检索结果-内蒙古大学图书馆

Boosted convolutional neural networks for motor imagery EEG decoding with multiwavelet-based time-frequency conditional granger causality analysis

arXiv

引用

arXiv 2018年

作者： Li, Yang Lei, Mengying Zhang, Xianrui Cui, Weigang Guo, Yuzhu Huang, Ting-Wen Wei, Hua-Liang Department of Automation Sciences and Electrical Engineering Beijing Advanced Innovation Center for Big Data and Brain Computing Beijing Advanced Innovation Center for Big Date-based Precision Medicine Beihang University Beijing China Department of Automation Sciences and Electrical Engineering Beihang University Beijing China Department of Mathematics Texas A&M University at Qatar Doha23874 Qatar Department of Automatic Control and Systems Engineering University of Sheffield SheffieldS1 3DJ United Kingdom

Decoding EEG signals of different mental states is a challenging task for brain-computer interfaces (BCIs) due to non-stationarity of perceptual decision processes. This paper presents a novel boosted convolutional neural networks (ConvNets) decoding scheme for motor imagery (MI) EEG signals assisted by the multiwavelet-based time-frequency (TF) causality analysis. Specifically, multiwavelet basis functions are first combined with Geweke spectral measure to obtain high-resolution TF-conditional Granger causality (CGC) representations, where a regularized orthogonal forward regression (ROFR) algorithm is adopted to detect a parsimonious model with good generalization performance. The causality images for network input preserving time, frequency and location information of connectivity are then designed based on the TF-CGC distributions of alpha band multichannel EEG signals. Further constructed boosted ConvNets by using spatio-temporal convolutions as well as advances in deep learning including cropping and boosting methods, to extract discriminative causality features and classify MI tasks. Our proposed approach outperforms the competition winner algorithm with 12.15% increase in average accuracy and 74.02% decrease in associated inter subject standard deviation for the same binary classification on BCI competition-IV dataset-IIa. Experiment results indicate that the boosted ConvNets with causality images works well in decoding MI-EEG signals and provides a promising framework for developing MI-BCI systems. Copyright © 2018, The Authors. All rights reserved.

关键词： Statistical tests

来源：评论

学校读者我要写书评

暂无评论

Linear ODE Based Geometric Modelling for Compressor Blades

Linear ODE Based Geometric Modelling for Compressor Blades

引用

2017 2nd International Conference on Electrical, Automation and Mechanical Engineering(EAME2017)

作者： Guanying Huo Xin Jiang Danlei Ye Cheng Su Zehong Lu Bolun Wang Zhiming Zheng LMIB and School of Mathematics and Systems Science Beihang University Big Data Brain Computing Center Beihang University School of Mathematical Science Peking University

Geometric modeling based on physical environment of the objects has been emerging as a powerful modeling technique and started to gain popularity for surface modeling and design. These methods usually allow the geometric objects to be defined and governed by a set of differential equations. In this paper, we focus on the geometric modeling for compressor blades, upon which the flow is governed by Navier-Stokes(NS) equations. As we cannot use NS equations directly due to its essential complexity, linear ODE systems are used to describe the elementary blade types of the blade surface. Then, we use the homotopy based method to reconstruct the full surface. A specific blade surface represented as data scatter is used to verify our method. According to the properties of the original data, different parametrization methods are discussed. Numerical results show that our method offers a nice representation for the blade surface.

关键词： ODE systems navier-stokes equations homotopy

来源：评论

学校读者我要写书评

暂无评论

Low-resolution face recognition in the wild via selective knowledge distillation

arXiv

引用

arXiv 2018年

作者： Ge, Shiming Zhao, Shengwei Li, Chenyu Li, Jia Institute of Information Engineering Chinese Academy of Sciences Beijing100095 China Institute of Information Engineering Chinese Academy of Sciences School of Cyber Security at University of Chinese Academy of Sciences China State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing100191 China

