检索结果-内蒙古大学图书馆

2023 IEEE Signal Processing in Medicine and Biology Symposium, SPMB 2023

作者： Liu, M. Wang, S. Beyette, F.R. University of Georgia School of Electrical and Computer Engineering AthensGA United States Hebei Normal Univ. of Sci. & Tech Sch. of Math. and Info. Sci. & Tech Hebei Qinhuangdao China Yanshan University School of Information Science and Engineering Hebei Qinhuangdao China

ISBN: (纸本)9798350341256

As one kind of Event-Related Potentials (ERPs), P300 plays an important role in studying neural activities and cognitive processes, and lays the foundation for P300 speller - the Brain Computer Interface (BCI) working by detecting P300. However, due to P300's high subject variability and low Signal Noise Ratio (SNR), it's always a challenge to do P300 detection. Convolutional Neural Networks (CNNs) have been widely recognized as effective methods for P300 detection, leading to the development of increasingly complex CNN architectures for P300 detection in recent years. However, this paper takes a different approach by proposing the bantamweight CNN (BCNN), the simplest and fast-training CNN for P300 detection. BCNN comprises only one convolutional filter and a total of 141 parameters. Surprisingly, it achieves state-of-the-art performance after just 2 epochs of training, making it an exceptionally lightweight and fast CNN for P300 detection. BCNN not only provides new ideas for CNN design, but also effectively address resource and time constrained situations. © 2023 IEEE.

关键词： Brain computer interface

来源：评论

学校读者我要写书评

暂无评论

Design of intelligent transportation system based on a genetic algorithm and distributed computing

Engineering Intelligent Systems

引用

Engineering Intelligent Systems 2021年第2期29卷 129-136页

作者： Yuqing, Wei Xing, Gao Sch. of Math. and Info. Science and Technology Hebei Normal University of Science and Technology Hebei Qinhuangdao066004 China

With the development of society the Internet and artificial intelligence technology have been increasingly used in human life. When people use the Internet and artificial intelligence technology, the historical data generated is saved, which not only has a high scientific research value, but also has a high commercial value. By making full use of this data, the income of the enterprise can be effectively improved, the costs of the enterprise can be reduced, the competitiveness of the enterprise in the whole field can be improved, and most importantly the development potential of the enterprise can be improved. However, the biggest difficulty is that it is difficult to extract beneficial data to the development of enterprises quickly and accurately. Firstly, as the dataset is so large, and the amount of data with practical value for enterprises is scarce, there is also no rule to follow within the distribution. Therefore, it is very difficult to quickly extract the data that is beneficial to the development of enterprises. Secondly, the development of data extraction technology is not mature, and the efficiency and accuracy of data extraction are low. Current transportation big data has the characteristics of multi-source heterogeneous data, complex data types and high requirements for real-time data. Using traditional data extraction methods to extract useful traffic info.mation from big data has been unable to keep up with the development of the times and social needs. This project aims to develop an intelligent transportation big data monitoring platform based on Ambari technology to improve the intensity of traffic supervision and the utilization of traffic data resources. ©2021 CRL Publishing Ltd.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

BCNN: A Bantamweight Convolutional Neural Network for P300 Detection

BCNN: A Bantamweight Convolutional Neural Network for P300 D...

引用

IEEE Signal Processing in Medicine and Biology Symposium (SPMB)

作者： M. Liu S. Wang F. R. Beyette School of Electrical and Computer Engineering University of Georgia Athens Georgia USA Sch. of Math. and Info. Sci. & Tech Hebei Normal Univ. of Sci. & Tech Qinhuangdao Hebei China School of Information Science and Engineering Yanshan University Qinhuangdao Hebei China

As one kind of Event-Related Potentials (ERPs), P300 plays an important role in studying neural activities and cognitive processes, and lays the foundation for P300 speller – the Brain Computer Interface (BCI) working by detecting P300. However, due to P300’s high subject variability and low Signal Noise Ratio (SNR), it’s always a challenge to do P300 detection. Convolutional Neural Networks (CNNs) have been widely recognized as effective methods for P300 detection, leading to the development of increasingly complex CNN architectures for P300 detection in recent years. However, this paper takes a different approach by proposing the bantamweight CNN (BCNN), the simplest and fast-training CNN for P300 detection. BCNN comprises only one convolutional filter and a total of 141 parameters. Surprisingly, it achieves state-of-the-art performance after just 2 epochs of training, making it an exceptionally lightweight and fast CNN for P300 detection. BCNN not only provides new ideas for CNN design, but also effectively address resource and time constrained situations.

