检索结果-内蒙古大学图书馆

2023 International Conference on Mobile Internet, Cloud Computing and Information Security, MICCIS 2023

作者： Ji, Jiezhou Yu, Donghui Yang, Dewang Shen, Xiao Liu, Haoran Zhao, Linqiang Wang, Tao Zeng, Yu Pan, Qiuhui Dalian University of Technology School of Mathematical Sciences Dalian China Dalian University of Technology School of Control Science and Engineering Dalian China Dalian University of Technology School of Computer Science and Technology Dalian China Quarkdata Technology Beijing China China Telecom Research Institute Beijing China

ISBN: (纸本)9798350300932

This paper develops a kind of Model Predictive control (MPC) based on the Transformer proxy model. Traditional MPC usually makes predictions via linear models which are unable to understand the interaction between various input variables. In this paper, we utilize the Transformer to approximate the nonlinear model, and capture the law of time series data. Specifically, we exploit the idea of dynamic programming to optimize the model to predict the cost of the trajectory, and recommend the control operation at each time point to determine the optimal strategy, and finally achieve the purpose of optimization. Experiments conducted on the data room energy-saving control problem demonstrated that, our Transformer based MPC model can predict the temperature change more accurately and is more robust to the field environment change. Moreover, compared with the previous Proportion Integration (PI) control, the MPC developed by us can make the temperature in the machine room is stable around 22°C, and the power consumption is reduced by 37.40%. © 2023 IEEE.

关键词： Model predictive control

来源：评论

学校读者我要写书评

暂无评论

Constructing Equivalent Hodgkin-Huxley Neuron Spice Model of the Subthalamic Nucleus Verified by Swine Deep Brain Stimulation

Constructing Equivalent Hodgkin-Huxley Neuron Spice Model of...

引用

Neural Imaging and Sensing 2025

作者： Wu, Kun-Ta Chiang, Chih-Chuan Chen, Peng-Jye Yan, Yung-Jhe Mang, Ou-Yang Institute of Electrical and Control Engineering National Yang Ming Chiao Tung University Hsinchu Taiwan Biomedical Technology and Device Research Laboratories Industrial Technology Research Institute Hsinchu Taiwan Institute of Electrical and Computer Engineering National Yang Ming Chiao Tung University Hsinchu Taiwan

ISBN: (纸本)9781510683549

Deep brain stimulation (DBS) is an invasive treatment widely used to alleviate motor disorders in patients with Parkinson's disease (PD). DBS can disrupt pathological neural activity and restore functional motor control by delivering electrical impulses to specific brain regions. DBS is generally divided into two types: open-loop and closed-loop DBS. Open-loop DBS provides constant electrical stimulation without real-time feedback, while closed-loop DBS dynamically adjusts stimulation parameters based on real-time detection of biomarkers, offering the potential for more precise and energyefficient therapy. However, ensuring the stability and efficacy of closed-loop DBS systems requires a deeper understanding of the underlying neural dynamics and accurate modeling techniques. To address these needs, this study focuses on developing an Equivalent Hodgkin-Huxley (HH) neuron SPICE model for the subthalamic nucleus (STN), a key target for DBS in PD treatment. The HH model is a well-known framework including ion channel dynamics and membrane potential changes. Integrating the HH model into SPICE enables its compatibility with electrical components, facilitating its application in circuit-based closed-loop DBS systems. First, an equivalent HH neuron SPICE model for the STN was constructed using a computational model. Then, the model parameters were adjusted based on experimental data collected from a swine brain to ensure biological relevance. Finally, an STN Equivalent HH neuron SPICE model with minimized quantization error was obtained. This model not only bridges computational neuroscience and circuit simulation but also provides a robust foundation for enhancing DBS system design, paving the way for personalized and adaptive PD treatments. © 2025 SPIE.

