基于I-BGLAM纹理和光谱融合的高光谱显微成像木材树种分类

为了提高木材树种分类的正确率,提出了一种基于I-BGLAM纹理特征和光谱特征融合的高光谱图像的木材树种分类方法。实验数据是利用SOC710VP高光谱成像仪获取的可见光/近红外（372.53~1 038.57 nm）范围内的高光谱图像。首先,利用基于OIF的特征波段选择方法降低高光谱图像的维数,选择出含有信息量大的波段。其次,对选择出的波段图像使用NSCT及NSCT逆变换得到融合图像,对得到的融合图像使用I-BGLAM提取其纹理特征。与此同时,对高光谱图像的全波段求取平均光谱并进行S-G（Savitzky-Golay）平滑得到光谱特征。最后,将得到的纹理特征和光谱特征融合后送进极限学习机（ELM）中进行分类。此外,还和基于灰度共生矩阵（GLCM）的木材识别的传统方法以及近几年木材树种识别领域内被提出的主流方法进行了比较。该研究主要创新点有两个：一是将强纹理提取器I-BGLAM用于高光谱图像中提取其纹理特征;二是提出一种新的特征融合的模型用于高光谱图像的分类。针对8个树种的实验结果表明,单独使用I-BGLAM提取的纹理特征来进行分类的正确率最高可到达88.54%,而使用GLCM提取纹理特征的传统方法正确率最高只有76.04%,该结果可以得出本文使用I-BGLAM在纹理特征提取方面要优于GLCM,这为后面建立的融合模型打下很好的基础,单独使用平均光谱特征来分类的正确率最高可以达到92.71%,使用所提出的特征融合方法所得到的分类正确率最高可达到100%,这说明使用所提出的融合模型来分类要比以前单独使用某一种特征的分类模型要好。此外,使用所提出的方法得到的分类正确率要高于本领域内其他两种主流的识别方法。因此,所提出的基于I-BGLAM纹理特征和光谱特征融合的方法能够提高木材树种分类的正确率,该方法在木材树种分类方面有着一定的利用价值。     

Detection of Coronary Artery Disease Using Multi-Domain Feature Fusion of Multi-Channel Heart Sound Signals

Heart sound signals reflect valuable information about heart condition. Previous studies have suggested that the information contained in single-channel heart sound signals can be used to detect coronary artery disease (CAD). But accuracy based on single-channel heart sound signal is not satisfactory. This paper proposed a method based on multi-domain feature fusion of multi-channel heart sound signals, in which entropy features and cross entropy features are also included. A total of 36 subjects enrolled in the data collection, including 21 CAD patients and 15 non-CAD subjects. For each subject, five-channel heart sound signals were recorded synchronously for 5 min. After data segmentation and quality evaluation, 553 samples were left in the CAD group and 438 samples in the non-CAD group. The time-domain, frequency-domain, entropy, and cross entropy features were extracted. After feature selection, the optimal feature set was fed into the support vector machine for classification. The results showed that from single-channel to multi-channel, the classification accuracy has increased from 78.75% to 86.70%. After adding entropy features and cross entropy features, the classification accuracy continued to increase to 90.92%. The study indicated that the method based on multi-domain feature fusion of multi-channel heart sound signals could provide more information for CAD detection, and entropy features and cross entropy features played an important role in it.     

圈养瓶鼻海豚通讯信号分析及融合分类方法

针对圈养条件下瓶鼻海豚通讯信号（whistle）分类时混叠大量回声定位信号（click）导致分类正确率降低的问题,提出了一种基于机器学习的融合分类方法。分别提取whistle信号的时频分布特征训练随机森林分类器,梅尔时频图特征训练卷积神经网络分类器,在此基础上设计融合判决器对混叠whistle信号进行分类识别。对圈养海豚声信号采集实验数据的分类识别结果表明,融合分类方法具有更好的分类性能,对混叠whistle信号分类正确率大于94%,优于时频分布特征分类器和梅尔时频图特征分类器,能够提高混叠信号的分类能力。      

Fusion of deep shallow features and models for speaker recognition

In order to further improve the performance of speaker recognition, features fusion and models fusion are proposed. The features fusion method is to fuse deep and shallow features. The fused feature describes speaker characteristics more comprehensively than a single feature because of the complementarity between different levels of features. The models fusion method is to fuse i-vectors extracted from different speaker recognition systems. The fused model can combine advantages of different speaker recognition systems. Experimental results show the effectiveness of the proposed methods. Compared with the state-of-the-art system on CASIA North and South dialect corpus,the proposed features fusion system and models fusion system achieved about 54.8% and 69.5% relative improvement on the equal error rate(EER),respectively.     

