采用GAF-D3Net深度学习网络的水下目标有源识别方法

提出一种基于格拉姆角场(GAF)和卷积神经网络(CNN)的水下目标有源识别方法。该方法利用GAF将目标回波信号编码为二维图像,使用空洞卷积构建轻量级的卷积神经网络GAF-D3Net实现对目标的特征提取与分类识别。实验表明,与基于传统图像特征的分类方法相比,所提方法的分类精度有显著提高,达到99.65%。在泛化性测试中,对比了经典CNN使用声呐图像的迁移学习方法,本文方法的曲线下面积(AUC)达到89%,具有更好的泛化性能以及抗干扰能力,为实现水下目标有源识别提供了一种可靠方法。     

核–核碰撞中喷注淬火导致的双强子产生压低

通过考虑喷注淬火效应,分析了相对论性高能重离子碰撞中双强子的产生.结果表明,喷注淬火压低了大不变质量谱和大横动量的双强子的产生.与质子–质子碰撞的情形类似,核–核的擦边碰撞(碰撞参数很大)产生的强子有很强的背靠背的关联.在核–核对心碰撞(碰撞参数很小)中,由于喷注穿过强作用物质导致的喷注淬火介质效应,产生的强子的背靠背的关联几乎消失.     

胶子喷注和夸克喷注性质的蒙特卡洛研究

用蒙特卡洛方法研究了91.2GeV e⁺e^－碰撞产生的3喷注事件.用3个喷注之间的夹角来标识各个喷注,分别计算了3个喷注的能量及能量分布,并在相同能量下计算了3个喷注的多重数,横动量及其分布.通过与能量相同的2喷注事件中单夸克喷注的上述性质的比较,得到了从3喷注事件中挑选胶子喷注和夸克喷注的一种简便方法.这样挑选出来的胶子和夸克喷注在性质上与QCD的理论预言一致,并且胶子和夸克喷注的平均多重数比值的计算结果与实验观测值符合     

基于压缩残差网络的雷达辐射源识别方法研究

针对低信噪比条件下,现有的雷达辐射源信号识别方法存在识别正确率低、时效性差的问题,提出了一种基于压缩残差网络的雷达辐射源信号识别方法。首先,利用Choi-Williams分布的时频分析方法将时域信号转换为二维时频图像;然后,根据应用场景特点,选择卷积神经网络（Convolutional Neural Networks, CNN）“压缩”范围;最后,构建压缩残差网络来自动提取图像特征并完成分类。仿真实验结果表明,在同等体量的设计下,与当前较为常用的标准CNN以及ResNet模型相比,所提模型能够降低信号识别运行时间约88%,在信噪比为-14 dB条件下对14种雷达辐射源信号的平均识别率高约5%。提供了一种高效的雷达辐射源信号智能识别方法,具有潜在的工程应用前景。     

小孔喷注消声器在宇航设备上的应用

宇航设备中的供氧排气系统在排气过程中产生了很高的喷注噪声,小孔喷注消声器是控制喷注噪声的有效措施。以喷注噪声理论为基础,利用小孔喷注消声器设计方法,为宇航设备供氧排气系统喷口设计小孔喷注消声器。设计中通过限制孔间距要求,降低孔径,实现了小孔喷注消声器的高降噪效果。加工消声器并测试,降噪效果理想。喷注噪声的计算和实测结果对比显示,两者吻合良好,误差在2 dB(A)左右,但驻压比为4时,计算结果与实测结果相差较大,分析原因是喷口后附加喇叭口结构对喷注噪声中的冲击噪声产生了影响,而经典计算公式并未考虑此种情况。小孔喷注消声器在宇航设备供氧排气系统中应用的可行性和小孔喷注消声器设计方法的可靠性得到了验证。     

喷注电荷截面方法

我们提出了一种新的计算方法(喷注电荷截面)。用这种方法进行微扰QCD计算,不但能像末态正反强子截面差dσ(AB→h⁺X)—dσ(AB→h^-+X)那样少受海夸克和胶子分布函数的影响,而且与任何部分子的碎裂函数无关。用这种方法还可以在不能识别夸克味道的实验条件下,间接测定各种夸克喷注的平均电荷。 关键词：     

