Fuzzy rule-based faulty node classification and management scheme for large scale wireless sensor networks

In a wireless sensor network (WSNs), probability of node failure rises with increase in number of sensor nodes within the network. The, quality of service (QoS) of WSNs is highly affected by the faulty sensor nodes. If faulty sensor nodes can be detected and reused for network operation, QoS of WSNs can be improved and will be sustainable throughout the monitoring period. The faulty nodes in the deployed WSN are crucial to detect due to its improvisational nature and invisibility of internal running status. Furthermore, most of the traditional fault detection methods in WSNs do not consider the uncertainties that are inherited in the WSN environment during the fault diagnosis period. Resulting traditional fault detection methods suffer from low detection accuracy and poor performance. To address these issues, we propose a fuzzy rule-based faulty node classification and management scheme for WSNs that can detect and reuse faulty sensor nodes according to their fault status. In order to overcome uncertainties that are inherited in the WSN environment, a fuzzy logic based method is utilized. Fuzzy interface engine categorizes different nodes according to the chosen membership function and the defuzzifier generates a non-fuzzy control to retrieve the various types of nodes. In addition, we employed a routing scheme that reuses the retrieved faulty nodes during the data routing process. We performed extensive experiments on the proposed scheme using various network scenarios. The experimental results are compared with the existing algorithms to demonstrate the effectiveness of the proposed algorithm in terms of various important performance metrics.     

基于深度森林的无线传感器网络故障分类算法

针对无线传感器网络(WSN)节点容易出现故障从而导致网络瘫痪的问题,提出了一种基于改进的深度森林的无线传感器网络故障分类方法;深度森林是基于森林的集成学习方法,其输入是多维特征向量,特征向量将由多粒度扫描和级联森林这两个主要组成部分进行处理,多粒度扫描通过处理数据之间的关系来增强数据表示的能力,级联森林用于分类或预测;针对级联森林部分随着层数的增加可能造成的维数问题进行优化后,将该算法用于故障分类可以提高故障诊断的精确度;在仿真验证阶段,将该算法与深度神经网络(DNN)和支持向量机(SVM)算法进行对比;结果显示,该算法可以准确地识别出不同的故障类型,并且在损坏故障和电源故障的识别达到了最高精度,综合平均精度在98.4%;对偏移故障、漂移故障和通信故障的识别略低于卷积神经网络(CNN)算法,但综合训练时间、参数调节来看,该算法更能满足实际工程的需要。     

基于移动代理的三维DV-Hop算法

三维空间的无线传感器网络节点定位算法研究是当前的研究热点之一。通过对现有三维定位算法的不足进行分析,将无需测距的DV-Hop算法拓展到三维空间,并在通信量、定位精度方面进行了相关改进,提出了一种基于移动代理的三维DV-Hop定位算法。仿真结果表明,所提算法能对三维环境中的传感器节点进行有效的定位,信标节点的密度和通信半径对定位误差和覆盖率的影响较小,且定位精度和覆盖率相对于其他算法有明显提高。     

Distributed denial of service attack detection using an ensemble of neural classifier

The vulnerabilities in the Communication (TCP/IP) protocol stack and the availability of more sophisticated attack tools breed in more and more network hackers to attack the network intentionally or unintentionally, leading to Distributed Denial of Service (DDoS) attack. The DDoS attacks could be detected using the existing machine learning techniques such as neural classifiers. These classifiers lack generalization capabilities which result in less performance leading to high false positives. This paper evaluates the performance of a comprehensive set of machine learning algorithms for selecting the base classifier using the publicly available KDD Cup dataset. Based on the outcome of the experiments, Resilient Back Propagation (RBP) was chosen as base classifier for our research. The improvement in performance of the RBP classifier is the focus of this paper. Our proposed classification algorithm, RBPBoost, is achieved by combining ensemble of classifier outputs and Neyman Pearson cost minimization strategy, for final classification decision. Publicly available datasets such as KDD Cup, DARPA 1999, DARPA 2000, and CONFICKER were used for the simulation experiments. RBPBoost was trained and tested with DARPA, CONFICKER, and our own lab datasets. Detection accuracy and Cost per sample were the two metrics evaluated to analyze the performance of the RBPBoost classification algorithm. From the simulation results, it is evident that RBPBoost algorithm achieves high detection accuracy (99.4%) with fewer false alarms and outperforms the existing ensemble algorithms. RBPBoost algorithm outperforms the existing algorithms with maximum gain of 6.6% and minimum gain of 0.8%.     

