检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Wang, Ziming Zhang, Yuhao Lian, Shuang Cui, Xiaoxin Yan, Rui Tang, Huajin College of Computer Science and Technology Zhejiang University Hangzhou310027 China Research Center for Intelligent Computing Hardware Zhejiang Lab Hangzhou311100 China School of Integrated Circuits Peking University Beijing100871 China College of Computer Science Zhejiang University of Technology Hangzhou310014 China State Key Laboratory of Brain-Machine Intelligence Zhejiang University Hangzhou310027 China

Spiking neural networks (SNNs) operating with asynchronous discrete events show higher energy efficiency with sparse computation. A popular approach for implementing deep SNNs is ANN-SNN conversion combining both efficient training of ANNs and efficient inference of SNNs. However, the accuracy loss is usually non-negligible, especially under few time steps, which restricts the applications of SNN on latencysensitive edge devices greatly. In this paper, we first identify that such performance degradation stems from the misrepresentation of the negative or overflow residual membrane potential in SNNs. Inspired by this, we decompose the conversion error into three parts: quantization error, clipping error, and residual membrane potential representation error. With such insights, we propose a two-stage conversion algorithm to minimize those errors respectively. Besides, We show each stage achieves significant performance gains in a complementary manner. By evaluating on challenging datasets including CIFAR-10, CIFAR- 100 and ImageNet, the proposed method demonstrates the stateof- the-art performance in terms of accuracy, latency and energy preservation. Furthermore, our method is evaluated using a more challenging object detection task, revealing notable gains in regression performance under ultra-low latency when compared to existing spike-based detection algorithms. Codes are available at https://***/Windere/snn-cvt-dual-phase. Copyright © 2022, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

A DECOUPLED STRUCTURE PRESERVING SCHEME FOR THE POISSON-NERNST-PLANCK NAVIER-STOKES EQUATIONS AND ITS ERROR ANALYSIS

arXiv

引用

arXiv 2023年

作者： Yu, Ziyao Cheng, Qing Shen, Jie Wang, Changyou Department of Mathematics West LafayetteIN47907 United States Key Laboratory of Intelligent Computing and Application Tongji University Ministry of Education Department of Mathematics Tongji University Shanghai200092 China Eastern Institute of Technology Zhejiang Ningbo315200 China

We consider in this paper a numerical approximation of Poisson-Nernst-Planck-Navier-Stokes (PNP-NS) system. We construct a decoupled semi-discrete and fully discrete scheme that enjoys the properties of positivity preserving, mass conserving, and unconditionally energy stability. Then, we establish the well-posedness and regularity for the initial and (periodic) boundary value problem of the PNP-NS system under suitable assumptions on the initial data, and carry out a rigorous convergence analysis for the fully discretized scheme. We also present some numerical results to validate the positivity preserving property and the accuracy of our scheme. Copyright © 2023, The Authors. All rights reserved.

关键词： Navier Stokes equations

来源：评论

学校读者我要写书评

暂无评论

SIMULTANEOUS RECOVERY OF LEFT VENTRICULAR MOTION AND INPUT FORCES FROM MEDICAL IMAGE SEQUENCES

SIMULTANEOUS RECOVERY OF LEFT VENTRICULAR MOTION AND INPUT F...

引用

IEEE International Symposium on biomedical Imaging

作者： Heye Zhang Shan Tong Huafeng Liu Pengcheng Shi Medical Image Computing Group Hong Kong University of Science and Technology Hong Kong China State Key Laboratory of Modern Optical Instrumentation University of Zhejiang Hangzhou China School of Biomedical Engineering Southern Medical University Guangzhou China

ISBN: (纸本)9781424406715;1424406714

Since the introduction of biomechanical models into cardiac image analysis, there have been a number of efforts to estimate patient-specific cardiac kinematic functions and material properties, assuming the unobservable driving forces (a.k.a. the input forces) as known or constructible from boundary conditions. In this paper, we present a multiframe estimation framework which simultaneously recovers the cardiac motion parameters and the input forces from periodic medical image sequences. It is realized through a Kalman filter which generates the residual innovation sequences, followed by an on-line recursive least-squares filter that uses the residual innovation sequences to compute the values of input forces and to correct the estimations of cardiac kinematic functions. We demonstrate the ability of the framework on synthetic data and magnetic resonance image sequences

关键词： biomedical imaging Image sequences Kinematics Technological innovation Image motion analysis Image sequence analysis Material properties Boundary conditions Motion estimation Magnetic separation

