Advanced Satellite Image Classification of Various Resolution Image Using a Novel Approach of Deep Neural Network Classifier

Wireless Personal Communications - Image registration is computationally intensive and applied in a variety of applications, for example, multispectral classification, change recognition, climate...     

基于分数布朗运动和概率神经网络的自然纹理分类

该文基于自然纹理的分数布朗运动(FBM)模型,引入一种新的分形特征参数分形尺度,提出计算分形尺度的截矩线性度(IAL)方法。实验表明,将纹理图像的分形尺度与分形维数结合,既反映了物理表面分形的尺度范围又反映了该尺度范围内的纹理粗糙程度,从而更有效地描述和区分纹理特征。文中利用纹理图像在水平、垂直和对角3个方向上的分形尺度和分形维数作为特征集,采用概率神经网络(PNN)作为分类器进行自然纹理图像分类,得到准确的分类结果。     

Defect Prediction in Android Binary Executables Using Deep Neural Network

Software defect prediction locates defective code to help developers improve the security of software. However, existing studies on software defect prediction are mostly limited to the source code. Defect prediction for Android binary executables (called apks) has never been explored in previous studies. In this paper, we propose an explorative study of defect prediction in Android apks. We first propose smali2vec, a new approach to generate features that capture the characteristics of smali (decompiled files of apks) files in apks. Smali2vec extracts both token and semantic features of the defective files in apks and such comprehensive features are needed for building accurate prediction models. Then we leverage deep neural network (DNN), which is one of the most common architecture of deep learning networks, to train and build the defect prediction model in order to achieve accuracy. We apply our defect prediction model to more than 90,000 smali files from 50 Android apks and the results show that our model could achieve an AUC (the area under the receiver operating characteristic curve) of 85.98% and it is capable of predicting defects in apks. Furthermore, the DNN is proved to have a better performance than the traditional shallow machine learning algorithms (e.g., support vector machine and naive bayes) used in previous studies. The model has been used in our practical work and helped locate many defective files in apks.     

Classification of Breast Abnormalities Using a Deep Convolutional Neural Network and Transfer Learning

Journal of Communications Technology and Electronics - A new algorithm for classification of breast pathologies in digital mammography using a convolutional neural network and transfer learning is...     

稀疏卷积神经网络用于低成本图像分类系统稀疏卷积神经网络用于低成本图像分类系统

传统卷积神经网络大量的计算及内存需求使嵌入式设备智能应用的开发成为挑战,为尝试将高度复杂的深度学习应用与性能有限的低成本嵌入式平台相结合,设计了一款小型嵌入式图像分类系统.实验基于结构化稀疏学习算法在Caffe框架下构建结构稀疏卷积神经网络模型,将其部署在工业派(IndustriPi)最小化系统上,通过测试得到了85....     

基于深度卷积神经网络的图上半监督极化SAR图像分类算法

为实现在只有少量标记数据情况下的高质量的图像分类,本文提出了一种基于深度卷积神经网络的图上半监督极化SAR图像分类算法.该算法将极化SAR图像建模为无向图,并基于该无向图,定义了包含半监督项,卷积神经网络项和类标光滑项的能量函数.算法所采用的卷积神经网络提取抽象的数据驱动的极化特征.半监督项约束了有标记像素的类标在分类过程中保持不变.类标光滑项约束了像素间类标的光滑性.基于对PauliRGB图像进行超像素分割而产生的初始化类标图,交替迭代优化所定义的能量函数直至其收敛.在两幅真实极化SAR图像上的实验结果表明,该算法达到了优异的分类效果,其性能优于当前已有算法.     

No-reference Stereoscopic Image Quality Assessment Using Binocular Self-similarity and Deep Neural Network

Quality assessment of three-dimensional (3D) images is more challenging than that of 2D images. The quality of 3D visual experience is one of the most challenging areas of human binocular perception and is affected by multiple factors such as asymmetric stereo image/video compression, depth perception, visual discomfort, and single view quality. In this paper, we propose a new no-reference quality assessment method for stereoscopic images based on Binocular Self-similarity (BS) and Deep Neural Networks (DNN). To be more specific, a BS index is defined and computed according to binocular rivalry and suppression based on the depth image-based rendering technique. Then, a DNN is trained in an opinion unaware way to predict local quality. Binocular integration (BI) index is calculated by using the trained DNN, accounting for binocular integration behaviors. Finally, the final quality score of stereoscopic image is obtained by combining the BS and BI indexes together. Experimental results on four public 3D image quality assessment databases demonstrate that compared with existing methods, the proposed method can achieve high consistency with subjective perception on stereoscopic images with both symmetric and asymmetric distortions.     

