检索结果-内蒙古大学图书馆

Medical Artificial Intelligence (MedAI), IEEE International Conference on

作者： Xin Xu Wenjing Lu Jiahao Lei Peng Qiu Hong-Bin Shen Yang Yang Department of Computer Science and Engineering Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University Shanghai China Department of Vascular Surgery Shanghai Ninth People's Hospital Shanghai Jiao Tong University School of Medicine Institute of Image Processing and Pattern Recognition and Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai Jiao Tong University Shanghai China

Interactive medical image segmentation methods have become increasingly popular in recent years. These methods combine manual labeling and automatic segmentation, reducing the workload of annotation while maintaining high accuracy. However, most current interactive segmentation frameworks are limited to 2D image data, and are not suitable for 3D image data due to the large size and high complexity of 3D data, as well as the challenges posed by information asymmetry and sparse annotation. In this paper, we propose SliceProp, an interactive segmentation framework that implements slice-wise label Bidirectional Propagation (LBP) for 3D medical image segmentation. SliceProp extends the interactive 2D image segmentation algorithm to 3D image segmentation, and can handle 3D data with large size and high complexity. Moreover, equipped with a Backtracking Feedback Check (BFC) module, SliceProp effectively addresses the issues of information asymmetry and spatial sparse annotation in 3D medical image segmentation. Additionally, we adopt an uncertainty-based criterion to pri-oritize the slices to be refined interactively, which enhances the efficiency of the interaction process by enabling the model to focus on the regions with the most unreliable predictions. SliceProp is evaluated on two datasets and achieves promising results compared to state-of-the-art methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research on the multi-objective resource-constrained transport task scheduling problem

引用

Wuhan Ligong Daxue Xuebao/Journal of Wuhan University of Technology 2008年第5期30卷 155-158页

作者： Wang, Jian Wang, Hong-Wei Institute of Systems Engineering Huazhong University of Science and Technology Wuhan 430074 China Key Laboratory of Image Processing and Intelligent Control Huazhong University of Science and Technology Wuhan 430074 China

A resource-constrained transport task scheduling problem (RCTTSP) with two optimal objectives was considered, and a multi-objective hybrid genetic algorithm (HGA) was proposed. The proposed algorithm used the serial scheduling method to initialize the population and evaluated the individual. It used the weighted sum method and the rank-based fitness assignment method to assign the individual fitness. Firstly, this paper described the multi-objective RCTTSP and presented the principle of the HGA, and then developed the algorithm to implement several experimental cases with different problem size;lastly the effectiveness and efficiency of the algorithm were compared. The numerical result indicated that the proposed multi-objective HGA can resolve the proposed multi-objective RCTTSP efficiently.

关键词： Hybrid genetic algorithm Multi-objective Resource-constrained Serial scheduling Transport task scheduling

来源：评论

学校读者我要写书评

暂无评论

The Objective Dementia Severity Scale Based on MRI with Contrastive Learning: A Whole Brain Neuroimaging Perspective

引用

SENSORS 2023年第15期23卷 6871-6871页

作者： Zhang, Yike Fan, Wenliang Chen, Xi Li, Wei Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Wuhan 430074 Peoples R China Educ Minist China Image Proc & Intelligent Control Key Lab Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Union Hosp Tongji Med Coll Dept Radiol Wuhan 430074 Peoples R China

In the clinical treatment of Alzheimer's disease, one of the most important tasks is evaluating its severity for diagnosis and therapy. However, traditional testing methods are deficient, such as their susceptibility to subjective factors, incomplete evaluation, low accuracy, or insufficient granularity, resulting in unreliable evaluation scores. To address these issues, we propose an objective dementia severity scale based on MRI (ODSS-MRI) using contrastive learning to automatically evaluate the neurological function of patients. The approach utilizes a deep learning framework and a contrastive learning strategy to mine relevant information from structural magnetic resonance images to obtain the patient's neurological function level score. Given that the model is driven by the patient's whole brain imaging data, but without any possible biased manual intervention or instruction from the physician or patient, it provides a comprehensive and objective evaluation of the patient's neurological function. We conducted experiments on the Alzheimer's disease Neuroimaging Initiative (ADNI) dataset, and the results showed that the proposed ODSS-MRI was correlated with the stages of AD 88.55% better than all existing methods. This demonstrates its efficacy to describe the neurological function changes of patients during AD progression. It also outperformed traditional psychiatric rating scales in discriminating different stages of AD, which is indicative of its superiority for neurological function evaluation.

