基于声音特征优化和改进支持向量机的鸟声识别

为了在低参数量下提高鸟鸣声的识别准确率,提出了一种新的鸟声识别方法,包括鸟声信号特征优化和乌鸦搜索-支持向量机（Support Vector Machine,SVM）分类识别。该方法首先采用主成分分析法对从鸟声中提取的梅尔频率倒谱系数（Mel Frequency Cepstrum Coefficient,MFCC）和翻转梅尔频率倒谱系数进行选择,得到优化后的声音特征参数并将其作为鸟声识别算法的输入;然后利用乌鸦搜索算法对SVM的核参数和损失值进行选优,得到改进的SVM网络用于鸟声分类识别。试验结果表明,该方法对5种鸟声识别的准确率为92.2%,声音特征维数在16时可以得到最好的识别效果。该方法为野外鸟声自动识别提供了一种可行的方式。     

基于深度学习算法的无线传感器异常数据检测

提出了基于深度学习的异常数据检测的方法,精准检测到无线传感器异常数据并直观展现检测结果。基于无线传感器网络模型分簇原理,通过异常数据驱动的簇内数据融合机制,去除无线传感器网络中的无效数据,获取无线传感器网络有效数据融合结果。构建了具有4层隐含层的深度卷积神经网络,将预处理后的无线传感器网络数据作为模型输入,通过隐含层完成数据特征提取和映射后,由输出层输出异常数据检测结果。实验证明：该方法可有效融合不同类型数据,且网络节点平均能耗较低;包含4层隐含层的深度卷积神经网络平均分类精度高达98.44%,1000次迭代后隐含层的训练损失均趋于0,可实现无线传感器异常数据实时、直观、准确检测。     

无线传感器网络能量优化与建模技术综述

由于无线传感器网络的能量受限,如何优化网络能量消耗和评估网络生存周期是当前无线传感器网络研究的首要挑战。在分析无线传感器网络能量消耗特征的基础上,调研传感器网络节点和网络系统的能量优化策略;并针对能量优化存在的不足,分析近几年兴起的无线传感器网络能耗建模工作;从基于无线通信、状态转换、协议栈等方面归纳总结无线传感器网络能耗模型的建模方法;指出跨层能量优化以及软硬件综合的能耗建模技术是无线传感器网络能量研究的重点。     

基于MFCC-IMFCC和GA-SVM的鸟声识别

鸟声识别研究中声音特征选取对识别分类的准确度有很大影响.为了提高鸟声识别正确率,针对传统的梅尔倒谱系数(MFCC)对鸟声高频信息表征不足.提出了基于Fisher准则MFCC和翻转梅尔倒谱系数(IMFCC)的特征融合,得到新的特征参数MFCC-IMFCC应用于鸟声识别,提高对鸟声高频信息表征.同时通过遗传算法(GA)对支持向量机(SVM)中的惩罚因子C和核参数g进行优化,训练出GA-SVM分类模型.实验表明,在同一条件下,MFCC-IMFCC与MFCC相比,识别率有一定的提高.     

基于簇首能量均衡分布的无线传感器网络LEACH协议改进

能量有限性是无线传感器网络(WSN)的最重要的特性,在网络路由算法中也是优先考虑的一个主要因素。分析了传统LEACH算法的不足,并对一些改进协议的LEACH进行认真研究,在此基础上提出了一种新的LEACH改进协议,仿真结果表明,改进后的协议能均衡节点能耗,提高了负载均衡度,并延长了无线传感器网络的生存时间。     

基于路由算法的无线传感器网络伪装研究

在研究如何通过无线传感器网络WSN有效获取信息的同时,如何确保敏感地区的信息不被WSN窃取也成为研究者关注的热点问题。基于WSN已有的路由算法,利用其开放的特点在敏感地区设置WSN伪装节点,并使其加入WSN节点的路由构建过程,伪装节点采用路由算法自适应伪装,通过修改数据报中的控制信息进而实现阻止WSN节点构建有效路由,并在最大程度上消耗WSN节点能量的目的。从WSN节点能耗速度和网络生命周期两方面验证了基于路由算法的WSN伪装的有效性。     

Interacting multiple model and sensor selection algorithms for manoeuvring target tracking in wireless sensor networks with multiplicative noise

This article addresses the problem of tracking a manoeuvring target in a wireless sensor network (WSN) consisting of distance-measuring sensor nodes. In order to cope with target manoeuvres, an interacting multiple model (IMM) filter is applied to estimate the position and velocity of the target. The distance-dependent measurement error of sensors is formulated as both additive and multiplicative noise in the observation equation. To deal with nonlinearities in the process and observation equations and also to solve the problem of multiplicative measurement noise, a new particle filter (PF)-based IMM approach is developed. Furthermore, the multiple-model posterior Cramér-Rao lower bound (PCRLB) is derived in the presence of both additive and multiplicative noise and it is used to perform a sensor selection algorithm to reduce energy consumption in WSN nodes. Simulation results show the effectiveness of the proposed IMMPF and sensor selection algorithms in target tracking.     

