检索结果-内蒙古大学图书馆

A pretrained transformer model for decoding individual glucose dynamics from continuous glucose monitoring data

National Science Review 2025年第5期12卷 362-381页

作者： Yurun Lu Dan Liu Zhongming Liang Rui Liu Pei Chen Yitong Liu Jiachen Li Zhanying Feng Lei M.Li Bin Sheng Weiping Jia Luonan Chen Huating Li Yong Wang Center for Excellence in Mathematical Sciences National Center for Mathematics and Interdisciplinary Sciences Hua Loo-Keng Center for Mathematical Sciences Key Laboratory of Management Decision and Information System Academy of Mathematics and Systems ScienceChinese Academy of Sciences School of Mathematics University of Chinese Academy of SciencesChinese Academy of Sciences Department of Endocrinology and Metabolism Shanghai Sixth People's Hospital Affiliated to Shanghai Jiao Tong University School of MedicineShanghai Diabetes InstituteShanghai Clinical Center for Diabetes Shanghai Key Laboratory of Diabetes Mellitus Key Laboratory of Systems Health Science of Zhejiang Province School of Life ScienceHangzhou Institute for Advanced StudyUniversity of Chinese Academy of Sciences BGI-Research School of Mathematics South China University of Technology Department of Statistics Department of Biomedical Data Science Bio-X ProgramStanford University Department of Computer Science and Engineering Shanghai Jiao Tong University State Key Laboratory of Cell Biology Center for Excellence in Molecular Cell Science Shanghai Institute of Biochemistry and Cell Biology Chinese Academy of Sciences Guangdong Institute of Intelligence Science and Technology Pazhou Laboratory (Huangpu)

Continuous glucose monitoring(CGM) technology has grown rapidly to track real-time blood glucose levels and trends with improved sensor accuracy. The ease of use and wide availability of CGM will facilitate safe and effective decision making for diabetes management. Here, we developed an attention-based deep learning model, CGMformer, pretrained on a well-controlled and diverse corpus of CGM data to represent individual's intrinsic metabolic state and enable clinical applications. During pretraining, CGMformer encodes glucose dynamics including glucose level, fluctuation, hyperglycemia, and hypoglycemia into latent space with self-supervised learning. It shows generalizability in imputing glucose value across five external datasets with different populations and metabolic states(MAE = 3.7 mg/d L). We then fine-tuned CGMformer towards a diverse panel of downstream tasks in the screening of diabetes and its complications using task-specific data, which demonstrated a consistently boosted predictive accuracy over direct fine-tuning on a single task(AUROC = 0.914 for type 2 diabetes(T2D) screening and 0.741 for complication screening). By learning an intrinsic representation of an individual's glucose dynamics,CGMformer classifies non-diabetic individuals into six clusters with elevated T2D risks, and identifies a specific cluster with lean body-shape but high risk of glucose metabolism disorders, which is overlooked by traditional glucose measurements. Furthermore, CGMformer achieves high accuracy in predicting an individual's postprandial glucose response with dietary modelling(Pearson correlation coefficient = 0.763)and helps personalized dietary recommendations. Overall, CGMformer pretrains a transformer neural network architecture to learn an intrinsic representation by borrowing information from a large amount of daily glucose profiles, and demonstrates predictive capabilities fine-tuned towards a broad range of downstream applications, holding promise for the ear

关键词： pretrained model diabetes continuous glucose monitoring glucose dynamics

来源：评论

学校读者我要写书评

暂无评论

A Review on IoT Botnet 2021

A Review on IoT Botnet

引用

2nd International Conference on computing and Data Science, CONF-CDS 2021

作者： Zhao, Hao Shu, Hui Xing, Ying State Key Laboratory of Mathematical Engineering and Advanced Computing Zhengzhou China Software College Zhongyuan University of Technology Zhengzhou China

ISBN: (纸本)9781450389570

The rapid development of the Internet of Things (IoT) also generates security threats that cannot be ignored. This paper lists the development history of botnets, introduces representative IoT botnets, and reveals their new characteristics. The botnet mechanism and characteristics of IoT botnets are analyzed in depth from three aspects: composition structure, life cycle, and attack behavior, and are compared with traditional botnets. Networks for comparison. The analysis discusses the details of IoT botnet technologies such as scanning discovery, covert communication and survival residency. Summarizes the research status of IoT botnet detection technologies and gives future directions. Finally, the importance of preventing IoT botnets and solving IoT security problems is discussed. © 2021 ACM.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Optimal Tracking Performance of Networked Control Systems Under DoS and Its Applications

Optimal Tracking Performance of Networked Control Systems Un...

