检索结果-内蒙古大学图书馆

MtCLSS: Multi-Task Contrastive Learning for Semi-Supervised Pediatric Sleep Staging

IEEE JOURNAL OF BIOMEDICAL AND HEALTH informatICS 2023年第6期27卷 2647-2655页

作者： Li, Yamei Luo, Shengqiong Zhang, Haibo Zhang, Yinkai Zhang, Yuan Lo, Benny Southwest Univ Coll Elect & Informat Engn Chongqing Key Lab Nonlinear Circuits & Intelligent Chongqing 400715 Peoples R China Ninth Peoples Hosp Chongqing Pediat Respirol Dept Chongqing 400700 Peoples R China Univ Otago Dept Comp Sci Dunedin 9016 New Zealand Shandong Univ Tradit Chinese Med Coll Intelligence & Informat Engn Jinan 16369 Peoples R China Imperial Coll London Hamlyn Ctr London SW7 2AZ England

The continuing increase in the incidence and recognition of children's sleep disorders has heightened the demand for automatic pediatric sleep staging. Supervised sleep stage recognition algorithms, however, are often faced with challenges such as limited availability of pediatric sleep physicians and data heterogeneity. Drawing upon two quickly advancing fields, i.e., semi-supervised learning and self-supervised contrastive learning, we propose a multi-task contrastive learning strategy for semi-supervised pediatric sleep stage recognition, abbreviated as MtCLSS. Specifically, signal-adapted transformations are applied to electroencephalogram (EEG) recordings of the full night polysomnogram, which facilitates the network to improve its representation ability through identifying the transformations. We also introduce an extension of contrastive loss function, thus adapting contrastive learning to the semi-supervised setting. In this way, the proposed framework learns not only task-specific features from a small amount of supervised data, but also extracts general features from signal transformations, improving the model robustness. MtCLSS is evaluated on a real-world pediatric sleep dataset with promising performance (0.80 accuracy, 0.78 F1-score and 0.74 kappa). We also examine its generality on a well-known public dataset. The experimental results demonstrate the effectiveness of the MtCLSS framework for EEG based automatic pediatric sleep staging in very limited labeled data scenarios.

关键词： Sleep staging pediatric semi-supervised contrastive learning

来源：评论

学校读者我要写书评

暂无评论

A Primal-Dual Forward-Backward Splitting Algorithm for Distributed Convex Optimization

引用

IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE 2023年第1期7卷 278-284页

作者： Li, Huaqing Su, Enbing Wang, Chengbo Liu, Jiawei Zheng, Zuqing Wang, Zheng Xia, Dawen Southwest Univ Chongqing Key Lab Nonlinear Circuits & Intelligen Coll Elect & Informat Engn Chongqing 400715 Peoples R China Southwest Univ Westa Coll Chongqing 400715 Peoples R China Univ New South Wales Sch Elect Engn & Telecommun Sydney NSW 2052 Australia Guizhou Minzu Univ Coll Data Sci & Informat Engn Guiyang 550025 Peoples R China

Motivated by modern large-scale information processing problems in engineering, this paper concentrates on studying distributed constrained convex optimization problems over a connected undirected network. The problem involves a sum of a differentiable convex function with Lipschitz continuous gradient and two non-smooth convex functions with a linear operator. To solve such a problem, we propose a novel distributed primal-dual forward-backward splitting algorithm, called D-PDFBS. Each agent locally computes the Lipschitz continuous gradient and two proximal operators, and exchanges information with its neighbors. D-PDFBS adopts non-identical stepsizes, and we reveal the relationship between selection of stepsizes and parameters of objective functions. The simulation results verify the feasibility of D-PDFBS and the correctness of theoretical findings.