Dynamic sensor activation and decision-level fusion in wireless acoustic sensor networks for classification of domestic activities

For the past decades there has been a rising interest for wireless sensor networks to obtain information about an environment. One interesting modality is that of audio, as it is highly informative for numerous applications including speech recognition, urban scene classification, city monitoring, machine listening and classifying domestic activities. However, as they operate at prohibitively high energy consumption, commercialisation of battery-powered wireless acoustic sensor networks has been limited. To increase the network’s lifetime, this paper explores the joint use of decision-level fusion and dynamic sensor activation. Hereby adopting a topology where processing – including feature extraction and classification – is performed on a dynamic set of sensor nodes that communicate classification outputs which are fused centrally. The main contribution of this paper is the comparison of decision-level fusion with different dynamic sensor activation strategies on the use case of automatically classifying domestic activities. Results indicate that using vector quantisation to encode the classification output, computed at each sensor node, can reduce the communication per classification output to 8 bit without loss of significant performance. As the cost for communication is reduced, local processing tends to dominate the overall energy budget. It is indicated that dynamic sensor activation, using a centralised approach, can reduce the average time a sensor node is active up to 20% by leveraging redundant information in the network. In terms of energy consumption, this resulted in an energy reduction of up to 80% as the cost for computation dominates the overall energy budget.     

无线传感器网络分簇路由节能研究

在大规模传感和环境监测中,节约能源延长传感器节点生命已成为无线传感器网络最重要的研究课题之一。提供合理的能源消耗和改善无线网络生命周期的传感器网络系统,必须设计一种新的有效的节能方案和节能路由体系。方案采用一种聚类算法减少无线传感器网络的能量消耗,创建一种cluster-tree分簇路由结构的传感器网络。该方案主要目标是做一个理想的分簇分配,减少传感器节点之间的数据传输距离,降低传感器节点能源消耗,延长寿命。实验结果表明,该方案有效地降低了能源消耗从而延长无线传感器网络生命。     

无线传感网中一种智能数据融合算法的实现及仿真分析

在无线传感网中,传感器节点一般都由自身装配的电池供电,难以进行电量补充,因此节约电量对于无线传感网来说至关重要.为了提高无线传感网能量使用效率,延长网络生存时间,提出了一种结合遗传算法和粒子群算法优化BP神经网络的智能数据融合算法 GAPSOBP(BP Neural Network Data Fusion algorithm optimized by Genetic algorithm and Particle swarm).GAPSOBP算法将无线传感网的节点类比为BP神经网络中的神经元,通过神经网络提取无线传感网采集的感知数据并结合分簇路由对收集的传感数据进行融合处理,从而大幅减少发往汇聚节点的网络数据量.仿真结果表明,与经典LEACH算法和PSOBP算法相比,GAPSOBP算法能有效减少网络通信量,节约节点能量,显著延长网络生存时间.     

线形异构传感器的网络生命周期

无线传感器网络的能耗决定了网络的生命周期,如何有效部署传感器节点来延长网络的生命周期是一个重要的研究课题。针对由高级节点和普通节点组成的线形异构传感器网络,给出了最大化网络生命周期模型。通过分析节点的能量消耗,求解出了两种节点的分配比例,得出了最大化网络生命周期的节点部署方案。     

数据集成技术在树型WSN中的应用与研究

针对无线传感器网络中节点能量有限这一特点,如何提高能量利用率、延长网络寿命是每个WSN研究者所必须面临的问题,同样也是WSN发展过程中必须被解决的难题。为此,本文将一种数据集成算法引入无线传感器网络,通过去除节点间的冗余信息来降低网络中的数据流量,从而降低网络能耗,达到提高网络能量利用率和延长网络寿命的目的。文章以树型无线传感器网络为例,分别对采用数据集成算法前后的网络能量消耗进行分析研究,并给出了相应的能量消耗模型。随后又通过计算机仿真和实验数据监测的方法,验证了此数据集成算法在降低树型WSN能耗中是有效的,而且具有一定的实用价值。     

Performance analysis of energy efficient modulation and coding schemes for wireless sensor networks

Sensor nodes of a typical wireless sensor network (WSN) are battery driven, so energy conservation is a critical factor for node's life time. Thus optimisation of energy consumption is a major objective in the area of WSNs. One such method is asymmetric communication which uses different channel codes and modulation schemes for downlink (base station (BS) to node link) and uplink (node to BS link). In this paper, a performance analysis of different channel code–modulation pair for energy efficient asymmetric communication is carried out followed by the field programmable gate array implementation of channel codes required at the node. The per information bit node energy for the uplink has been calculated for efficient channel code–modulation pair, for three different channels, viz. additive white gaussian noise, Rayleigh flat-fading and log-normal shadowing channels, resulting in reduction in energy consumption at sensor nodes.     