基于自适应无参经验小波变换和选择集成分类模型的运动想象

运动想象模式识别率的提高对脑机接口(BCI)技术的应用具有重要意义,本文采用自适应无参经验小波变换(APEWT)和选择集成分类模型相结合的方法提高脑电(EEG)信号的分类识别准确率.首先,通过APEWT将EEG信号分解成不同的模态;然后,使用最优模态重构后的信号计算其能量谱(ES)特征,使用最优模态分量计算其边际谱(MS)特征;最后,将不同时间段的ES特征和不同频段的MS特征输入到构建的选择集成分类模型中,从而得到其分类结果,并将该方法与其他4种组合方法进行比较.实验结果表明,本文方法具有较好分类准确率和实时性,其平均分类正确率高于其他4种方法,同时较近期使用相同数据的文献也有优势.本文为在线运动想象类BCI的应用提供了新的方法和思路.     

联合稀疏表示在水下目标分类中的应用

水下目标分类识别的性能受所选特征的限制,多特征往往可以获得更加稳定的结果,针对这一问题,提出了一种基于联合稀疏表示模型的水下目标分类识别方法。首先对水下目标回波信号提取3种具有信息互补性与关联性的特征:中心矩特征、小波包能量谱特征、梅尔频率倒谱系数特征,然后应用加速近端梯度法对联合稀疏表示模型进行优化,求解得到最优联合稀疏系数,最后根据最小误差准则确定目标类别。在消声水池开展模拟实验,对6类目标进行分类识别,结果表明:与传统算法相比,提出的算法具有更高识别准确率,并且其执行效率较传统算法有很大提升。      

Multi-Stream Convolution-Recurrent Neural Networks Based on Attention Mechanism Fusion for Speech Emotion Recognition

The quality of feature extraction plays a significant role in the performance of speech emotion recognition. In order to extract discriminative, affect-salient features from speech signals and then improve the performance of speech emotion recognition, in this paper, a multi-stream convolution-recurrent neural network based on attention mechanism (MSCRNN-A) is proposed. Firstly, a multi-stream sub-branches full convolution network (MSFCN) based on AlexNet is presented to limit the loss of emotional information. In MSFCN, sub-branches are added behind each pooling layer to retain the features of different resolutions, different features from which are fused by adding. Secondly, the MSFCN and Bi-LSTM network are combined to form a hybrid network to extract speech emotion features for the purpose of supplying the temporal structure information of emotional features. Finally, a feature fusion model based on a multi-head attention mechanism is developed to achieve the best fusion features. The proposed method uses an attention mechanism to calculate the contribution degree of different network features, and thereafter realizes the adaptive fusion of different network features by weighting different network features. Aiming to restrain the gradient divergence of the network, different network features and fusion features are connected through shortcut connection to obtain fusion features for recognition. The experimental results on three conventional SER corpora, CASIA, EMODB, and SAVEE, show that our proposed method significantly improves the network recognition performance, with a recognition rate superior to most of the existing state-of-the-art methods.     

基于三维荧光光谱和四元数主成分分析的食醋品牌溯源研究

提出基于四元数主成分分析的三维荧光光谱特征提取新方法,并将其运用于品牌食醋溯源研究。首先利用F7000荧光光谱仪测得不同品牌食醋样本的三维荧光光谱数据,获取样本的等高线图和三维投影图,并进行三维荧光等高线图分析;然后利用激发波长分别为380,360和400 nm下的发射光谱数据建立食醋三维荧光光谱数据的四元数并行表示模型,对四元数荧光光谱矩阵进行四元数主成分特征提取,并基于乘积运算、模值运算和求和运算三种方法对提取出来的四元数主成分特征进行特征融合;最后将融合特征作为K近邻分类器的输入,得到不同食醋品牌的最优分类模型。分别讨论三种不同特征融合方法和四元数主成分个数与最终模型分类正确率之间的关系。针对四个不同食醋品牌120个样本的分析结果可得：基于求和特征融合运算所得到的融合特征可以利用最少的特征数目,建立最优的溯源模型,样本预测集溯源正确率可达100%。研究结果表明：四元数主成分特征提取和特征融合方法能够并行表示三维荧光光谱数据所蕴含的丰富信息,为三维荧光光谱数据分析提供新思路。     

Bearing-Fault Diagnosis with Signal-to-RGB Image Mapping and Multichannel Multiscale Convolutional Neural Network

