Large-Scale Location-Aware Services in Access: Hierarchical Building/Floor Classification and Location Estimation Using Wi-Fi Fingerprinting Based on Deep Neural Networks

We report the results of our investigation on the use of deep neural networks (DNNs) for building/floor classification and floor-level location estimation based on Wi-Fi fingerprinting. We propose a new DNN architecture based on a stacked autoencoder for feature space dimension reduction and a feed-forward classifier for multi-label classification with arg max functions to convert multi-label classification results into multi-class classification ones. We also demonstrate a prototype system for floor-level location estimation using received signal strengths measured on XJTLU campus. Our results show the strengths of DNN-based approaches, providing near state-of-the-art performance with less parameter tuning and higher scalability.     

Neural Network Used for the Fusion of Predictions Obtained by the K-Nearest Neighbors Algorithm Based on Independent Data Sources

The article concerns the problem of classification based on independent data sets—local decision tables. The aim of the paper is to propose a classification model for dispersed data using a modified k-nearest neighbors algorithm and a neural network. A neural network, more specifically a multilayer perceptron, is used to combine the prediction results obtained based on local tables. Prediction results are stored in the measurement level and generated using a modified k-nearest neighbors algorithm. The task of neural networks is to combine these results and provide a common prediction. In the article various structures of neural networks (different number of neurons in the hidden layer) are studied and the results are compared with the results generated by other fusion methods, such as the majority voting, the Borda count method, the sum rule, the method that is based on decision templates and the method that is based on theory of evidence. Based on the obtained results, it was found that the neural network always generates unambiguous decisions, which is a great advantage as most of the other fusion methods generate ties. Moreover, if only unambiguous results were considered, the use of a neural network gives much better results than other fusion methods. If we allow ambiguity, some fusion methods are slightly better, but it is the result of this fact that it is possible to generate few decisions for the test object.     

基于RBF神经网络的强流LIA故障诊断与性能评价技术

 用于流体动力学诊断的强流LIA是庞大而复杂的系统，其性能预测和评估是十分困难的。针对强流LIA大量的单次快脉冲非平稳信号，提出基于小波包分析与RBF神经网络技术相结合实现故障智能诊断和性能评价的方法。该方法以强流LIA高维信号的小波包结点能量提取的特征向量来表征信号平顶、脉宽以及暂态特性。在此基础上，建立了“神龙一号”加速器腔电压及注入器出口束流故障诊断与性能评价原型系统，该系统不仅可进行故障诊断和性能评价，还可探测到加速器运行参数的变化趋势，为加速器的精细维护提供预测信息。     

Quantum neural networks: Current status and prospects for development

The idea of quantum artificial neural networks, first formulated in [34], unites the artificial neural network concept with the quantum computation paradigm. Quantum artificial neural networks were first systematically considered in the PhD thesis by T. Menneer (1998). Based on the works of Menneer and Narayanan [42, 43], Kouda, Matsui, and Nishimura [35, 36], Altaisky [2, 68], Zhou [67], and others, quantum-inspired learning algorithms for neural networks were developed, and are now used in various training programs and computer games [29, 30]. The first practically realizable scaled hardware-implemented model of the quantum artificial neural network is obtained by D-Wave Systems, Inc. [33]. It is a quantum Hopfield network implemented on the basis of superconducting quantum interference devices (SQUIDs). In this work we analyze possibilities and underlying principles of an alternative way to implement quantum neural networks on the basis of quantum dots. A possibility of using quantum neural network algorithms in automated control systems, associative memory devices, and in modeling biological and social networks is examined.     

基于径向基函数神经网络的高光谱遥感图像分类

从径向基函数神经网络的理论出发,针对高光谱数据的特点,设计了有效的特征提取模型,再与径向基函数神经网络的输入层连接,建立了一个新的径向基函数神经网络的高光谱遥感影像分类模型,并用国产OMISII传感器获得的64波段数据进行试验。首先进行了最小噪声分离变换,提取了1～20个分量的数据,使用提取后的数据（20维）、提取后数据的纹理变换（20维）和主成分分析的前（20维）,组成了60维向量数据进行分类处理,这种分类器结构简单、容易训练、收敛速度快,其分类精度达到69.27%,高于BP神经网络分类算法(51.20%)以及常用的最小距离分类（MDC）算法(40.88%)。通过对结果和过程进行分析,实验证明径向基函数神经网络在高光谱遥感分类中具有较好的适用性。     

Algorithm for Processing and Analysis of Raman Spectra using Neural Networks

The solution of the problem of processing of a large data set when analyzing Raman spectra of a gas mixture is considered. The algorithm is based on the artificial neural network. Conditions for the use of neural networks in solving practical problems of real-time analyzing spectra, including that for remote search for heavy hydrocarbons are determined. The algorithm speed is estimated using computer aids with sequential and parallel data processing.     

