检索结果-内蒙古大学图书馆

Surrogate-Assisted Multiobjective Gene Selection for Cell Classification from Large-Scale Single-Cell RNA Sequencing Data

引用

IEEE Transactions on Evolutionary Computation 2025年第3期29卷 601-615页

作者： Lin, Jianqing He, Cheng Jiang, Hanjing Huang, Yabing Jin, Yaochu Huazhong University of Science and Technology Key Laboratory of Image Information Processing and Intelligent Control of Education Ministry of China School of Artificial Intelligence and Automation Wuhan430074 China Huazhong University of Science and Technology State Key Laboratory of Advanced Electromagnetic Technology School of Electrical and Electronic Engineering Wuhan430074 China Renmin Hospital Department of Pathology Wuhan University Wuhan430060 China Westlake University Trustworth and General Artificial Intelligence Laboratory School of Engineering Hangzhou310030 China

Accurate cell classification is crucial but expensive for large-scale single-cell RNA sequencing (scRNA-seq) analysis. Gene selection (GS) emerges as a pivotal technique in identifying gene subsets of scRNA-seq for classification accuracy improvement and gene scale reduction. Nevertheless, the rising scale of scRNA-seq data presents challenges to existing GS methods regarding performance and computational time. Thus, we propose a surrogate-assisted evolutionary algorithm for multiobjective GS to address these deficiencies. An innovative two-phase initialization method is proposed to select sparse solutions to provide preliminary insights into gene contributions. Then, a binary competitive swarm optimizer is proposed for effective global search, where a local search method is embedded to eliminate irrelevant genes for efficiency consideration. Additionally, a surrogate model is adopted to forecast classification accuracy efficiently and substitutes part of the computationally expensive classification process. Experiments are conducted on eight large-scale scRNA-seq datasets with more than 20,000 genes. The effectiveness of the proposed GS method for scRNA-seq cell classification compared with eight state-of-the-art methods is validated. Gene expression analysis results of selected genes further validated the significance of the genes selected by the proposed method in the classification of scRNA-seq data. © 1997-2012 IEEE.

关键词： Gene expression

来源：评论

学校读者我要写书评

暂无评论

Adaptive Synchronization of Reaction-Diffusion Neural Networks With Nondifferentiable Delay via State Coupling and Spatial Coupling

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2023年第10期34卷 7555-7566页

作者： Zhang, Hao Zeng, Zhigang Huazhong Agr Univ Coll Informat Wuhan 430070 Peoples R China Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Wuhan 430074 Peoples R China Educ Minist China Key Lab Image Proc & Intelligent Control Wuhan 430074 Peoples R China

In this article, master-slave synchronization of reaction-diffusion neural networks (RDNNs) with nondifferentiable delay is investigated via the adaptive control method. First, centralized and decentralized adaptive controllers with state coupling are designed, respectively, and a new analytical method by discussing the size of adaptive gain is proposed to prove the convergence of the adaptively controlled error system with general delay. Then, spatial coupling with adaptive gains depending on the diffusion information of the state is first proposed to achieve the master-slave synchronization of delayed RDNNs, while this coupling structure was regarded as a negative effect in most of the existing works. Finally, numerical examples are given to show the effectiveness of the proposed adaptive controllers. In comparison with the existing adaptive controllers, the proposed adaptive controllers in this article are still effective even if the network parameters are unknown and the delay is nonsmooth, and thus have a wider range of applications.

关键词： Synchronization Biological neural networks Couplings Delays Adaptive control Convergence Stochastic processes Adaptive synchronization nondifferentiable delay reaction-diffusion neural network (RDNN) spatial coupling

来源：评论

学校读者我要写书评

暂无评论

Correlation-aware constrained many-objective service composition in crowdsourcing design

引用

ADVANCED ENGINEERING INFORMATICS 2025年 65卷

作者： Li, Gui Xiao, Renbin Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Wuhan 430074 Hubei Peoples R China Huazhong Univ Sci & Technol Inst Artificial Intelligence Wuhan 430074 Hubei Peoples R China Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Key Lab Image Proc & Intelligent Control Wuhan 430074 Hubei Peoples R China

