基于DIGNET网络的数据融合方法

针对数据融合和目标识别的特点,提出了基于DIGNET自组织聚类人工神经网络的数据融合方法。考虑到多传感器系统测量多个参量的特点,用并行的子网络结构代替中间隐层,实现了基于决策层的信息融合目标识别。利用仿真数据对基于DIGNET的数据融合方法进行了实验研究。实验结果表明,该方法具有数据正确分类率高和抗噪能力强等优点,有效地实现了融合识别。将该方法应用于前视红外和可见光双传感器目标跟踪系统的数据融合识别是可行的。     

一种新的自组织聚类网络及其在数据融合目标分类中的应用

介绍了一种新的自组织聚类人工神经网络(DIGNET)模型和网络的非监督学习算法。针对数据融合和目标识别的特点,提出了基于DIGNET的决策层数据融合目标分类方法。利用仿真数据研究了DIGNET和自组织特征映射网络(SOFM)的聚类性能以及基于DIGNET的决策层数据融合结构,实验结果表明DIGNET较SOFM正确分类率高、抗噪能力好;基于DIGNET的决策层数据融合能够有效地实现融合识别。将该数据融合方法应用于前视红外(FLIR)和可见光摄像机目标跟踪系统,结果表明该方法是可行的。     

注意力机制融合前端网络中间层的语声情感识别

为了使机器能够更好地理解人的情感并改善人机交互体验,可对语声特征及分类网络进行融合以提升情感识别性能。本文从网络融合的角度,把基于梅尔倒谱系数和逆梅尔倒谱系数的二维卷积神经网络和基于散射卷积网络系数的长短期记忆网络作为前端网络,提取前端网络的中间层作为话语级的特征表示,利用压缩-激励(SE)通道注意力机制对前端网络的中间层的权重进行调整并融合,然后由深度神经网络后端分类器输出情感分类结果。在汉语情感数据集中进行五折交叉验证的对比实验,实验结果表明,基于SE通道注意力机制的网络融合方式可以有效地利用不同前端网络在语声情感识别任务中的优势,提高语声情感识别的准确率。     

Diabetic Retinal Grading Using Attention-Based Bilinear Convolutional Neural Network and Complement Cross Entropy

Diabetic retinopathy (DR) is a common complication of diabetes mellitus (DM), and it is necessary to diagnose DR in the early stages of treatment. With the rapid development of convolutional neural networks in the field of image processing, deep learning methods have achieved great success in the field of medical image processing. Various medical lesion detection systems have been proposed to detect fundus lesions. At present, in the image classification process of diabetic retinopathy, the fine-grained properties of the diseased image are ignored and most of the retinopathy image data sets have serious uneven distribution problems, which limits the ability of the network to predict the classification of lesions to a large extent. We propose a new non-homologous bilinear pooling convolutional neural network model and combine it with the attention mechanism to further improve the network’s ability to extract specific features of the image. The experimental results show that, compared with the most popular fundus image classification models, the network model we proposed can greatly improve the prediction accuracy of the network while maintaining computational efficiency.     

基于LSSVM混淆矩阵和改进DS合成的多源传感器网络安全态势预测

针对现有的网络安全态势预测方法正确性和合理性难以得到保证,同时不能有效应对不确定情况的问题,设计了一种基于最小二乘支持向量机(Least square support vector machine, LSSVM)和改进证据理论的网络安全态势预测方法。首先,将由多源传感器采集的历史标记数据作为样本数据,实现对LSSVM的训练,然后,将当前采集的数据输入LSSVM进行分类,并通过混淆矩阵获得数据对应每个类的概率,为了有效地对采集的数据进行进一步融合,将各类转换为证据,同时将数据相对每个类的概率作为证据的基本信度分配,采用改进的DS证据合成规则对各证据进行融合,实现对网络安全态势的预测,最后,设计了基于LSSVM和改进DS证据合成规则的网络安全状态预测算法。在MATLAB环境下进行实验,实验表明了文中方法能对网络的安全态势进行实时精确的预测,与其它方法相比,具有更高的预测精度,是一种可行的网络安全态势预测方法。     

