检索结果-南通市图书馆

第13届中国系统仿真技术及其应用学术年会

作者： Kenji NAKAYAMA Akihiro HIRANO Graduate School of Natural Science and Technology Kanazawa University

In this paper, a novel method was proposed based on wavelet packet decomposition （WPD） for extracting the brainwave features from EEG signals, and support vector machines （SVMs） for mental task classification. Besides, an original voting mechanism was put forward for the final decision of classification. Moreover, some useful preprocessing methods were also applied. Segmentation along the time axis for fast response and increasing the correct classification rate, nonlinear and linear normalization for emphasizing the important information in small magnitude and optimizing data distribution. Furthermore, an especial grouping method was put forward to realize optimizing several parameters automatically. The simulation results have proved the effectiveness of the proposed method.

关键词： brain computer interface (BCI) wavelet packet decomposition (WPD) support vector machines (SVMs) voting mechanism grouping method

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Incentive Compatibility of voting Procedure

引用

Systems Science and Systems Engineering 1995年第1期5卷 49-54页

作者： LUO Yunfeng YUE Chaoyuan and CHEN Ting(Institute of Systems Engineering, Huazhong University of Science and Technology Wuhan Hubei,People's Republic of China,430074)

The present paper investigates the problem of incentive compatibility of voting mechanism and shows that the mechanism of approval voting is incentive-compatible,i.e. its mechanism gives voters incentive for voting si... 详细信息

关键词： incentive-compatibility voting mechanism approval voting voting procedure stable strategy set

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

A new physical unclonable function architecture

引用

Journal of Semiconductors 2015年第3期36卷 121-126页

作者：白创邹雪城戴葵 School of Optical and Electronic Information Huazhong University of Science and Technology

This paper describes a new silicon physical unclonable function （PUF） architecture that can be fabri- cated on a standard CMOS process. Our proposed architecture is built using process sensors, difference amplifier, comparator, voting mechanism and diffusion algorithm circuit. Multiple identical process sensors are fabricated on the same chip. Due to manufacturing process variations, each sensor produces slightly different physical charac- teristic values that can be compared in order to create a digital identification for the chip. The diffusion algorithm circuit ensures further that the PUF based on the proposed architecture is able to effectively identify a population of ICs. We also improve the stability of PUF design with respect to temporary environmental variations like temperature and supply voltage with the introduction of difference amplifier and voting mechanism. The PUF built on the proposed architecture is fabricated in 0.18 μm CMOS technology. Experimental results show that the PUF has a good output statistical characteristic of uniform distribution and a high stability of 98.1% with respect to temperature variation from -40 to 100 ℃, and supply voltage variation from 1.7 to 1.9 V.

关键词： physical unclonable functions digital identification process sensors voting mechanism diffusion algorithm

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Classifying Hematoxylin and Eosin Images Using a Super-Resolution Segmentor and a Deep Ensemble Classifier

引用

Intelligent Automation & Soft Computing 2023年第8期37卷 1983-2000页

作者： P.Sabitha G.Meeragandhi Department of Computer Science and Engineering Sathyabama Institute of Science and TechnologyChennaiTamilnaduIndia

Developing an automatic and credible diagnostic system to analyze the type,stage,and level of the liver cancer from Hematoxylin and Eosin(H&E)images is a very challenging and time-consuming endeavor,even for experienced pathologists,due to the non-uniform illumination and *** several Machine Learning(ML)and Deep Learning(DL)approaches are employed to increase the performance of automatic liver cancer diagnostic systems,the classi-ﬁcation accuracy of these systems still needs signiﬁcant improvement to satisfy the real-time requirement of the diagnostic *** this work,we present a new Ensemble Classiﬁer(hereafter called ECNet)to classify the H&E stained liver histopathology images *** proposed model employs a Dropout Extreme Learning Machine(DrpXLM)and the Enhanced Convolutional Block Attention Modules(ECBAM)based residual *** applies voting mechanism(VM)to integrate the decisions of individual classiﬁers using the average of probabilities ***,the nuclei regions in the H&E stain are seg-mented through Super-resolution Convolutional Networks(SrCN),and then these regions are fed into the ensemble DL network for classiﬁ*** effectiveness of the proposed model is carefully studied on real-world *** results of our meticulous experiments on the Kasturba Medical College(KMC)liver dataset reveal that the proposed ECNet signiﬁcantly outperforms other existing classiﬁca-tion networks with better accuracy,sensitivity,speciﬁcity,precision,and Jaccard Similarity Score(JSS)of 96.5%,99.4%,89.7%,95.7%,and 95.2%,*** obtain similar results from ECNet when applied to The Cancer Genome Atlas Liver Hepatocellular Carcinoma(TCGA-LIHC)dataset regarding accuracy(96.3%),sensitivity(97.5%),speciﬁcity(93.2%),precision(97.5%),and JSS(95.1%).More importantly,the proposed ECNet system consumes only 12.22 s for training and 1.24 s for ***,we carry out the Wilcoxon statistical test to determine whether the ECN

关键词： Convolutional block attention modules dropout ELM ensemble classiﬁer liver cancer segmentation voting mechanism

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Silicon Melt Liquid Level Detection Based on Improved Laser Trigonometry

Silicon Melt Liquid Level Detection Based on Improved Laser ...

引用

第37届中国控制会议

作者： Xinyu Zhang Ding Liu Simi Wang Xiaoguo Zhao Lei Jiang National & Local Joint Engineering Research Center of Crystal Growth Equipment and System Integration Xi'an University of Technology Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing

In order to improve the robustness of laser triangulation to detect the liquid level of silicon melt, this paper firstly proposes a method of calculating the laser spot coordinates based on the voting mechanism. The vote is taken according to the coordinates of small laser spots, which are formed by the effect of liquid surface fluctuation on the line laser in the liquid level measurement image. Secondly, the Kalman filter method is used to correct the liquid level measurement data and compensate the missing data. Then the linear conversion is performed to obtain the liquid level value. Finally, the experimental results show that this method can effectively improve the robustness of the liquid level measurement by the laser triangulation method, and avoid the generation of impulse noise. The introduction of the Kalman filter can accurately correct the level measurement data and compensate for missing data.

关键词： Single crystal furnace Liquid level detection Coordinate calculation voting mechanism Kalman filter

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

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：