Typically, the deployment of face recognition models in the wild needs to identify low-resolution faces with extremely low computational cost. To address this problem, a feasible solution is compressing a complex face model to achieve higher speed and lower memory at the cost of minimal performance drop. Inspired by that, this paper proposes a learning approach to recognize low-resolution faces via selective knowledge distillation. In this approach, a two-stream convolutional neural network (CNN) is first initialized to recognize high-resolution faces and resolution-degraded faces with a teacher stream and a student stream, respectively. The teacher stream is represented by a complex CNN for high-accuracy recognition, and the student stream is represented by a much simpler CNN for low-complexity recognition. To avoid significant performance drop at the student stream, we then selectively distil the most informative facial features from the teacher stream by solving a sparse graph optimization problem, which are then used to regularize the fine-tuning process of the student stream. In this way, the student stream is actually trained by simultaneously handling two tasks with limited computational resources: approximating the most informative facial cues via feature regression, and recovering the missing facial cues via low-resolution face classification. Experimental results show that the student stream performs impressively in recognizing low-resolution faces and costs only 0.15MB memory and runs at 418 faces per second on CPU and 9, 433 faces per second on GPU. Copyright © 2018, The Authors. All rights reserved.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

A Novel Intrusion Detection System Based on Advanced Naive Bayesian Classification 1st

A Novel Intrusion Detection System Based on Advanced Naive B...

引用

1st International Conference on 5G for Future Wireless Networks, 5GWN 2017

作者： Wang, Yunpeng Li, Yuzhou Tian, Daxin Wang, Congyu Wang, Wenyang Hui, Rong Guo, Peng Zhang, Haijun Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University XueYuan Road No. 37 Beijing100191 China China Automotive Technology and Research Center Automotive Engineering Research Institute East Xianfeng Road No. 68 Tianjin300300 China School of Computer and Communication Engineering University of Science and Technology Beijing XueYuan Road No. 30 Beijing100083 China XueYuan Road No. 37 Beijing100191 China Jiangsu Province Collaborative Innovation Center of Modern Urban Traffic Technologies Si Pai Lou. 2 Nanjing210096 China Key Lab of Urban ITS Technology Optimization and Integration The Ministry of Public Security of China Hefei230088 China

ISBN: (纸本)9783319728223

Intrusion Detection System is a pattern recognition task whose aim is to detect and report the occurrence of abnormal or unknown network behaviors in a given network system being monitored. In this paper, we propose a machine learning model, advanced Naive Bayesian Classification (NBC-A) which is based on NBC and ReliefF algorithm, to be used in the novel IDS. We use ReliefF algorithm to give every attribute of network behavior in KDD’99 dataset a weight that reflects the relationship between attributes and final class for better classification results. The novel IDS has a higher True Positive (TP) rate and a lower False Positive (FP) rate in detection performance. © 2018, ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering.

关键词： Intrusion detection

来源：评论

学校读者我要写书评

暂无评论

Spatial functional linear model and its estimation method

arXiv

引用

arXiv 2018年

作者： Huang, Tingting Saporta, Gilbert Wang, Huiwen Wang, Shanshan School of Economics and Management Beihang University Beijing China CEDRIC CNAM 292 rue St Martin Paris Cedex 0375141 France Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing China Beijing Key Laboratory of Emergence Support Simulation Technologies for City Operations Beijing China School of Economics and Management Beihang University Xueyuan Road No.37 Haidian District Beijing China

The classical functional linear regression model (FLM) and its extensions, which are based on the assumption that all individuals are mutually independent, have been well studied and are used by many researchers. This independence assumption is sometimes violated in practice, especially when data with a network structure are collected in scientific disciplines including marketing, sociology and spatial economics. However, relatively few studies have examined the applications of FLM to data with network structures. We propose a novel spatial functional linear model (SFLM), that incorporates a spatial autoregressive parameter and a spatial weight matrix into FLM to accommodate spatial dependencies among individuals. The proposed model is relatively flexible as it takes advantage of FLM in handling high-dimensional covariates and spatial autoregressive (SAR) model in capturing network dependencies. We develop an estimation method based on functional principal component analysis (FPCA) and maximum likelihood estimation. Simulation studies show that our method performs as well as the FPCA-based method used with FLM when no network structure is present, and outperforms the latter when network structure is present. A real weather data is also employed to demonstrate the utility of the SFLM. Copyright © 2018, The Authors. All rights reserved.

关键词： Economics

来源：评论

学校读者我要写书评

暂无评论

Coordinate Basis Transformation Based Linearisation Method for Ordinary Differential Equations

Coordinate Basis Transformation Based Linearisation Method f...