从二维视图识别三维目标的多网络融合方法

提出了一种从二维视图识别三维目标的多网络融合方法,基于单个网络分类的置信度概念,有效地结合多个网络的输出结果作出最终分类判决,应用三个多层前向网络（隐层神经元数,初始权值等取不同值）,设计了基于分类确认度的多网络融合结构,对四类车辆目标进行的识别实验表明,所提出的多网络融合方法明显优于单个网络的识别性能。     

Multi-Focus Image Fusion Based on Multi-Scale Generative Adversarial Network

The methods based on the convolutional neural network have demonstrated its powerful information integration ability in image fusion. However, most of the existing methods based on neural networks are only applied to a part of the fusion process. In this paper, an end-to-end multi-focus image fusion method based on a multi-scale generative adversarial network (MsGAN) is proposed that makes full use of image features by a combination of multi-scale decomposition with a convolutional neural network. Extensive qualitative and quantitative experiments on the synthetic and Lytro datasets demonstrated the effectiveness and superiority of the proposed MsGAN compared to the state-of-the-art multi-focus image fusion methods.     

Multimodal biometric authentication based on score level fusion using support vector machine

Fusion of multiple biometrics for human authentication performance improvement has received considerable attention. This paper presents a novel multimodal biometric authentication method integrating face and iris based on score level fusion. For score level fusion, support vector machine (SVM) based fusion rule is applied to combine two matching scores, respectively from Laplacianface based face verifier and phase information based iris verifier, to generate a single scalar score which is used to make the final decision. Experimental results show that the performance of the proposed method can bring obvious improvement comparing to the unimodal biometric identification methods and the previous fused face-iris methods.     

Revealing how network structure affects accuracy of link prediction

Link prediction plays an important role in network reconstruction and network evolution. The network structure affects the accuracy of link prediction, which is an interesting problem. In this paper we use common neighbors and the Gini coefficient to reveal the relation between them, which can provide a good reference for the choice of a suitable link prediction algorithm according to the network structure. Moreover, the statistical analysis reveals correlation between the common neighbors index, Gini coefficient index and other indices to describe the network structure, such as Laplacian eigenvalues, clustering coefficient, degree heterogeneity, and assortativity of network. Furthermore, a new method to predict missing links is proposed. The experimental results show that the proposed algorithm yields better prediction accuracy and robustness to the network structure than existing currently used methods for a variety of real-world networks.     

A neural-network method for the synthesis of informative features for the classification of signal sources in cognitive radio systems

This paper discusses possible methods for the synthesis of informative features for the classification of signal sources in cognitive radio systems using artificial neural networks. A synthesis method based on the use of autoassociative neural networks is proposed. From the point of view of the classification of the signals, informativeness of synthesized features is estimated using a modified artificial neural network based on radial basis functions that contains an additional self-organizing layer of neurons that provide the automatic selection of the variance of basis functions and a significant reduction of the network dimension. It is shown that the use of autoassociative networks in the problem of the classification of signal sources makes it possible to synthesize the feature space with a minimum dimension while maintaining separation properties.     

水体透射光谱的多特征融合COD含量估算研究

化学需氧量(chemical oxygen demand,COD)是一项可以快速检测有机污染物的参数,能够很好地反映水污染的程度.提出一种基于透射光谱测量的多特征融合水体COD含量估算模型,透射高光谱法采集100组COD水体光谱信息,对光谱数据进行预处理以及特征波段的选取,分析不同预处理方法对模型精度的影响并进行特征融...     

