A Support Data-Based Core-Set Selection Method for Signal Recognition

In recent years,deep learning-based signal recognition technology has gained attention and emerged as an important approach for safeguarding the electromagnetic environment.However,training deep learning-based classifiers on large signal datasets with redundant samples requires significant memory and high costs.This paper proposes a support databased core-set selection method(SD)for signal recognition,aiming to screen a representative subset that approximates the large signal dataset.Specifically,this subset can be identified by employing the labeled information during the early stages of model training,as some training samples are labeled as supporting data frequently.This support data is crucial for model training and can be found using a border sample selector.Simulation results demonstrate that the SD method minimizes the impact on model recognition performance while reducing the dataset size,and outperforms five other state-of-the-art core-set selection methods when the fraction of training sample kept is less than or equal to 0.3 on the RML2016.04C dataset or 0.5 on the RML22 dataset.The SD method is particularly helpful for signal recognition tasks with limited memory and computing resources.

CYCLOSTATIONARITY-BASED OFDM SIGNAL SENSING OVER DOUBLY-SELECTIVE FADING CHANNELS

In this paper,using cyclostationarity-based sensing method to detect the presence of Orthogonal Frequency Division Multiplexing(OFDM) signal over doubly-selective fading channels is studied.By approximating the channel with Basis Expansion Model(BEM),we derive the second-order cyclostationary statistics of the received OFDM signal over doubly-selective fading channels.Theoretical analysis indicates that new cyclostationary signatures produced by Doppler spread and multipath delay can be further exploited in the detecting process.Simulation examples demonstrate that the sensing methods using channel-induced cyclostationary features provide substantial improvements on detection performance.

Adaptive controller design based on input-output signal selection for voltage source converter high voltage direct current systems to improve power system stability

An input-output signal selection based on Phillips-Heffron model of a parallel high voltage alternative current/high voltage direct current(HVAC/HVDC) power system is presented to study power system stability. It is well known that appropriate coupling of inputs-outputs signals in the multivariable HVDC-HVAC system can improve the performance of designed supplemetary controller. In this work, different analysis techniques are used to measure controllability and observability of electromechanical oscillation mode. Also inputs–outputs interactions are considered and suggestions are drawn to select the best signal pair through the system inputs-outputs. In addition, a supplementary online adaptive controller for nonlinear HVDC to damp low frequency oscillations in a weakly connected system is proposed. The results obtained using MATLAB software show that the best output-input for damping controller design is rotor speed deviation as out put and phase angle of rectifier as in put. Also response of system equipped with adaptive damping controller based on HVDC system has appropriate performance when it is faced with faults and disturbance.

Selection of optimal window length using STFT for quantitative SNR analysis of LFM signal

An adaptive approach to select analysis window param- eters for linear frequency modulated （LFM） signals is proposed to obtain the optimal 3 dB signal-to-noise ratio （SNR） in the short- time Fourier transform （STFT） domain. After analyzing the instan- taneous frequency and instantaneous bandwidth to deduce the relation between the window length and deviation of the Gaus- sian window, high-order statistics is used to select the appropriate window length for STFT and get the optimal SNR with the right time-frequency resolution according to the signal characteristic under a fixed sampling rate. Computer simulations have verified the effectiveness of the new method.

Region-Aware Trace Signal Selection Using Machine Learning Technique for Silicon Validation and Debug

In today’s modern design technology,post-silicon validation is an expensive and composite task.The major challenge involved in this method is that it has limited observability and controllability of internal signals.There will be an issue during execution how to address the useful set of signals and store it in the on-chip trace buffer.The existing approaches are restricted to particular debug set-up where all the components have equivalent prominence at all the time.Practically,the verification engineers will emphasis only on useful functional regions or components.Due to some constraints like clock gating,some of the regions can be ignored during execution.Likewise,some of these regions can be verified deeply and have minimum errors compared to other control regions.The proposed system focusses on random signals that identify more errors which are prone to signal selection technique with low area overhead.To enhance the observability,a machine learning technique is developed.Based on the training samples of smaller designs,a model is developed to find out the contiguous neighbours of each flip-flop.This can eliminate the obstacles of unknown signals.This system demonstrates using Opencores and ISCAS’89 benchmark circuits that result in easy and fast error detection compared to the state-of-theart of other methods.This is also verified using gate-level error models by cross-validation of each debug run.