来源：评论

学校读者我要写书评

暂无评论

NONINVASIVE IMAGING OF 3D CARDIAC ELECTROPHYSIOLOGY

NONINVASIVE IMAGING OF 3D CARDIAC ELECTROPHYSIOLOGY

引用

IEEE International Symposium on biomedical Imaging

作者： Linwei Wang Heye Zhang Ken C.L. Wong Huafeng Liu Pengcheng Shi Medical Image Computing Group Hong Kong University of Science and Technology Hong Kong China State Key Laboratory of Modern Optical Instrumentation University of Zhejiang Hangzhou China School of Biomedical Engineering Southern Medical University Guangzhou China

ISBN: (纸本)1424406714

Noninvasive imaging of cardiac electrophysiology has been an active area with increasing clinical significance. Instead of equivalent-source-based approaches, however, noninvasive 3D cardiac transmembrane potentials (TMP) mapping remains a formidable goal due to the remote and integrative nature of body surface potential recordings. We recognized the incorporation of a priori physiological knowledge as one desired paradigm and presented a model-based general Bayesian framework for 3D TMP mapping from body surface potential maps (BSPMs), based on optimal integration of a priori physiological models and patient-specific observations within their respective uncertainties. An alternative being the use of additional observations for volumetric cardiac electrophysiological information, we also worked on recovering cardiac electrical excitation pattern from tomographic medical image sequences. Furthermore, aiming for a model-based data fusion framework wherein information from BSPMs and medical image sequences are integrated, we presented the dynamic image guided mapping of 3D cardiac electrophysiology.

关键词： Heart biomedical imaging Myocardium Tomography Electrocardiography Medical diagnostic imaging Image sequences Bayesian methods Torso biomedical optical imaging

来源：评论

学校读者我要写书评

暂无评论

Auto-MatRegressor材料性能自动预测器:解放材料机器学习"调参师"

引用

Science Bulletin 2023年第12期68卷 1259-1270,M0004页

作者：刘悦王双燕杨正伟 Maxim Avdeev 施思齐 School of Computer Engineering and Science Shanghai UniversityShanghai 200444China Shanghai Engineering Research Center of Intelligent Computing System Shanghai 200444China State Key Laboratory of Advanced Special Steel School of Materials Science and EngineeringShanghai UniversityShanghai 200444China Materials Genome Institute Shanghai UniversityShanghai 200444China Zhejiang Laboratory Hangzhou 311100China Australian Nuclear Science and Technology Organisation Sydney 2232Australia School of Chemistry The University of SydneySydney 2006Australia

机器学习因其能够快速、精准拟合数据的潜在模式而被广泛应用于材料构效关系研究。然而,材料科学家往往需要进行繁琐的模型选择及参数寻优才能构建出高精度预测模型,为了解放材料机器学习"调参师",本文研发了基于元学习的材... 详细信息

机器学习因其能够快速、精准拟合数据的潜在模式而被广泛应用于材料构效关系研究。然而,材料科学家往往需要进行繁琐的模型选择及参数寻优才能构建出高精度预测模型,为了解放材料机器学习"调参师",本文研发了基于元学习的材料性能自动预测器,采集了60份文献公开数据集与60份标准数据集,基于此训练18种常用回归算法并获得其预测性能,定义与计算了27个刻画数据集特点的元特征,以此构建了一份蕴含建模经验的元数据集;同时,创建了表征数据集所属材料类型的类别树,将其嵌入基于距离的元学习算法,进一步耦合贝叶斯优化算法,实现领域知识和元数据协同驱动下的自动算法推荐和模型参数确定,实验结果表明,材料科学家仅需为新材料性能预测任务提供数据集,便可利用该预测器高效地构建具有与文献报道相当或更高预测精度的机器学习模型.

关键词：机器学习贝叶斯优化算法预测器材料科学家元数据参数寻优预测性能材料性能

来源：评论

学校读者我要写书评

暂无评论

Epilepsy Classification for Mining Deeper Relationships between EEG Channels based on GCN

Epilepsy Classification for Mining Deeper Relationships betw...

引用

Computer Vision, Image and Deep Learning (CVIDL), International Conference on

作者： Xin Chen Yuanjie Zheng Yi Niu Chengiiang Li School of Information Science and Engineering Shandong Normal University Jinan China Key Lab of Intelligent Computing and Information Security Universities of Shandong Jinan China Shandong Provincial Key Laboratory for Novel Distributed Computer Software Technology Institute of Biomedical Sciences Jinan China Shandong University of Science and Technology Jinan China

ISBN: (数字)9781728194813

ISBN: (纸本)9781728194820

Epilepsy is a brain disorder caused by abnormal discharges of neurons in brain. It is one of the most commonly studied disorders in neurology. The research of epilepsy electroencephalogram (EEG) has become a hot research topic. We find that in epilepsy EEG detection task, many previous methods focused on directly collecting the data of each channel, but these methods seldom analyse relationships between signals. Therefore, we propose the Epilepsy EEG Graph Convolutional Network EGCN, which makes full use of correlations between channels to deeply mine data information. We specifically design 5-layer graph convolutional network structure for classification of healthy and epileptic patients. The method is applied to public data set (Boon and CHB-MIT) to establish a reasonable classification model. And we compare it with some advanced algorithms. The experimental results show that the E-GCN method is superior to many existing methods in classification accuracy. In brief, the E-GCN method can be effectively used in classification and detection for epilepsy. This provides new ideas for colleagues, who study epilepsy EEG. In addition, this also provides richer experience for diagnosis of epilepsy.