关键词：

来源：评论

学校读者我要写书评

暂无评论

On orthogonal designs in order 48

引用

Journal of Statistical Planning and Inference 2005年第1期128卷 311-325页

作者： Holzmann, W.H. Kharaghani, H. Seberry, Jennifer Tayfeh-Rezaie, B. Department of Math./Computer Science University of Lethbridge Lethbridge Alta. T1K 3M4 Canada Sch. of Info. Technol./Computer Sci. University of Wollongong Wollongong NSW 2522 Australia Inst. Studies Theoret. Phys./Math. Tehran P.O. Box 19395-5746 Iran

关键词： Additive property for matrices Amicable set of matrices Autocorrelation Orthogonal designs Weighing matrices

来源：评论

学校读者我要写书评

暂无评论

Signal period analysis based on hilbert-huang transform and its application to texture analysis

Signal period analysis based on hilbert-huang transform and ...

引用

Proceedings - Third International Conference on Image and Graphics

作者： Yang, Zhihua Qi, Dongxu Yang, Lihua Sch. of Info. Science and Technology Sun Yat-sen University Guangzhou 510275 China Faculty of Information Technology Macao Univ. of Sci. and Technology Macao Sch. of Math. and Computing Science Sun Yat-sen University Guangzhou 510275 China

ISBN: (纸本)0769522440

An approach to analyze the period of a signal based on Hilbert-Huang Transform is presented in this paper. For an approximately periodic signal which contains plenty of high frequency components, the relation between its period and its main frequency is established. Our main result is that, for an approximately periodic signal which contains plenty of high frequency components, its period can be estimated accurately according to its main-frequency distribution. By applying the technique on texture analysis, a novel method to extract the perodicity features of a texture image is developed, which can be used in texture classification, segmentation, recognition and other applications. © 2004 IEEE.

关键词： Signal processing

来源：评论

学校读者我要写书评

暂无评论

Face recognition using SVM decomposition methods

Face recognition using SVM decomposition methods

引用

2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Qiao, Hong Zhang, Shaoyan Zhang, Bo Keane, John Institute of Automation Chinese Academy of Science Manchester United Kingdom School of Informatics Manchester University Manchester United Kingdom Sch. of Math. and Info. Science Coventry University Coventry United Kingdom

ISBN: (纸本)0780384636

Support Vector Machines (SVM) decomposition methods were proposed to solve high dimensional and/or large data classification problems. Two major decomposition algorithms: Karush-kuhn-Tucker (KKT) condition based algorithm, and 'Joachims' decomposition algorithm are popularly adopted. In this paper, both these two decomposition methods are analyzed and applied into face recognition with three basic mapping kernels. Numerical results showed that: a) Face recognition with SVM performs better accuracy than other existed methods;b) The decomposition methods can perform face recognition efficiently;c) Joachims decomposition method has better accuracy than that of decomposition algorithm based on KKT condition;d) Linear kernel can provide much higher recognition accuracy than polynomial and slightly better accuracy then Gaussian radial based function (RBF) kernel;Also due to the fact that the linear kernel method is much simpler than others, it is most suitable for face recognition.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Stability analysis for linear time-varying switched systems based on matrix measure

Stability analysis for linear time-varying switched systems ...