Feature Selection with Deep Belief Network for Epileptic Seizure Detection on EEG Signals

The term Epilepsy refers to a most commonly occurring brain disorder after a migraine.Early identification of incoming seizures significantly impacts the lives of people with Epilepsy.Automated detection of epileptic seizures(ES)has dramatically improved the life quality of the patients.Recent Electroencephalogram(EEG)related seizure detection mechanisms encountered several difficulties in real-time.The EEGs are the non-stationary signal,and seizure patternswould changewith patients and recording sessions.Further,EEG data were disposed to wide noise varieties that adversely moved the recognition accuracy of ESs.Artificial intelligence(AI)methods in the domain of ES analysis use traditional deep learning(DL),and machine learning(ML)approaches.This article introduces an Oppositional Aquila Optimizer-based Feature Selection with Deep Belief Network for Epileptic Seizure Detection(OAOFS-DBNECD)technique using EEG signals.The primary aim of the presented OAOFS-DBNECD system is to categorize and classify the presence of ESs.The suggested OAOFS-DBNECD technique transforms the EEG signals into.csv format at the initial stage.Next,the OAOFS technique selects an optimal subset of features using the preprocessed data.For seizure classification,the presented OAOFS-DBNECD technique applies Artificial Ecosystem Optimizer(AEO)with a deep belief network(DBN)model.An extensive range of simulations was performed on the benchmark dataset to ensure the enhanced performance of the presented OAOFS-DBNECD algorithm.The comparison study shows the significant outcomes of the OAOFS-DBNECD approach over other methodologies.In addition,the result of the suggested approach has been evaluated using the CHB-MIT database,and the findings demonstrate accuracy of 97.81%.These findings confirmed the best seizure categorization accuracy on the EEG data considered.

BLIND CHANNEL ESTIMATION IN DELAY DIVERSITY FOR FREQUENCY SELECTIVE CHANNELS

Delay diversity is an effective transmit diversity technique to combat adverse effects of fading. Thus far, previous work in delay diversity assumed that perfect estimates of current channel fading conditions are available at the receiver and training symbols are required to estimate the channel from the transmitter to the receiver. However, increasing the number of the antennas increases the required training interval and reduces the available time with in whichdata may be transmitted. Learning the channel coefficients becomes increasingly difficult for the frequency selective channels. In this paper, with the subspace method and the delay character of delay diversity, a channel estimation method is proposed, which does not use training symbols. It addresses the transmit diversity for a frequency selective channel from a single carrier perspective in the form of a simple equivalent flat fading model. Monte Carlo simulations give the performance of channel estimation and the performance comparison of our channel-estimation-based detector with decision feedback equalization, which uses the perfect channel information.

Metaheuristic Optimization Algorithm for Signals Classification of Electroencephalography Channels

Digital signal processing of electroencephalography(EEG)data is now widely utilized in various applications,including motor imagery classification,seizure detection and prediction,emotion classification,mental task classification,drug impact identification and sleep state classification.With the increasing number of recorded EEG channels,it has become clear that effective channel selection algorithms are required for various applications.Guided Whale Optimization Method(Guided WOA),a suggested feature selection algorithm based on Stochastic Fractal Search(SFS)technique,evaluates the chosen subset of channels.This may be used to select the optimum EEG channels for use in Brain-Computer Interfaces(BCIs),the method for identifying essential and irrelevant characteristics in a dataset,and the complexity to be eliminated.This enables(SFS-Guided WOA)algorithm to choose the most appropriate EEG channels while assisting machine learning classification in its tasks and training the classifier with the dataset.The(SFSGuided WOA)algorithm is superior in performance metrics,and statistical tests such as ANOVA and Wilcoxon rank-sum are used to demonstrate this.

Frequency Selectivity Analysis Based on Inductively Coupled Channel for Current Transmission Through Seawater

Inductively coupled channels are based on the electromagnetic induction principle and realize long-distance current signal transmission through seawater.Due to a few difficulties in performing actual experiments,it is unclear how the seawater medium affects the frequency selectivity of the current signal.In this paper,a dual dipole model of the inductively coupled seawater transmission channel is established for the traditional short-distance current field transmission mode.The transmission characteristics of electrical signals in seawater are theoretically derived.A platform is used to measure the amplitude-frequency and phase-frequency characteristics of the current signal transmission in seawater with transmission frequencies ranging from 30 kHz to 1 MHz,and transmission distances in the vertical range of 4 m.The COMSOL Multiphysics simulation and practical test analysis are carried out to analyze the frequency selectivity of seawater conductivity.It is proved that the seawater resistance increases as the frequency increases,which is the key problem that affects the current signal.This study provides an important theoretical support and experimental evidence for improving the transmission performance of long-distance underwater current signals.