关键词： Epilepsy Electroencephalography Convolution Brain modeling Feature extraction Correlation Task analysis

来源：评论

学校读者我要写书评

暂无评论

A study of 10 Rotating Radio Transients using Parkes radio telescope

arXiv

引用

arXiv 2024年

作者： Ren, Xinhui Wang, Jingbo Yan, Wenming Xie, Jintao Wang, Shuangqiang Wen, Yirong Xia, Yong Xinjiang Astronomical Observatory Chinese Academy of Sciences Xinjiang Urumqi830011 China University of Chinese Academy of Sciences Beijing100049 China Institute of Optoelectronic Technology Lishui University Zhejiang Lishui323000 China Xinjiang Key Laboratory of Radio Astrophysics Xinjiang Urumqi830011 China Research Center for Intelligent Computing Platforms Zhejiang Laboratory Zhejiang Hangzhou311100 China

Rotating Radio Transients (RRATs) are a relatively new subclass of pulsars that emit detectable radio bursts sporadically. We conducted an analysis of 10 RRATs observed using the Parkes telescope, with 8 of these observed via the Ultra-Wideband Receiver. We measured the burst rate and produced integrated profiles spanning multiple frequency bands for 3 RRATs. We also conducted a spectral analysis on both integrated pulses and individual pulses of 3 RRATs. All of their integrated pulses follow a simple power law, consistent with the known range of pulsar spectral indices. Their average spectral indices of single pulses are -0.9, -1.2, and -1.0 respectively, which are within the known range of pulsar spectral indices. Additionally, we find that the spreads of single-pulse spectral indices for these RRATs (ranging from -3.5 to +0.5) are narrower compared to what has been observed in other RRATs (Shapiro-Albert et al. 2018;Xie et al. 2022). It is notable that the average spectral index and scatter of single pulses are both relatively small. For the remaining 5 RRATs observed at the UWL receiver, we also provided the upper limits on fluence and flux density. In addition, we obtained the timing solution of PSR J1709-43. Our analysis shows that PSRs J1919+1745, J1709-43 and J1649-4653 are potentially nulling pulsars or weak pulsars with sparse strong pulses. © 2024, CC BY.

关键词： Pulsars

来源：评论

学校读者我要写书评

暂无评论

Red blood cell membrane-derived phototherapeutic nanodiscs: A new platform for enhanced phototherapy

引用

Journal of Controlled Release 2025年 384卷 113873页

作者： Deli Zhuge Li Li Xueying Sun Hui Liang Chenjie Jin Ailing Lu Wenli Gao Yutong Zhong Wenlu Li Sihao Chen Fang Wang Linzhi Yan Weiyang Meng Xiaoji Lin Xufei Zhang Yong Liu Yuanfeng Li Yingzheng Zhao Xiang Zhang Mengchun Chen Yijie Chen Department of Pharmaceutics School of Pharmaceutical Sciences of Wenzhou Medical University Wenzhou 325035 China Department of Obstetrics and Gynecology The Second Affiliated Hospital of Wenzhou Medical University Wenzhou 325027 China Cixi Biomedical Research Institute Wenzhou Medical University Ningbo 315302 China Guangxi Technology Innovation Cooperation Base of Prevention and Control Pathogenic Microbes with Drug Resistance Youjiang Medical University for Nationalities Baise 533000 China Department of Emergency Medicine The Second Affiliated Hospital of Wenzhou Medical University Wenzhou 325027 China Department of Chemotherapy and Radiotherapy The Second Affiliated Hospital of Wenzhou Medical University Wenzhou 325027 China Zhejiang Engineering Research Center for Innovation and Application of Intelligent Radiotherapy Technology The Second Affiliated Hospital of Wenzhou Medical University Wenzhou 325027 China Experimental Animal Center Wenzhou Medical University Wenzhou 325027 China State Key Laboratory of Medicinal Chemical Biology Key Laboratory of Functional Polymer Materials of Ministry of Education and Institute of Polymer Chemistry College of Chemistry Nankai University Tianjin 300071 China Translational Medicine Laboratory The First Affiliated Hospital of Wenzhou Medical University Wenzhou 325035 China Department of Clinical Laboratory The Fifth Hospital of Rui'an Rui'an 325000 China Department of Pharmacy The Second Affiliated Hospital of Wenzhou Medical University Wenzhou 325027 China