A study of polynomial fit-based methods for qualitative trend analysis

Qualitative trend analysis (QTA) of sensor data is a useful tool for process monitoring, fault diagnosis and data mining. However, because of the varying background noise characteristics and different scales of sensor trends, automated and reliable trend extraction remains a challenge for trend-based analysis systems. In this paper, several new polynomial fit-based trend extraction algorithms are first developed, which determine the parameters automatically in the hypothesis testing framework. An existing trend analysis method developed by Dash et al. (2004) is then modified and added to the abovementioned trend extraction algorithms, which form a complete solution for QTA. The performance comparison of these algorithms is made on a set of simulated data and Tennessee Eastman process data based on several metrics.     

基于邻居节点预状态的无线传感器网络故障诊断算法

针对无线传感器网络（WSN）故障节点率高于50%时故障检测率降低的问题,提出一种基于邻居节点预状态及邻居节点数据的无线传感器节点故障诊断算法。首先利用节点自身历史数据对节点状态进行初步预判断;然后结合节点间相似性和邻居节点的预状态对节点状态进行最终的判断;最后利用移动传感器节点将故障节点信息通过最优路径发送给基站,有效地减少了通信次数。仿真实验在100 m×100 m的方形区域内模拟WSN。实验结果表明,与传统的分布式故障诊断（DFD）算法相比,诊断精度提升了9.84个百分点,并且当节点故障率高达50%时,该算法仍能达到95%的诊断精度。在实际应用中,所提算法在提高故障诊断精度的同时,能有效地减少能量消耗、延长网络寿命。     

基于簇的分布式传感器故障检测算法

针对大规模无线传感器网络(WSN)中故障检测准确率降低,并产生较大通信负载的问题,根据传感器节点的时空相关性特点,提出一种基于簇的分布式传感器故障检测算法。通过邻居节点间的数据交换和互相测试检测簇首节点,并以正常簇首节点作为参照诊断故障节点。性能分析与实验结果表明,在大规模WSN中,该算法具有良好的故障检测能力和较低的通信负载,在邻居节点数较少、节点故障率较高的情况下,能达到98%以上的故障检测准确率,并保持较低的能耗水平。     

基于锚节点连通性的移动WSN定位优化算法

为提高传统移动无线传感网络非测距方式定位算法的节点定位精度、降低算法对锚节点密度的要求,提出一种基于网络中锚节点连通性的蒙特卡洛优化定位算法,并分析了其节点定位性能.算法首先引入平均锚节点连通度的概念来评价网络锚节点连通性,然后提出根据节点实时分布情况进行采样区域划分,并实时控制移动锚节点分布,提升网络的整体定位精度.仿真结果表明,相较于传统的移动无线传感网络中基于蒙特卡洛方法的节点定位算法,所提出的算法有效提升了整体的定位精度,并有效降低了算法对于锚节点密度的要求,提升了算法节点定位性能.     

WSN中故障诊断性能与平均节点度研究

在基于无线传感器网络的结构健康监测中,故障节点产生并传输的错误数据将消耗节点的能量和带宽,同时会形成结构健康监测的错误决策。针对该问题,提出一种节点故障诊断算法,利用节点感知传感数据的空间相似性,通过对邻节点所感知的传感数据进行比较,确定检测节点的状态,将测试状态向网络中其他相邻节点进行扩散,实现网络中全部节点的故障检测。同时介绍在不同平均节点度下改善故障诊断率的方法。实验结果表明,该算法能够获得较好的性能。     

基于累积和控制图的分布式传感网络故障诊断

由于无线气象传感网具有资源受限及分布式等特点,传感器节点的故障诊断面临着很大挑战。针对现有诊断方法误报率高、计算冗余量大的问题,提出了一种基于累积和控制图（CUSUM）与邻居协作融合的故障诊断方法。首先,通过累积和控制图分析传感器节点上的历史数据,提高对节点故障判断的灵敏度并且定位出异常时间点;然后,结合网络内邻居节点间的数据交换,通过判断节点的状态诊断出故障节点。实验结果表明,即使在整个网络中在节点故障率高达35%时,算法检测精度仍然高于97.7%,而误报率不超过2%。由此可见,在节点故障概率很高的情况下,此所提法也能得到很高的检测精度和较低的误报率,受节点故障率的影响明显减小。     

