MRNN:一种新的基于改进型递归神经网络的WSN动态建模方法:应用于故障检测

提出了一种适用于无线传感器网络WSN的故障检测方法,该方法运用改进的递归神经网络MRNN为WSN的节点、节点的动态特性以及节点间的关系建立相关模型,对WSN节点进行识别和故障检测。MRNN的输入选择建模节点的先前输出值及其邻居节点的当前及先前输出值,模型基于一种新的改进的反向传播型神经网络,该神经网络的输入以及传感器网络的拓扑结构基于通用的非线性传感器模型。仿真实验将MRNN方法与卡尔曼滤波法进行了全面的比较。实验表明,MRNN在置信因子较小的情况下与卡尔曼滤波方法相比有较高的故障检测精度。     

A hybrid data-fusion system using modal data and probabilistic neural network for damage detection

This paper addresses a novel hybrid data-fusion system for damage detection by integrating the data fusion technique, probabilistic neural network (PNN) models and measured modal data. The hybrid system proposed consists of three models, i.e. a feature-level fusion model, a decision-level fusion model and a single PNN classifier model without data fusion. Underlying this system is the idea that we can choose any of these models for damage detection under different circumstances, i.e. the feature-level model is preferable to other models when enormous data are made available through multi-sensors, whereas the confidence level for each of multi-sensors must be determined (as a prerequisite) before the adoption of the decision-level model, and lastly, the single model is applicable only when data collected is somehow limited as in the cases when few sensors have been installed or are known to be functioning properly. The hybrid system is suitable for damage detection and identification of a complex structure, especially when a huge volume of measured data, often with uncertainties, are involved, such as the data available from a large-scale structural health monitoring system. The numerical simulations conducted by applying the proposed system to detect both single- and multi-damage patterns of a 7-storey steel frame show that the hybrid data-fusion system cannot only reliably identify damage with different noise levels, but also have excellent anti-noise capability and robustness.     

基于概率神经网络的高速公路事件检测

针对高速公路事件检测这一非线性分类问题,提出一种基于概率神经网络的事件检测方法。阐述了概率神经网络的结构与训练算法,分析了事件对交通流的影响规律,并合理地选取了概率神经网络的输入量,用高速公路管理部门提供的样本数据进行了仿真研究。仿真实验表明,基于概率神经网络的事件检测方法具有学习速度快、泛化能力好、检测准确率高等优点,具有良好的应用前景。     

改进的无线传感网混沌Hopfield盲检测算法

在密集部署的无线传感器网络中,相邻传感器的信号可能高度相关。在无线传感网传输模型分簇的基础上,针对Hopfield神经网络极易陷入局部最优解、收敛速度慢等缺陷,利用混沌序列的遍历性和类随机性,提出一种改进的混沌Hopfield盲检测算法解决无线传感网簇内传感器信号盲检测问题。算法的思想是:利用混沌映射产生初始发送序列,并且在算法出现早熟收敛时进行小幅度的混沌扰动,借此降低算法的误码率。仿真结果表明,改进的混沌Hopfield神经网络算法所需数据量极短,从而成功实现簇内簇首传感器信号盲检测。     

基于细胞神经网络鲁棒性的彩色图像边缘检测

根据细胞神经网络(CNN)数学模型,提出一种新的彩色图像边缘检测方法。 新方法继承了CNN 的优点,解决了CNN 现有算法不能直接检测彩色图像边缘的问题。该 方法充分利用图像中的颜色信息,通过欧几里得距离度量像素之间的差异,使CNN 方程可 以在RGB 彩色空间中进行运算。对CNN 模板进行理论分析和鲁棒性研究,提出一个实现 彩色图像边缘检测功能要求的CNN 鲁棒性定理,为设计相应的CNN 模板参数提供了解析 判据。实验结果表明,该方法可以对彩色图像进行有效的边缘提取,定量评价验证了CNN 边缘检测定位准确的优点。     

A new watermarking approach based on probabilistic neural network in wavelet domain

A novel scheme of digital image watermarking based on the combination of dual-tree wavelet transform (DTCWT) and probabilistic neural network is proposed in this paper. Firstly, the original image is decomposed by DTCWT, and then the watermark bits are added to the selected coefficients blocks. Because of the learning and adaptive capabilities of neural networks, the trained neural networks can recover the watermark from the watermarked images. Experimental results show that the proposed scheme has good performance against several attacks.     

Large-scale network intrusion detection based on distributed learning algorithm

As network traffic bandwidth is increasing at an exponential rate, it’s impossible to keep up with the speed of networks by just increasing the speed of processors. Besides, increasingly complex intrusion detection methods only add further to the pressure on network intrusion detection (NIDS) platforms, so the continuous increasing speed and throughput of network poses new challenges to NIDS. To make NIDS usable in Gigabit Ethernet, the ideal policy is using a load balancer to split the traffic data and forward those to different detection sensors, which can analyze the splitting data in parallel. In order to make each slice contains all the evidence necessary to detect a specific attack, the load balancer design must be complicated and it becomes a new bottleneck of NIDS. To simplify the load balancer this paper put forward a distributed neural network learning algorithm (DNNL). Using DNNL a large data set can be split randomly and each slice of data is presented to an independent neural network; these networks can be trained in distribution and each one in parallel. Completeness analysis shows that DNNL’s learning algorithm is equivalent to training by one neural network which uses the technique of regularization. The experiments to check the completeness and efficiency of DNNL are performed on the KDD’99 Data Set which is a standard intrusion detection benchmark. Compared with other approaches on the same benchmark, DNNL achieves a high detection rate and low false alarm rate.     