关键词： Optimization Convex functions Convergence Wireless sensor networks Wireless communication Symmetric matrices Smart grids Forward-backward splitting method distributed optimization primal-dual algorithm non-smooth function

来源：评论

学校读者我要写书评

暂无评论

Action-dependent heuristic dynamic programming for hybrid-order systems based on dynamic event-triggered mechanism

引用

NEUROCOMPUTING 2024年 600卷

作者： Li, Jun Li, Huaqing Zheng, Lifeng Ran, Liang Ji, Lianghao Southwest Univ Chongqing Key Lab Nonlinear Circuits & Intelligent Tiansheng St Chongqing 400715 Peoples R China Chongqing Univ Posts & Telecommun Chongqing Key Lab Image Cognit Chongwen Rd Chongqing 400065 Peoples R China

We investigate the distributed optimal consensus control problem based on action-dependent heuristic dynamic programming (ADHDP). In order to strike a stable balance between the learning cost of reinforcement learning and the resource utilization efficiency of the hybrid-order multi-agent systems (MASs), we propose an improved dynamic event-triggered ADHDP (dET-ADHDP) method. This approach can non-periodically explore the control policy distribution using the online action-dependent actor-critic (ADAC) learning framework. Meanwhile, it can dynamically adjust the trigger lower bound by exploiting the designed trigger threshold function, and adaptively decide the signal trigger moment during the ADAC learning process. In addition, we demonstrate the boundedness of the ADAC network weights and show that under the designed dynamic event-triggering rules, the MASs can asymptotically achieve optimal tracking control without Zeno phenomenon. Finally, compared with the traditional static counterparts, simulation experiments demonstrate that the proposed dynamic eventtriggered ADAC (dET-ADAC) algorithm has more efficient resource utilization while maintaining satisfactory learning performance.

关键词： Adaptive dynamic programming Optimal consensus control Dynamic event-triggered mechanism Heterogeneous multi-agent systems

来源：评论

学校读者我要写书评

暂无评论

Toward 3-D AAV-Ground BS CoMP-NOMA Transmission: Optimal Resource Allocation and Trajectory Design

引用

IEEE INTERNET OF THINGS JOURNAL 2025年第8期12卷 9671-9686页

作者： Zeng, Haiyong Zhang, Rui Zhu, Xu Wei, Zhongxiang Jiang, Yufei Sun, Sumei Zheng, Fu-Chun Cao, Bin Guangxi Normal Univ Sch Elect & Informat Engn Sch Integrated Circuits Guangxi Key Lab Brain Inspired Comp & Intelligent Guilin 541001 Peoples R China Guangxi Normal Univ Educ Dept Guangxi Zhuang Autonomous Reg Guilin 541001 Peoples R China Guangxi Normal Univ Sch Elect & Informat Engn Sch Integrated Circuits Guangxi Key Lab Brain Inspired Computing & Intelli Guilin 541001 Peoples R China Guangxi Normal Univ Educ Dept Guangxi Zhuang Autonomous Reg Guilin 541001 Peoples R China Harbin Inst Technol Shenzhen Guangdong Prov Key Lab Aerosp Commun & Networking Sch Elect & Informat Engn Shenzhen 510855 Peoples R China Harbin Inst ofTechnol Shenzhen Key Lab AIoT Commun Shenzhen 518055 Peoples R China Tongji Univ Shanghai Inst Intelligent Sci & Technol Shanghai 200070 Peoples R China Tongji Univ Coll Elect & Informat Engn Shanghai 200070 Peoples R China Southeast Univ Natl Mobile Commun Res Lab Nanjing 211102 Peoples R China Agcy Sci Technol & Res Inst Infocomm Res Dept Commun & Networks Singapore Singapore

In this article, we focus on the resource allocation and autonomous aerial vehicle (AAV) 3-D trajectory design for the AAV-ground base station (GBS) coordinated multipoint nonorthogonal multiple access (CoMP-NOMA) system to maximize the sum-rate of CoMP users while maintaining users' high Quality of Service requirements. The main contributions of this article are summarized as follows: 1) with the assistance of closed-form power allocation result, a generalized joint user scheduling and power allocation (G-USPA) algorithm is proposed to derive the optimal user scheduling solution;2) by revealing the monotone increasing relationship between the sum transmit power and the transmit rates of non-CoMP users, the optimal rate of each non-CoMP users turns out to be its inherent minimum required rate, consequently, the optimal transmit rates and power allocation of all users can also be derived;and 3) moreover, considering the Line of Sight (LoS) and non-LoS factors in the air-ground channel, the 3-D trajectory of AAV is designed based on successive convex approximation to provide a flexible user-centric service. The proposed G-USPA algorithm is compatible with the AAV trajectory design, which is optimized alternatively and can lead to fast convergence. Numerical results verify that the 3-D AAV-GBS CoMP-NOMA model and the G-USPA scheme have a superior performance in terms of total system sum rate and the sum rate of CoMP users over the non-CoMP AAV assisted nonorthogonal multiple access (NOMA) systems.