引用

2024 China Automation Congress, CAC 2024

作者： Ren, Xinyu Li, Bo Zhao, Feng Chen, Xiangyong Zhang, Xianhe Jiang, Xiaowei School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation of Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan China School of Finance Anhui University of Finance and Economics Bengbu China Key Laboratory of Complex systems and Intelligent Computing in Universities of Shandong Linyi University Linyi China School of Automation and Electrical Engineering Key Laboratory of Complex systems and Intelligent Computing in Universities of Shandong Linyi University Linyi China School of Electrical Engineering and Automation Hubei Normal University Huangshi China

ISBN: (纸本)9798350368604

This paper investigates the optimal tracking performance (OTP) of multiple-input multiple-output (MIMO) discrete networked control systems (NCSs) under the influence of Denial of Service (DoS) attack, channel noise, and bandwidth constraints. The channel noise is assumed to be additive Gaussian white noise (AWGN). Due to the randomness of DoS attack, a Bernoulli distribution is used for DoS modeling. Utilizing frequency domain analysis methods, coprime factorization, all-pass decomposition, and Youla parameterization, an explicit expression for the optimal tracking performance (OTP) of the system under the two-degree-of-freedom (TDOF) controller is derived. The analysis indicates that non-minimum phase (NMP) zeros, unstable poles (UPs), DoS attack, and network constraints affect the OTP of NCSs. Finally, the theoretical results are validated through simulations of MIMO NCS and vehicle control system. © 2024 IEEE.

关键词： White noise

来源：评论

学校读者我要写书评

暂无评论

Immune Defense: A Novel Adversarial Defense Mechanism for Preventing the Generation of Adversarial Examples

arXiv

引用

arXiv 2023年

作者： Wang, Jinwei Wu, Hao Wang, Haihua Zhang, Jiawei Luo, Xiangyang Ma, Bin Nanjing University of Information Science and Technology China State Key Laboratory of Mathematical Engineering and Advanced Computing China Qilu University of Technology China

The vulnerability of Deep Neural Networks (DNNs) to adversarial examples has been confirmed. Existing adversarial defenses primarily aim at preventing adversarial examples from attacking DNNs successfully, rather than preventing their generation. If the generation of adversarial examples is unregulated, images within reach are no longer secure and pose a threat to non-robust DNNs. Although gradient obfuscation attempts to address this issue, it has been shown to be circumventable. Therefore, we propose a novel adversarial defense mechanism, which is referred to as immune defense and is the example-based pre-defense. This mechanism applies carefully designed quasi-imperceptible perturbations to the raw images to prevent the generation of adversarial examples for the raw images, and thereby protecting both images and DNNs. These perturbed images are referred to as Immune Examples (IEs). In the white-box immune defense, we provide a gradient-based and an optimization-based approach, respectively. Additionally, the more complex black-box immune defense is taken into consideration. We propose Masked Gradient Sign Descent (MGSD) to reduce approximation error and stabilize the update to improve the transferability of IEs and thereby ensure their effectiveness against black-box adversarial attacks. The experimental results demonstrate that the optimization-based approach has superior performance and better visual quality in white-box immune defense. In contrast, the gradient-based approach has stronger transferability and the proposed MGSD significantly improve the transferability of baselines. Copyright © 2023, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

On tuning of ADRC with competing design indices:a quantitative study

引用

Control Theory and Technology 2023年第1期21卷 16-33页

作者： Yutao Zhao Yi Huang Zhiqiang Gao Key Laboratory of Systems and Control Academy of Mathematics and Systems ScienceChinese Academy of SciencesBeijing 100190China School of Mathematical Sciences University of Chinese Academy of SciencesBeijing 100049China Department of Electrical Engineering and Computer Science Center for Advanced Control TechnologiesCleveland State UniversityClevelandOH 44115USA

Controller optimization has mostly been done by minimizing a certain single cost *** practice,however,engineers must contend with multiple and conflicting considerations,denoted as design indices(DIs)in this *** to account for such complexity and nuances is detrimental to the applications of any advanced control *** paper addresses this challenge heads on,in the context of active disturbance rejection controller(ADRC)and with four competing DIs:stability margins,tracking,disturbance rejection,and noise *** this end,the lower bound for the bandwidth of the extended state observer is first established for guaranteed closed-loop ***,one by one,the mathematical formula is meticulously derived,connecting each DI to the set of controller *** our best knowledge,this has not been done in the context of *** formulas allow engineers to see quantitatively how the change of each tuning parameter would impact all of the DIs,thus making the guesswork *** example is given to show how such analytical methods can help engineers quickly determine controller parameters in a practical scenario.