关键词： SPICE

来源：评论

学校读者我要写书评

暂无评论

Interference Suppression and Jitter Elimination Ability-Based Adaption Tracking Guidance for Robotic Fishes

引用

IEEE/CAA Journal of Automatica Sinica 2025年第1期12卷 126-137页

作者： Dongfang Li Jie Huang Rob Law Xin Xu Limin Zhu Edmond Q.Wu IEEE the School of Electrical Engineering and Automation Fuzhou University the Key Laboratory of System Control and Information Processing Ministry of Education the School of Electrical Engineering and Automation Fuzhou University 5G+Industrial Internet Institute Fuzhou University the University of Macau the College of Mechatronics and Automation National University of Defense Technology the School of Mechanical Engineering Shanghai Jiao Tong University the Department of Computer Science and Engineering Shanghai Jiao Tong University

This work presents an adaptive tracking guidance method for robotic fishes. The scheme enables robots to suppress external interference and eliminate motion jitter. An adaptive integral surge line-of-sight guidance rule is designed to eliminate dynamics interference and sideslip issues. Limited-time yaw and surge speed observers are reported to fit disturbance variables in the model. The approximation values can compensate for the system's control input and improve the robots' tracking ***, this work develops a terminal sliding mode controller and third-order differential processor to determine the rotational torque and reduce the robots' run jitter. Then, Lyapunov's theory proves the uniform ultimate boundedness of the proposed method. Simulation and physical experiments confirm that the technology improves the tracking error convergence speed and stability of robotic fishes.

关键词： Adaptive integral surge line-of-sight approximation robotic fish speed observer

来源：评论

学校读者我要写书评

暂无评论

Establishing the Neuron SPICE Model of Basal Ganglia in Parkinson's Disease Based on the Hodgkin-Huxley Conductance-Based Theory

Establishing the Neuron SPICE Model of Basal Ganglia in Park...

引用

Neural Imaging and Sensing 2025

作者： Wu, Kun-Ta Chen, Peng-Jye Chiang, Chih-Chuan Yan, Yung-Jhe Mang, Ou-Yang Institute of Electrical and Control Engineering National Yang Ming Chiao Tung University Hsinchu Taiwan Biomedical Technology and Device Research Laboratories Industrial Technology Research Institute Hsinchu Taiwan Institute of Electrical and Computer Engineering National Yang Ming Chiao Tung University Hsinchu Taiwan

ISBN: (纸本)9781510683549

Deep brain stimulation (DBS) is a surgical treatment used to reduce movement impairments in individuals suffering from Parkinson's disease. To ensure the stability of a DBS system, it is vital to develop an equivalent Hodgkin-Huxley neuron SPICE model that can be simulated with circuit components. Accordingly, this study proposes a neuron SPICE model for the basal ganglia (BG). First, conductance-based models for several brain regions are established in SPICE, including the internal segment of globus pallidus (GPi), subthalamic nucleus (STN), thalamus (TH), and external segment of globus pallidus (GPe). Notably, the amount of the constant bias current from other brain regions is adjusted for the healthy and Parkinsonian states respectively. Next, the synapse model connecting the neurons is constructed and classified into excitatory and inhibitory types. Subsequently, the TH is stimulated by the pulse wave from sensorimotor cortex (SMC). Eventually, the TH neuron in the healthy state responds faithfully to the stimulus with spikes, while the neuron in the Parkinson's state sometimes fails to respond. After DBS at the STN in Parkinsonian state, the TH neuron responds to the SMC similarly to the healthy state. In summary, this model provides a way to simulate Parkinson's disease founded on a conductance-based model that includes various brain regions while incorporating realistic electrical properties of the experimental environment into the simulation, such as electrodes applied in DBS and amplifier circuits for sensing signals. © 2025 SPIE.

关键词： Neurodegenerative diseases

来源：评论

学校读者我要写书评

暂无评论

EDB-Net: An Edge-Guided Dual-Branch Neural Network for Skin Cancer Classification 27th

EDB-Net: An Edge-Guided Dual-Branch Neural Network for Skin...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Ray, Amartya Gayen, Soumyajit Kaplun, Dmitrii Sarkar, Ram Department of Computer Science and Engineering Jadavpur University Kolkata India Artificial Intelligence Research Institute China University of Mining and Technology Xuzhou China Department of Automation and Control Processes Saint Petersburg Electrotechnical University "LETI" Saint Petersburg Russia