引用

2017 International Conference on Applied Mathematics, Modeling and Simulation (AMMS2017)

作者： Danlei Ye Xin Jiang Guanying Huo Cheng Su Zehong Lu Bolun Wang Zhiming Zheng LMIB and School of Mathematics and Systems Science Beihang University Beijing Advanced Innovation Center for Big Data and Brain Computing (BDBC) Beihang University School of Mathematical Science Peking University

In this paper, a linearisation method for nonlinear ordinary differential equations based on coordinate basis transformation is proposed. In order to transform a nonlinear equation into a linear one, we introduce a general framework to extract the coordinate basis of the differential system. Actually, by introducing a mapping function predefined, this extraction method could connect each state variable of the new system with the variables in the original one. Further, by using vector space for the closure of the Lie derivative, we can analytically obtain the mapping based on the subspace iteration. We argue that this method might be efficient in analyzing and solving ordinary differential systems of complex nonlinear forms.

关键词： coordinate basis linearisation Lie derivative

来源：评论

学校读者我要写书评

暂无评论

GARCH-LSSVM Coupled Predication Model and Its Application on Stock Index Forecasting

GARCH-LSSVM Coupled Predication Model and Its Application on...

引用

2017 International Conference on Mathematics, Modelling and Simulation Technologies and Applications（MMSTA 2017)

作者： Xiao-xu HU Meng-qi ZHANG Xin JIANG Key Laboratory of Mathematics Informatics and Behavioral ScienceMinistry of EducationBeihang University School of Mathematics and Systems Science Beihang University Beijing Advanced Innovation Center for Big Data and Brain Computing

It is usually a challenge for traditional time series prediction models to combine the linear and non-linear factors effectively,which might cause a problem that the trend forecast is not *** this paper we propose a new prediction model based on GARCH and *** GARCH model is used to deal with the heteroscedasticity of the residual series of the closing price of the stock index *** the same time,a number of technical indicators are constructed to train the LSSVM model and the corresponding predicted values and residuals are ***,the predicted value and the residual obtained respectively from GARCH and LSSVM are used as the training set to modify the LSSVM model,with the predicted value of the logarithmic closing price of the stock index *** coupled model not only contains the linear trend of historical information,but also integrates the non-linear features such as market volatility information which is closely related to the target *** experimental results show that the prediction accuracy of the model is 98.22% on the testing data *** model performs also better than the GARCH 97.84% and the LSSVM 98.04% respectively in accuracy deviation.

关键词： Generalized auto-regressive conditional heteroscedastic(GARCH) Least square support vector machine(LSSVM) Coupled prediction algorithm Stock index forecasting Technical indicators

来源：评论

学校读者我要写书评

暂无评论

A Vehicular Positioning Enhancement with Connected Vehicle Assistance Using Extended Kalman Filtering 1st

A Vehicular Positioning Enhancement with Connected Vehicle A...

引用

1st International Conference on 5G for Future Wireless Networks, 5GWN 2017

作者： Tian, Daxin Liu, Wenhao Duan, Xuting Rong, Hui Guo, Peng Wang, Wenyang Zhang, Haijun Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University XueYuan Road No. 37 Beijing100191 China China Automotive Technology and Research Center Automotive Engineering Research Institute East Xianfeng Road No. 68 Tianjin300300 China School of Computer and Communication Engineering University of Science and Technology Beijing XueYuan Road No. 30 Beijing100083 China Beijing Key Laboratory for Cooperative Vehicle Infrastructure Systems and Safety Control School of Transportation Science and Engineering Beihang University XueYuan Road No. 37 Beijing100191 China Jiangsu Province Collaborative Innovation Center of Modern Urban Traffic Technologies Si Pai Lou. 2 Nanjing210096 China Key Lab of Urban ITS Technology Optimization and Integration The Ministry of Public Security of China Hefei230088 China

ISBN: (纸本)9783319728223

In this paper, we consider the problem of vehicular positioning enhancement with emerging connected vehicles (CV) technologies. In order to actually describe the scenario, the Interacting Multiple Model (IMM) filter is used for depicting varies of observation models. A CV-enhanced IMM filtering approach is proposed to locate a vehicle by data fusion from both coarse GPS data and the Doppler frequency shifts (DFS) measured from dedicated short-range communications (DSRC) radio signals. Simulation results state the effectiveness of the proposed approach called CV-IMM-EKF. © 2018, ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering.