关键词： Uncertain systems Active disturbance rejection control(ADRC) Design indices(DIs) Extended state observer(ESO)

来源：评论

学校读者我要写书评

暂无评论

Rotation Transformation: A Method to Improve the Transferability of Adversarial Examples

Rotation Transformation: A Method to Improve the Transferabi...

引用

2021 International Conference on Digital Society and Intelligent Systems, DSInS 2021

作者： Li, Zheming Zhang, Hengwei Ma, Junqiang Yang, Bo Li, Chenwei Li, Jingwen Key Laboratory of Information Security of Henan Provincial State Key Laboratory of Mathematical Engineering and Advanced Computing Zhengzhou China PLA Army Staff Department Beijing China

ISBN: (纸本)9781665406307

Convolutional neural network models are fragile to adversarial examples. Adding disturbances that humans cannot observe in clean images can make the model classification error. Among the adversarial attack methods, white-box attacks have achieved a high attack success rate, but the "overfitting"between the adversarial examples and the model has led to a low success rate of black-box attacks. To this end, this paper introduces the data augmentation method into the adversarial examples generation process, establishes a probability model to perform random rotation transformation on clean images, improves the mobility of adversarial examples, and improves the success rate of adversarial examples under black-box setting. The experimental results on ImageNet show that the RO-MI-FGSM method we proposed has a stronger attack effect, achieving a black-box attack success rate up to 80.3%. © 2021 IEEE.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

Publicly Verifiable Private Set Intersection from Homomorphic Encryption 8th

Publicly Verifiable Private Set Intersection from Homomorph...

引用

8th International Symposium on Security and Privacy in Social Networks and Big Data, SocialSec 2022

作者： Jiang, Yuting Wei, Jianghong Pan, Jing Xidian University Xi’an710071 China State Key Laboratory of Mathematical Engineering and Advanced Computing PLA Strategic Support Force Information Engineering University Zhengzhou450001 China Guangzhou Institute of Technology Xidian University Guanzhou510555 China

ISBN: (纸本)9789811972416

Private Set Intersection (PSI) enables two mistrusting parties to securely evaluate the intersection of their private inputs, without revealing any additional information. With its wide application in privacy protection, it is required to ensure the correctness of the evaluation, especially in conventional client-server setting (also known as unbalanced PSI). Unfortunately, most existing work cannot verify the integrity of the data and the correctness of the evaluation. In this paper, we propose a new publicly verifiable private set intersection protocol in the malicious setting, based on oblivious pseudo-random function (OPRF), fully homomorphic encryption (FHE), and verifiable computation (VC). The key tool to obtain our new protocol is a new publicly verifiable inner product computation on encrypted data. The protocol supports public verification for computation correctness and integrity under preserving privacy with less round number (only requiring 2 rounds), allows batching technique under Residue Number System (RNS). That is used for enhancing the FHE. Also, we implement our protocol, and the result is close to the most effective unbalanced PSI. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Numbering systems

来源：评论

学校读者我要写书评

暂无评论

A Formal Verification Method for Security Protocol Implementations Based on Model Learning and Tamarin 6

A Formal Verification Method for Security Protocol Implement...

引用

2021 6th International Symposium on Advances in Electrical, Electronics and Computer engineering, ISAEECE 2021

作者： Zhang, Xieli Zhu, Yuefei Gu, Chunxiang Miao, Xuyang State Key Laboratory of Mathematical Engineering and Advanced Computing Zhengzhou Henan450001 China Henan Key Laboratory of Network Cryptography Technology Zhengzhou Henan450002 China

The verification of security protocol implementations is notoriously difficult and important. In this paper, combining with the model learning using Tamarin, a formal verification tool of protocol specification, a formal verification method for security protocol implementations is proposed. We extract state machine information from protocol implementations by model learning, and determine suspicious paths in the finite-state machines by cross-validation between different implementations of the same protocol;and then verify whether the suspicious paths violate the security properties of the protocol using Tamarin. It can be used to detect logical errors in protocol implementations and avoid relying on expert experience to make compliance rules from protocol documents when using model checking tools. The effectiveness of this method is demonstrated by the vulnerability detection of the typical ChangeCipherSpec in the TLS protocol implementation. The method proposed can help developers to develop more robust implementations of security protocols. © Published under licence by IOP Publishing Ltd.