ISBN: (纸本)9783031781032

Skin cancer poses a serious global health challenge, where timely and precise diagnosis is essential to improve patient outcomes. Recently, neural networks have proven to be highly effective tools for automated skin cancer classification, significantly advancing the field of dermatology. This paper introduces a novel approach to generate edge maps from dermoscopic images using a holistically nested edge detector model. These edge maps enhance the detection of shape and symmetry irregularities, which are key indicators of malignancy, and improve the focus on relevant regions of interest. We then propose an edge-guided dual-branch neural network, called EDB-Net, for the classification task. Branch 1 handles edge maps, while Branch 2 processes original dermoscopic images. To highlight significant regions and focus on specific lesion areas, we incorporate a novel channel-spatial synergistic attention block within Branch 2. Additionally, we introduce a unique strategy to modulate the generated attention maps using edge features extracted from the edge maps in Branch 1, creating edge-guided features that refine the overall feature representation. In the final stage, both edge-guided and attention-aided features are combined, producing more distinct and contextually relevant outputs, thereby significantly enhancing classification performance. Our model achieves accuracies of 0.927 and 0.848 on the challenging HAM10000 and ISIC 2016 datasets, respectively, without employing any data augmentation. The source code of the proposed model is available at: https://***/Cmatermedicalimageanalysis/EDB_Net. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

Metaheuristic Optimization Algorithm for Signals Classification of Electroencephalography Channels

引用

computers, Materials & Continua 2022年第6期71卷 4627-4641页

作者： Marwa M.Eid Fawaz Alassery Abdelhameed Ibrahim Mohamed Saber Department of Communications and Electronics Delta Higher Institute of Engineering and TechnologyMansoura35111Egypt Department of Computer Engineering College of Computers and Information TechnologyTaif UniversityTaif21944Saudi Arabia Computer Engineering and Control Systems Department Faculty of EngineeringMansoura UniversityMansoura35516Egypt Department of Electronics and Communications Engineering Faculty of EngineeringDelta University for Science and TechnologyMansoura11152Egypt

Digital signal processing of electroencephalography(EEG)data is now widely utilized in various applications,including motor imagery classification,seizure detection and prediction,emotion classification,mental task classification,drug impact identification and sleep state *** the increasing number of recorded EEG channels,it has become clear that effective channel selection algorithms are required for various *** Whale Optimization Method(Guided WOA),a suggested feature selection algorithm based on Stochastic Fractal Search(SFS)technique,evaluates the chosen subset of *** may be used to select the optimum EEG channels for use in Brain-computer Interfaces(BCIs),the method for identifying essential and irrelevant characteristics in a dataset,and the complexity to be *** enables(SFS-Guided WOA)algorithm to choose the most appropriate EEG channels while assisting machine learning classification in its tasks and training the classifier with the ***(SFSGuided WOA)algorithm is superior in performance metrics,and statistical tests such as ANOVA and Wilcoxon rank-sum are used to demonstrate this.

关键词： Signals metaheuristics optimization feature selection multilayer perceptron support vector machines

来源：评论

学校读者我要写书评

暂无评论

Parameter Design Method of the Magnetic Coupler for Wireless Charging System Using Metamodel of Optimal Prognosis

Parameter Design Method of the Magnetic Coupler for Wireless...

引用

China International Electrical and Energy Conference (CIEEC)

作者： Jun Ma Jiafang He Zhenjie Li Shuai Dong Harbin Institute of Technology Zhengzhou Research Institute Harbin Institute of Technology Harbin China Northeast Forestry University College of Computer and Control Engineering Harbin China

ISBN: (数字)9798350359558

ISBN: (纸本)9798350359565

This paper addresses the parameter design problem of magnetic couplers and proposes a multi-objective optimization design method based on the Metamodel of Optimal Prognosis (MOP). The method involves mathematically fitting optimization objectives and design parameters using the optimal predictive metamodel, thereby establishing response surfaces for multi-objective optimization. By transforming finite element calculations of the magnetic coupler into numerical computations through fitting, the optimization process is accelerated. The parameters ultimately selected are verified through simulation, thus validating the effectiveness of the proposed optimization method.