关键词： Autonomous aerial vehicles NOMA Resource management Trajectory Three-dimensional displays Interference Air to ground communication Quality of service Scheduling Internet of Things 3-D trajectory design air-ground (A2G) coordinated multipoint (CoMP) transmission nonorthogonal multiple access (NOMA) resource allocation autonomous aerial vehicle (AAV)

来源：评论

学校读者我要写书评

暂无评论

A Flexible-Integrated Multimodal Hydrogel-Based Sensing Patch

引用

NANO-MICRO LETTERS 2025年第1期17卷 1-19页

作者： Wang, Peng Wang, Guoqing Sun, Guifen Bao, Chenchen Li, Yang Meng, Chuizhou Yao, Zhao Univ Jinan Sch Informat Sci & Engn Jinan 250022 Peoples R China Univ Jinan Sch Mech Engn Jinan 250022 Peoples R China Hebei Univ Technol Engn Res CtrMinist Educ Intelligent Rehabil Devic Sch Mech EngnHebei Key Lab Smart Sensing & Human State Key Lab Reliabil & Intelligence Elect Equipm Tianjin 300401 Peoples R China Shandong Univ Sch Integrated Circuits Jinan 250101 Peoples R China Qingdao Univ Coll Elect & Informat Qingdao 266071 Peoples R China Fudan Univ State Key Lab Integrated Chips & Syst Shanghai 200433 Peoples R China

Sleep monitoring is an important part of health management because sleep quality is crucial for restoration of human health. However, current commercial products of polysomnography are cumbersome with connecting wires and state-of-the-art flexible sensors are still interferential for being attached to the body. Herein, we develop a flexible-integrated multimodal sensing patch based on hydrogel and its application in unconstraint sleep monitoring. The patch comprises a bottom hydrogel-based dual-mode pressure-temperature sensing layer and a top electrospun nanofiber-based non-contact detection layer as one integrated device. The hydrogel as core substrate exhibits strong toughness and water retention, and the multimodal sensing of temperature, pressure, and non-contact proximity is realized based on different sensing mechanisms with no crosstalk interference. The multimodal sensing function is verified in a simulated real-world scenario by a robotic hand grasping objects to validate its practicability. Multiple multimodal sensing patches integrated on different locations of a pillow are assembled for intelligent sleep monitoring. Versatile human-pillow interaction information as well as their evolution over time are acquired and analyzed by a one-dimensional convolutional neural network. Track of head movement and recognition of bad patterns that may lead to poor sleep are achieved, which provides a promising approach for sleep monitoring.

关键词： Multimodal sensing Proximity sensor Pressure sensor Temperature sensor Electrospun nanofibers

来源：评论

学校读者我要写书评

暂无评论

AuNU Dimers on ITO Substrate With the Highest Refractive Index Sensitivity as Chemical Sensor

引用

IEEE SENSORS JOURNAL 2022年第8期22卷 7580-7589页

作者： Chen, Bin Liu, Chuanjun Ge, Lingpu Shang, Liang Guo, Hao Hayashi, Kenshi Southwest Univ Chongqing Key Lab Nonlinear Circuit & Intelligent Coll Elect & Informat Engn Chongqing 400715 Peoples R China Kyushu Univ Grad Sch Informat Sci & Elect Engn Dept Elect Fukuoka 8190395 Japan Chinese Acad Sci Shenyang Inst Automat State Key Lab Robot Shenyang 110016 Peoples R China

We synthesized gold (Au) nano-urchins (AuNUs) and deposited these AuNUs on indium tin oxide (ITO) glass. We compared the influence of the resistance of ITO glass and the deposition density of NUs on refractive index sensitivity (RIS) of these ITO substrates, and found that ITO glass with resistance of 8-12 /sq and substrates with many AuNU dimers gave the highest RIS which was as high as 455 nm/RIU (refractive index unit), which is the highest on substrate as we known. Compared with AuNUs deposited on quartz glass, the extinction peak intensity andRISwere enhancedon ITOglass. The RIS enhancement ismainly attributed to the considerably enhanced electric field at the tips of AuNUs, electrical hot spots generated by AuNU aggregates (such as dimers), and the repulsive forcesdecreasein eachAuNU by the ITOlayer. It is thought that further shape, distribution, and size changeof AuNUs and dimers on ITO glass will greatly affect the RIS and spectral characteristics. AuNU substrate is then proposed for heparin detection through Au etching. The results showed that heparin detection was realized in a linear range of 0.05 to 5 mu g/mL with a detection limit of 8 ng/mL, which has potential to be applied in the practical environment.