关键词： Formal verification

来源：评论

学校读者我要写书评

暂无评论

Versatility of π-d Conjugated Coordination Nickel Metal-Organic Frameworks as Electrode Materials of Metal-Ion Batteries

引用

Energy Material Advances 2024年第1期5卷 120-132页

作者： Zaohong Zhang Kaihui Xu Jing Yang Zhuoyu Ji Yunchen Ge Zhicong Shi Yongwei Zhang Kai Zhang Chuan Wu Jia Hong Pan State Key Laboratory of Featured Metal Materials and Life-Cycle Safety for Composite Structures School of ResourcesEnvironments and MaterialsGuangxi UniversityNanning 530004China Low Carbon Energy Process Intensification Research Institute and MOE Key Laboratory of Resources and Environmental Systems Optimization North China Electric Power UniversityBeijing 102206China Institute of High Performance Computing Agency for ScienceTechnology and Research(A*STAR)Singapore 138632Singapore Guangxi Key Laboratory of Manufacturing Systems and Advanced Manufacturing Technology Guilin University of Electronic TechnologyGuilin 541004China School of Materials Science and Engineering Beijing Institute of TechnologyBeijing 100081China Beijing Key Laboratory of Environmental Science and Engineering School of Materials Science and EngineeringBeijing Institute of TechnologyBeijing 100081China Yangtze Delta Region Academy of Beijing Institute of Technology Jiaxing 314019China

Metal-organic frameworks have emerged as promising electrode materials for metal-ion batteries due to their superior structural ***,they face challenges such as poor reversibility and easy degradation during electrochemical redox ***,we report the synthesis ofπ-d conjugated coordination polymers through NH_(3)-vapor-assisted self-polymerization of NiCl_(2)·6H_(2)O with 1,2,4,5-benzenetetramine tetrahydrochloride(namely,Ni-BTA).The synthesized Ni-BTA exhibits an open lattice structure that enhances the capacity for metal-ion diffusion,ensuring prolonged electrochemical cycling ***,electrochemical characterizations reveal that Ni-BTA functions as a bifunctional material,serving as both cathode and anode materials for lithium-ion batteries(LIBs).After 1,000 cycles at 1.0 A g^(−1),the cathode and anode show high discharge capacities of 199.7 and 338.4 mAh g^(−1),***,symmetrical all-organic batteries constructed with Ni-BTA exhibit a high specific capacity of 30.6 mAh g-1 and an ultrastable coulombic efficiency of approximately≈100%after 6,000 cycles at 1.0 A g^(−1).Furthermore,Ni-BTA exhibits versatility as a robust cathode for aluminum ion batteries(AIBs),delivering a discharge capacity of 18.7 mAh g^(−1) after 10,000 cycles at 1.0 A g^(−1).These findings highlight the potential of Ni-BTA as a versatile and durable electrode materials for both LIBs and AIBs.

关键词： d conjugation electrochemical stability open lattice stru metal ion batteries electrochemical redox processesherewe lithium ion batteries coordination polymers electrode materials

来源：评论

学校读者我要写书评

暂无评论

Medical image registration and its application in retinal images:a review

引用

Visual computing for Industry,Biomedicine,and Art 2024年第1期7卷 142-164页

作者： Qiushi Nie Xiaoqing Zhang Yan Hu Mingdao Gong Jiang Liu Research Institute of Trustworthy Autonomous Systems and Department of Computer Science and Engineering Southern University of Science and TechnologyShenzhen 518055China Center for High Performance Computing and Shenzhen Key Laboratory of Intelligent Bioinformatics Shenzhen Institute of Advanced TechnologyChinese Academy of SciencesShenzhen 518055China Singapore Eye Research Institute Singapore 169856Singapore State Key Laboratory of Ophthalmology Optometry and Visual ScienceEye HospitalWenzhou Medical UniversityWenzhou 325027China

Medical image registration is vital for disease diagnosis and treatment with its ability to merge diverse informa-tion of images,which may be captured under different times,angles,or *** several surveys have reviewed the development of medical image registration,they have not systematically summarized the existing med-ical image registration *** this end,a comprehensive review of these methods is provided from traditional and deep-learning-based perspectives,aiming to help audiences quickly understand the development of medical image *** particular,we review recent advances in retinal image registration,which has not attracted much *** addition,current challenges in retinal image registration are discussed and insights and prospects for future research provided.

关键词： Computer-aided diagnosis Medical image registration Deep learning Generative model Transformer Retina

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：