引用

WCICA 2004 - Fifth World Congress on Intelligent Control and Automation, Conference Proceedings

作者： Jing, Li Gao, Liqun Sch. of Info. Sci. and Engineering Northeastern University Shenyang 110004 Sch. of Math. and System Science Shenyang Normal University Shenyang 110034

ISBN: (纸本)0780382730

Analyze stability of switched systems with linear and time-varying system matrices. First, present two concepts: equal-time interval (ETI) switching sequence and periodic switching sequence. Then under periodic switching sequences derive sufficient conditions for stability and instability of the systems based on matrix measure theory. Further simplify the conditions for time-invariant ones. Last give two examples to illustrate the effectiveness of the results.

关键词： Time varying systems

来源：评论

学校读者我要写书评

暂无评论

A five-year followup of hand function and activities of daily living in systemic sclerosis (scleroderma)

引用

Journal of Hand Therapy 2004年第4期17卷 407-411页

作者： Poole, Janet L. Watzlaf, Valerie J.M. Depts. of Orthopaedics and Rehab. Occup. Therapy Graduate Program Univ. New Mex. Albuquerque New M. United States Dept. of Hlth. Info. Management Sch. of Hlth. and Rehab. Sciences Univ. Pittsburgh Pittsburgh P. United States Dept. of Math. and Computer Science Duquesne University Pittsburgh Pennsylvania United States Occup. Therapy Graduate Program Dept. Orthopaedics Rehab. Univ. N. MSC 09 5240 Albuquerque N. United States

The purpose of this study was to identify hand factors that change over a five-year period that may be risk factors for the development of functional disability in persons with systemic sclerosis (scleroderma). Sixty individuals with scleroderma were administered assessments of grip and pinch strength, joint range of motion, and pain, and were observed for the presence of digital ulcers, digital scars, calcium deposits, puffy fingers, and tendon friction rubs. Matched-pairs chi square analyses and Fisher's exact tests were performed to compare variables at year 1 and five years later. Grip and pinch strength increased as did joint motion except for the wrist and thumb carpometacarpal joint. There were also significant increases in the presence of scars, friction rubs, calcium deposits, and puffy fingers. Regression analysis was done to determine which variables predicted functional ability. Only puffy fingers predicted functional disability. In conclusion, hand impairment persisted over time while functional ability decreased.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Chinese newspaper layout analysis with antecedent compartmenatl lines

Chinese newspaper layout analysis with antecedent compartmen...

引用

2003 International Conference on Machine Learning and Cybernetics

作者： Liu, Dong-Rong Wang, Ke-Jian Zhao, Ming-Hua Han, Xian-Zhong Sch. of Math./Information Science Heibei Normal University Shijiazhuang China Sch. of Info. Technol. and Science Hebei Agriculture University Baoding China

ISBN: (纸本)0780378652

There exist many compartmental lines in Chinese newspapers, which make layout analysis very inconvenient. This paper proposes an approach based on compartmental lines, which extracts compartmental lines first, then segments the whole page with these lines, finally analyzes the interior area further using rectangle extension model. This method makes efficient use of the coordinate of the compartmental lines and avoids setting so many parameters in the components merging procedure, so it is more flexible. This method can locate compartmental lines accurately. Experiment shows that it is a page layout analysis algorithm with more universality.

关键词： Optical character recognition

来源：评论

学校读者我要写书评

暂无评论

Managing XML sch.mas through XRDB

Managing XML schemas through XRDB

引用

Proceedings of the International Conference on info.mation and Knowledge Engineering 2003

作者： Lu, James J. Wyss, Catharine M. Cheung, Shun Yan Akhavein, Mehdi M. Dept. of Math. and Computer Science Emory University Atlanta GA 30332-1950 United States Dept. Comp. Sci. and Sch. of Info. Indiana University Bloomington IN 47405 United States

ISBN: (纸本)1932415076

eXtensible relational database (XRDB) is a novel extension to the relational database model that integrates metadata and ordinary data within the relational model. At the core of XRDB is a rich collection of meta-datatypes. The current paper explores the management of XML sch.mas via XRDB. In particular, it is shown that a combined structure-based mapping and model-based mapping can be naturally achieved hi XRDB.

关键词： Relational database systems

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：