Deep learning bearing-fault diagnosis has shown strong vitality in recent years. In industrial practice, the running state of bearings is monitored by collecting data from multiple sensors, for instance, the drive end, the fan end, and the base. Given the complexity of the operating conditions and the limited number of bearing-fault samples, obtaining complementary fault features using the traditional fault-diagnosis method, which uses statistical characteristic in time or frequency, is difficult and relies heavily on prior knowledge. In addition, intelligent bearing-fault diagnosis based on a convolutional neural network (CNN) has several deficiencies, such as single-scale fixed convolutional kernels, excessive dependence on experts’ experience, and a limited capacity for learning a small training dataset. Considering these drawbacks, a novel intelligent bearing-fault-diagnosis method based on signal-to-RGB image mapping (STRIM) and multichannel multiscale CNN (MCMS-CNN) is proposed. First, the signals from three different sensors are converted into RGB images by the STRIM method to achieve feature fusion. To extract RGB image features effectively, the proposed MCMS-CNN is established, which can automatically learn complementary and abundant features at different scales. By increasing the width and decreasing the depth of the network, the overfitting caused by the complex network for a small dataset is eliminated, and the fault classification capability is guaranteed simultaneously. The performance of the method is verified through the Case Western Reserve University’s (CWRU) bearing dataset. Compared with different DL approaches, the proposed approach can effectively realize fault diagnosis and substantially outperform other methods.     

基于听觉谱特征的变压器绕组状态检测研究

绕组松动是变压器常见故障之一,对变压器的安全运行产生巨大威胁.故对其进行精准的监测,对提高电力系统的安全稳定性具有十分重要的意义.基于声信号的变压器绕组松动检测,由于其具有无损检测和不需停运变压器等优点,成为近年来研究的热点.但声信号检测存在故障特征提前复杂和易受噪声干扰等缺陷,限制了其工程应用.该文提出了一种基于声信...     

残差网络分层融合的高光谱地物分类

高光谱图像具有较高的空间分辨率,蕴含着丰富的空间光谱信息,近年来被广泛用于城市地物分类中。在高光谱图像分类过程中,空间光谱特征的提取直接影响着分类精度;传统的高光谱图像特征提取方法只利用了4或8邻域的像素进行简单卷积处理,因而丢失了大量的复杂、有效信息;卷积神经网络（CNN）虽然可以自动提取空间光谱特征,在保留图像空间信息的同时,简化网络模型,但是,随着网络深度增加,网络分类产生退化现象,而且网络间缺乏相关信息的互补性,从而影响分类精度。该工作引入CNN自动提取空间光谱特征,并且针对CNN深度增加所导致的退化问题,设计了面向地物分类的高光谱特征融合残差网络。首先,为了降低高光谱图像的光谱冗余度,利用PCA提取主要光谱波段;然后,为了逐级提取光谱图像的空间光谱特征,定义了卷积核为16,32,64的低、中、高3层残差网络模块,并利用64个1×1的卷积核对3层特征输出进行卷积,完成维度匹配与特征图融合;接着,对融合后的特征图进行全局平均池化(GAP)生成用于分类的特征向量;最后,引入具有可调节机制的Large-Margin Softmax损失函数,监督模型完成训练过程,实现高光谱图像分类。实验采用Indian Pines,University of Pavia和Salinas地区的高光谱图像来验证方法有效性,设置批次训练的样本集为100,网络训练的初始学习率为0.1,当损失函数稳定后学习率降低为0.001,动量为0.9,权重延迟为0.000 1,最大训练迭代次数为2×104,当3个数据集的样本块像素分别设置为25×25,23×23,27×27,网络深度分别为28,32和28时,3个数据集的分类准确率最高,其平均总体准确率（OA）为98.75%、平均准确率（AA）的评价值为98.1%,平均Kappa系数为0.98。实验结果表明,基于残差网络的分类方法能够自动学习更丰富的空间光谱特征,残差网络层数的增加和不同网络层融合可以提高高光谱分类精度;Large-Margin Softmax实现了类内紧凑和类间分离,可以进一步提高高光谱图像分类精度。     

Fusion Domain-Adaptation CNN Driven by Images and Vibration Signals for Fault Diagnosis of Gearbox Cross-Working Conditions