基于BP神经网络的人脸检测AbaBoost算法

人脸检测在日常生产和应用非常重要。本文提出了一种基于BP神经网络的AdaBoost人脸检测算法。首先,使用BP神经网络代替YCbCr高斯模型建立肤色模型。同时,针对AdaBoost算法提出了一种新的权值更新方法。在权值更新中引入阈值与样本之间的距离。另外权重有一个边界值。最后,利用BP神经网络提取图像中的肤色候选区域,并采用改进的AdaBoost算法对图像中的人脸进行精确检测。实验结果表明,利用BP神经网络和改进的AdaBoost算法的新的解决方案比现有的方法具有更高的精度。     

基于神经网络的僵尸网络检测

目前主流的僵尸网络检测方法主要利用网络流量分析技术,这往往需要数据包的内部信息,或者依赖于外部系统提供的信息或僵尸主机的恶意行为,并且大多数方法不能自动存储僵尸网络的流量特征,不具有联想记忆功能.为此提出了一种基于BP神经网络的僵尸网络检测方法,通过大量的僵尸网络和正常流量样本训练BP神经网络分类器,使其学会辨认僵尸网络的流量,自动记忆僵尸流量特征,从而有效检测出被感染的主机.该神经网络分类器以主机对为分析对象,提取2个主机间通信的流量特征,将主机对的特征向量作为输入,有效地区分出正常主机和僵尸主机.实验表明,该方法的检测率达到99%,误报率在1%以下,具有良好的性能.     

A novel distributed scheduling scheme for OFDMA uplink using channel information and probabilistic transmission

Distributed uplink scheduling in OFDMA systems is considered. In the proposed model, mobile terminals have the responsibility of making their own transmission decisions. The proposed scheme is based on two dimensional reservation in time and frequency. Terminals use channel state information in order to favor transmissions over certain subchannels, and transmission is done in a probabilistic manner. The proposed approach provides more autonomy to mobile devices in making transmission decisions. Furthermore, it allows avoiding collisions during transmission since it leads to collision detection during the resource reservation phase. The proposed approach is compared to other random access methods and shown to be superior in terms of increasing sum-rate, reducing the number of users in outage, and reducing the collision probability in the reservation phase.     

基于可拓神经网络的火灾探测算法

为解决传统单一传感器式的火灾探测器容易造成火灾报警的漏报和误报的问题,采用多传感器信息融合技术,将温度、烟雾浓度和CO浓度等多个参数相结合,进行综合分析,对火灾进行早期预测。采用可拓神经网络作为数据融合算法,以温度、烟雾浓度、CO气体浓度三个物理参量作为输入,以三种火灾预警等级作为输出。通过仿真分析结果表明：火灾正确识别率很高,达到93.9%以上。同时通过与传统BP神经网络的对比,表明可拓神经网络在数据融合的速度和可靠性上有突出的优势,从而使可拓神经网络实际应用于火灾早期预测成为可能。     

基于深度卷积神经网络的小目标检测算法

针对YOLO目标检测算法在小目标检测方面存在的不足,以及难以在嵌入式平台上达到实时性的问题,设计出了一种基于YOLO算法改进的dense_YOLO目标检测算法。该算法共分为2个阶段:特征提取阶段和目标检测回归阶段。在特征提取阶段,借鉴DenseNet结构的思想,设计了新的基于深度可分离卷积的slim-densenet特征提取模块,增强了小目标的特征传递,减少了参数量,加快了网络的传播速度。在目标检测阶段,提出自适应多尺度融合检测的思想,将提取到的特征进行融合,在不同的特征尺度上进行目标的分类和回归,提高了对小目标的检测准确率。实验结果表明:在嵌入式平台上,针对小目标,本文提出的dense_YOLO目标检测算法相较原YOLO算法mAP指标提高了7%,单幅图像检测时间缩短了15 ms,网络模型大小减少了90 MB,明显优于原算法。     

基于卷积神经网络的焊缝表面缺陷检测方法

针对工业激光焊接中,采用传统方法进行焊缝质量检测效率低下的问题,提出了一种基于卷积神经网络的工业钢板表面焊缝缺陷检测方法;首先基于卷积神经网络,搭建了一个多分类模型框架,并分析了各层中所用到的函数及相关参数;然后基于工业数控机床和工业相机进行了焊缝数据采集,并对这些数据进行了分类、增强、扩增等前期预处理;最后基于数控机器轴,采用滑动窗口检测的形式采集实际待测图像,并通过实验对比了传统的机器学习算法在该类图像数据中的性能评估;经实验证实,通过卷积神经网络训练得到的多分类模型,焊缝缺陷检测精度能达到97%以上,且每张待测图像的测试时间均在300 ms左右,远超机器学习算法,在准确性和实时性上均能达到实际工业要求。     