基于深度卷积神经网络和多核学习的遥感图像分类方法

为解决传统遥感图像分类方法特征提取过程复杂、特征表现力不强等问题,该文提出一种基于深度卷积神经网络和多核学习的高分辨率遥感图像分类方法。首先基于深度卷积神经网络对遥感图像数据集进行训练,学习得到两个全连接层的输出将作为遥感图像的两种高层特征;然后采用多核学习理论训练适合这两种高层特征的核函数,并将它们映射到高维空间,实现两种高层特征在高维空间的自适应融合;最后在多核融合特征的基础上,设计一种基于多核学习-支持向量机的遥感图像分类器,对遥感图像进行精确分类。实验结果表明,与目前已有的基于深度学习的遥感图像分类方法相比,该算法在分类准确率、误分类率和Kappa系数等性能指标上均有所提升,在实验测试集上3个指标分别达到了96.43%, 3.57%和96.25%,取得了令人满意的结果。

     

用神经元网络识别仿射变换下的飞机模型

本文推广了付立叶描绘矛的方法,产生了一组在任意仿射变换下都不改变的不变量,用这些不变量来训练一个三层网感知器对飞机模型进行识别和分类.在本文中我们引进了一个加速算法可以大大减少学习时间.最后,给出了用这个神经网分类器进行识别和分类的结果及其抗噪声性能.     

Blind Equalization Using a Novel Recurrent Neural Network Training Algorithm

ＢｌｉｎｄＥｑｕａｌｉｚａｔｉｏｎＵｓｉｎｇａＮｏｖｅｌＲｅｃｕｒｒｅｎｔＮｅｕｒａｌＮｅｔｗｏｒｋＴｒａｉｎｉｎｇＡｌｇｏｒｉｔｈｍＭａｎｕｓｃｒｉｐｔｒｅｃｅｉｖｅｄＮｏｖ．２１，１９９６．Ｔｈｉｓｐｒｏｇｒａｍｗａｓｓｕｐｐｏｒｔｅｄｂｙｔｈｅ...     

基于卷积神经网络的超声红外热图像分类

在超声红外热像技术应用中,从红外热图像来判断被测对象是否含有裂纹,通常需要先基于人工经验,从红外热图像中提取特征再采用某种模式识别方法进行分类,裂纹的识别与定位过程繁琐且识别率较低.为此,提出一种基于卷积神经网络技术的超声红外热图像裂纹检测与识别方法,其特点是可以直接从超声红外图像中学习特征进而实现是否含有裂纹红外热图...     

A Convolutional and Transformer Based Deep Neural Network for Automatic Modulation Classification

Automatic modulation classification(AMC) aims at identifying the modulation of the received signals, which is a significant approach to identifying the target in military and civil applications. In this paper, a novel data-driven framework named convolutional and transformer-based deep neural network(CTDNN) is proposed to improve the classification performance. CTDNN can be divided into four modules, i.e., convolutional neural network(CNN) backbone, transition module, transformer module, and fin...     

一种用于图像编码的区域分割新方法

为了适应图像分割编码的需要,提高编码性能和效率,本文研究了一种图像区域分割新方法.源于人眼成像原理和视神经网络的知觉分割特性,首先提出一种具有脉冲耦合和梯度锐化能力的神经元网络模型.然后通过构造一个拟合函数对相邻神经元的相似刺激输入进行平滑处理,而对具有不连续变化特性的刺激输入进行锐化,使得神经元比较容易地感知到均匀亮度区域和目标边缘的准确位置.最后通过实验验证了该算法的有效性.本文算法能够准确、有效地的分割出均匀区域,并且与原始图像具有很好的对应关系.在将本文算法应用到图像区域分割编码中,能够大大提高编码的效率,并得到高质量的重建图像.     