关键词： medical robots disease evaluation Alzheimer's disease contrastive learning

来源：评论

学校读者我要写书评

暂无评论

Fixed-time stabilization of switched two-time-scale systems: Mode-dependent control and event-triggered control

引用

JOURNAL OF THE FRANKLIN INSTITUTE-ENGINEERING AND APPLIED MATHEMATICS 2024年第11期361卷

作者： Zeng, Ze-Hong Wang, Yan-Wu Lei, Yan Xiao, Jiang-Wen Chen, Wu-Hua Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Key Lab Image Proc & Intelligent Control Minist Educ Wuhan 430074 Peoples R China Guangxi Univ Sch Math & Informat Sci Nanning 530004 Guangxi Peoples R China

This paper concentrates on the fixed -time stabilization of switched two-time-scale systems (switched TTSSs). Unlike the existing asymptotical or exponential stabilization results on switched TTSSs, the fixed -time stabilization problem is solved for switched TTSS for the first time via switching control. The upper bounds of the convergence time and the singular perturbation parameter are given explicitly, respectively. Further, the fixed -time stabilization of switched TTSS is achieved by event-triggered control. Unlike the existing event-triggered mechanisms designed for non-switched TTSSs or single-time-scale systems, a mode -dependent and boundary-layer-related event-triggered mechanism is designed to maintain a fixed time convergence, as well as the explicit upper bound of the singular perturbation parameter and the exclusive of Zeno behavior. Finally, three numerical examples, including a comparison study, are given to show the proposed control methods' effectiveness and advantages.

关键词： Switched two-time-scale system Fixed-time stability Average dwell time Event-triggered controller

来源：评论

学校读者我要写书评

暂无评论

Energy management strategy based on health state for a PEMFC/Lithium-ion batteries hybrid power system

引用

ENERGY CONVERSION AND MANAGEMENT 2022年 271卷

作者： Sheng, Chuang Fu, Jun Li, Dong Jiang, Chang Guo, Ziang Li, Beijia Lei, Jingzhi Zeng, Linghong Deng, Zhonghua Fu, Xiaowei Li, Xi Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Key Lab Image Proc & Intelligent Control Educ Mini Wuhan 430074 Peoples R China Shenzhen Huazhong Univ Sci Technol Res Inst Shenzhen 518055 Peoples R China

The traditional energy management strategies (EMSs) for fuel cell/battery hybrid vehicle systems frequently neglect the degradation issues of power sources. The health-conscious EMS can take active control over the operation, thus mitigating the detrimental effects of degradation. Here, we will discuss an EMS that takes into account both proton exchange membrane fuel cell (PEMFC) and lithium-ion battery (LIB) degradation. To develop the desired strategy, performance degradation models for two power sources are constructed. It is the first time that the aggregation of platinum particles is taken into account in the water content model and used as the degradation index of PEMFC. The model's accuracy is checked by comparing the voltage drop when the model outputs steadily with data from experiments. Meanwhile, the optimal range of water content is deter-mined based on the analysis of the impact of water content on the stack voltage degradation. This provides a benchmark for the health control of PEMFC in EMS. Then, accurate knowledge of battery SoC can contribute to the rational management of LIBs. An improved UKF (unscented Kalman filter) algorithm is utilized to jointly estimate the SoC and model parameters of the battery and is compared with other methods. It can be found that the proposed joint estimation method has more precise SoC estimation results than the EKF (extended Kalman filter) and the traditional UKF approaches. This provides a reliable basis for the regulation of LIBs in EMS. Finally, taking PEMFC water content, battery SoC, and the required power as inputs, a rule-based health -conscious EMS is developed. The power response curve obtained from the HIL (hardware-in-the-loop) simulation platform shows that the proposed EMS can meet different load demand changes. In addition, during the test, the water content in the stack is kept in the range of 14-18.5, and the battery SoC is kept in the range of 0.6-0.8. Both of them are within the established benchma

关键词： PEMFC Lithium -ion battery Platinum particles agglomeration UKF Energy management strategy

来源：评论

学校读者我要写书评

暂无评论

Optimization of Coordinate Transformation Matrix for Discrete-Time H∞ Static-Output-Feedback control Problems

Optimization of Coordinate Transformation Matrix for Discret...

