检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Ma, Chenxiang Chen, Xinyi Li, Yanchen Yang, Qu Wu, Yujie Li, Guoqi Pan, Gang Tang, Huajin Tan, Kay Chen Wu, Jibin Department of Data Science and Artificial Intelligence The Hong Kong Polytechnic University Hong Kong Department of Computing The Hong Kong Polytechnic University Hong Kong Department of Electrical and Computer Engineering National University of Singapore 119077 Singapore Institute of Automation Chinese Academy of Sciences Beijing100045 China State Key Laboratory of Brain-Machine Intelligence College of Computer Science and Technology MOE Frontier Science Center for Brain Science and Brain-Machine Integration Zhejiang University Hangzhou310027 China

Temporal processing is fundamental for both biological and artificial intelligence systems, as it enables the comprehension of dynamic environments and facilitates timely responses. Spiking Neural Networks (SNNs) excel in handling such data with high efficiency, owing to their rich neuronal dynamics and sparse activity patterns. Given the recent surge in the development of SNNs, there is an urgent need for a comprehensive evaluation of their temporal processing capabilities. In this paper, we first conduct an in-depth assessment of commonly used neuromorphic benchmarks, revealing critical limitations in their ability to evaluate the temporal processing capabilities of SNNs. To bridge this gap, we further introduce a benchmark suite consisting of three temporal processing tasks characterized by rich temporal dynamics across multiple timescales. Utilizing this benchmark suite, we perform a thorough evaluation of recently introduced SNN approaches to elucidate the current status of SNNs in temporal processing. Our findings indicate significant advancements in recently developed spiking neuron models and neural architectures regarding their temporal processing capabilities, while also highlighting a performance gap in handling long-range dependencies when compared to state-of-the-art non-spiking models. Finally, we discuss the key challenges and outline potential avenues for future research. Copyright © 2025, The Authors. All rights reserved.

关键词： Spatio-temporal data

来源：评论

学校读者我要写书评

暂无评论

Examining the Fourier Spectrum of Speech Signal from a Time-Frequency Perspective for Automatic Depression Level Prediction

引用

IEEE Transactions on Affective Computing 2025年

作者： Niu, Mingyue Tao, Jianhua He, Yongjun Zhang, Shiqing Li, Ming YanShan University School of Information Science and Engineering Qinhuangdao066004 China Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province China Tsinghua University Department of Automation Bejing100190 China University of Chinese Academy of Sciences School of Artificial Intelligence Beijing100049 China Harbin Institute of Technology School of Computer Science and Technology Harbin150001 China Taizhou University Institute of Intelligent Information Processing Taizhou318000 China Zhejiang Normal University Zhejiang Key Laboratory of Intelligent Education Technology and Application Jinhua321004 China Zhejiang Institute of Optoelectronics Jinhua321004 China

Currently, many studies use Fourier amplitude spectra of speech signals to predict depression levels. However, those works often treat Fourier amplitude spectra as images or sequences to capture depression cues using convolutional neural networks or multilayer perceptrons. Therefore, they ignore the complex element composition and time-frequency attributes of Fourier spectra, which is not conducive to capturing the differences among individuals with different depression levels. For this reason, we construct a Time-Frequency Self-Embedding (TFSE) module, which not only stores the correlation relationship among real (imaginary) parts of Fourier spectra of different subjects from the time-frequency perspective, but also maintain the physical properties of data through the weight embedding process. Besides, Global Average Pooling (GAP) or linear layers are difficult to balance both temporal and frequency dimensions in the vectorization process. Therefore, we construct a Time-Frequency Tensor Vectorization (TFTV) module, which summarizes each channel along time and frequency dimensions, and then generates the vectorization result by integrating various channels. In this way, we combine TFSE and TFTV modules to form our SpectrumFormer model for predicting depression levels. Evaluation indicators on AVEC 2013 and AVEC 2014 depression databases imply the progressiveness of our model. © 2010-2012 IEEE.

关键词： Depression level prediction Real and imaginary parts Tensor vectorization Time-frequency attributes

来源：评论

学校读者我要写书评

暂无评论

A Design of Gas Turbine computer-Integrated Control System Based on Energy Cycle Optimization 4

A Design of Gas Turbine Computer-Integrated Control System B...

引用

4th International Conference on Power and Renewable Energy, ICPRE 2019

作者： Xu, Jianqiao Zhang, Fucheng Stopakevych, A.O. Institute of Automation and Computer Integration Odessa National Academy of Telecommunications China Scholarship Council Odessa Ukraine Institute of Automation Ukrainian National Makarov Ship University China Scholarship Council Nikolayev Ukraine Institute of Automation and Computer Integration Odessa National Academy of Telecommunications Odessa Ukraine

ISBN: (纸本)9781728145747

In this study, a gas turbine computer integrated control system based on energy cycle optimization is designed to solve the problem of large energy loss caused by gas turbine during normal operation. At first, the circulation conditions of the internal energy of the gas turbine are analyzed through the thermodynamic structure of the gas turbine. Then, a ring structure is added to enhance the operability of the fuel supply system. Furthermore, a SCADA monitoring and control system for energy cycle are designed based on their unique system architecture. Finally, the hierarchical control principle of the system is explained from the perspective of system organization to facilitate future system development. © 2019 IEEE.

