利用图像区域自然尺度特征的海面舰船目标检测

为了提高动态海面背景中目标的检测性能,提出了一种新的基于图像区域自然尺度特征的海面舰船目标检测算法.算法将一维信号的自然尺度特征提取方法拓展到二维图像信号,通过相空间重构和分类,提取了图像灰度时间序列的自然尺度特征.利用BP神经网络,得到背景与目标自然尺度特征的辨识模型,然后对图像序列的自然尺度进行分类,检测得到舰船目...     

Optimizing feature extraction for multiclass problems

Feature extraction has been an important research topic in pattern classification and has been studied extensively by many researchers. Most of the conventional feature extraction methods are performed using a criterion function defined between two classes or a global function. Although these methods work relatively well in most cases, it is generally not optimal in any sense for multiclass problems. In order to address this problem, the authors propose a method to optimize feature extraction for multiclass problems. The authors first investigate the distribution of classification accuracies of multiclass problems in the feature space and find that there exist much better feature sets that the conventional feature extraction algorithms fail to find. Then the authors propose an algorithm that finds such features. Experiments with remotely sensed data show that the proposed algorithm consistently provides better performances compared with the conventional feature extraction algorithms     

Bidirectional recurrent neural networks

In the first part of this paper, a regular recurrent neural network (RNN) is extended to a bidirectional recurrent neural network (BRNN). The BRNN can be trained without the limitation of using input information just up to a preset future frame. This is accomplished by training it simultaneously in positive and negative time direction. Structure and training procedure of the proposed network are explained. In regression and classification experiments on artificial data, the proposed structure gives better results than other approaches. For real data, classification experiments for phonemes from the TIMIT database show the same tendency. In the second part of this paper, it is shown how the proposed bidirectional structure can be easily modified to allow efficient estimation of the conditional posterior probability of complete symbol sequences without making any explicit assumption about the shape of the distribution. For this part, experiments on real data are reported     

Modulation classification in the presence of adjacent channel interference using convolutional neural networks

This paper investigates a vital issue in wireless communication systems, which is the modulation classification. A proposed framework for modulation classification based on deep learning (DL) is presented in the presence of adjacent channel interference (ACI). This framework begins with the generation of constellation diagrams from the received data. These constellation diagrams are fed to convolutional neural networks (CNNs) for modulation classification. The objective of this process is to eliminate the manual feature extraction from the received data and make feature extraction process as a built‐in step with CNNs. Three types of CNNs are considered in this paper and compared for this objective. These types are AlexNet, VGG‐16, and VGG‐19. The proposed classifier is applied on Rayliegh and Rician fading channels.     

Classification and Detection of Single Evoked Brain Potentials Using Time-Frequency Amplitude Features

The classification and detection of event-related brain potentials was investigated using signal processing and statistical pattern recognition techniques. Amplitudes at sampled time points and frequency quantities have previously been used as features. Improvements to these procedures were obtained by using features from the time-frequency plane to utilize the geometric relationship between time and frequency, capitalizing on the nonstationarity of the evoked potential signals. These features were transformed from the original data sets based upon a two-step classification/feature selection procedure which uses selected frequencies from step 1 as parameters for data filtering in step 2. Features were selected from the filtered data, classifiers were designed, and the estimated classification accuracies were computed.     

基于图像配准的混合遗传FCM算法研究

针对目前图像变化检测的相关研究,提出一种新的算法:基于SAR图像配准的混合遗传FCM算法.算法主要分为4个步骤.第一步,利用Harris算法和SIFT算法对两幅图像进行匹配,证明它们是同源不同时相的图像.第二步,利用两种不同变化检测方法提取初步差异图像.第三步,利用PCA方法对差异图像进行降维处理.第四步,利用混合遗传FCM算法对特征矢量空间进行分类,并将分类结果与参考差异图像进行比较,获得变换信息.采用渥太华地区的部分图像作为检测算法的性能的数据库.获得的结果与FCM算法相比较,结果表明,提出的算法具有最高的全局正确率98.10％,算法效果更佳.     

Data-Derived Symbol Synchronization of MASK and QASK Signals

Much has been said in the literature with regard to the problem of establishing symbol synchronization in binary baseband digital communication systems. By comparison, the literature contains little information relating to the extraction of symbol sync from multilevel baseband data. With the recent interest in multilevel amplitude-shift keying (MASK) and quadrature amplitude-shift keying (QASK) as signaling techniques for multilevel digital communications systems, the problem of providing symbol synchronization in the receivers of such systems becomes paramount. This paper presents a technique for extracting symbol sync from an MASK or QASK signal which has been transmitted over an infinite bandwidth white Gaussian noise channel. The scheme is essentially a generalization of the data transition tracking loop (DTTL) which has heretofore been used in PSK systems. The performance of the loop is analyzed in terms of its mean-squared symbol sync jitter and its effects on the data detection process in MASK and QASK systems.     

