为了提高脑电情绪识别分类精度,最大限度利用脑电信号的空间和时间信息,提出一种Inception残差注意力卷积神经网络与双向长短期记忆(bi-directional long short-term memory, BiLSTM)网络相结合的新型架构时空Inception残差注意力网络...为了提高脑电情绪识别分类精度,最大限度利用脑电信号的空间和时间信息,提出一种Inception残差注意力卷积神经网络与双向长短期记忆(bi-directional long short-term memory, BiLSTM)网络相结合的新型架构时空Inception残差注意力网络。将脑电信号采集电极位置映射到二维矩阵中,采集信号作为通道,构成三维数据;将得到的三维数据输入到时空Inception残差注意力卷积网络之中,提取时空信息;将得到的特征输入到全连接层进行分类;将Inception结构引入脑电情绪识别领域,实现多尺度特征提取,并将电极映射到矩阵之中,保留电极位置信息,使用时空Inception残差注意力网络从时空两个维度获取脑电相关信息。实验表明,使用该模型对DEAP数据集进行情绪四分类可得到93.71%的准确度,相较于对比模型,识别精度提高了10%~20%。提出的模型在脑电信号情绪识别领域具有优良性能。展开更多
为提高ORB-SLAM2 (oriented fast and rotated brief, and simultaneous localization and mapping)系统的位姿估计精度并解决仅能生成稀疏地图的问题,提出了融合迭代最近点拟合(iterative closest point, ICP)算法与曼哈顿世界假说的...为提高ORB-SLAM2 (oriented fast and rotated brief, and simultaneous localization and mapping)系统的位姿估计精度并解决仅能生成稀疏地图的问题,提出了融合迭代最近点拟合(iterative closest point, ICP)算法与曼哈顿世界假说的位姿估计策略并在系统中加入稠密建图线程。首先通过ORB(oriented fast and rotated brief)特征点法、最小显著性差异(least-significant difference, LSD)算法和聚集层次聚类(agglomerative hierarchical clustering, AHC)方法提取点、线、面特征,其中点、线特征与上一帧匹配,面特征在全局地图匹配。然后采用基于surfel的稠密建图策略将图像划分为非平面与平面区域,非平面采用ICP算法计算位姿,平面则通过面与面的正交关系确定曼哈顿世界从而使用不同估计策略,其中曼哈顿世界场景通过位姿解耦实现基于曼哈顿帧观测的无漂移旋转估计,而该场景的平移以及非曼哈顿世界场景的位姿采用追踪的点、线、面特征进行估计和优化;最后根据关键帧和相应位姿实现稠密建图。采用慕尼黑工业大学(technische universit?t münchen, TUM)数据集验证所提建图方法,经过与ORB-SLAM2算法比较,均方根误差平均减少0.24 cm,平均定位精度提高7.17%,验证了所提方法进行稠密建图的可行性和有效性。展开更多
Hyperstatic structure plane model being built by structural mechanics is studied. Space model precisely reflected in real stress of the structure is built by finite element method （FEM） analysis commerce software. M...Hyperstatic structure plane model being built by structural mechanics is studied. Space model precisely reflected in real stress of the structure is built by finite element method （FEM） analysis commerce software. Mapping model of complex structure system is set up, with convenient calculation just as in plane model and comprehensive information as in space model. Plane model and space model are calculated under the same working condition. Plane model modular construction inner force is considered as input data; Space model modular construction inner force is considered as output data. Thus specimen is built on input data and output dam. Character and affiliation are extracted through training specimen, with the employment of nonlinear mapping capability of the artificial neural network. Mapping model with interpolation and extrpolation is gained, laying the foundation for optimum design. The steel structure of high-layer parking system （SSHLPS） is calculated as an instance. A three-layer back-propagation （BP） net including one hidden layer is constructed with nine input nodes and eight output nodes for a five-layer SSHLPS. The three-layer structure optimization result through the mapping model interpolation contrasts with integrity re-analysis, and seven layers structure through the mapping model extrpulation contrasts with integrity re-analysis. Any layer SSHLPS among 1-8 can be calculated with much accuracy. Amount of calculation can also be reduced if it is appfied into the same topological structure, with reduced distortion and assured precision.展开更多
Fractal structures in a generalized squared map with exponential terms are expanded in this paper. We describe how complex behaviors can arise as the parameters change. The appearances of different kinds of fractal st...Fractal structures in a generalized squared map with exponential terms are expanded in this paper. We describe how complex behaviors can arise as the parameters change. The appearances of different kinds of fractal structures, in both the attractive and the divergent regions, and most interestingly, on small regular islands embedded in the chaotic region, are manifested to have a variety of extraordinary geometries in the parameter plane.展开更多
A new exact and universal conformal mapping is proposed. Using Muskhelishvili＇s complex potential method, the plane elasticity problem of power function curved cracks is investigated with an arbitrary power of a natu...A new exact and universal conformal mapping is proposed. Using Muskhelishvili＇s complex potential method, the plane elasticity problem of power function curved cracks is investigated with an arbitrary power of a natural number, and the general solutions of the stress intensity factors （SIFs） for mode I and mode II at the crack tip are obtained under the remotely uniform tensile loads. The present results can be reduced to the well-known solutions when the power of the function takes different natural numbers. Numerical examples are conducted to reveal the effects of the coefficient, the power, and the projected length along the x-axis of the power function curved crack on the SIFs for mode I and mode II.展开更多