Monaural Speech Separation Using Dual-Output Deep Neural Network with Multiple Joint Constraint

Monaural speech separation is a significant research field in speech signal processing. To achieve a better separation performance, we propose three novel joint-constraint loss functions and a multiple joint-constraint loss function for monaural speech separation based on dual-output deep neural network(DNN). The multiple joint-constraint loss function for DNN separation model not only restricts the ideal ratio mask(IRM) errors of the two outputs, but also constrains the relationship of the esti...     

基于小波变换和深度网络的着陆地貌图像分类

针对无人机着陆地貌图像场景复杂、纹理特征丰富等问题,提出一种基于小波变换和深度网络的无人机着陆地貌图像分类算法.利用非下采样小波变换(Non-Subsampled Wavelet Transform,NSWT)的快速压缩能力,将小波变换后的前两层子图系数引入到卷积神经网络(CNN)中,压缩数据量.根据无人机着陆地貌图像的特点,采用轻量化卷积模块设计了15层卷积神经网络.通过支持向量机(SVM)实现复杂地貌场景的正确分类.实验结果表明:所提算法具有良好的特征表达能力,提升了着陆地貌图像的分类准确率.     

基于神经网络的新型缺陷接地结构优化设计

应用人工神经网络与单纯形优化算法相结合的方法,对一种新型组合式非周期性缺陷接地结构(CNPDGS)进行优化设计.与电磁场数值分析方法相比,以神经网络模型作分析单元,可以在保证精度的基础上大大提高分析速度,因此在优化设计中可用来替代FDTD分析方法作为结构分析的计算单元.本文中以所要求的传输系数为期望日标,以可以使误差函数达到极小化的结构尺寸为输出,经单纯形优化算法寻优,进行该具有双阻带特性CNPDGS的优化设计.仿真设计和实验的对比结果表明了这一方法的有效性.     

一种基于多尺度卷积神经网络和分类统计的图像去雾霾方法

传统的去雾霾方法会导致天空、白云和明亮区域内的颜色失真.为了解决以上问题,提出了一种基于多尺度卷积神经网络和分类统计的去除图像雾霾的方法.首先用多尺度卷积神经网络估计图像的透射率,其次对所估计的透射率进行分类统计以确定在暗通道内天空、白云和明亮区域的像素值,最后通过低通高斯滤波器平滑图像场景的辐射度,得到恢复的无雾霾图像.实验结果表明,采用提出的方法对图像去雾霾后明亮区域内的颜色不会失真,且保留了图像的自然外观,对合成图像和真实图像均有较好的去雾霾效果.     

基于状态连续变化的Hopfield神经网络的图像复原

针对图像复原提出了神经元状态连续变化的Hopfield神经网络模型,详细讨论了两种连续函数串行、全并 行复原算法的收敛性和参数选择,仿真实验表明,该模型能够精确达到能量极小点,并对复原图像的信噪比有一定的提高。     

一种基于有序二元决策图和布尔函数性质计算网络可靠性的算法

有序二元决策图(OBDD)被广泛用到网络可靠度的计算中,在基于OBDD计算网络可靠度时,其计算时间主要取决于参与操作的OBDD的大小,而OBDD的大小严重依赖于OBDD的变量序。该文根据布尔函数的性质和OBDD原理提出一种优化计算网络可靠性的算法(BF-OBDD),提高计算网络可靠性的效率。实验结果表明改进的算法有较少的 OBDD节点数量,在计算网络可靠性时,花费的时间较少。     

Soft Fault Classification of Analog Circuits Using Network Parameters and Neural Networks

A new method to identify component faults in analog circuits is proposed using network parameters like driving point impedance, transfer impedance, voltage gain and current gain. Using Monte-Carlo simulation each component of the circuit is varied within its tolerance limit and samples of each network parameter are found for fault free circuit. Similarly all possible single faults are introduced and the corresponding samples of network parameters are found. Fault classification is done through neural network. The proposed method is validated through second order Sallenkey band pass filter. Numerical results are presented to clarify the proposed method and prove its efficiency.