With the development of social productivity, crowdsourcing design, a new service-oriented innovative design model emerged. The optimal selection of service resources in crowdsourcing design has a great impact on the quality of task implementation and consumer satisfaction. Unlike the previous research, this paper models and solves the problem from the perspective of constrained many-objective optimization. Firstly, a constrained 6objective combination optimization model is constructed according to the characteristics of service resources in crowdsourcing design. Secondly, a variety of correlation categories and correlation forms of services are considered. It is not limited to the correlation between two services but rather correlations between any number of services. In order to improve search efficiency, a multi-objective service pruning (MOSP) method based on efficient non-dominated sorting (ENS) is used to reduce the decision space. The new constraint strategy handles complex constraints, and a correlation-aware local search strategy is proposed to deal with correlations between services. The results of comparison experiments prove the superiority of the proposed method in solving the constrained correlation-aware many-objective service composition problem.

关键词： Many-objective optimization Dynamic learning evolutionary algorithm Crowdsourcing design Service composition Constraint optimization

来源：评论

学校读者我要写书评

暂无评论

RBP-Former: Joint Prediction of RNA-protein Binding Sites on Full-length RNA Transcripts for Multiple RBPs

RBP-Former: Joint Prediction of RNA-protein Binding Sites on...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Li, Yichong Liu, Xiaojian Cheng, Fan Pan, Xiaoyong Yang, Yang Shanghai Jiao Tong University Department of Computer Science and Engineering Shanghai200240 China Shanghai Jiao Tong University Institute of Image Processing and Pattern Recognition Shanghai200240 China Ministry of Education of China Key Laboratory of System Control and Information Processing Shanghai200240 China Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai200240 China

ISBN: (纸本)9798350386226

RNA-binding proteins (RBPs) are essential for gene expression, and the complex RNA-protein interaction mechanisms require analysis of global RNA information. Therefore, accurate prediction of RBP binding sites on full-length RNA transcripts is crucial for understanding these mechanisms and their roles in diseases. While machine learning methods can predict RBP binding to RNA fragments, extending this to full-length transcripts presents challenges due to sequence length and data imbalance. In this paper, we introduce RBP-Former, a binding site joint prediction model designed specifically for full-length RNA transcripts that can be used for multiple RBPs. This model processes information at both coarse and fine-grained levels to fully exploit sequence data and its interactions with multiple RBPs. We develop multi-level imbalance learning strategies, achieving favorable results on imbalanced data. Our method outperforms existing methods in predicting binding sites on full-length RNA transcripts for multiple RBPs, demonstrating its effectiveness in handling imbalanced label and sample distributions. © 2024 IEEE.

关键词： Binding sites

来源：评论

学校读者我要写书评

暂无评论

Finite-time H∞ output synchronization for DCRDNNs with multiple delayed and adaptive output couplings

引用

NEURAL NETWORKS 2025年 184卷 107104页

作者： Qiu, Qian Chen, Yin Su, Housheng Henan Univ Sch Artificial Intelligence Zhengzhou 450046 Peoples R China Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Image Proc & Intelligent Control Key Lab Educ Minist China Wuhan 430074 Peoples R China Univ Strathclyde Dept Elect & Elect Engn Glasgow G1 1XW Scotland

This work concentrates on solving the finite-time H infinity output synchronization (FTHOS) issue of directed coupled reaction-diffusion neural networks (DCRDNNs) with multiple delayed and adaptive output couplings in the presence of external disturbances. Based on the output information, an adaptive law to adjust output coupling weights and a controller are respectively developed to ensure that the DCRDNNs achieve FTHOS. Then, in the special case of no external disturbances, a corollary on the finite-time output synchronization (FTOS) of the DCRDNNs with multiple delayed and adaptive output couplings is provided. In addition, a novel adaptive scheme to update output coupling weights is devised to ensure H infinity output synchronization (HOS) in the DCRDNNs with multiple delayed output couplings. Finally, the relevant simulation graphs are provided to certify the validity of several synchronization criteria.