关键词： Global positioning system

来源：评论

学校读者我要写书评

暂无评论

REFF: REliable and Fast Forwarding in Vehicular Ad-hoc Network 1st

REFF: REliable and Fast Forwarding in Vehicular Ad-hoc Netwo...

引用

1st International Conference on 5G for Future Wireless Networks, 5GWN 2017

作者： Tian, Daxin Dai, Ziyi Zheng, Kunxian Zhou, Jianshan Duan, Xuting Guo, Peng Rong, Hui Wang, Wenyang Zhang, Haijun Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University XueYuan Road No. 37 Beijing100191 China China Automotive Technology and Research Center Automotive Engineering Research Institute East Xianfeng Road No. 68 Tianjin300300 China School of Computer and Communication Engineering University of Science and Technology Beijing XueYuan Road No. 30 Beijing100083 China Beijing Key Laboratory for Cooperative Vehicle Infrastructure Systems and Safety Control School of Transportation Science and Engineering Beihang University XueYuan Road No. 37 Beijing100191 China Jiangsu Province Collaborative Innovation Center of Modern Urban Traffic Technologies Si Pai Lou. 2 Nanjing210096 China Key Lab of Urban ITS Technology Optimization and Integration The Ministry of Public Security of China Hefei230088 China

ISBN: (纸本)9783319728223

Vehicular Ad-Hoc Network (VANET) has emerged as an increasingly dominant technology for future connected vehicle and vehicular networks, where the focus of the development of VANET lies in the standardization of message transmission and dissemination via multi-hop broadcasting. However, the current communication protocols concerning VANET face many challenges, including data flooding and collision, transmission delay and other problems. Most of the challenges are closely related to next-hop selection. Therefore, this paper proposes a new routing protocol named REliable and Fast Forwarding (REFF) to optimize the selection of nodes in VANET. In this protocol, node filtering and node evaluation are two main steps. Distance between previous node and candidate node, relative velocity between previous node and candidate nodes, included angle between direction of target node’s velocity and candidate node’s velocity and transmission power of candidate node are adopted as indexes to help select a specific node as the next hop using Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS). By using this technique, the number of candidates as next-hop is largely reduced, avoiding the data flooding and resulting transmission relay. In addition, simulations based on experiments are done to verify the feasibility. The results show that message achieves a faster and more reliable transmission using REFF. © 2018, ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering.

关键词： Vehicular ad hoc networks

来源：评论

学校读者我要写书评

暂无评论

Modeling and Simulation on Cooperative Movement of Vehicle Group Based on the Behavior of Fish 1st

Modeling and Simulation on Cooperative Movement of Vehicle G...

引用

1st International Conference on 5G for Future Wireless Networks, 5GWN 2017

作者： Tian, Daxin Kang, Lu Zheng, Kunxian Duan, Xuting Rong, Hui Guo, Peng Wang, Wenyang Zhang, Haijun Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University XueYuan Road No.37 Beijing100191 China China Automotive Technology and Research Center Automotive Engineering Research Institute East Xianfeng Road No.68 Tianjin300300 China School of Computer and Communication Engineering University of Science and Technology Beijing XueYuan Road No.30 Beijing100083 China Beijing Key Laboratory for Cooperative Vehicle Infrastructure Systems and Safety Control School of Transportation Science and Engineering Beihang University XueYuan Road No.37 Beijing100191 China Jiangsu Province Collaborative Innovation Center of Modern Urban Traffic Technologies Si Pai Lou. 2 Nanjing210096 China Key Lab of Urban ITS Technology Optimization and Integration The Ministry of Public Security of China Hefei230088 China

ISBN: (纸本)9783319728223

Fatigue driving might affect the traffic safety when the vehicles are on the cruising state in highway. Trying to solve this problem, this paper uses the movement pattern of the fish to the vehicles fleet, and develops a model of vehicle group with realistic restrictions based on the existed fish algorithms, the mobile behavioral model and cluster behavior model, and then demonstrates the feasibility of applying the fish behavior to the cooperative movement of vehicle groups through analyzing the trajectory, velocity and spacing of vehicles. © 2018, ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering.

关键词： Vehicles

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：