关键词： Gas turbines

来源：评论

学校读者我要写书评

暂无评论

Asymptotic Solution for Coupled Heat and Mass Transfer During the Solidification of High Water Content Materials

引用

Transactions of Tianjin University 2010年第4期16卷 239-243页

作者：齐德瑄何凯杜如虚张义同 School of Mechanical Engineering Tianjin University Institute of Advanced Integration Technology Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Department of Automation and Computer-Aided Engineering The Chinese University of Hong Kong

This paper focuses on obtaining an asymptotic solution for coupled heat and mass transfer problem during the solidification of high water content materials. It is found that a complicated function involved in governing equations can be approached by Taylor polynomials unlimitedly, which leads to the simplification of governing equations. The unknown functions involved in governing equations can then be approximated by Chebyshev polynomials. The coefficients of Chebyshev polynomials are determined and an asymptotic solution is obtained. With the asymptotic solution, the dehydration and freezing fronts of materials are evaluated easily, and are consistent with numerical results obtained by using an explicit finite difference method.

关键词： heat transfer mass transfer solidification asymptotic analysis

来源：评论

学校读者我要写书评

暂无评论

Geometric algorithm for point projection and inversion onto Bézier surfaces

引用

中国高等学校学术文摘·计算机科学 2009年第4期3卷 472-476页

作者： Jinting XU Weijun LIU Jianhuang WU Hongyou BIAN Lun LI School of Automotive Engineering Daiian University of TechnologyDaiian 116024China Shenyang Institute of Automation Chinese Academy of SciencesShenyang 110016China Shenyang Institute of Automation Chinese Academy of SciencesShenyang 110016China Centre for Human Computer Interaction Shenzhen Institution of Advanced Integration TechnologyChinese Academy of SciencesShenzhen 518067China

This paper presents an accurate and efficient method for the computation of both point projection and inversion onto Bézier ***,these two problems are formulated in terms of solution of a polynomial equation with u and v variables expressed in the Bernstein ***,based on subdivision of the Bézier surface and the recursive quadtree decomposition,a novel solution method is *** computation of point projection is shown to be equivalent to the geometrically intuitive intersection of a surface with the u-v ***,by comparing the distances between the test point and the candidate points,the closest point is *** illustrate the feasibility of this method.

关键词： point projection point inversion Bézier surface

来源：评论

学校读者我要写书评

暂无评论

Position Measurement Based Slave Torque Feedback Control for Teleoperation Systems With Time-Varying Communication Delays

引用

IEEE/CAA Journal of Automatica Sinica 2023年第2期10卷 388-402页

作者： Xian Yang Jing Yan Changchun Hua Xinping Guan the Institute of Information Science and Engineering Yanshan University the Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province Qinhuangdao 066004China IEEE the Institute of Electrical Engineering Yanshan UniversityQinhuangdao 066004China the Department of Automation Shanghai Jiao Tong UniversityShanghai 200240China

Bilateral teleoperation system is referred to as a promising technology to extend human actions and intelligence to manipulating objects *** the tracking control of teleoperation systems,velocity measurements are necessary to provide feedback ***,due to hardware technology and cost constraints,the velocity measurements are not always *** addition,the time-varying communication delay makes it challenging to achieve tracking *** paper provides a solution to the issue of real-time tracking for teleoperation systems,subjected to unavailable velocity signals and time-varying communication *** order to estimate the velocity information,immersion and invariance(I&I)technique is employed to develop an exponential stability velocity *** the proposed velocity observer,a linear relationship between position and observation state is constructed,through which the need of solving partial differential and certain integral equations can be ***,the mean value theorem is exploited to separate the observation error terms,and hence,all functions in our observer can be analytically *** the estimated velocity information,a slave-torque feedback control law is presented.A novel Lyapunov-Krasovskii functional is constructed to establish asymptotic tracking *** particular,the relationship between the controller design parameters and the allowable maximum delay values is ***,simulation and experimental results reveal that the proposed velocity observer and controller can guarantee that the observation errors and tracking error converge to zero.