关键词： Indium tin oxide Glass Gold Substrates Sensors Resistance Plasmons LSPR sensor Au nano-urchin dimers plasmonic coupling electrical hot spots

来源：评论

学校读者我要写书评

暂无评论

Copyright protection framework for federated learning models against collusion attacks

引用

informatION SCIENCES 2024年 680卷

作者： Luo, Yuling Li, Yuanze Qin, Sheng Fu, Qiang Liu, Junxiu Guangxi Normal Univ Sch Elect & Informat Engn Guangxi Key Lab Brain Inspired Comp & Intelligent Guilin 541004 Peoples R China Guangxi Normal Univ Key Lab Nonlinear Circuits & Opt Commun Educ Dept Guangxi Zhuang Autonomous Reg Guilin 541004 Peoples R China

Federated learning (FL) models are constructed by multiple participants who provide their training datasets and collaborate in joint training. However, training and deployment processes have encountered various challenges in terms of intellectual property protection, such as illegal theft and data leakage. Existing FL protection frameworks focus on each client independently and verify the model ownership. When they are under collusion attacks (i.e., when multiple clients negotiate to steal together), they cannot accurately identify the clients that have stolen the model. To address this challenge, a novel watermarking protection scheme against collusion attacks for federated learning is proposed in this work. It employs anti-collusion coding to design unique watermark information for each client, which can effectively detect colluders. Furthermore, it utilizes a specific regularized loss function for watermark information embedding along with the incorporation of skip connections to embed the watermark information within each batch normalization layer. The experimental results demonstrated that embedding different watermark information into each client did not affect the accuracy of the original task. The accuracy was approximately 100% when identifying the colluders. The embedding and extraction times for the original task were only 1.53% and 0.29%, respectively. Further, it exhibited high robustness against various common attacks, including fine-tuning, shearing, and collusion attacks.

关键词： Federated learning Anti-collusion coding Intellectual property protection Watermark

来源：评论

学校读者我要写书评

暂无评论

Phase-change material enabled silicon phase shifter actuated by a highly durable graphene microheater

引用

JOURNAL OF OPTICAL MICROSYSTEMS 2024年第3期4卷

作者： Liu, Shichang Yang, Xing Lu, Liangjun Chen, Jianping Li, Yu Chen, Guorui Zhou, Linjie Shanghai Jiao Tong Univ Dept Elect Engn Key Lab Adv Opt Commun Syst & Networks Shanghai Peoples R China SJTU Pinghu Inst Intelligent Optoelect Jiaxing Peoples R China Chinese Acad Sci Shanghai Inst Microsyst & Informat Technol State Key Lab Mat Integrated Circuits Shanghai Peoples R China Shanghai Jiao Tong Univ Sch Phys & Astron Key Lab Artificial Struct & Quantum Control Minist Educ Shanghai Peoples R China

We demonstrate a high-efficiency silicon optical phase shifter based on a silicon-Sb2Se3 hybrid integrated waveguide. The optical field has large confinement in the Sb(2)Se(3)material, leading to high optical wave modulation efficiency upon phase change of Sb2Se3. The phase change is initiated by electro-thermal heating generated by a highly durable graphene microheater positioned between the Sb(2)Se(3)strip and the silicon slab of the hybrid waveguide. To effectively couple the phase shifter with single-mode silicon waveguides, we design a two-layer taper structure as a mode spot size converter. Utilizing this phase shifter, we implemented a Mach-Zehnder interferometer structure to function as an optical switch. The number of effective switching events exceeds 30,000, and 66 non-volatile switching levels are obtained. Our work provides an effective solution for introducing highly durable graphene microheaters on silicon-based phase-change platforms.