The vibration signal of gearboxes contains abundant fault information, which can be used for condition monitoring. However, vibration signal is ineffective for some non-structural failures. In order to resolve this dilemma, infrared thermal images are introduced to combine with vibration signals via fusion domain-adaptation convolutional neural network (FDACNN), which can diagnose both structural and non-structural failures under various working conditions. First, the measured raw signals are converted into frequency and squared envelope spectrum to characterize the health states of the gearbox. Second, the sequences of the frequency and squared envelope spectrum are arranged into two-dimensional format, which are combined with infrared thermal images to form fusion data. Finally, the adversarial network is introduced to realize the state recognition of structural and non-structural faults in the unlabeled target domain. An experiment of gearbox test rigs was used for effectiveness validation by measuring both vibration and infrared thermal images. The results suggest that the proposed FDACNN method performs best in cross-domain fault diagnosis of gearboxes via multi-source heterogeneous data compared with the other four methods.     

基于MCKD-EEMD近似熵和TWSVM的齿轮箱故障诊断

在复杂环境下齿轮箱信号往往会淹没在噪声信号中,特征向量难以提取;为了有效地进行故障诊断,提出了基于最大相关反褶积(MCKD)总体平均经验模态分解(EEMD)近似熵和双子支持向量机(TWSVM)的齿轮箱故障诊断方法;首先采用MCKD方法对强噪声信号进行滤波处理,在采用EEMD方法对齿轮箱信号进行分解,分解后得到本征模函数(IMF)分量进行近似熵求解,得到齿轮特征向量,最后将其输入到TWSVM分类器中进行故障识别;仿真实验表明,采用MCKD-EEMD方法能够有效地提取原始信号,与其他分类器相比,TWSVM的计算时间短,分类效果好等优点。     

融合多尺度特征的短时音频场景识别方法EI北大核心CSCD

为解决短时音频场景识别任务中识别性能差的问题,提出一种融合多尺度特征的音频场景识别方法。首先将双声道音频中左右声道的和差作为输入,并使用长时帧长进行分帧处理,以保证提取出的帧级特征中包含足够多的音频信息。然后将特征逐帧输入到融合多尺度特征的一维卷积神经网络中,以充分利用网络中不同尺度的浅层、中层和深层嵌入特征。最后综合所有帧级软标签得到短时音频的场景分类结果。实验结果表明,该方法在国际声学场景和事件检测与分类挑战赛(DCASE) 2021短时音频场景数据集上的准确率为79.02%,实现了该数据集上目前为止的最优性能。     

Multi-focus image fusion based on robust principal component analysis and pulse-coupled neural network

Multi-focus image fusion combines multiple source images with different focus points into one image, so that the resulting image appears all in-focus. In order to improve the accuracy of focused region detection and fusion quality, a novel multi-focus image fusion scheme based on robust principal component analysis (RPCA) and pulse-coupled neural network (PCNN) is proposed. In this method, registered source images are decomposed into principal component matrices and sparse matrices with RPCA decomposition. The local sparse features computed from the sparse matrix construct a composite feature space to represent the important information from the source images, which become inputs to PCNN to motivate the PCNN neurons. The focused regions of the source images are detected by the firing maps of PCNN and are integrated to construct the final, fused image. Experimental results demonstrate that the superiority of the proposed scheme over existing methods and highlight the expediency and suitability of the proposed method.     

基于局部线性嵌入的特征融合方法在岩石破裂 状态分类的应用*

为了获取岩石破裂过程有效的声发射信号特征,更好的对岩石破裂状态进行分类,提出一种基于流形学习算法的LLE特征融合方法进行数据降维。以红砂岩为研究对象设计室内单轴压缩实验采集信号,然后对原始声发射信号预处理并对信号进行特征提取,以时域、频域下的特征向量重新组合成一组新的多维特征向量,采用线性主元(PCA)和流形学习LLE算法分别进行降维。比较两种算法降维后融合特征的聚类效果二维和三维分布图,使用LLE算法降维后,四种状态分布相对更近,呈一条水平线趋势,且各状态交叉混叠数目较少,第一状态没有一个样本错判,且四个状态相比于PCA降维后的聚类效果更集中。再比较两种算法降维后融合特征的敏感度之和,LLE算法融合特征敏感度之和远大于PCA算法,说明经过LLE算法降维后得到的融合特征更多地表征了原始信号包含的局部信息同时证明了LLE算法相比PCA算法具有更好的聚类效果。最后经LLE特征融合下的砂岩破裂状态分类实验验证,融合特征后的识别率相对单一的时域特征识别提高了6%。表明该方法能显著提高岩石破裂状态分类的识别率,降维性能相对突出。     

