hidden in the black box and its optimization algorithm can select the optimal scheduling strategy for various applications in a jointcloud environment. FCloudless reduces the runtime by 23.3% and 24.7% for cold and warm invocations respectively under cost constraints.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Graph-Augmented Contrastive Clustering for Time Series

SSRN

引用

SSRN 2023年

作者： Zhang, Qin Liang, Zhuoluo Ngueilbaye, Alladoumbaye Zhang, Peng Chen, Junyang Chen, Xiaojun Huang, Joshua Zhexue Big Data Institute College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China Cyberspace Institute of Advanced Technology Guangzhou University Guangzhou510006 China

The recent emergence of time series contrastive clustering methods can be broadly categorized into two classes. The first class uses contrastive learning to learn universal representations for time series. Though they perform well in various downstream tasks, such methods disregard the important categorical information and clustering objective, leading to unsuitable representations of clustering tasks. The second class incorporates contrastive learning into the clustering objective. The potential connections and structures between the time series data are not fully explored during contrastive learning. To this end, we propose a graph-augmented contrastive learning framework called the "Time Series Graph-augmented Contrastive Clustering (TSGCC) method." We observed that the original samples should be similar to their augmentations and other samples in the same cluster. Hence, we used a weighted $KNN$ graph to build positive and negative sample pairs for contrastive learning. Subsequently, we projected the instance samples into a feature space with the dimensionality number of clusters and learned cluster-friendly features and cluster assignments by iteratively optimizing the contrastive loss. Experimental results demonstrate that TSGCC outperforms 16 advanced time-series clustering methods on 36 challenging UCR benchmarks, achieving the best clustering results on 12 datasets and the highest average rank (2.83) of RI overall methods. © 2023, The Authors. All rights reserved.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

Channel Cycle Time: A New Measure of Short-Term Fairness

Channel Cycle Time: A New Measure of Short-Term Fairness

引用

IEEE Conference on Wireless Communications and Networking

作者： Pengfei Shen Yulin Shao Haoyuan Pan Lu Lu Yonina C. Eldar Key Laboratory of Space Utilization Technology and Engineering Center for Space Utilization CAS Beijing China University of Chinese Academy of Sciences Beijing China State Key Laboratory of Internet of Things for Smart City University of Macau Macau S.A.R Department of Electrical and Computer Engineering University of Macau Macau S.A.R. College of Computer Science and Software Engineering Shenzhen University China Weizmann Institute of Science Rehovot Israel

ISBN: (数字)9798350303582

ISBN: (纸本)9798350303599

This paper puts forth a new metric, dubbed channel cycle time (CCT), to measure the short-term fairness of Communication networks. CCT characterizes the average duration between two consecutive successful transmissions of a user, during which all other users successfully accessed the channel at least once. In contrast to existing short-term fairness measures, CCT provides more comprehensive insight into the transient dynamics of communication networks, with a particular focus on users' delays and jitter. To validate the efficacy of our approach, we analytically characterize the CCTs for two classical commu-nication protocols: slotted Aloha and CSMA/CA. The analysis demonstrates that CSMA/CA exhibits superior short-term fairness over slotted Aloha. Beyond its role as a measurement metric, CCT has broader implications as a guiding principle for the design of future communication networks by emphasizing factors like fairness, delay, and jitter in short-term behaviors.

关键词： Jitter Media Access Protocol Time measurement Real-time systems Heterogeneous networks Delays Communication networks

来源：评论

学校读者我要写书评

暂无评论

DVS-RG: Differential Variable Speed Limits control using Deep Reinforcement Learning with Graph State Representation

arXiv

引用

arXiv 2024年

作者： Yang, Jingwen Wang, Ping Golpayegani, Fatemeh Wang, Shen School of Electronic and Control Engineering Chang'an University Shaanxi Xi’an710054 China School of Intelligent Systems Engineering Sun Yat-sen University Guangdong Shenzhen510006 China School of Computer Science University College Dublin Dublin4 D04 V1W8 Ireland

Variable speed limit (VSL) control is an established yet challenging problem to improve freeway traffic mobility and alleviate bottlenecks by customizing speed limits at proper locations based on traffic conditions. Recent advances in deep reinforcement learning (DRL) have shown promising results in solving VSL control problems by interacting with sophisticated environments. However, the modeling of these methods ignores the inherent graph structure of the traffic state which can be a key factor for more efficient VSL control. Graph structure can not only capture the static spatial feature but also the dynamic temporal features of traffic. Therefore, we propose the DVS-RG: DRLbased differential variable speed limit controller with graph state representation. DVS-RG provides distinct speed limits per lane in different locations dynamically. The road network topology and traffic information(e.g., occupancy, speed) are integrated as the state space of DVS-RG so that the spatial features can be learned. The normalization reward which combines efficiency and safety is used to train the VSL controller to avoid excessive inefficiencies or low safety. The results obtained from the simulation study on SUMO show that DRL-RG achieves higher traffic efficiency (the average waiting time reduced to 68.44%) and improves the safety measures (the number of potential collision reduced by 15.93% ) compared to state-of-the-art DRL methods. Copyright © 2024, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

TCSloT: Text Guided 3D Context and Slope Aware Triple Network for Dental Implant Position Prediction

TCSloT: Text Guided 3D Context and Slope Aware Triple Networ...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Xinquan Yang Jinheng Xie Xuechen Li Xuguang Li Linlin Shen Yongqiang Deng College of Computer Science and Software Engineering Shenzhen University Shenzhen China Show Lab National University of Singapore Singapore National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China Department of Stomatology Shenzhen University General Hospital Shenzhen China

In implant prosthesis treatment, the surgical guide of implant is used to ensure accurate implantation. However, such design heavily relies on the manual location of the implant position. When deep neural network has been proposed to assist the dentist in locating the implant position, most of them take a single slice as input, which do not fully explore 3D contextual information and ignores the influence of implant slope. In this paper, we design a Text Guided 3D Context and Slope Aware Triple Network (TCSloT) to integrate the perception of contextual information from multiple adjacent slices and awareness of variation of implant slopes. A Texture Variation Perception (TVP) module is correspondingly design to process the multiple slices and capture the texture variation among slices and a Slope-Aware Loss (SAL) is proposed to dynamically assign adaptive weights for the regression head. Additionally, we design a conditional text guidance (CTG) module to integrate the text condition (i.e., left, middle and right) from the CLIP to assist the implant position prediction. Extensive experiments on a dental implant dataset through five-fold cross-validation, demonstrated that the proposed TCSloT achieves superior performance than existing methods.

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：