关键词： Design methodology Fitting Optimization methods Couplers Wireless power transfer Surface charging Response surface methodology

来源：评论

学校读者我要写书评

暂无评论

Target-oriented Reference Construction for supervised cell type identification in scRNA-seq

Target-oriented Reference Construction for supervised cell t...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Wei, Xin Ma, Wenjing Wu, Zhijin Wu, Hao Brown University Department of Biostatistics United States University of Michigan Department of Biostatistics Ann Arbor United States Shenzhen University of Advanced Technology Faculty of Computer Science and Control Engineering Shenzhen China Chinese Academy of Sciences Shenzhen Institute of Advanced Technology Shenzhen China

ISBN: (纸本)9798350386226

Cell type identification is a crucial step in single-cell RNA-seq (scRNA-seq) data analysis. The supervised cell type identification method is a preferred solution due to its accuracy and efficiency. The performance of such methods highly depends on the quality of the reference data. Although there are many supervised cell type identification tools, no method currently exists for constructing reference data. Here, we develop Target-Oriented Reference Construction (TORC), a widely applicable strategy for constructing references based on target datasets in scRNA-seq supervised cell type identification. TORC focuses on alleviating differences in cell type composition between the reference and target sets. Extensive benchmarks on simulated and real data analyses demonstrate consistent improvements in cell type identification with TORC. © 2024 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Distributed model predictive control without terminal cost under inexact distributed optimization

arXiv

引用

arXiv 2025年

作者： Liu, Xiaoyu Dimarogonas, Dimos V. Liu, Changxin Dabiri, Azita De Schutter, Bart Delft Center for Systems and Control Delft University of Technology Netherlands Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Sweden

This paper presents a novel distributed model predictive control (MPC) formulation without terminal cost and a corresponding distributed synthesis approach for distributed linear discrete-time systems with coupled constraints. The proposed control scheme introduces an explicit stability condition as an additional constraint based on relaxed dynamic programming. As a result, contrary to other related approaches, system stability with the developed controller does not rely on designing a terminal cost. A distributed synthesis approach is then introduced to handle the stability constraint locally within each local agent. To solve the underlying optimization problem for distributed MPC, a violation-free distributed optimization approach is developed, using constraint tightening to ensure feasibility throughout iterations. A numerical example demonstrates that the proposed distributed MPC approach ensures closed-loop stability for each feasible control sequence, with each agent computing its control input in parallel. © 2025, CC BY.

关键词： Predictive control systems

来源：评论

学校读者我要写书评

暂无评论

Synergistically Learning Class-specific Tokens for Multi-class Whole Slide Image Classification

Synergistically Learning Class-specific Tokens for Multi-cla...

引用

2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023

作者： Sun, Pengzhong Wang, Wei Li, Xiangyu Dong, Suyu Li, Shuo Wang, Kuanquan Luo, Gongning Harbin Institute of Technology Faculty of Computing Harbin China Harbin Institute of Technology Faculty of Computing Shenzhen China Northeast Forestry University College of Computer and Control Engineering Harbin China Case Western Reserve University Case School of Engineering Cleveland United States

ISBN: (纸本)9798350337488

The application of transformer architecture in analyzing whole slide images (WSIs) has become increasingly popular due to its remarkable ability to learn complex associations. Nevertheless, a significant drawback emerges in the multiclass analysis of WSIs. The majority of the transformer-based methods available currently rely primarily on a single, class-agnostic token. This approach might not ideally capture the subtleties of class-discriminative information. To address this challenge, we present an innovative approach tailored for multi-class WSI analysis that harnesses the power of class-specific tokens. Central to our method is a novel attention mechanism designed to foster a synergistic learning relationship between patch and class tokens, enhancing the granularity of information captured and ensuring a more comprehensive representation of the WSI. Complementing this, we introduce a dynamic class-centric training strategy designed to optimize token representation learning, ensuring each token is informatively aligned with its corresponding class. Through extensive experimentation on three challenging multi-class WSI analysis datasets, our method consistently demonstrates superior performance, underscoring its potential as a robust solution for multi-class WSI analysis tasks. © 2023 IEEE.

关键词： Multi-class whole slide image analysis Multiple instance learning Transformer

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：