Structure dependence of second harmonic generation in asymmetricquantum-well structures

Second harmonic generation in stepped asymmetric quantum wells (AQW) is discussed and shown to depend strongly on several controllable AQW parameters. The influence of inter-subband absorption is also investigated. It is demonstrated that with appropriate choice of semiconductor materials and precise bandgap engineering, optimized devices may be developed for a given input laser frequency     

轻武器射击系统建模及计算结果分析

通过简化臣姿持枪射击系统，利用拉格朗日方程，建立了该射击系统的物理模型和数学模型，并通过数值模拟，论述了缓冲簧对系统动态特性的影响，最后通过实验，对无缓冲簧射击系统的动态特性参数进行验证。     

Identification of Hammerstein systems with asymmetric dead-zone nonlinearities using canonical parameterized model

A non-iterative identification method with parameterization of the unknown dead-zone is proposed for Hammerstein systems in presence of asymmetric dead-zone nonlinearities.The canonical parameterized model which is a single expression without segmentation is utilized to describe the dead-zone,based on which a universal-type parametric model can be established to approximate the entire system.This model can be established without separating the nonlinear part from the linear part.The dead-zone parameters and the coefficients in the linear transfer function can be estimated simultaneously according to the proposed algorithm.Numerical experiments are presented to illustrate the effectiveness of the proposed scheme.     

产品开发方案优化的模糊机会约束规划模型及求解

为解决项目网络计划中产品开发方案的时间、成本、质量的不确定优化问题,在模糊机会约束规划的框架下分别建立了基于关键路线的项目周期优化模型、基于资源使用的项目周期-成本优化模型和基于质量功能展开(QFD)的产品周期-质量优化模型,在此基础上构建了项目周期-成本-质量多目标优化模型;在使用模糊模拟技术处理3个目标函数约束的过程中,构建了一个基于遗憾度的适应度函数,然后利用离散微粒群算法对多目标优化模型进行求解.最后,以滚珠丝杆副产品开发项目的方案优化为例验证了文中模型的合理性和算法的有效性;实验结果表明,周期-成本-质量多目标优化模型的求解得到的方案能够取得时间、成本和质量的平衡优化,为产品开发项目的规划提供了定量、可靠的决策依据.     

三维标量场并行等值面提取与绘制技术

通过研究并行等值面提取与绘制的各项关键技术要点,面向三维标量场的特点,在sort-last并行绘制模式的基础上提出一个三维标量场并行等值面提取与绘制框架.该框架在任务分配时采用静态分配的模式,在等值面提取时采用Marching Tetrahedra等值面提取算法,在并行绘制与场景合成时采用预先构建绘制节点控制模型的混合场景并行绘制合成算法.实验结果表明,该框架能够有效地提高大规模时变三维标量场的等值面提取与绘制效率,满足实际应用的需要.     

稀疏差分网络和多监督哈希用于高效图像检索

针对基于深度哈希的图像检索中卷积神经网络（CNN）特征提取效率较低和特征相关性利用不充分的问题,提出一种融合稀疏差分网络和多监督哈希的新方法SDNMSH（sparse difference networks and multi-supervised hashing）,并将其用于高效图像检索。SDNMSH以成对的图像作为训练输入,通过精心设计的稀疏差分卷积神经网络和一个监督哈希函数来指导哈希码学习。稀疏差分卷积神经网络由稀疏差分卷积层和普通卷积层组成。稀疏差分卷积层能够快速提取丰富的特征信息,从而实现整个网络的高效特征提取。同时,为了更加充分地利用语义信息和特征的成对相关性,以促进网络提取的特征信息能够更加有效地转换为具有区分性的哈希码、进而实现SDNMSH的高效图像检索,采用一种多监督哈希（MSH）函数,并为此设计了一个目标函数。在MNIST、CIFAR-10和NUS-WIDE三个广泛使用的数据集上进行了大量的对比实验,实验结果表明,与其他先进的深度哈希方法相比,SDNMSH取得了较好的检索性能。     

Predicting the blast-induced vibration velocity using a bagged support vector regression optimized with firefly algorithm

Ground vibration is the most detrimental effect induced by blasting in surface mines. This study presents an improved bagged support vector regression (BSVR) combined with the firefly algorithm (FA) to predict ground vibration. In other words, the FA was used to modify the weights of the SVR model. To verify the validity of the BSVR–FA, the back-propagation neural network (BPNN) and radial basis function network (RBFN) were also applied. The BSVR–FA, BPNN and RBFN models were constructed using a comprehensive database collected from Shur River dam region, in Iran. The proposed models were then evaluated by means of several statistical indicators such as root mean square error (RMSE) and symmetric mean absolute percentage error. Comparing the results, the BSVR–FA model was found to be the most accurate to predict ground vibration in comparison to the BPNN and RBFN models. This study indicates the successful application of the BSVR–FA model as a suitable and effective tool for the prediction of ground vibration.

     

Spatial division networks for weakly supervised detection

Neural Computing and Applications - With only global image-level annotations, weakly supervised learning of deep convolutional neural networks has shown enough capacity in classification and...     

From text to graph: a general transition-based AMR parsing using neural network

Neural Computing and Applications - Semantic understanding is an essential research issue for many applications, such as social network analysis, collective intelligence and content computing,...     

结合LSTM的强化学习动态环境路径规划算法

在路径规划领域已经涌现出了诸多的优秀的经典算法,但这些传统方法往往基于静态环境,对于动态可变环境缺乏处理能力.本文提出一种结合LSTM强化学习动态环境路径规划算法.首先,本文以环境图像作为输入,最大限度了保证了原始的信息来源.而后构建了自动编码器用来对环境图像进行特征降维,降低了整体模型的复杂程度.最后采用深度强化学习算法DDPG进行路径规划,其中Actor部分采用LSTM的网络构建,使Actor在决策时可以参考前序信息,做到有预测的避开动态障碍.最后通过实验证明了本文算法的可行性和高效性.