文摘为了提高脑电情绪识别分类精度,最大限度利用脑电信号的空间和时间信息,提出一种Inception残差注意力卷积神经网络与双向长短期记忆(bi-directional long short-term memory, BiLSTM)网络相结合的新型架构时空Inception残差注意力网络。将脑电信号采集电极位置映射到二维矩阵中,采集信号作为通道,构成三维数据;将得到的三维数据输入到时空Inception残差注意力卷积网络之中,提取时空信息;将得到的特征输入到全连接层进行分类;将Inception结构引入脑电情绪识别领域,实现多尺度特征提取,并将电极映射到矩阵之中,保留电极位置信息,使用时空Inception残差注意力网络从时空两个维度获取脑电相关信息。实验表明,使用该模型对DEAP数据集进行情绪四分类可得到93.71%的准确度,相较于对比模型,识别精度提高了10%~20%。提出的模型在脑电信号情绪识别领域具有优良性能。
文摘为提高ORB-SLAM2 (oriented fast and rotated brief, and simultaneous localization and mapping)系统的位姿估计精度并解决仅能生成稀疏地图的问题,提出了融合迭代最近点拟合(iterative closest point, ICP)算法与曼哈顿世界假说的位姿估计策略并在系统中加入稠密建图线程。首先通过ORB(oriented fast and rotated brief)特征点法、最小显著性差异(least-significant difference, LSD)算法和聚集层次聚类(agglomerative hierarchical clustering, AHC)方法提取点、线、面特征,其中点、线特征与上一帧匹配,面特征在全局地图匹配。然后采用基于surfel的稠密建图策略将图像划分为非平面与平面区域,非平面采用ICP算法计算位姿,平面则通过面与面的正交关系确定曼哈顿世界从而使用不同估计策略,其中曼哈顿世界场景通过位姿解耦实现基于曼哈顿帧观测的无漂移旋转估计,而该场景的平移以及非曼哈顿世界场景的位姿采用追踪的点、线、面特征进行估计和优化;最后根据关键帧和相应位姿实现稠密建图。采用慕尼黑工业大学(technische universit?t münchen, TUM)数据集验证所提建图方法,经过与ORB-SLAM2算法比较,均方根误差平均减少0.24 cm,平均定位精度提高7.17%,验证了所提方法进行稠密建图的可行性和有效性。
基金This project is supported by Provincial Natural Science Foundation of Shanxi, China (No. 20041074)Provincial Natural Science Youth Foundation of Shanxi, China (No. 20051030)Provincial Education Office Key Subject of Shanxi, China (No. 20045027-20045028)
文摘Hyperstatic structure plane model being built by structural mechanics is studied. Space model precisely reflected in real stress of the structure is built by finite element method （FEM） analysis commerce software. Mapping model of complex structure system is set up, with convenient calculation just as in plane model and comprehensive information as in space model. Plane model and space model are calculated under the same working condition. Plane model modular construction inner force is considered as input data; Space model modular construction inner force is considered as output data. Thus specimen is built on input data and output dam. Character and affiliation are extracted through training specimen, with the employment of nonlinear mapping capability of the artificial neural network. Mapping model with interpolation and extrpolation is gained, laying the foundation for optimum design. The steel structure of high-layer parking system （SSHLPS） is calculated as an instance. A three-layer back-propagation （BP） net including one hidden layer is constructed with nine input nodes and eight output nodes for a five-layer SSHLPS. The three-layer structure optimization result through the mapping model interpolation contrasts with integrity re-analysis, and seven layers structure through the mapping model extrpulation contrasts with integrity re-analysis. Any layer SSHLPS among 1-8 can be calculated with much accuracy. Amount of calculation can also be reduced if it is appfied into the same topological structure, with reduced distortion and assured precision.
基金Project supported by the National Natural Science Foundation of China (Grant No.11161027)the Natural Science Foundation of Gansu Province,China (Grant No. 1010RJZA067)
文摘Fractal structures in a generalized squared map with exponential terms are expanded in this paper. We describe how complex behaviors can arise as the parameters change. The appearances of different kinds of fractal structures, in both the attractive and the divergent regions, and most interestingly, on small regular islands embedded in the chaotic region, are manifested to have a variety of extraordinary geometries in the parameter plane.
基金supported by the National Natural Science Foundation of China(Nos.10932001,11072015, and 10761005)the Scientific Research Key Program of Beijing Municipal Commission of Education (No.KZ201010005003)+1 种基金the Specialized Research Fund for the Doctoral Program of Higher Education of China(No.20101102110016)the Ph.D.Innovation Foundation of Beijing University of Aeronautics and Astronautics(No.300351)
文摘A new exact and universal conformal mapping is proposed. Using Muskhelishvili＇s complex potential method, the plane elasticity problem of power function curved cracks is investigated with an arbitrary power of a natural number, and the general solutions of the stress intensity factors （SIFs） for mode I and mode II at the crack tip are obtained under the remotely uniform tensile loads. The present results can be reduced to the well-known solutions when the power of the function takes different natural numbers. Numerical examples are conducted to reveal the effects of the coefficient, the power, and the projected length along the x-axis of the power function curved crack on the SIFs for mode I and mode II.