离群点检测算法的评价指标

随着离群点检测技术的深入研究和广泛应用,越来越多的优秀算法被提出来,然而,现有的离群点检测技术的评价仍然沿用传统分类算法的测量指标,存在着评价指标单一、适应性差的问题。针对这些问题,提出了一类高真正率指标（HT_AUC）和二类低假正率指标（LF_AUC）。首先,整理常用的离群点检测评价指标,分析其优缺点和适用场景;然后,在已有的曲线下面积（AUC）方法的基础上,分别针对高真正率（TPR）要求和低假正率（FPR）要求,提出了一类高真正率指标和二类低假正率指标,为离群点检测算法的效果评价和量化集成提供了更合适的指标。在真实数据集上的实验结果表明,与传统评价指标的相比,所提出的方法更能满足一类高真正率和二类低假正率要求。     

离群点检测算法的评价指标

随着离群点检测技术的深入研究和广泛应用，越来越多的优秀算法被提出来，然而，现有的离群点检测技术的评价仍然沿用传统分类算法的测量指标，存在着评价指标单一、适应性差的问题。针对这些问题，提出了一类高真正率指标（HT_AUC）和二类低假正率指标（LF_AUC）。首先，整理常用的离群点检测评价指标，分析其优缺点和适用场景；然后，在已有的曲线下面积（AUC）方法的基础上，分别针对高真正率（TPR）要求和低假正率（FPR）要求，提出了一类高真正率指标和二类低假正率指标，为离群点检测算法的效果评价和量化集成提供了更合适的指标。在真实数据集上的实验结果表明，与传统评价指标的相比，所提出的方法更能满足一类高真正率和二类低假正率要求。     

基于移动Agent无线传感器网络节点自定位算法

目前提出的无线传感器网络自身定位技术有基于测距和不基于测距两类方法,在无线传感器网络应用中,它们各自有其局限性,而移动Agent技术可以较好地弥补这些缺陷。提出了一种基于移动Agent的无线传感器网络自身定位算法,介绍了算法的基本原理和实现方法。该算法不需要额外的硬件支持,减少了无线传感器网络自身定位的通信和计算开销,提高了定位精度。     

基于改进的粗糙集和神经网络的WSN故障诊断

综合粗糙集理论和人工神经网络的优点,提出了改进的粗糙集理论算法,并结合人工神经网络,实现了一种无线传感器网络(Wireless Sensor Network,WSN)节点智能故障诊断方法。首先基于WSN的应用环境和故障特征的分析,通过数据采集、数据预处理和数据压缩来获得诊断决策表,并利用粗糙集中改进的归纳属性约简算法(Improved Inductive Attribute Reduction Algorithm,IIARA)对决策表进行属性约简,从而提取对故障诊断贡献最大的最小故障诊断特征集合,进而确定后端径向基函数神经网络(Radial Basis Function Neural Network,RBFNN)的拓扑结构。最后通过网络训练建立故障征兆与故障类型之间的非线性映射关系,得到诊断结果。仿真实验结果显示,该诊断算法在对WSN节点进行故障诊断时,可以有效地减少网络输入层个数,简化神经网络结构,减少网络的训练时间,提高模型的诊断准确性。     

Divide-and-conquer architecture based collaborative sensing for target monitoring in wireless sensor networks

Most surveillance applications in wireless sensor network (WSN) have stringent accuracy requirements in targets surveillance with maximized system lifetime, while large amount of continuous sensing data and limited resource in WSNs pose great challenges. So it is necessary to select appropriate sensors that can collaboratively work with each other in order to obtain balance between accuracy and system lifetime. However, because of sensing diversity and big data from WSN, most existing methods can not select appropriate sensors to cover all critical monitoring locations in large scale real deployments. Accordingly, an AdaBoost based algorithm is first proposed to identify valid sensors with contribution towards accuracy improvement, which can reduce computation and communication overhead by excluding invalid sensors. The valid sensors are combined and work in a collaborative way, which can obtain better performance than other ways. Then, because of independence of each monitoring location, a divide-and-conquer architecture based method (EasiSS) is proposed to select the most informative sensor clusters from the valid sensors for critical monitoring locations. EasiSS can obtain higher classification accuracy at different user requirement. Finally, according to the experiment on real data, we demonstrate that our proposed method can get a better performance of sensor selection, comparing with traditional methods.     