利用深度神经网络实现分布式相干瑞利光纤振动事件分类

该文利用分布式相干瑞利光纤传感系统,在西气东输一线无锡至苏州段开展现场测试,采集了光纤沿线车辆行走、机械挖掘、人工锄地、定向钻孔等8种振动作业产生的光纤信号,并提出了一种具有5层结构的全连接深度神经网络用于振动事件分类识别以实现不同振动作业的分级管理。振动作业产生的光纤信号能量集中在低频,该文利用梅尔对数频率的非均匀特性提取了25维单帧信号特征量,并将连续40帧信号特征量组合成高维向量作为网络输入特征向量,实现对不同振动作业时变特性的建模。分类识别结果表明,基于深度神经网络结构的振动信号分类识别器能够有效识别不同振动作业类型,实际线路实验验证了该文算法的有效性。     

Novel Convolutional Neural Network with Variational Information Bottleneck for P300 Detection

In the area of brain-computer interfaces (BCI), the detection of P300 is a very important technique and has a lot of applications. Although this problem has been studied for decades, it is still a tough problem in electroencephalography (EEG) signal processing owing to its high dimension features and low signal-to-noise ratio (SNR). Recently, neural networks, like conventional neural networks (CNN), has shown excellent performance on many applications. However, standard convolutional neural networks suffer from performance degradation on dealing with noisy data or data with too many redundant information. In this paper, we proposed a novel convolutional neural network with variational information bottleneck for P300 detection. Wiht the CNN architecture and information bottleneck, the proposed network termed P300-VIB-Net could remove the redundant information in data effectively. The experimental results on BCI competition data sets show that P300-VIB-Net achieves cutting-edge character recognition performance. Furthermore, the proposed model is capable of restricting the flow of irrelevant information adaptively in the network from perspective of information theory. The experimental results show that P300-VIB-Net is a promising tool for P300 detection.     

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。     

Multi-task learning approach for modulation and wireless signal classification for 5G and beyond: Edge deployment via model compression

Future communication networks must address the scarce spectrum to accommodate extensive growth of heterogeneous wireless devices. Efforts are underway to address spectrum coexistence, enhance spectrum awareness, and bolster authentication schemes. Wireless signal recognition is becoming increasingly more significant for spectrum monitoring, spectrum management, secure communications, among others. Consequently, comprehensive spectrum awareness on the edge has the potential to serve as a key enabler for the emerging beyond 5G (fifth generation) networks. State-of-the-art studies in this domain have (i) only focused on a single task – modulation or signal (protocol) classification – which in many cases is insufficient information for a system to act on, (ii) consider either radar or communication waveforms (homogeneous waveform category), and (iii) does not address edge deployment during neural network design phase. In this work, for the first time in the wireless communication domain, we exploit the potential of deep neural networks based multi-task learning (MTL) framework to simultaneously learn modulation and signal classification tasks while considering heterogeneous wireless signals such as radar and communication waveforms in the electromagnetic spectrum. The proposed MTL architecture benefits from the mutual relation between the two tasks in improving the classification accuracy as well as the learning efficiency with a lightweight neural network model. We additionally include experimental evaluations of the model with over-the-air collected samples and demonstrate first-hand insight on model compression along with deep learning pipeline for deployment on resource-constrained edge devices. We demonstrate significant computational, memory, and accuracy improvement of the proposed model over two reference architectures. In addition to modeling a lightweight MTL model suitable for resource-constrained embedded radio platforms, we provide a comprehensive heterogeneous wireless signals dataset for public use.     

基于异步延迟采样的光通信性能监测方法

基于异步延迟采样和人工神经网络统计学习提出了一种光通信性能监测方法。通过对高速光信号进行异步延迟采样,获得信号二维幅度直方图,然后提取其中特征参数并对人工神经网络进行训练,最后以人工神经网络的预测输出实现对光信号损伤的监测。构建10 Gb/s非归零码开关键控,40 Gb/s光学双二进制码和归零码差分移相键控光通信仿真系统,并对光信噪比、色散和偏振模色散损伤进行监测。仿真结果表明,所提方法对被监测光信号的速率、码型调制格式透明,可同时准确监测多种并存的传输损伤,损伤参数监测误差小于5%。该方法具有电域处理带宽要求低、采样机制简单的特点,适用于分布式在线光性能监测。     