Condition Monitoring of Roller Bearing by K-star Classifier andK-nearest Neighborhood Classifier Using Sound Signal

Most of the machineries in small or large-scale industry have rotating elementsupported by bearings for rigid support and accurate movement. For proper functioning ofmachinery, condition monitoring of the bearing is very important. In present study soundsignal is used to continuously monitor bearing health as sound signals of rotatingmachineries carry dynamic information of components. There are numerous studies inliterature that are reporting superiority of vibration signal of bearing fault diagnosis.However, there are very few studies done using sound signal. The cost associated withcondition monitoring using sound signal (Microphone) is less than the cost of transducerused to acquire vibration signal (Accelerometer). This paper employs sound signal forcondition monitoring of roller bearing by K-star classifier and k-nearest neighborhoodclassifier. The statistical feature extraction is performed from acquired sound signals. Thentwo-layer feature selection is done using J48 decision tree algorithm and random treealgorithm. These selected features were classified using K-star classifier and k-nearestneighborhood classifier and parametric optimization is performed to achieve the maximumclassification accuracy. The classification results for both K-star classifier and k-nearestneighborhood classifier for condition monitoring of roller bearing using sound signals werecompared.

“特藏寒羊”群体遗传结构分析与选择信号的对比分析

旨在了解“特藏寒羊”群体遗传结构和优势性能的遗传来源,为配种方案和杂交利用提供依据,帮助组建特定性能的家系。本研究应用SNP 50K v3芯片对50只“特藏寒羊”(公羊18只,母羊32只)、24只特克塞尔羊(公母各半)和48只欧拉羊(藏系绵羊)(公羊20只,母羊28只)进行单核苷酸多态性(single nucleotide polymorphisim,SNPs)检测;使用Plink、GCTA和MegaX软件对“特藏寒羊”进行遗传结构分析;Tajima’D法对“特藏寒羊”、特克塞尔羊和欧拉羊(藏系绵羊)进行群体内基因组选择信号分析,将“特藏寒羊”的选择信号分别与特克赛尔羊和欧拉羊(藏系绵羊)的选择信号取交集进行GO和KEGG功能富集分析,找到可能影响“特藏寒羊”优势性能的亲本来源和相关基因。结果显示:“特藏寒羊”平均多态信息含量(PIC)为0.26±0.12,平均期望杂合度(He)为0.36±0.14,平均观测杂合度(Ho)为0.37±0.16,平均最小等位基因频率(MAF)为0.25±0.15,平均有效等位基因数(Ne)为1.59±0.07;ROHs长度主要分布在1~5 Mb,占比50.4%,长度20 Mb+的ROH占比9.52%,近交系数F_(ROH)中位数为0.085;遗传距离D值为0.1527~0.3491,平均遗传距离0.2796;NJ聚类分析共划分5个家系,家系内个体分布不均;“特藏寒羊”与欧拉羊(藏系绵羊)交集信号定位的基因与免疫相关,包括原发性免疫缺陷、造血细胞系和T细胞受体信号通路;“特藏寒羊”与特克塞尔羊交集信号定位的基因与生物代谢相关。综上所述,“特藏寒羊”存在一定程度近交,需加强管理;欧拉羊(藏系绵羊)更影响“特藏寒羊”免疫功能,特克塞尔羊更影响“特藏寒羊”生长发育和肉质性状。

面向辐射源识别的多尺度特征提取与特征选择网络

目前应用于辐射源识别的卷积神经网络对时序同相正交(in-phase and quadrature-phase,IQ)信号的处理有两种方式:一种方式是将其变换为图像,另一种方式是提取IQ时序数据的浅层特征。前一种方式会导致算法计算量大,而后一种方式会导致识别准确率低。针对上述问题,提出一种多尺度特征提取与特征选择网络。该网络以IQ信号为输入,经多尺度特征提取网络提取IQ信号的浅层特征和多尺度特征,采用特征选择网络降低多尺度特征的数据维度,通过自适应线性整流单元实现特征增强,使用单个全连接层对辐射源进行分类。在FIT/CorteXlab射频指纹识别数据集上,与ORACLE、CNN-DLRF和IQCNet对比实验表明,所提网络在一定程度上提高了识别准确率,降低了计算量。