基于传感器网络的水下声音源定位方法研究

提出一种分层结构的自组织无线传感器网络(WSN)用于水下声音源的定位研究,可以广泛应用于军事、民用监控等场景;在修正的声音源衰减模型基础上,提出一种改进的非线性最小二乘算法以及极大似然算法用于水下声音源定位;仿真试验对比研究了两种算法在不同的传感器节点以及背景噪声情况下对预估定位误差的影响;试验结果表明了这种分层结构的WSN用于水下声音源定位是可行的,同时验证了最小二乘算法以及极大似然两种算法定位的有效性。     

半径可调的无线传感器网络三维覆盖算法

针对三维无线传感器网络区域中节点覆盖的问题,提出一种半径可调的无线传感器网络三维覆盖算法（3D-CAAR）。该算法利用虚拟力作用实现无线传感器网络的节点均匀部署,同时结合传感器节点的半径可调覆盖机制,判断节点与被覆盖区域中目标点之间的距离。引入能耗阈值,使得节点根据自身情况调节节点感知半径,从而降低无线传感器网络的整体能耗,提高了节点利用率。最后,通过与传统基于人工势场的三维部署算法（APFA3D）、基于与未知目标精确覆盖的三维算法（ECA3D）仿真实验对比,3D-CAAR的事件集覆盖效能明显较高,能有效解决三维无线传感器网络中对目标节点的覆盖问题。     

Opportunistic routing in wireless sensor networks powered by ambient energy harvesting

Energy consumption is an important issue in the design of wireless sensor networks (WSNs) which typically rely on portable energy sources like batteries for power. Recent advances in ambient energy harvesting technologies have made it possible for sensor nodes to be powered by ambient energy entirely without the use of batteries. However, since the energy harvesting process is stochastic, exact sleep-and-wakeup schedules cannot be determined in WSNs Powered solely using Ambient Energy Harvesters (WSN–HEAP). Therefore, many existing WSN routing protocols cannot be used in WSN–HEAP. In this paper, we design an opportunistic routing protocol (EHOR) for multi-hop WSN–HEAP. Unlike traditional opportunistic routing protocols like ExOR or MORE, EHOR takes into account energy constraints because nodes have to shut down to recharge once their energy are depleted. Furthermore, since the rate of charging is dependent on environmental factors, the exact identities of nodes that are awake cannot be determined in advance. Therefore, choosing an optimal forwarder is another challenge in EHOR. We use a regioning approach to achieve this goal. Using extensive simulations incorporating experimental results from the characterization of different types of energy harvesters, we evaluate EHOR and the results show that EHOR increases goodput and efficiency compared to traditional opportunistic routing protocols and other non-opportunistic routing protocols suited for WSN–HEAP.     

Fault diagnosis in wireless sensor network using negative selection algorithm and support vector machine

In this article, an improved negative selection algorithm (INSA) has been proposed to identify faulty sensor nodes in wireless sensor network (WSN) and then the faults are classified into soft permanent, soft intermittent, and soft transient fault using the support vector machine technique. The performance metrics such as fault detection accuracy, false alarm rate, false positive rate, diagnosis latency (DL), energy consumption, fault classification accuracy (FCA), and false classification rate (FCR) are used to evaluate the performance of the proposed INSA. The simulation result shows that the INSA gives better result as compared to the existing algorithms in terms of performance metrics. The fault classification performance is measured by FCA and FCR. It has also seen that the proposed algorithm gives less DL and consumes less energy than that of existing algorithms proposed by Mohapatra et al, Zhang et al, and Panda et al for WSN.     

基于无线通信和计算特征分析的能耗模型

无线传感器网络(wireless sensor network, WSN)是能量严重受限的网络,这就要求WSN必须是能量有效的.有必要掌握WSN的能量实时消耗情况,这需要有正确的能耗模型提供支持.但目前的能耗建模研究在一般假设方面仍存在种种与WSN实际不符的情况,这导致现有能耗模型不能应用于WSN实践.首先结合WSN应用实际,综合分析了通信活动、计算活动及物理特性因素对节点能耗的影响.进而提出了一种基于无线通信和计算特征分析的节点能耗模型.最后对该能耗模型等进行了物理实现,并通过现场实验验证了该模型的有效性.     

用改进蚁群算法求解无线传感器网络多sink节点关联问题

在无线传感器网络W SN(wireless sensor networks)中使用多个sink节点既能有效减少传感器节点与sink之间的距离,又能有效降低通信中的能量消耗。如何为传感器节点分配sink节点使得系统总能耗最低,称为多sink节点的关联问题。首先建立带约束的多sink节点关联问题的优化模型,进而用蚂蚁算法解决给定多sink节点部署方案下的普通节点与sink节点间的关联问题,最后给出相关算法的仿真结果。     

一种基于虚拟网格位置的分簇算法

为了延长无线传感器网络生命周期, 提出一种基于虚拟网格的分簇路由算法RPLG. 该算法将监测区域划分为若干虚拟网格, 同一网格内节点自组织成簇. 根据节点所在网格位置和剩余能量启动计时器选取本地簇首, 且簇内成员可以根据局部的信息调整簇的大小, 达到节省能量的目的. 仿真实验和分析表明: 该协议能均衡网络能量, 延长网络的生存时间.