混沌干扰中基于同步挤压小波变换的谐波信号提取方法

针对混沌干扰背景下多个谐波信号的提取问题, 提出了一种基于同步挤压小波变换(SST)的谐波信号抽取方法. 首先利用SST将混沌信号和谐波信号组成的混合信号分解为不同的内蕴模态类函数, 然后利用Hilbert变换对分离出的内蕴模态类函数进行频率识别, 从中分离出各谐波信号. 以Duffing混沌背景为例, 对混沌干扰下多谐波信号的提取进行了实验分析. 实验结果表明: 对于不同频率间隔的多个谐波分量, 本文方法的提取结果都具有较高的精度, 而且所提方法对高斯白噪声的干扰具有较好的鲁棒性, 综合提取效果优于经典的经验模态分解方法.     

一种提高超燃流场羟基示踪速度测量中信号提取能力的方法

针对羟基示踪测速技术在超燃流场应用中测量图像受复杂背景干扰严重的问题,提出一种提高信号提取能力的方法.该方法通过三个步骤实现信号提取能力的提升:利用霍夫变换进行信号识别;基于感兴趣区域的大津阈值算法进行图像分割;结合骨架提取和方向模板方法进行标记线提取.在此基础上,结合仿真和实验,验证了该方法可提高超燃复杂背景干扰下的信号提取能力,解决了提取羟基有效信号精度不够的问题.     

基于卷积神经网络与一致性预测器的稳健视觉跟踪EI北大核心CSCD

针对视频序列的稳健性目标跟踪问题,提出一种基于卷积神经网络(CNN)与一致性预测器(CP)的视觉跟踪算法。该算法通过构建一个双路输入CNN模型,同步提取帧采样区域和目标模板的高层特征,利用逻辑回归方法区分目标与背景区域;将CNN嵌入至CP框架,利用算法随机性检验评估分类结果的可靠性,在指定风险水平下,以域的形式输出分类结果;选择高可信度区域作为候选目标区域,优化时空域全局能量函数获得目标轨迹。实验结果表明,该算法能够适应目标遮挡、外观变化以及背景干扰等复杂情况,与当前多种跟踪算法相比具有更强的稳健性和准确性。     

高能强子–强子碰撞中喷注性质的蒙特卡洛研究

在喷注“圆锥判定法”的基础上,对高能强子–强子碰撞中产生的喷注(微喷注)的性质进行了蒙特卡洛研究.采用以喷注动量为z轴的“喷注坐标系”,给出了表征喷注性质的各物理量在新坐标系中的分布情况.结果表明,圆锥判定法能够作为一种有效手段来对高能强子–强子碰撞和相对论重离子碰撞中发生的硬和半硬过程开展实验研究.由有喷注事件和无喷注事件的多重数分布可以看到,E_t=2GeV是用圆锥法确定喷注的合理的横能截断值.     

Multilevel Deep Feature Generation Framework for Automated Detection of Retinal Abnormalities Using OCT Images

Optical coherence tomography (OCT) images coupled with many learning techniques have been developed to diagnose retinal disorders. This work aims to develop a novel framework for extracting deep features from 18 pre-trained convolutional neural networks (CNN) and to attain high performance using OCT images. In this work, we have developed a new framework for automated detection of retinal disorders using transfer learning. This model consists of three phases: deep fused and multilevel feature extraction, using 18 pre-trained networks and tent maximal pooling, feature selection with ReliefF, and classification using the optimized classifier. The novelty of this proposed framework is the feature generation using widely used CNNs and to select the most suitable features for classification. The extracted features using our proposed intelligent feature extractor are fed to iterative ReliefF (IRF) to automatically select the best feature vector. The quadratic support vector machine (QSVM) is utilized as a classifier in this work. We have developed our model using two public OCT image datasets, and they are named database 1 (DB1) and database 2 (DB2). The proposed framework can attain 97.40% and 100% classification accuracies using the two OCT datasets, DB1 and DB2, respectively. These results illustrate the success of our model.     