可重构通道选择型功率放大器设计

为满足现代无线通信系统小型化、集成化、低成本和高性能的需求,提出了一种新型的可重构功率放大器结构。该结构设计的输入匹配网络,能够实现1~3 GHz频段内的良好匹配;输出匹配网络将可重构技术和滤波匹配技术相结合,通过分布式PIN开关连接不同的滤波匹配电路,实现信号在多通道内高效的放大特性和工作频带的高选择性输出。采用CGH40010F GaN晶体管设计并加工了一款工作在1.5、1.8、2.4、2.6 GHz的功率放大器,其带宽约为200 MHz,通带外信号衰减可达-30 dB。通过测试,该功率放大器的饱和输出功率为40 dBm,增益维持在10 dB左右,最大功率附加效率(power added efficiency, PAE)可达到63%,实测结果与仿真结果具有较好的一致性。本文结构降低了电路复杂度和设计难度,具有高效率、高选择性等优势,为设计宽频带多功能可重构功率放大器提供了一种可行的方案。

基于选频电平表设计的信号与系统综合实验

针对学生的工程实践能力培养,为信号与系统实验课程设计了项目驱动式综合实验“选频电平表设计”。基于CDIO工程教育模式设计了实验内容,指导学生通过团队协作完成电子产品从研发到运行的完整周期。实验项目涉及傅里叶变换、频谱搬移、滤波等信号的频域分析和处理方法,同时结合了模拟电路设计、单片机技术、 EDA技术、电路焊接与调试等内容,综合性强,紧贴工程实际。教学实践表明,该实验能帮助学生加深对理论知识的理解,积累实践经验,提高学习兴趣和实践能力。

小型磁选态铯原子钟性能测试数据的统计与分析

LIP Cs-3000是一种国产的小型磁选态铯原子钟,在时频计量、卫星导航等领域获得应用。对近期交付的LIP Cs-3000性能测试数据进行统计与分析,得到了准确度的分布与范围,同时得到了峰谷比、信噪比、Ramsey线宽等指标的分布。从理论上估计了铯原子钟输出信号的稳定度指标范围,验证了该范围与实际测量相符。同时对电子倍增器电压每日增幅进行了统计,结合装铯量给出了LIP Cs-3000铯钟倍增器寿命的分布。统计与分析结果不仅有助于磁选态铯钟的性能提高,也有助于其他小型铯原子钟的性能提升。

轴流风机故障诊断中的信号特征选择方法研究

为确保煤矿工作人员的安全及提高生产效率,研究了一种基于多类型信号特征选择的轴流风机故障诊断模型。该模型主要通过监测风机在不同工况下的振动加速度信号,并经过信号处理获得速度信号和位移信号。通过提取这些信号的时频域统计特征,并利用极致梯度提升(Extreme Gradient Boosting,XGBoost)技术进行特征选择,以增强诊断准确性。实验结果显示,通过特征选择优化后的多信号数据集,模型在测试集上的平均判识准确率达到98.33%,对数损失仅为0.0534。相较于单一信号或未进行特征选择的数据集,模型表现出更高的效率和准确度,显著提升了故障诊断的可靠性和速度,从而有效减少了由风机故障可能导致的安全隐患。