关键词： FTHOS FTOS HOS DCRDNNs Multiple delayed and adaptive output couplings

来源：评论

学校读者我要写书评

暂无评论

Global Exponential Synchronization of Delayed Fuzzy Neural Networks With Reaction Diffusions

引用

IEEE TRANSACTIONS ON FUZZY SYSTEMS 2023年第8期31卷 2809-2820页

作者： Sheng, Yin Xing, Yun Huang, Tingwen Zeng, Zhigang Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Wuhan 430074 Peoples R China Educ Minist China Key Lab Image Proc & Intelligent Control Wuhan 430074 Peoples R China Texas A&M Univ Qatar Sci Program Doha 5825 Qatar

This article is concerned with global exponential synchronization of delayed fuzzy neural networks with reaction diffusions (RDFNNs). By adopting analytic method and some inequality techniques, a global exponential synchronization criterion in terms of p-norm (p = 2) is obtained for the RDFNNs via adaptive intermittent control. One numerical example is provided to demonstrate the validity of the proposed outcomes. Two other examples are given to show the applications in image encryption and pseudorandom number generation, respectively.

关键词： Adaptive intermittent control exponential synchronization fuzzy neural networks (FNNs) reaction diffusions (RDs)

来源：评论

学校读者我要写书评

暂无评论

3-D temperature field reconstruction of lithium-ion battery pack using real-time distributed moving horizon estimation 35

3-D temperature field reconstruction of lithium-ion battery ...

引用

35th Chinese control and Decision Conference (CCDC)

作者： Yan, Jiayu Wan, Yiming Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Wuhan 430074 Peoples R China Minist Educ Key Lab Image Proc & Intelligent Control Wuhan 430074 Peoples R China

ISBN: (纸本)9798350334722

As lithium-ion batteries are widely used in different fields, the thermal effect is of serious concern. How to achieve accurate temperature estimation in real time is the main challenge of current research. To address this problem, we propose a real-time distributed moving horizon estimation (RT-DMHE) based on partial differential equations describing thermal dynamics of a lithium-ion battery pack. It decomposes the real-time centralized moving horizon estimation (RT-CMHE) into multiple local estimators that run in parallel with information exchange from adjacent subsystems. Simulation validation shows that the root mean square error of temperature estimates from the proposed RT-DMHE is smaller than that of an existing distributed Kalman filter in literature. Moreover, compared to the RT-CMHE, the proposed RT-DMHE achieves comparable estimation accuracy while vastly reducing the average computation time per sample.

关键词： lithium-ion battery pack distributed moving horizon estimation real-time computation state-of-temperature estimation

来源：评论

学校读者我要写书评

暂无评论

An Assist-as-Needed Variable Admittance controller for Adaptive Support of Mobile Walking Assistive Robots 30

An Assist-as-Needed Variable Admittance Controller for Adapt...

引用

30th International Conference on Mechatronics and Machine Vision in Practice, M2VIP 2024

作者： Chen, Xinxing Zheng, Yue Su, Zongming Leng, Yuquan Huang, Jian Fu, Chenglong Guangdong Provincial Key Laboratory of Human-Augmentation and Rehabilitation Robotics in Universities Southern University of Science and Technology Shenzhen China Huawei Technologies Technology Planning Department Shenzhen China Key Laboratory for Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China

ISBN: (纸本)9798350391916

Mobile walking assistive robots have been widely used for monitoring patients' gait patterns and providing support to prevent falls. Traditional approaches often separate the operational modes of these robots into human-following and supporting modes, which can lead to discontinuities in assistance and potentially compromise safety. This paper proposes a novel assist-as-needed control strategy that incorporates a Balance Index (BI) to dynamically adjust the robot's support based on the user's balance capability. The BI is calculated using the interaction force between the user and the robot along the z-axis and the gait symmetry index (GSI). The proposed variable admittance controller modifies its parameters based on the BI, ensuring seamless transitions between compliance and support modes. Experimental validation was conducted with a healthy subject walking both with and without a knee fixation brace. The results demonstrate that the robot provides minimal interference during natural gait and increased support during impaired gait, validating the effectiveness of the proposed control strategy in enhancing user safety and promoting natural walking patterns. © 2024 IEEE.