Hybridizing firefly algorithms with a probabilistic neural network for solving classification problems

Classification is one of the important tasks in data mining. The probabilistic neural network (PNN) is a well-known and efficient approach for classification. The objective of the work presented in this paper is to build on this approach to develop an effective method for classification problems that can find high-quality solutions (with respect to classification accuracy) at a high convergence speed. To achieve this objective, we propose a method that hybridizes the firefly algorithm with simulated annealing (denoted as SFA), where simulated annealing is applied to control the randomness step inside the firefly algorithm while optimizing the weights of the standard PNN model. We also extend our work by investigating the effectiveness of using Lévy flight within the firefly algorithm (denoted as LFA) to better explore the search space and by integrating SFA with Lévy flight (denoted as LSFA) in order to improve the performance of the PNN. The algorithms were tested on 11 standard benchmark datasets. Experimental results indicate that the LSFA shows better performance than the SFA and LFA. Moreover, when compared with other algorithms in the literature, the LSFA is able to obtain better results in terms of classification accuracy.     

基于神经网络与模糊算法图像边缘检测方法*

针对传统图像边缘检测方法中出现毛边、噪边、边缘定位不精确等缺点,提出一种神经网络与模糊算法相结合的检测方法。根据图像特征,将图像分为高频和低频部分分别处理,高频部分适宜用双层网络结构,可以很好地减弱噪声;对于图像低频部分,将模糊理论引入到边缘检测中,能够检测出弱边。最后对检测出的两个图像边缘进行融合,实验结果证明得出的检测效果较好,比传统边缘检测算子所获结果有很大改善。     

尺度无关的级联卷积神经网络人脸检测算法

卷积神经网络在进行图片处理时需要输入固定尺寸大小的图片,该限制会导致原图在放缩过程中损失大部分信息。另外,目前人脸检测算法多用单一结构网络进行特征提取,这就使得算法的泛化能力较弱。针对以上两个问题,提出了一种将级联卷积神经网络与空间金字塔池化相结合的人脸检测算法。该方法将三级卷积神经网络模型连接起来,其中三级神经网络模型之间各不相同,结构从简单到复杂,在不同层次的神经网络上提取不同的人脸特征并筛选图片,完成对图片中人脸区域的检测。同时,在每级网络层次中加入空间金字塔池化层,这种池化策略无须固定尺寸大小的输入,增加了模型输入的尺寸选择。在标准人脸数据集中,该方法相对于传统方法实现了模型的多尺度输入,提升了检测的性能,并降低了检测人脸的时间。     

基于卷积神经网络的多尺度Logo检测算法

针对自然场景图像中多尺度Logo的检测需求,提出了一种基于卷积神经网络的多尺度Logo检测算法。该算法基于两阶段目标检测的实现思路,通过构建特征金字塔并采取逐层预测的方式实现多尺度候选区域的生成,通过融合卷积神经网络中的多层特征图以增强特征的表达能力。在FlickrLogos-32数据集上的实验结果显示,相比基线方法,所提算法能够提升生成候选区域的召回率,并且在保证大中尺度 Logo 检测精度的前提下,提升小尺度Logo的检测性能,验证了所提算法的优越性。     

A distributed approach for track occupancy detection

This paper investigates the problem of track occupancy detection in distributed settings. Track occupancy detection determines which tracks are occupied in a railway system. For each track, the Neyman–Pearson structure is applied to reach the local decision. Globally, it is a multiple hypotheses testing problem. The Bayesian approach is employed to minimize the probability of the global decision error. Based on the prior probabilities of multiple hypotheses and the approximation of the receiving operation characteristic curve of the local detector, a person-by-person optimization method is implemented to obtain the fusion rule and the local strategies off line. The results are illustrated through an example constructed from in situ devices.     

基于结构感知深度神经网络的显著性对象检测算法

由于现有的基于深度神经网络的显著性对象检测算法忽视了对象的结构信息,使得显著性图不能完整地覆盖整个对象区域,导致检测的准确率下降。针对此问题,提出一种结构感知的深度显著性对象检测算法。算法基于一种多流结构的深度神经网络,包括特征提取网络、对象骨架检测子网络、显著性对象检测子网络和跨任务连接部件四个部分。首先,在显著性对象子网络的训练和测试阶段,通过对象骨骼检测子网络学习对象的结构信息,并利用跨任务连接部件使得显著性对象检测子网络能自动编码对象骨骼子网络学习的信息,从而感知对象的整体结构,克服对象区域检测不完整问题;其次,为了进一步提高所提方法的准确率,利用全连接条件随机场对检测结果进行进一步的优化。在三个公共数据集上的实验结果表明,该算法在检测的准确率和运行效率上均优于现有存在的基于深度学习的算法,这也说明了在深度神经网络中考虑对象结构信息的捕获是有意义的,可以有助于提高模型准确率。