基于加权模糊C均值算法改进的高光谱图像分类方案设计

为了有效改善高光谱图像数据分类的精确度,减少对大数目数据集的依赖,在原型空间特征提取方法的基础上提出一种基于加权模糊C均值算法改进型原型空间特征提取方案。该方案通过加权模糊 C 均值算法对每个特征施加不同的权重,从而保证提取后的特征含有较高的信息量。实验结果表明,与业内公认的原型空间提取算法相比 该方案在相对较小的数据集下,其性能仍具有较为理想的稳定性,且具有相对较高的分类精度,这样子就大大降低了对数据集样本数量的依赖性,同时改善了原型空间特征方法的效率。     

基于免疫克隆高斯过程隐变量模型的SAR目标特征提取与识别

作为一种非线性维数约减算法,高斯过程隐变量模型(Gaussian process latent variable model,GPLVM)由于其适合处理小样本、高维数据,因而在模式识别、计算机视觉等领域得到了广泛应用.基于此,提出一种基于改进GPLVM的SAR图像目标特征提取及自动识别方法,其中利用改进的GPLVM进行特征提取,高斯过程分类进行目标识别.传统GPLVM使用共轭梯度法对似然函数进行优化,为避免梯度估值易受噪声干扰、步长对算法影响严重等缺点,提出基于免疫克隆选择算法的GPLVM,利用其具有快速收敛到全局最优的特性提高算法性能.实验结果表明,该算法不仅降低了特征维数,且提高了识别精度,从而验证了算法用于SAR图像目标识别的有效性.     

基于轻量级光谱-空间注意力交互网络的高光谱地物分类研究

通过引入基于卷积神经网络(convolutional neural network, CNN)的分类算法,高光谱图像(hyperspectral image, HSI)分类任务的精度取得显著的提升,但目前主流CNN算法往往较为复杂且参数量大,从而导致网络难以训练以及容易产生过拟合问题。为在保证网络分类性能的前提下实现轻量化,本文提出一个轻量级架构的基于光谱-空间注意力交互机制的CNN网络用于HSI分类。为实现HSI的光谱-空间特征提取,构建了一个轻量化的双路径骨干网络用于两种特征的提取和融合。其次,为提高特征的表征能力,设计了两个注意力模块分别用于光谱和空间特征的权重再调整。同时,为加强双路径特征之间的关联以实现特征的更好融合,注意力交互机制被引入到网络中以进一步提升网络性能。在3个真实HSI数据集上的分类结果表明,本文所提网络可达到99.5%的分类准确度,并相比于其他网络至少减少50%的参数量。     

基于特征提取相似日的ELM短期负荷预测研究

为解决短期电力负荷预测中预测精度差、计算时间长等问题,提出一种基于自组织特征映射网络进行特征提取相似日的极限学习机短期电力负荷预测方法。通过自组织特征映射网络找出与预测日同类型的历史数据作为训练样本;并采用预测能力强、计算时间短的ELM网络进行预测。以某市电力负荷数据进行仿真,并将上述方法与传统神经网络进行对比。仿真算例表明,基于特征提取相似日的ELM方法具有较高的预测精度,泛化性能好,且运算时间短。     

基于深度学习网络的神经元自适应投影分类方法

传统的基于几何形态的神经元分类方法依赖于神经元空间结构特征的提取与选择,会损失大量有用的神经元分类信息.应用自适应投影算法将三维神经元进行转换,不需要提取神经元的几何特征,提出了一种基于深度学习网络的神经元几何形态分类方法.该方法将原始神经元数据进行三维体素重建,经过自适应投影过程构成二维神经元图像数据,并构建了基于双卷积门限循环神经网络的深度学习模型对神经元进行分类.将该方法应用于三种神经元分类数据集,通过与基于特征提取的神经元分类方法相比,实验结果表明该方法具有更高的分类准确率和良好的适应能力.     

一种构造系数的自相关函数特征提取算法

由于遥感影像具有数据量大、维数高和不确定性等特点,遥感影像的分类已经远远超出了人的分析和解译能力,为了达到理想的分类效果,提取深层次空间结构信息的需求越来越强烈。根据各类样本的均值和方差构造加权系数,对样本的自相关函数进行加权,提出1种新的自相关函数特征提取算法,以改善样本不足造成的分类精度较低问题;采用支持向量机方法,对新的样本数据进行训练与分类性能研究。实验结果表明分类精度提高,在一定程度上能够反映遥感影像的深层次空间结构信息,验证了此算法的有效性与可行性。     

KFDA and clustering based multiclass SVM for intrusion detection

To improve the classification accuracy and reduce the training time, an intrusion detection technology is proposed, which combines feature extraction technology and multiclass support vector machine （SVM） classification algorithm. The intrusion detection model setup has two phases. The first phase is to project the original training data into kernel fisher discriminant analysis （KFDA） space. The second phase is to use fuzzy clustering technology to cluster the projected data and construct the decision tree, based on the clustering results. The overall detection model is set up based on the decision tree. Results of the experiment using knowledge discovery and data mining （KDD） from 99 datasets demonstrate that the proposed technology can be an an effective way for intrusion detection.     