引用

第三十三届中国控制会议

作者： Zhi-Yong Feng Li Xu Ye Li Huijin Fan Xue-Xun Guo Hubei Key Laboratory of Advanced Technology of Automotive Parts Wuhan University of Technology Hubei Collaborative Innovation Center for Automotive Components Technology Department of Electronics and Information Systems Akita Prefectural UniversityYuri-HonjoAkita 015-0055Japan Department of Control Science and Engineering University of Shanghai for Science and Technology Key Laboratory of Image Processing and Intelligent Control School of AutomationHuazhong University of Science and Technology

ISBN: (纸本)9781479947249

The problem of how to select a coordinate transformation matrix to improve the LMI conditions for H∞ staticoutput-feedback(SOF) control of discrete-time systems is a challenging open *** paper applies a newly proposed strategy to solve this *** iterative algorithm is developed to produce controllers with locally optimal closed-loop H∞*** algorithm is also applied to other H∞ SOF control problems,such as decentralized H∞ SOF control and simultaneous H∞ SOF ***,numerical examples are provided to demonstrate the effectiveness and advantages of the proposed method.

关键词： H∞ control,Static output feedback,Decentralized control,Simultaneous control,Linear matrix inequality(LMI)

来源：评论

学校读者我要写书评

暂无评论

Public authority control strategy for opinion evolution in social networks

引用

CHAOS 2016年第8期26卷 083105-083105页

作者： Chen, Xi Xiong, Xi Zhang, Minghong Li, Wei Huazhong Univ Sci & Technol Sch Automat Wuhan 430074 Peoples R China Huazhong Univ Sci & Technol Nontradit Secur Ctr Wuhan 430074 Peoples R China Educ Minist China Image Proc & Intelligent Control Key Lab Wuhan 430074 Peoples R China

This paper addresses the need to deal with and control public opinion and rumors. Existing strategies to control public opinion include degree, random, and adaptive bridge control strategies. In this paper, we use the HK model to present a public opinion control strategy based on public authority (PA). This means utilizing the influence of expert or high authority individuals whose opinions we control to obtain the optimum effect in the shortest time possible and thus reach a consensus of public opinion. Public authority (PA) is only influenced by individuals' attributes (age, economic status, and education level) and not their degree distribution;hence, in this paper, we assume that PA complies with two types of public authority distribution (normal and power-law). According to the proposed control strategy, our experiment is based on random, degree, and public authority control strategies in three different social networks (small-world, scale-free, and random) and we compare and analyze the strategies in terms of convergence time (T), final number of controlled agents (C), and comprehensive efficiency (E). We find that different network topologies and the distribution of the PA in the network can influence the final controlling effect. While the effect of PA strategy differs in different network topology structures, all structures achieve comprehensive efficiency with any kind of public authority distribution in any network. Our findings are consistent with several current sociological phenomena and show that in the process of public opinion/rumor control, considerable attention should be paid to high authority individuals. Published by AIP Publishing.

关键词： Network topology Social networks Process monitoring and control Economic issues Experiment design

来源：评论

学校读者我要写书评

暂无评论

Simplified and Yet Turing Universal Spiking Neural P Systems with Communication on Request

引用

INTERNATIONAL JOURNAL OF NEURAL SYSTEMS 2018年第8期28卷 1850013-1850013页

作者： Wu, Tingfang Bilbie, Florin-Daniel Paun, Andrei Pan, Linqiang Neri, Ferrante Huazhong Univ Sci & Technol Sch Automat Educ Minist China Key Lab Image Informat Proc & Intelligent Control Wuhan 430074 Hubei Peoples R China Univ Bucharest Fac Math & Comp Sci Dept Comp Sci Str Acad 14Sect 1 Bucharest 010014 Romania Natl Inst Res & Dev Biol Sci Dept Bioinformat Splaiul Independentei 296Sect 6 Bucharest Romania Zhengzhou Univ Light Ind Sch Elect & Informat Engn Zhengzhou 450002 Henan Peoples R China De Montfort Univ Sch Comp Sci & Informat Ctr Computat Intelligence Leicester LE1 9BH Leics England