关键词： Asymptotic stability bilateral teleoperation time-varying delay velocity observer

来源：评论

学校读者我要写书评

暂无评论

Two Stages Segmentation Algorithm of Breast Tumor in DCE-MRI Based on Multi-Scale Feature and Boundary Attention Mechanism

引用

computers, Materials & Continua 2024年第7期80卷 1543-1561页

作者： Bing Li Liangyu Wang Xia Liu Hongbin Fan Bo Wang Shoudi Tong School of Automation Harbin University of Science and TechnologyHarbin150080China Heilongjiang Provincial Key Laboratory of Complex Intelligent System and Integration Harbin150080China School of Computer Engineering Technology Guangdong Institute of Science and TechnologyZhuhai519090China

Nuclearmagnetic resonance imaging of breasts often presents complex *** tumors exhibit varying sizes,uneven intensity,and indistinct *** characteristics can lead to challenges such as low accuracy and incorrect segmentation during tumor ***,we propose a two-stage breast tumor segmentation method leveraging multi-scale features and boundary attention ***,the breast region of interest is extracted to isolate the breast area from surrounding tissues and ***,we devise a fusion network incorporatingmulti-scale features and boundary attentionmechanisms for breast tumor *** incorporate multi-scale parallel dilated convolution modules into the network,enhancing its capability to segment tumors of various sizes through multi-scale convolution and novel fusion ***,attention and boundary detection modules are included to augment the network’s capacity to locate tumors by capturing nonlocal dependencies in both spatial and channel ***,a hybrid loss function with boundary weight is employed to address sample class imbalance issues and enhance the network’s boundary maintenance capability through additional *** was evaluated using breast data from 207 patients at RuijinHospital,resulting in a 6.64%increase in Dice similarity coefficient compared to the *** results demonstrate the superiority of the method over other segmentation techniques,with fewer model parameters.

关键词： Dynamic contrast-enhanced magnetic resonance imaging(DCE-MRI) breast tumor segmentation multi-scale dilated convolution boundary attention the hybrid loss function with boundary weight

来源：评论

学校读者我要写书评

暂无评论

A Design of Gas Turbine computer-Integrated Control System Based on Energy Cycle Optimization

A Design of Gas Turbine Computer-Integrated Control System B...

引用

IEEE International Conference on Power and Power and Renewable Energy (ICPRE)

作者： Jianqiao Xu Fucheng Zhang A.O. Stopakevych Institute of Automation and Computer Integration Odessa National Academy of Telecommunications China Scholarship Council Odessa Ukraine Institute of Automation Ukrainian National Makarov Ship University China Scholarship Council Nikolayev Ukraine Institute of Automation and Computer Integration Odessa National Academy of Telecommunications Odessa Ukraine

ISBN: (数字)9781728145747

ISBN: (纸本)9781728145754

关键词： Turbines Control systems Fuels Combustion Optimization Monitoring Temperature measurement

来源：评论

学校读者我要写书评

暂无评论

Corrections to “Brain-Inspired Computing: A Systematic Survey and Future Trends”

引用

Proceedings of the IEEE 2025年第12期112卷 1850-1850页

作者： Guoqi Li Lei Deng Huajin Tang Gang Pan Yonghong Tian Kaushik Roy Wolfgang Maass Institute of Automation Chinese Academy of Sciences Beijing China Key Laboratory of Brain Cognition and Brain-inspired Intelligence Technology Chinese Academy of Sciences Beijing China Peng Cheng Laboratory Shenzhen China Department of Precision Instrument Tsinghua University Beijing China State Key Laboratory of Brain-Machine Intelligence College of Computer Science and Technology MOE Frontier Science Center for Brain Science and Brain-Machine Integration Zhejiang University Hangzhou China Department of Computer Science Peking University Beijing China School of Electrical and Computer Engineering Purdue University West Lafayette IN USA School of Computer Science Graz University of Technology Graz Austria

Presents corrections to the paper, (Corrections to “Brain-Inspired Computing: A Systematic Survey and Future Trends”).

关键词： Artificial intelligence Computational modeling Brain modeling Biological system modeling Surveys computer architecture Benchmark testing Bio-inspired computing Neuromorphic engineering Sensors Neural networks Software tools

来源：评论

学校读者我要写书评

暂无评论

Object-Specific Rapid Feature Adaption for One-Shot Contour Primitive of Interest Extraction

Object-Specific Rapid Feature Adaption for One-Shot Contour ...

引用

2023 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2023

作者： Qin, Fangbo Fang, Cheng Li, Jun Zhang, Wei Chinese Academy of Sciences Institute of Automation Beijing100190 China Northwestern Polytechnical University School of Computer Science Xi'an710129 China National Key Laboratory of Special Vehicle Design and Manufacturing Integration Technology Inner Mongolia Baotou014032 China

ISBN: (纸本)9798350327182

The one-shot contour primitive of interest (CPI) extraction method is meaningful for flexible machine vision, which can obtain the target CPI on a novel object under the guidance of a support image. The one-shot guidance is based on an object-agnostic feature extractor and the feature comparison in a metric space. Therefore, the discrimination and generalization abilities of the object-agnostic feature extractor are essential to the one-shot CPI extraction. In this paper, we propose an object-specific rapid feature adaption method to enhance a trained CPI extraction network. Three lightweight feature adaption modules are designed to adjust the features specifically for the present object type. A module can be flexibly plugged into a trained network at three different candidate positions, to influence the network's final outputs. The parameters of the module are learned with the annotated support sample and only tens of optimization steps in several seconds. Thus, although the feature adaption module only works for a specific object, it can be deployed flexibly and rapidly. The effectiveness of the proposed method is validated with a series of experiments. © 2023 IEEE.

关键词： computer vision

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：