一种新型广义RBF神经网络在混沌时间序列预测中的研究

提出了一种新颖的广义径向基函数神经网络模型,其径向基函数(RBF)的形式由生成函数确定.然后,给出了易实现的梯度学习算法,同时为了进一步提高网络的收敛速度和网络性能,又给出了基于卡尔曼滤波的动态学习算法.为了验证网络的学习性能，采用基于卡尔曼滤波算法的新型广义RBF网络预测模型对Mackey-Glass混沌时间序列和Henon映射进行了仿真.结果表明,所提出的新型广义RBF神经网络模型能快速、精确地预测混沌时间序列,是研究复杂非线性动力系统辨识和控制的一种有效方法. 关键词： 广义径向基函数神经网络 卡尔曼滤波 梯度下降学习算法 混沌时间序列 预测     

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。      

Computing Influential Nodes Using the Nearest Neighborhood Trust Value and PageRank in Complex Networks

Computing influential nodes gets a lot of attention from many researchers for information spreading in complex networks. It has vast applications, such as viral marketing, social leader creation, rumor control, and opinion monitoring. The information-spreading ability of influential nodes is greater compared with other nodes in the network. Several researchers proposed centrality measures to compute the influential nodes in a complex network, such as degree, betweenness, closeness, semi-local centralities, and PageRank. These centrality methods are defined based on the local and/or global information of nodes in the network. However, due to their high time complexity, centrality measures based on the global information of nodes have become unsuitable for large-scale networks. Very few centrality measures exist that are based on the attributes between nodes and the structure of the network. We propose the nearest neighborhood trust PageRank (NTPR) based on the structural attributes of neighbors and nearest neighbors of nodes. We define the measure based on the degree ratio, the similarity between nodes, the trust values of neighbors, and the nearest neighbors. We computed the influential nodes in various real-world networks using the proposed centrality method. We found the maximum influence by using influential nodes with SIR and independent cascade methods. We also compare the maximum influence of our centrality measure with the existing basic centrality measures.     

Deep Link-Prediction Based on the Local Structure of Bipartite Networks

Link prediction based on bipartite networks can not only mine hidden relationships between different types of nodes, but also reveal the inherent law of network evolution. Existing bipartite network link prediction is mainly based on the global structure that cannot analyze the role of the local structure in link prediction. To tackle this problem, this paper proposes a deep link-prediction (DLP) method by leveraging the local structure of bipartite networks. The method first extracts the local structure between target nodes and observes structural information between nodes from a local perspective. Then, representation learning of the local structure is performed on the basis of the graph neural network to extract latent features between target nodes. Lastly, a deep-link prediction model is trained on the basis of latent features between target nodes to achieve link prediction. Experimental results on five datasets showed that DLP achieved significant improvement over existing state-of-the-art link prediction methods. In addition, this paper analyzes the relationship between local structure and link prediction, confirming the effectiveness of a local structure in link prediction.     

基于深度学习的气溶胶荧光光谱识别应用研究

空气中的高危病原微生物对人类社会存在着极大威胁,而传统的监测方法无法对空气中的微生物实现准确的识别与分类。因此采用激光诱导荧光技术原理,以单光子探测器为核心器件,设计并搭建了一种高效的荧光光谱仪用于空气中高危病原微生物的识别与分类,并且该光谱仪可以实现对微生物浓度的预测,其对于环境安全具有重要意义。对于该光谱仪采集的数据,探索了以一维向量和二维矩阵2种输入形式来实现荧光光谱的识别与分类,并研究对比了主成分分析网络、卷积神经网络和全卷积网络等深度学习网络的识别与分类效果。实验结果表明以矩阵形式输入的卷积神经网络模型在测试集中识别分类准确率达到98.05%。采用矩阵形式输入的全卷积网络模型在测试集中微生物浓度预测准确率达到98.97%。     

基于DBN,SVM和BP神经网络的光谱分类比较

恒星的分类对了解恒星和星系形成与演化历史具有重要的研究价值。面对大型巡天计划及由此产生的海量数据,如何迅速准确地将天体自动分类显得尤为重要。通过对SDSS DR9的恒星光谱数据进行深度置信神经网络(DBN)、神经网络和支持向量机(SVM)等算法分类的对比,分析三种自动光谱分类方法在恒星分类上的适用性。首先利用上述三种方法对K,F恒星进行识别分类,然后再分别对K1,K3和K5次型和F2,F5,F9次型识别,最后基于SVM支持向量机的二次分类模型,利用K次型的数据,构建剔除不属于K次型的模型。结果表明:深度置信网络对K,F型恒星分类效果较好,但是对K,F次型的分类效果不佳;SVM支持向量机在K,F型恒星分类以及相应的次型分类都具有较好的识别率,对K,F型分类效果要好于K,F次型的分类效果;BP神经网络对K,F型恒星以及其次型的识别一般;在剔除不属于K次型实验中,剔除率高达100%,可知SVM能够对未知的光谱数据进行筛选与分类。     