一种基于图像特征和神经网络的苹果图像分割算法

苹果识别是开发苹果采摘机器人的关键环节,利用图像处理技术和神经网络分类器探索苹果图像分割算法.从苹果树图片中选取苹果图像样本和背景网像样本.分别计算这两类图像样本的颜色特征和纹理特征.颜色特征的计算基于RGB色彩模型,纹理特征的计算基于灰度共生矩阵.选取适当的颜色特征(R/B值)和纹理特征(对比度值和相关性值)作为输入节点,利用反向传播神经网络分类器建模,输出值是一个O～1之间的计算值.通过阈值将输出结果分类为苹果或背景.试验结果表明,该算法正确率大于87.6%,对光照的影响不敏感,是一利较为实用的苹果分割算法.     

深度神经网络在红外光谱定量分析VOCs中的应用

鉴于浅层人工神经网络(ANN)需要依靠先验知识进行人工提取特征,同时较浅的网络结构限制了神经网络学习复杂非线性关系的能力,将深度神经网络(DNN)应用于利用傅里叶变换红外光谱(FTIR)对多组分易挥发性有机物(VOCs)进行的浓度反演研究,并利用仿真实验验证了算法的有效性。从美国环境保护署(EPA)的数据库中选取了包括苯、甲苯、 1,3-丁二烯、乙苯、苯乙烯、邻二甲苯、间二甲苯、对二甲苯在内的八种VOCs气体在8~12μm波长范围内的吸光度谱,每种气体有四种不同浓度下的谱线,依据Beer-Lambert定律从每种VOCs气体中选择一种浓度下的吸光度谱进行混合,得到65 536种不同的VOCs混合气体吸光度谱样本。随机选择5 000组混合气体的吸光度谱,其中4 000组作为训练样本, 1 000组作为预测样本。通过积分提取和主成分提取对光谱矩阵进行降维预处理,将光谱维度从3 457维降到30维。将光谱矩阵经过预处理后得到的新矩阵作为网络输入,对应八种VOCs的浓度矩阵作为输出,建立了30-25-15-10-8的深度神经网络回归预测模型来实现多组分VOCs浓度反演,反演得到样本的均方根误差为0.002 7×10-6,相比于前人利用非线性偏最小二乘拟合、人工神经网络等方法拟合的精度有了明显的提高。每种VOCs气体的均方根误差均不超过0.005×10-6,每个样本的均方根误差均不超过0.006×10-6,证明了深度神经网络预测模型具有良好的非线性拟合能力和良好的稳定性。当训练样本不足(典型值:小于500)时,深度神经网络无法充分地学习,网络误差较大,精度低于单隐藏层的人工神经网络,但随着训练样本数量的增加,深度神经网络的精度不断提高,当训练样本数充足时,相比浅层的人工神经网络,深度神经网络具有更强的非线性关系学习能力,预测精度更高,模型更为稳定。同时,由于训练前对光谱矩阵进行了降维处理,大大降低了算法的复杂度,有效提高了反演效率。分析表明,深度神经网络预测模型具有良好的非线性拟合能力和良好的稳定性,无需人工提取特征就能够充分学习数据特征,同时对多组分VOCs进行浓度反演并达到较高精度。     

基于小波系数图和卷积神经网络的太赫兹光谱物质识别

许多太赫兹光谱物质识别方法依靠寻找该物质在太赫兹波段范围内不同光谱表现出的不同特征来识别特定物质。吸收峰提取法是常用的光谱特征提取算法,但当光谱无明显特征吸收峰或峰位、峰值相近或难以识别时,难以利用吸收峰特征辨别物质。将机器学习和统计学习技术用于太赫兹光谱的识别中虽减少了吸收峰的干扰,但常常需要人为定义特征而导致分类误差。深度学习法能自动提取特征,但在识别前往往需要进行复杂的预处理操作,并且在特征提取的过程中容易丢失部分特征从而导致分类误差。针对以上问题,提出了一种基于小波系数图和卷积神经网络的太赫兹光谱识别方法。利用太赫兹光谱信号进行小波变换时,由于小波系数矩阵的每一行系数与原始光谱信号存在着对应关系,因此将太赫兹光谱的吸收系数通过小波变换在频率域上展开,能得到不同的二维的频率-尺度分布图,又称小波系数图。然后构造一个卷积神经网络(CNN)对小波系数图进行分类,可得到太赫兹光谱物质的分类结果。为了验证所提出算法的有效性,将三组小波系数图数据与原始光谱数据分别输入CNN、Support Vector Machin (SVM)、Multilayer Perceptron (MLP)三种不同的分类器作对比,从实验结果可以发现本文算法在三组数据中的识别率均达到了100%,说明相比于传统方法,本文方法能准确分类没有明显特征吸收峰的光谱,证明了使用卷积神经网络识别小波系数图的有效性。为了体现本文算法的优势,与小波脊线寻峰识别算法作对比,实验结果表明本文算法几乎不受峰频、峰位、峰值的影响,无论是识别不存在吸收峰的淀粉,还是识别相似度高的蔗糖和葡萄糖,都具有较高的识别率,分类准确率达97.62%,证明了所提算法的优越性。该算法为太赫兹光谱数据识别提供了一种新思路,同时也可以推广运用到其他谱图物质的识别中。     