Learnable three-dimensional Gabor convolutional network with global affinity attention for hyperspectral image classification

Benefiting from the development of hyperspectral imaging technology, hyperspectral image (HSI) classification has become a valuable direction in remote sensing image processing. Recently, researchers have found a connection between convolutional neural networks (CNNs) and Gabor filters. Therefore, some Gabor-based CNN methods have been proposed for HSI classification. However, most Gabor-based CNN methods still manually generate Gabor filters whose parameters are empirically set and remain unchanged during the CNN learning process. Moreover, these methods require patch cubes as network inputs. Such patch cubes may contain interference pixels, which will negatively affect the classification results. To address these problems, in this paper, we propose a learnable three-dimensional (3D) Gabor convolutional network with global affinity attention for HSI classification. More precisely, the learnable 3D Gabor convolution kernel is constructed by the 3D Gabor filter, which can be learned and updated during the training process. Furthermore, spatial and spectral global affinity attention modules are introduced to capture more discriminative features between spatial locations and spectral bands in the patch cube, thus alleviating the interfering pixels problem. Experimental results on three well-known HSI datasets (including two natural crop scenarios and one urban scenario) have demonstrated that the proposed network can achieve powerful classification performance and outperforms widely used machine-learning-based and deep-learning-based methods.     

Machine learning for detailed chemistry reduction in DNS of a syngas turbulent oxy-flame with side-wall effects

A novel chemistry reduction strategy based on convolutional neural networks (CNNs) is developed and applied to direct numerical simulation (DNS) of a turbulent non-premixed flame interacting with a cooled wall. The fuel syngas mixture is burning in pure oxygen. The training and the subsequent application of the CNN rely on the processing of two-dimensional (2D) images built from species mass fractions and temperature (CNN input), to predict the corresponding chemical sources at the center of the image (CNN output). This image-type treatment of chemistry is found to efficiently capture intermediate radicals species highly sensitive to the local flame topology. To reduce the CPU cost, a simplified 2D DNS database with detailed chemistry serves as reference and is used for training and testing the neural network. Comparisons are also made a posteriori against the same 2D DNS with a reduced chemical scheme specialized for syngas. Then, three-dimensional (3D) DNS are conducted either with CNN or the reduced chemistry for more a posteriori tests. The CNN reduced chemistry outperforms the reduced Arrhenius based mechanism in the prediction of radical species, such as monoatomic hydrogen, and also in terms of CPU cost.     

Recognizing pedestrian’s unsafe behaviors in far-infrared imagery at night

Pedestrian behavior recognition is important work for early accident prevention in advanced driver assistance system (ADAS). In particular, because most pedestrian-vehicle crashes are occurred from late of night to early of dawn, our study focus on recognizing unsafe behavior of pedestrians using thermal image captured from moving vehicle at night. For recognizing unsafe behavior, this study uses convolutional neural network (CNN) which shows high quality of recognition performance. However, because traditional CNN requires the very expensive training time and memory, we design the light CNN consisted of two convolutional layers and two subsampling layers for real-time processing of vehicle applications. In addition, we combine light CNN with boosted random forest (Boosted RF) classifier so that the output of CNN is not fully connected with the classifier but randomly connected with Boosted random forest. We named this CNN as randomly connected CNN (RC-CNN). The proposed method was successfully applied to the pedestrian unsafe behavior (PUB) dataset captured from far-infrared camera at night and its behavior recognition accuracy is confirmed to be higher than that of some algorithms related to CNNs, with a shorter processing time.     

Robustness Design for CNN Templates with Performance of Extracting Closed Domain

The cellular neural/nonlinear network (CNN) is a powerful tool for image and video signal processing, robotic and biological visions. This paper introduces a kind of CNNs with performance of extracting closed domains in binary images, and gives a general method for designing templates of such a kind of CNNs. One theorem provides parameter inequalities for determining parameter intervals for implementing prescribed image processing functions, respectively. Examples for extracting closed domains in binary scale images are given.     

Hybrid quantum-classical convolutional neural networks

Deep learning has been shown to be able to recognize data patterns better than humans in specific circumstances or contexts. In parallel, quantum computing has demonstrated to be able to output complex wave functions with a few number of gate operations,which could generate distributions that are hard for a classical computer to produce. Here we propose a hybrid quantum-classical convolutional neural network(QCCNN), inspired by convolutional neural networks(CNNs) but adapted to quantum computing to enhance the feature mapping process. QCCNN is friendly to currently noisy intermediate-scale quantum computers, in terms of both number of qubits as well as circuit's depths, while retaining important features of classical CNN, such as nonlinearity and scalability. We also present a framework to automatically compute the gradients of hybrid quantum-classical loss functions which could be directly applied to other hybrid quantum-classical algorithms. We demonstrate the potential of this architecture by applying it to a Tetris dataset, and show that QCCNN can accomplish classification tasks with learning accuracy surpassing that of classical CNN with the same structure.     