基于RSSI等级的蒙特卡罗定位算法应用研究

感知节点的定位是无线传感网应用的基础。现有的静态定位算法无法应用于动态传感网。针对一类目标节点移动而锚节点静止的传感网应用,提出了一种RRMCL（RSSI Rank Monte Carlo Localization）定位算法。该算法以蒙特卡罗算法为基础,利用RSSI（Received Signal Strength Indication）值与距离的单调递减关系划分通信域,减少采样区域大小。为了避免锚节点共线出现定位失效的情况,引入共线影响角度,提出了一种约束策略。仿真结果表明,提出的RRMCL与现有的MCL和MCB定位算法相比,能有效缩小采样区域,提高了定位精度和速度。     

基于全神经网络增强算法的WSNs故障预警与检测

针对现有WSNs故障检测算法存在的故障分类检测率低、耗时长、节点能耗控制差等问题,提出一种全神经网络增强故障预警与检测算法。全神经网络的神经元节点与临近层的节点连接,形成具有强大故障数据训练功能的深度网络结构,选择平滑性更好的sigmoid函数作为模型的激活函数,并基于感知机合理调节相邻两个隐含层之间的阈值权重,降低模型的训练损失;采用Adam优化算法抑制模型的梯度膨胀和梯度消失等异常情况,并消除训练中产生的数据冗余,以降低故障数据训练中产生的虚预警。实验结果显示:提出算法的总体故障检测率和不同类型故障的分类检测率都优于传统算法,此外全神经网络增强算法在节点故障检测耗时和能耗控制方面,也具有显著优势。     

An efficient scheme of target classification and information fusion in wireless sensor networks

In this paper, an efficient target classification and fusion scheme for wireless sensor networks (WSNs) is proposed and evaluated. When a classification algorithm for WSN nodes is designed, parametric approaches such as Gaussian mixture model (GMM) should be more preferred to non-parametric ones due to the hard limitation in resources. The GMM algorithm not only shows good performances for target classification in WSNs but it also requires very small resources. Based on the classifier, a decision tree generated by the classification and regression tree algorithm is used to fuse the information from heterogeneous sensors. This node-level classification scheme provides a satisfactory classification rate, 94.10%, with little resources. Finally, a confidence-based fusion algorithm improves the overall accuracy by fusing the information among sensor nodes. Our experimental results show that the proposed group-level fusion algorithm improves the accuracy by an average of 4.17% accuracy with randomly selected nodes.     

一种无线传感器网络节点的故障检测算法

在无线传感器网络(WSN)中,容易因为故障节点存在冗余的故障属性、噪声数据以及数据可靠性等问题,从而产生传输错误数据,这将极大地消耗WSN节点中能量和带宽,向用户形成错误的决策。为此,提出了基于蚁群算法和BP神经网络模型的WSN节点故障检测方法。通过使用蚁群算法,使用户通过寻找优化路径来定位WSN节点的位置,通过这种随机搜索算法以及蚁群算法的搜索策略使用户对WSN故障节点的位置进行总体把握。然后又基于BP神经网络模型对获取的WSN故障节点信息进一步学习,在数据训练过程中,依据WSN故障节点预测误差,并进一步调整网络的权值和阈值,增加了故障诊断的精度。采用的算法对检测WSN故障节点具有较好的性能,使无线传感器网络的服务质量大大提高,增强了系统的稳定性,实验结果验证了算法的可行性和有效性。     

无线传感器网络不重复记录求和近似算法

针对现有的求和算法基本上都是对副本敏感的算法,提出一种对副本不敏感的求和近似算法FM-S。网络中各节点由FM-S和服从二项分布的随机数样本对节点记录进行哈希转换以填充一个长度为L的二进制求和序列,并且每个节点会把生成的序列转发给路由树中的父亲节点,根节点将接收到全网的求和序列,最终根据此序列可计算出网络中不重复记录求和的近似值。实验结果显示该算法是一种分布式、低功耗、容错性高、扩展性和健壮性强的聚集查询算法。