关键词： integrated photonics phase-change material silicon photonics phase shifter graphene

来源：评论

学校读者我要写书评

暂无评论

Distributed Continuous and Discrete Time Projection Neurodynamic Approaches for Sparse Recovery

引用

IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE 2022年第6期6卷 1411-1426页

作者： Zhao, You Liao, Xiaofeng He, Xing Chongqing Univ Coll Comp Sci Chongqing 400044 Peoples R China Southwest Univ Chongqing Key Lab Nonlinear Circuits & Intelligen Chongqing 400715 Peoples R China Southwest Univ Sch Elect & Informat Engn Chongqing 400715 Peoples R China

Sparse representation acts as a fundamental data science methodology for solving a wide range of problems in machine learning and engineering. In this paper, we respectively propose novel distributed continuous-time and discrete-time projection neurodynamic approaches for sparse recovery by seeking the minimum $l_1$-norm solution with the undetermined linear measurement $Ax=b$ in two cases over undirected networks. The proposed approaches only require the communication network to be undirected and connected, without the notion of central processing node, and no node visit the entire matrix $A$, so some privacy preserving efficiencies are guaranteed based on our approaches. First, for the one case that the rows of $A$ are distributed, we propose a distributed continuous-time projection neurodynamic approach based on the projection operators and prove the global convergence and optimality of it. Then, a corresponding distributed discrete-time projection neurodynamic algorithm with a fixed step size is also presented, and the convergence and the scope of values of the step size of it are also analyzed. Second, for another case that the columns of $A$ are distributed, a distributed continuous-time projection neurodynamic approach based on the projection operators and its derivative feedback is proposed and its global convergence is rigorously analyzed. Immediately following, we discuss its corresponding distributed discrete-time projection neurodynamic algorithm with a discrete version of the differential feedback term. Finally, the effectiveness and superiority of the proposed neurodynamic method are verified by the experiments of sparse signal and image reconstruction.

关键词： Neurodynamics Optimization Matching pursuit algorithms Image reconstruction Sparse matrices Smoothing methods Convex functions Continuous-time and discrete-time projection distributed approaches and algorithms global convergence sparse recovery

来源：评论

学校读者我要写书评

暂无评论

Analysis of autonomic nervous pattern in hypertension based on short-term heart rate variability

引用

BIOMEDICAL ENGINEERING-BIOMEDIZINISCHE TECHNIK 2021年第1期66卷 71-79页

作者： Zhang, Ruiqi Hua, Zhengchun Chen, Chen Liu, Guangyuan Wen, Wanhui Southwest Univ Sch Elect & Informat Engn Chongqing 400715 Peoples R China Chongqing Key Lab Nonlinear Circuits & Intelligen Chongqing 400715 Peoples R China

Physiological studies have found that the autonomic nervous system plays an important role in controlling blood pressure values. This paper, based on machine learning approaches, analysed short-term heart rate variability to determine differences in autonomic nervous function between hypertensive patients and normal population. The electrocardiogram (ECG) of hypertensive patients are 137 ECG recordings provided by Smart Health for Assessing the Risk of Events via ECG (SHAREE database). The RR intervals of healthy subjects include the data of 18 subjects from the MIT-BIH Normal Sinus Rhythm Database (nsrdb) and 54 subjects from the Normal Sinus Rhythm RR Interval Database (nsr2db). In this paper, each RR segment includes continuous 500 beats. Seventeen features were extracted to distinguish the hypertensive heart beat rhythms from the normal ones, and Kolmogorov-Smirnov test and sequential backward selection (SBS) were applied to get the best feature combinations. In addition, support vector machine (SVM), k-nearest neighbor (KNN) and random forest (RF) were applied as classifiers in the study. The performance of each classifier was evaluated independently using the leave-one-subject-out validation method. The best predictive model was based on RF and enabled to identify hypertensive patients by five features with an accuracy of 86.44%. The best five HRV features are sample entropy (SampEn), very low frequency spectral powers (VLF), root mean square of successful differences (RMSSD), ratio of low frequency spectral powers and high frequency spectral powers (LF/HF) and vector angle index (VAI). The results of the study show sympathetic overactivity and decreased parasympathetic tone in hypertensive patients.

关键词： autonomic nervous system hypertension machine learning short-term HRV analysis

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：