Phototherapy holds great potential for treating cancer and infections but faces limitations related to photosensitizer accumulation, tissue penetration, and diminished photo-conversion efficiency, particularly in deep-seated tumors and infections. Here, a biomimetic phototherapeutic nanodisc platform consisting of erythrocyte membranes and the photosensitizer IR780 is developed. With the advantages of the ultra-small size and exceptional biosafety of cell membrane-derived nanodiscs, this platform facilitates efficient accumulation and deep tissue penetration at disease sites. Upon near-infrared (NIR) irradiation, IR780 delivered via the nanodisc exhibits enhanced photothermal conversion efficiency, markedly inhibiting tumor growth in an orthotopic 4T1 breast cancer model and reducing bacterial load in a methicillin-resistant Staphylococcus aureus (MRSA) skin infection model. Furthermore, the nanodisc platform demonstrates outstanding biocompatibility in mice. In conclusion, this nanodisc system significantly extends the functional potential of cellular nanodiscs, presenting a promising strategy to address the challenges of photosensitizer delivery and biosafety in phototherapeutic applications.

关键词： Biomimetic nanomedicine Cellular nanoparticle Nanodisc Phototherapy Red blood cell membrane

来源：评论

学校读者我要写书评

暂无评论

Ultra-High Dynamic Extinction Ratio Electro-Optical Modulator with Coupled Microring on SOI Platform

Ultra-High Dynamic Extinction Ratio Electro-Optical Modulato...

引用

Asia Communications and Photonics Conference and Exhibition (ACP)

作者： Zhuo Cheng Bigeng Chen Chunlei Sun Maoliang Wei Shaoliang Yu Lan Li Hongtao Lin Yunjiang Rao Research Center for Optical Fiber Sensing Zhejiang Lab Hangzhou China Key Laboratory of 3D Micro/Nano Fabrication and Characterization of Zhejiang Province School of Engineering Westlake University Hangzhou China State Key Laboratory of Modern Optical Instrumentation College of Information Science and Electronic Engineering Zhejiang University Hangzhou China Research Center for Intelligent Optoelectronic Computing Zhejiang Lab Hangzhou China Key Lab of Optical Fiber Sensing & Communications University of Electronic Science &Technology of China Chengdu China

A 5 th -order coupled microring electro-optical modulator with PIN structures is proposed and experimentally demonstrated on SOI integrated photonics platform. Ultra-high dynamic extinction ratio (ER) up to 60 dB is achieved benefiting from the high-order optical band-pass filter design. The device size on chip is only 400×220 μm 2 including electrodes and the driving voltage is 2.1 V corresponding to 0.23 W power consumption. Such integrated modulators would be promising in building compact and low-power distributed optical fiber sensing systems using low-background-noise optical pulses.

关键词： Optical filters Optical fibers Power demand Voltage Electro-optic modulators Extinction ratio Pins

来源：评论

学校读者我要写书评

暂无评论

Stability Analysis and Hopf Bifurcation Research for DNA Strand Displacement with Time Delay

Stability Analysis and Hopf Bifurcation Research for DNA Str...

引用

Symposia and Workshops on Ubiquitous, Autonomic and Trusted computing, UIC-ATC

作者： Yanhong Liu Hui Lv Changjun Zhou Zhixiang Yin Xianwen Fang Zhonglong Zheng Qiang Zhang Key Laboratory of Advanced Design and Intelligent Computing Ministry of Education Dalian University Dalian China School of Mathematics and Big Data Anhui University of Science and Technology Huaian China College of Mathematics Zhejiang Normal University Jinhua China Department of Computer Science and Technology Dalian University of Technology Dalian China

ISBN: (纸本)9781538693810;9781538693803

In this paper, a nonlinear system with time delay mode for DNA strand displacement based on toehold exchange firstly is proposed. The boundedness of all the state variables of the DNA strand displacement system is proved. After that, local stability analysis is performed around the positive equilibrium point to obtain a necessary and sufficient condition for local stability, which depend on the coefficients of the characteristic equation corresponding to linearization of the system. In addition, the existence of the Hopf bifurcation is analyzed, which shows that the time delay parameter will guarantee that the system is stable within a certain range. However, Hopf bifurcation and chaos occur when the time delay parameter increases continuously and even exceeds the critical value. At last, numerical simulations have verified the correctness and validity of the DNA strand displacement studies.

关键词：

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：