Transient luminescence in organic light-emitting diodes explained by trap-assisted recombination of stored charges

We show that after voltage turn-off the recombination of the charges which are stored in the on-state may follow a trap-assisted mechanism instead of the Langevin formula in organic light-emitting diodes. A microscopic model based on this form of recombination is introduced, which not only fits the transient electroluminescence very well in the whole range of the off-state but also provides parameters quantitatively characterizing the stored charges in the on-state. In the last part, we briefly compare the work by Weichsel et al. [1] and our model, trying to constitute a comprehensive picture of the stored charges in OLEDs. As an OLED model system we have chosen a host/guest system co-doped with red and green phosphorescent emitters.     

Steganography using a 3-player game

Image steganography aims to securely embed secret information into cover images. Until now, adaptive embedding algorithms such as S-UNIWARD or Mi-POD, were among the most secure and most often used methods for image steganography. With the arrival of deep learning and more specifically, Generative Adversarial Networks (GAN), new steganography techniques have appeared. Among them is the 3-player game approach, where three networks compete against each other. In this paper, we propose three different architectures based on the 3-player game. The first architecture is proposed as a rigorous alternative to two recent publications. The second takes into account stego noise power. Finally, our third architecture enriches the second one with a better interaction between embedding and extracting networks. Our method achieves better results compared to existing works Hayes and Danezis (2017), Zhu et al. (2018), and paves the way for future research on this topic.     

Understanding convolutional neural networks with a mathematical model

This work attempts to address two fundamental questions about the structure of the convolutional neural networks (CNN): (1) why a nonlinear activation function is essential at the filter output of all intermediate layers? (2) what is the advantage of the two-layer cascade system over the one-layer system? A mathematical model called the “REctified-COrrelations on a Sphere” (RECOS) is proposed to answer these two questions. After the CNN training process, the converged filter weights define a set of anchor vectors in the RECOS model. Anchor vectors represent the frequently occurring patterns (or the spectral components). The necessity of rectification is explained using the RECOS model. Then, the behavior of a two-layer RECOS system is analyzed and compared with its one-layer counterpart. The LeNet-5 and the MNIST dataset are used to illustrate discussion points. Finally, the RECOS model is generalized to a multilayer system with the AlexNet as an example.     

基于多尺度圆周频率滤波与卷积神经网络的遥感图像飞机目标检测方法研究

针对遥感图像飞机目标检测因目标尺度不一存在漏警、虚警等问题,该文基于遥感图像中飞机目标形状特征和灰度变化特点提出了一种多尺度圆周频率滤波(MSCFF)与卷积神经网络(CNN)相结合的MSCFF+CNN飞机目标自动检测算法.该算法首先采用多尺度圆周频率滤波器滤除遥感图像复杂背景,实现不同尺度飞机目标候选区域提取;然后,通过构建卷积神经网络(CNN)模型实现候选区域有效分类,最终精确确定飞机目标位置.最后,基于获取的真实遥感图像进行目标检测算法实验验证,经统计该算法的飞机目标检测率为94.38%,虚警率为3.76%,实验结果充分验证了该文算法的有效性,该算法可为机场监管、军事侦察等应用提供重要的技术支持.     

基于无监督域适应的仿真辅助SAR目标分类方法及模型可解释性分析

卷积神经网络(CNN)在光学图像分类领域中得到广泛应用,然而,合成孔径雷达(SAR)图像样本标注难度大、成本高,难以获取满足CNN训练所需的样本数量.随着SAR仿真技术的发展,生成大量带标签的仿真SAR图像并不困难.然而仿真SAR图像样本与真实样本间难免存在差异,往往难以直接支撑实际样本的分类任务.为此,该文提出了一种...     

基于快速滤波算法的卷积神经网络加速器设计

为减少卷积神经网络(CNN)的计算量,该文将2维快速滤波算法引入到卷积神经网络,并提出一种在FPGA上实现CNN逐层加速的硬件架构。首先,采用循环变换方法设计行缓存循环控制单元,用于有效地管理不同卷积窗口以及不同层之间的输入特征图数据,并通过标志信号启动卷积计算加速单元来实现逐层加速;其次,设计了基于4并行快速滤波算法的卷积计算加速单元,该单元采用若干小滤波器组成的复杂度较低的并行滤波结构来实现。利用手写数字集MNIST对所设计的CNN加速器电路进行测试,结果表明：在xilinx kintex7平台上,输入时钟为100 MHz时,电路的计算性能达到了20.49 GOPS,识别率为98.68%。可见通过减少CNN的计算量,能够提高电路的计算性能。     

基于双流-非局部时空残差卷积神经网络的人体行为识别

3维卷积神经网络(3D CNN)与双流卷积神经网络(two-stream CNN)是视频中人体行为识别研究的常用架构,且各有优势。该文旨在研究结合两种架构且复杂度低、识别精度高的人体行为识别模型。具体地,该文提出基于通道剪枝的双流-非局部时空残差卷积神经网络(TPNLST-ResCNN),该网络采用双流架构,分别在时间流子网络和空间流子网络采用时空残差卷积神经网络(ST-ResCNN),并采用均值融合算法融合两个子网络的识别结果。进一步地,为了降低网络的复杂度,该文提出了针对时空残差卷积神经网络的通道剪枝方案,在实现模型压缩的同时,可基本保持模型的识别精度;为了使得压缩后网络能更好地学习到输入视频中人体行为变化的长距离时空依赖关系,提高网络的识别精度,该文提出在剪枝后网络的首个残差型时空卷积块前引入一个非局部模块。实验结果表明,该文提出的人体行为识别模型在公共数据集UCF101和HMDB51上的识别准确率分别为98.33%和74.63%。与现有方法相比,该文模型具有参数量小、识别精度高的优点。     

基于串联式一维神经网络的毫米波雷达动态手势识别方法

现有的基于雷达传感器的手势识别方法,大多先利用雷达回波对手势的距离、多普勒和角度等信息进行参数估计,得到各种数据谱图,然后再利用卷积神经网络对这些谱图进行分类,实现过程较为复杂.该文提出一种基于串联式1维神经网络(1D-ScNN)的毫米波雷达动态手势识别方法.首先基于毫米波雷达获取动态手势的原始回波,然后利用1维卷积和...     

融合相关滤波和CNN的点状目标跟踪技术研究

在研究点状目标跟踪的基础上,该算法利用多层卷积特征和相关滤波技术进行目标跟踪.为解决目标因淹没在杂波中丢失的问题,该算法使用重检测机制实现目标的长期跟踪.首先,使用V GG模型提取红外点状目标的多层卷积特征,然后在每一层上经过相关滤波计算最大响应值,最后通过权重融合获得最终响应值,实现点状目标跟踪.当目标丢失时,利用重...