Measurement of jet shapes in high-Q^2 deep inelastic scattering at HERA

The shapes of jets with transverse energies, , up to 45 GeV produced in neutral- and charged-current deep inelastic scattering (DIS) at GeV have been measured with the ZEUS detector at HERA. Jets are identified using a cone algorithm in the - plane with a cone radius of one unit. The jets become narrower as increases. The jet shapes in neutral- and charged-current DIS are found to be very similar. The jets in neutral-current DIS are narrower than those in resolved processes in photoproduction and closer to those in direct-photon processes for the same ranges in and jet pseudorapidity. The jet shapes in DIS are observed to be similar to those in interactions and narrower than those in collisions for comparable . Since the jets in interactions and DIS are predominantly quark initiated in both cases, the similarity in the jet shapes indicates that the pattern of QCD radiation within a quark jet is to a large extent independent of the hard scattering process in these reactions. Received: 2 April 1998 / Published online: 7 April 1999     

Weakly Supervised Building Semantic Segmentation Based on Spot-Seeds and Refinement Process

Automatic building semantic segmentation is the most critical and relevant task in several geospatial applications. Methods based on convolutional neural networks (CNNs) are mainly used in current building segmentation. The requirement of huge pixel-level labels is a significant obstacle to achieve the semantic segmentation of building by CNNs. In this paper, we propose a novel weakly supervised framework for building segmentation, which generates high-quality pixel-level annotations and optimizes the segmentation network. A superpixel segmentation algorithm can predict a boundary map for training images. Then, Superpixels-CRF built on the superpixel regions is guided by spot seeds to propagate information from spot seeds to unlabeled regions, resulting in high-quality pixel-level annotations. Using these high-quality pixel-level annotations, we can train a more robust segmentation network and predict segmentation maps. To iteratively optimize the segmentation network, the predicted segmentation maps are refined, and the segmentation network are retrained. Comparative experiments demonstrate that the proposed segmentation framework achieves a marked improvement in the building’s segmentation quality while reducing human labeling efforts.     

A Color Image Encryption Algorithm Based on Double Fractional Order Chaotic Neural Network and Convolution Operation

A color image encryption algorithm based on double fractional order chaotic neural network (CNN), interlaced dynamic deoxyribonucleic acid (DNA) encoding and decoding, zigzag confusion, bidirectional bit-level diffusion and convolution operation is proposed. Firstly, two fractional order chaotic neural networks (CNNs) are proposed to explore the application of fractional order CNN in image encryption. Meanwhile, spectral entropy (SE) algorithm shows that the sequence generated by the proposed fractional order CNNs has better randomness. Secondly, a DNA encoding and decoding encryption scheme with evolutionary characteristics is adopted. In addition, convolution operation is utilized to improve the key sensitivity. Finally, simulation results and security analysis illustrate that the proposed algorithm has high security performance and can withstand classical cryptanalysis attacks.     

Nondeterministic approach to tree-based jet substructure

Jet substructure is typically studied using clustering algorithms, such as k(T), which arrange the jets' constituents into trees. Instead of considering a single tree per jet, we propose that multiple trees should be considered, weighted by an appropriate metric. Then each jet in each event produces a distribution for an observable, rather than a single value. Advantages of this approach include (1) observables have significantly increased statistical stability, and (2) new observables, such as the variance of the distribution, provide new handles for signal and background discrimination. For example, we find that employing a set of trees substantially reduces the observed fluctuations in the pruned mass distribution, enhancing the likelihood of new particle discovery for a given integrated luminosity. Furthermore, the resulting pruned mass distributions for (background) QCD jets are found to be substantially wider than that for (signal) jets with intrinsic mass scales, e.g., boosted W jets. A cut on this width yields a substantial enhancement in significance relative to a cut on the standard pruned jet mass alone. In particular the luminosity needed for a given significance requirement decreases by a factor of 2 relative to standard pruning.