复合不变矩的特征提取

特征提取的目的是提取出一些精简、准确有效的数据来提高图像识别和分类的效率和准确率。在系统识别缺陷过程中,特征提取是很关键的一步,它是系统判别图片有无缺陷或分类的基础不变矩概念清晰、识别率稳定,对具有平移、旋转、尺度等变化的目标具有良好的不变性及抗干扰能力,能有效地反映图像的本质特征。在此分别采用HU不变矩、Zernike不变矩和该文提出的复合不变矩分别对塑料平板图片进行特征提取,反应出复合不变矩具有平移、尺度和旋转不变性。结果表明它能提供更全面特征信息,具有较高的抗噪能力,是行之有效的特征参数。     

Symbolic Time Series Analysis of Temporal Gait Dynamics

Signals obtained from biological systems exhibit pronounced complexity. The patterns of change contain valuable information about the dynamics of underlying control mechanism of the complex biological systems. Human gait is a complex process with multiple inputs and numerous outputs. Various complexity analysis tools have been proposed to extract information from human gait time series. In this study, we used recently developed threshold based symbolic entropy to compare the spontaneous output of the human locomotors system during constrained and metronomically paced walking protocols. For that purpose, stride interval time series of healthy subjects who walked for 1 h at normal, slow and fast rates under different conditions was transformed into symbol sequences. Normalized corrected Shannon entropy (NCSE) was computed from the symbol sequences of the stride interval time series. The findings indicated that the unprompted output of human locomotors system is more complex during unconstrained normal walking as compared with slow, fast or metronomically paced walking.     

Graph-Laplacian features for neural waveform classification

Analysis of extracellular recordings of neural action potentials (known as spikes) is highly dependent upon the accuracy of neural waveform classification, commonly referred to as spike sorting. Feature extraction is an important stage of this process because it can limit the quality of clustering that is performed in the feature space. Principal components analysis (PCA) is the most commonly used feature extraction method employed for neural spike recordings. To improve upon PCA's feature extraction performance for neural spike sorting, we revisit the PCA procedure to analyze its weaknesses and describe an improved feature extraction method. This paper proposes a linear feature extraction technique that we call graph-Laplacian features, which simultaneously minimizes the graph Laplacian and maximizes variance. The algorithm's performance is compared with PCA and a wavelet-coefficient-based feature extraction algorithm on simulated single-electrode neural data. A cluster-quality metric is proposed to quantitatively measure the algorithm performance. The results show that the proposed algorithm produces more compact and well-separated clusters compared to the other approaches.     

人脸识别中基于熵的局部保持特征提取算法

传统的局部线性流形特征提取算法以方差贡献率为特征提取质量评价准则,不能保证降维后的分类性能。为此,提出了一种基于香农熵的局部保持特征提取算法,采用总体熵描述特征提取对分类的不确定性,并作为特征提取的评价准则。分析与人脸识别实验表明,相对于局部线性流形特征提取算法,提出方法在保持数据局部特性的同时,改善了特征提取的分类性能。     

Framework for Content‐Based Image Identification with Standardized Multiview Features

Information identification with image data by means of low‐level visual features has evolved as a challenging research domain. Conventional text‐based mapping of image data has been gradually replaced by content‐based techniques of image identification. Feature extraction from image content plays a crucial role in facilitating content‐based detection processes. In this paper, the authors have proposed four different techniques for multiview feature extraction from images. The efficiency of extracted feature vectors for content‐based image classification and retrieval is evaluated by means of fusion‐based and data standardization–based techniques. It is observed that the latter surpasses the former. The proposed methods outclass state‐of‐the‐art techniques for content‐based image identification and show an average increase in precision of 17.71% and 22.78% for classification and retrieval, respectively. Three public datasets — Wang; Oliva and Torralba (OT‐Scene); and Corel — are used for verification purposes. The research findings are statistically validated by conducting a paired t‐test.     

基于差异度迭代的极化SAR图像机场跑道检测算法

机场在军事和交通运输领域都有很重要的作用,对它的自动检测具有重大意义。本文提出了一种利用极化SAR(Polarimetric Synthetic Aperture Radar)图像检测机场跑道的方法。首先,利用SLIC(Simple linear Iterative Clustering)算法对极化SAR图像进行超像素分割;然后利用新三分量分解和极化散射熵对图像进行粗分类,再利用改进的K均值聚类结合差异度迭代的方法完成精细分类,最后利用跑道的散射特性和几何结构特征从分类结果中提取完整的机场区域。本文采用极化SAR数据进行实验检测,结果表明该方法能有效的检测出机场跑道,并且保持结构完整,边缘细节清晰,虚警率低。