基于深度学习的语声抑郁识别*

世界各地抑郁症患者数量不断增多,抑郁症的诊断和治疗面临着医生短缺问题,针对这一问题,提出了CNN和结合注意力机制的BLSTM特征融合模型。从特征选择和网络构架两方面进行了研究,对比了几种经典语声特征,得出梅尔倒谱系数对抑郁分类效果最好,再将梅尔倒谱系数分别送进CNN和结合注意力机制的BLSTM网络实现抑郁分类。在DAIC-WOZ数据集上进行实验,所提出的方法对语声抑郁的分类精确度达到78.06 %,F1分数达到74.68%。 关键词：抑郁识别;语声分析;分类     

高光谱影像的鲜桃可溶性固形物含量预测模型

可溶性固形物含量(SSC)是决定鲜桃风味和品质的重要成分。高光谱影像的特征提取为无损检测可溶性固形物含量提供了数据基础和方法路径。先前的研究表明,基于多光谱、荧光谱、近红外光谱、电子鼻的水果内部品质评估取得较好的结果。但是,由于缺少多特征融合,从而限制了水果品质的精准估测。为此,提出了一种基于堆栈自动编码器-粒子群优化支持向量回归(SAE-PSO-SVR)模型预测鲜桃可溶性固形物含量。首先,利用高光谱影像提取光谱信息、空间信息及空-谱融合信息。其次,设置普适性堆栈自动编码器(SAE)提取光谱信息、空间信息及空-谱融合信息的深层特征。最后,将深层特征作为粒子群优化支持向量回归(PSO-SVR)模型的输入数据进行鲜桃可溶性固形物含量的预测。其中,对于光谱信息作为输入的SAE模型,设计了453-300-200-100-40, 453-350-250-150-50, 453-350-250-100-60的三个隐含层结构。对于空间信息作为输入的SAE模型,设计了894-700-500-300-50, 894-650-350-200-80, 894-800-700-500-100的三个隐含层结构。对于融合信息作为输入的SAE模型,设计了1347-800-400-200-40, 1347-750-550-400-100, 1347-700-500-360-150的三个隐含层结构。实验结果表明,对于输入数据分别为光谱信息、空间信息及融合信息的SAE模型,结构为453-300-200-100-40, 894-800-700-500-100和1347-750-550-400-100的模型效果较好,而且基于融合信息的模型预测精度明显优于基于光谱信息或者图像信息的模型。为了验证模型的普适性,利用结构为1347-750-550-400-100的SAE模型提取融合信息的深层特征估测不同品种鲜桃的可溶性固形物含量并进行可视化。结果表明,基于结构为1237-650-310-130的SAE-PSO-SVR模型预测效果最好(R2=0.873 3, RMSE=0.645 1)。因此,所提出的SAE-PSO-SVR模型提高了鲜桃可溶性固形物含量的估计精度,为鲜桃的其他成分检测提供了技术支撑。     

Dual-Domain Fusion Convolutional Neural Network for Contrast Enhancement Forensics

Contrast enhancement forensics techniques have always been of great interest for the image forensics community, as they can be an effective tool for recovering image history and identifying tampered images. Although several contrast enhancement forensic algorithms have been proposed, their accuracy and robustness against some kinds of processing are still unsatisfactory. In order to attenuate such deficiency, in this paper, we propose a new framework based on dual-domain fusion convolutional neural network to fuse the features of pixel and histogram domains for contrast enhancement forensics. Specifically, we first present a pixel-domain convolutional neural network to automatically capture the patterns of contrast-enhanced images in the pixel domain. Then, we present a histogram-domain convolutional neural network to extract the features in the histogram domain. The feature representations of pixel and histogram domains are fused and fed into two fully connected layers for the classification of contrast-enhanced images. Experimental results show that the proposed method achieves better performance and is robust against pre-JPEG compression and antiforensics attacks, obtaining over 99% detection accuracy for JPEG-compressed images with different QFs and antiforensics attack. In addition, a strategy for performance improvements of CNN-based forensics is explored, which could provide guidance for the design of CNN-based forensics tools.     

Hyperspectral remote sensing image classification based on decision level fusion

To apply decision level fusion to hyperspectral remote sensing (HRS) image classification,three decision level fusion strategies are experimented on and compared,namely,linear consensus algorithm,improved evidence theory,and the proposed support vector machine (SVM) combiner.To evaluate the effects of the input features on classification performance,four schemes are used to organize input features for member classifiers.In the experiment,by using the operational modular imaging spectrometer (OMIS) II HRS im...