水下高分辨率声图中小目标的深度网络分类方法

针对声成像数据缺少条件下的水下沉底小目标分类问题,提出一种深度网络分类算法。首先,采用高斯混合模型对声影区统计特性进行建模并提取声图阴影,在此基础上构建仿真数据集和真实数据集。将仿真数据集输入卷积神经网络进行训练,保留其特征提取部分,用于对真实数据集进行特征提取.重建网络分类部分并采用真实数据集的特征向量进行训练。结果表明,所提出的方法分类正确率可达88.24%,与6种对照方法相比平均分类正确率分别提升8.67%,20.47%,19.78%,11.59%,9.01%,11.58%。验证了所提出方法在小样本条件下具有较好对水下沉底小目标的分类能力。其学习曲线收敛到96.25%,仅比验证曲线高5.14%,说明在一定程度上缓解了过拟合问题。将改进的卷积神经网络应用于融合分类器,通过与逻辑回归分类器、支持向量机对目标进行分类并融合决策,正确率为93.33%,可进一步提高算法的正确率和稳定性.      

Taming the Chaos in Neural Network Time Series Predictions

Machine learning methods, such as Long Short-Term Memory (LSTM) neural networks can predict real-life time series data. Here, we present a new approach to predict time series data combining interpolation techniques, randomly parameterized LSTM neural networks and measures of signal complexity, which we will refer to as complexity measures throughout this research. First, we interpolate the time series data under study. Next, we predict the time series data using an ensemble of randomly parameterized LSTM neural networks. Finally, we filter the ensemble prediction based on the original data complexity to improve the predictability, i.e., we keep only predictions with a complexity close to that of the training data. We test the proposed approach on five different univariate time series data. We use linear and fractal interpolation to increase the amount of data. We tested five different complexity measures for the ensemble filters for time series data, i.e., the Hurst exponent, Shannon’s entropy, Fisher’s information, SVD entropy, and the spectrum of Lyapunov exponents. Our results show that the interpolated predictions consistently outperformed the non-interpolated ones. The best ensemble predictions always beat a baseline prediction based on a neural network with only a single hidden LSTM, gated recurrent unit (GRU) or simple recurrent neural network (RNN) layer. The complexity filters can reduce the error of a random ensemble prediction by a factor of 10. Further, because we use randomly parameterized neural networks, no hyperparameter tuning is required. We prove this method useful for real-time time series prediction because the optimization of hyperparameters, which is usually very costly and time-intensive, can be circumvented with the presented approach.     

TLP-CCC: Temporal Link Prediction Based on Collective Community and Centrality Feature Fusion

In the domain of network science, the future link between nodes is a significant problem in social network analysis. Recently, temporal network link prediction has attracted many researchers due to its valuable real-world applications. However, the methods based on network structure similarity are generally limited to static networks, and the methods based on deep neural networks often have high computational costs. This paper fully mines the network structure information and time-domain attenuation information, and proposes a novel temporal link prediction method. Firstly, the network collective influence (CI) method is used to calculate the weights of nodes and edges. Then, the graph is divided into several community subgraphs by removing the weak link. Moreover, the biased random walk method is proposed, and the embedded representation vector is obtained by the modified Skip-gram model. Finally, this paper proposes a novel temporal link prediction method named TLP-CCC, which integrates collective influence, the community walk features, and the centrality features. Experimental results on nine real dynamic network data sets show that the proposed method performs better for area under curve (AUC) evaluation compared with the classical link prediction methods.