DFTSA-Net: Deep Feature Transfer-Based Stacked Autoencoder Network for DME Diagnosis

Diabetic macular edema (DME) is the most common cause of irreversible vision loss in diabetes patients. Early diagnosis of DME is necessary for effective treatment of the disease. Visual detection of DME in retinal screening images by ophthalmologists is a time-consuming process. Recently, many computer-aided diagnosis systems have been developed to assist doctors by detecting DME automatically. In this paper, a new deep feature transfer-based stacked autoencoder neural network system is proposed for the automatic diagnosis of DME in fundus images. The proposed system integrates the power of pretrained convolutional neural networks as automatic feature extractors with the power of stacked autoencoders in feature selection and classification. Moreover, the system enables extracting a large set of features from a small input dataset using four standard pretrained deep networks: ResNet-50, SqueezeNet, Inception-v3, and GoogLeNet. The most informative features are then selected by a stacked autoencoder neural network. The stacked network is trained in a semi-supervised manner and is used for the classification of DME. It is found that the introduced system achieves a maximum classification accuracy of 96.8%, sensitivity of 97.5%, and specificity of 95.5%. The proposed system shows a superior performance over the original pretrained network classifiers and state-of-the-art findings.     

Functional holography analysis: simplifying the complexity of dynamical networks

We present a novel functional holography (FH) analysis devised to study the dynamics of task-performing dynamical networks. The latter term refers to networks composed of dynamical systems or elements, like gene networks or neural networks. The new approach is based on the realization that task-performing networks follow some underlying principles that are reflected in their activity. Therefore, the analysis is designed to decipher the existence of simple causal motives that are expected to be embedded in the observed complex activity of the networks under study. First we evaluate the matrix of similarities (correlations) between the activities of the network's components. We then perform collective normalization of the similarities (or affinity transformation) to construct a matrix of functional correlations. Using dimension reduction algorithms on the affinity matrix, the matrix is projected onto a principal three-dimensional space of the leading eigenvectors computed by the algorithm. To retrieve back information that is lost in the dimension reduction, we connect the nodes by colored lines that represent the level of the similarities to construct a holographic network in the principal space. Next we calculate the activity propagation in the network (temporal ordering) using different methods like temporal center of mass and cross correlations. The causal information is superimposed on the holographic network by coloring the nodes locations according to the temporal ordering of their activities. First, we illustrate the analysis for simple, artificially constructed examples. Then we demonstrate that by applying the FH analysis to modeled and real neural networks as well as recorded brain activity, hidden causal manifolds with simple yet characteristic geometrical and topological features are deciphered in the complex activity. The term "functional holography" is used to indicate that the goal of the analysis is to extract the maximum amount of functional information about the dynamical network as a whole unit.     

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。     

Hysteresis studies in a noisy autoassociative neural network

We define magnetization for a noisy autoassociative neural network driven by an external periodic field. Numerical simulations are carried out to investigate the effect of drive amplitude and frequency and noise strength on the area of the hysteresis loop. We observe that in the presence of weak periodic signal, the network exhibits a maximum in the hysteresis loop area at a nonzero noise intensity indicating maximum synchronization between the periodic signal and the response. It also goes through a maximum as a function of signal frequency.     

应用BP神经网络识别内层表面细小缺陷的研究

内层表面细小凹坑的识别是超声无损评估的一个难点。本文利用人工神经网络对于信号的分类功能,建构和训练了一个BP神经网络,并用它对尺寸为1mm的圆锥形和半球形两种凹坑成功地进行了识别。研究表明,应用凹坑回波的DCT谱作为缺陷特片输入,可使BP神经网络的训练和缺陷识别既快捷又有效。     

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