Spiking neural P systems are a class of third generation neural networks belonging to the framework of membrane computing. Spiking neural P systems with communication on request (SNQ P systems) are a type of spiking neural P system where the spikes are requested from neighboring neurons. SNQ P systems have previously been proved to be universal (computationally equivalent to Turing machines) when two types of spikes are considered. This paper studies a simplified version of SNQ P systems, i.e. SNQ P systems with one type of spike. It is proved that one type of spike is enough to guarantee the Turing universality of SNQ P systems. Theoretical results are shown in the cases of the SNQ P system used in both generating and accepting modes. Furthermore, the influence of the number of unbounded neurons (the number of spikes in a neuron is not bounded) on the computation power of SNQ P systems with one type of spike is investigated. It is found that SNQ P systems functioning as number generating devices with one type of spike and four unbounded neurons are Turing universal.

关键词： Bio-inspired computing membrane computing spiking neural network spiking neural P system computation power

来源：评论

学校读者我要写书评

暂无评论

An enhanced fireworks algorithm and its application in fault detection of the displacement sensor

引用

Measurement: Sensors 2024年 34卷

作者： Hao, Tianlu Ma, Zhuang Wang, Yaping Computer Center of Tangshan University Tangshan063000 China Key Lab of Intelligent Data Information Processing and Control of Hebei Province Tangshan University Tangshan063000 China Tangshan No.1 Middle School in Hebei Province Tangshan063000 China

Regarding the fault detection problem of the displacement sensor, an enhanced fireworks algorithm with information crossover and conversion factor (EFWA-IC) is proposed in this paper. In EFWA-IC, an information crossover strategy is proposed to maintain population diversity. This strategy is based on the predatory behavior of carnivores in nature. In addition, a conversion factor is set to control whether the explosion operator is executed or not to provide a more reasonable search. To fully evaluate the performance of EFWA-IC, a range of tests are carried out based on the CEC2017 and 23 classical test functions. The results show that the performance of EFWA-IC is better than other state-of-the-art optimization algorithms in terms of solution accuracy, convergence speed, and stability. Finally, EFWA-IC is utilized to optimize the particle filter (PF) to establish a fault detection model of displacement sensor in the continuous casting mold. The simulation experiment result of field data manifests that EFWA–IC–PF can accurately detect faults in the displacement sensor. For bias faults, the RMSE of the EFWA–IC–PF model is 0.14468, and the false alarm rate (FAR) and missed detection rate (MDR) are 1 % and 0.5 %, respectively. For stuck faults, the RMSE is 1.00148, and the FAR and MDR are 0.88 % and 1 %, respectively. © 2024 The Authors

关键词： Fault detection

来源：评论

学校读者我要写书评

暂无评论

Review of intelligent computing application 1st

Review of intelligent computing application

引用

1st International Conference on Smart Vehicular Technology, Transportation, Communication and Applications, VTCA 2017

作者： Wang, Yiou Liu, Tianyuan Zhang, Fuquan Xu, Lin Ding, Gangyi Xiong, Rui Liu, Fei Beijing Institute of Science and Technology Information Beijing100044 China Carnegie Mellon University 5000 Forbes Avenue PittsburghPA15213 United States Digital Performance and Simulation Technology Lab. School of Software Beijing Institute of Technology Beijing100081 China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang Univeristy Fuzhou350121 China Innovative Information Industry Research Institute Fujian Normal University Fuzhou350300 China

ISBN: (纸本)9783319707297

intelligent computing systems can automatically sense environmental changes in the sensor network, make judgments and prediction on the environmental status in time, and provide response strategies in different environments, applying some technologies of pattern recognition, time series prediction and big data analytics. Nowadays, intelligent computing is successfully used in a lot of areas such as transportation, healthcare, home, performance and environmental monitoring. In this paper, the concept of intelligent computing is introduced. Then, the applications in different areas are discussed detailedly. Finally, the future of intelligent computing is analyzed and the conclusion is briefly given. © Springer International Publishing AG 2018.

关键词： Wireless sensor networks

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：