关键词： Assistive technology

来源：评论

学校读者我要写书评

暂无评论

Presketched DNA Origami Canvas for Polymerase-Driven DNA Kirigami

引用

ACS NANO 2023年第17期17卷 17265-17272页

作者： Chen, Kuiting Xie, Chun Chen, Zhekun Wang, Shichen Hu, Yingxin Xu, Fei Pan, Linqiang Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Key Lab Image Informat Proc Intelligent Control Educ Minist China Wuhan 430074 Hubei Peoples R China Shijiazhuang Tiedao Univ Coll Informat Sci & Technol Shijiazhuang 050043 Hebei Peoples R China

Reconfigurable DNA origami provides a versatile tool to manipulate the conformation of matter on the nanometer scale. Typically, the DNA kirigami method enables the transformation of an origami structure from an initial shape to another predesigned shape by reconfiguring the staple strands. In a regular origami structure, since the perfectly matched and densely packed DNA duplexes block the removal of staple strands, the construction of finely trimmed "sub-origami" structures by the DNA kirigami method has remained challenging. Herein, we proposed a strategy to construct the presketched DNA origami canvas, where the offcut area in the canvas was sketched by loosely fixed staple strands with single-base insertion, to enhance the fineness of polymerase-driven DNA kirigami. We successfully trimmed presketched two-dimensional rectangular canvas, three-dimensional Mo''bius strip, and genie bottle canvases into complex letter patterns, supercoiled rings, and nanorods, respectively. Finally, we demonstrated a size-controlled DNA kirigami system: a presketched 6HB origami was trimmed into a set of shorter nanowires with predefined lengths, which quantitatively characterized the fineness of the improved DNA kirigami. The presketched origami design was a general method that applied to both 2D and 3D DNA origami structures in square and honeycomb lattices. Loosening DNA origami structures by introducing single-base insertions provides a practical approach to constructing dynamic components when designing DNA nanomachines. Furthermore, the delicate trimming of the DNA origami canvas driven by polymerase may inspire strategies for graphical information encryption and storage.

关键词： DNA nanotechnology DNA origami reconfigurableDNA nanostructure polymerase-triggered strand displacement DNA kirigami

来源：评论

学校读者我要写书评

暂无评论

Designing a completely distributed observer with robustness against disturbances

引用

INTERNATIONAL JOURNAL OF ROBUST AND NONLINEAR control 2024年第12期34卷 7912-7935页

作者： Wang, Xiaoling Zhang, Ankang Su, Housheng Chen, Guanrong Nanjing Univ Posts & Telecommun Coll Automat & AI Nanjing 210003 Peoples R China Jiangsu Engn Lab IOT Intelligent Robots IOTRobot Nanjing Peoples R China East China Univ Sci & Technol Minist Educ Key Lab Smart Mfg Energy Chem Proc Shanghai Peoples R China Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Image Proc & Intelligent Control Key Lab Educ Minist China Wuhan 430074 Peoples R China City Univ Hong Kong Dept Elect Engn Hong Kong Peoples R China

Distributed observer is an effective scheme for state estimation of a targeted system, utilizing a network of sensors to perform local output measurements. In this article, the problem of designing a distributed observer for a linear time-invariant system with external disturbances is addressed. The objective is to perform state estimation of such a system while simultaneously mitigating the impact of external disturbances and maintaining the distributed communication characteristics among the sensors. To achieve this, a completely distributed observer with robustness against disturbances is developed by combining the high-gain observer technique and the adaptive coupling strength strategy. Initially, a traditional high-gain observer is used for the state estimation on the observable subsystem, and subsequently a high-gain observer without peaking is introduced to avoid the peaking phenomenon. Finally, numerical simulations are presented to verify the theoretical results.

关键词： adaptive coupling gain distributed observer external disturbance high-gain observer robustness

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：