基于全基因组重测序解析皮山红羊群体遗传结构及产羔数候选基因研究

[目的]皮山红羊是分布于新疆和田地区的新发现多羔性地方绵羊品种。本研究基于全基因组重测序技术从基因组水平上了解皮山红羊的群体遗传结构及产羔性状受选择信号区域,并对候选基因进行验证。[方法]选择30只连续产2~3羔的经产皮山红羊母羊为高繁组(high fertility, HF),30只连续产单羔的经产皮山红羊母羊为低繁组(low fertility, LF),对这两个群体进行全基因组重测序。应用主成分分析(PCA)、系统进化树、群体遗传结构及全基因组扫描(Fst&θπ)等综合分析法确定候选区域,进一步筛选皮山红羊产羔性状候选基因。采用飞行质谱分型技术对候选基因进行分型验证。[结果]皮山红羊高、低繁殖组群体连锁不平衡(LD)分析衰减曲线相似,系统进化树显示两组群体分化程度不明显。PCA结果显示,两个群体明显聚成一簇,个别个体离群,其位置及相互关系符合进化树结构以及群体结构结果。设置同时达到Top 1%Z(Fst)值和θπ值的窗口为候选区域,共注释229个强选择信号,HF和LF组注释基因分别为86和143个,其中筛选到42个可能与繁殖性状相关的候选基因,如MARF1、CHGA、BMPR1B、IMMP2L、CDK14、ZDHHC3、CCDC71、DSCAML1、LIMK2、P2RY14等。经GO与KEGG通路分析发现,GO功能显著富集在钠离子跨膜转运蛋白活性的调控、凋亡过程的调控、钠离子通道调节剂活性、G蛋白偶联受体结合、G蛋白偶联嘌呤核苷酸受体活性等条目,KEGG显著富集通路主要与信号传递、信号通路、物质代谢等通路有关。分型结果表明,MARF1基因有11个SNPs位点在皮山红羊群体中真实存在,其中,g.14023542 T>A、g.14036507 A>G、g.14046123 C>T位点与群体平均产羔数显著关联,且前2个突变位点呈现强连锁关系(r2>0.3),g.14023542 T>A位点TT基因型具有最多的平均产羔数(1.901±0.675)。[结论]皮山红羊高繁组和低繁组两个群体遗传背景相似,具有一定程度的分化,但分化不明显。MARF1、CHGA、BMPR1B、IMMP2L、CDK14、ZDHHC3、CCDC71、DSCAML1、LIMK2、P2RY14等基因可能是影响皮山红羊产羔性状的候选基因。MARF1基因的3个SNPs位点可作为皮山红羊产羔性状潜在分子选育标记。

基于BS-1DCNN的海缆振动信号识别

光纤振动信号是非线性的,传统的非线性振动信号识别方法通常需要信号分析和特征选择,既耗时又复杂。本文提出一种光纤振动信号识别新方法,可以直接提取特征,对原始信号进行分类,简化识别过程。本方法用支持向量机代替Softmax分类器,优化一维卷积神经网络(one-dimensional convolution neural network,1DCNN),以提高1DCNN结果在小样本条件下的稳定性。采用鸟群算法(bird swarm algorithm,BSA)对支持向量机(support vector machine,SVM)参数进行了优化,有效地提高识别精度。将本文提出的BS-1DCNN方法与1DCNN、VMD-GA-SVM、VMD-PSO-SVM、VMD-BSA-SVM共4种方法进行比较,结果表明,BS-1DCNN在识别准确率和测试时间方面性能表现良好。该算法能有效提高海缆振动信号识别率,且在不同样本比例下均能达到较好的识别效果。

晋南牛遗传结构特征及选择信号分析

【目的】阐明晋南牛的遗传结构特征,通过选择信号检测挖掘与晋南牛经济性状相关的候选基因,探究其在进化过程中的受选择情况。【方法】对晋南牛和红安格斯牛全基因组测序数据进行分析,鉴定2个群体的单核苷酸多态性(single nucleotide polymorphism, SNP)标记,分析其在基因组的位置及其结构特征,基于SNP信息进行主成分分析(PCA)、构建状态同源矩阵(IBS);采用群体遗传分化指数(Fst)和核苷酸多样性比值(θπ)方法联合筛选晋南牛基因组受到强烈选择的区域,并对筛选到的受选择基因进行数量性状基因座(QTL)定位、GO功能和KEGG通路富集分析。【结果】晋南牛群体SNPs位点主要分布于基因间区域,其次位于内含子区域。PCA和IBS分析结果表明,晋南牛和红安格斯牛2个群体间不存在杂交现象,且晋南牛群体中个体间遗传距离较远。通过Fst和θπ联合分析共筛选到188个潜在受选择区域。QTL分析结果表明晋南牛的选择信号多与生长、肉质及抗病性状相关。GO功能和KEGG通路富集分析显示,筛选到晋南牛强受选择的与经济性状相关的候选基因11个,包括组织蛋白酶1(CATHL1)、CATHL3、组织蛋白酶抗菌肽(CAMP)、CATHL4、RAS1激酶抑制因子(KSR1)、梅氏同源框1(MEIS1)、不规则片段极性蛋白1(DVL1)、多梳组无名指1(PCGF1)、RB转录辅助抑制因子1(RB1)、再生家族成员4(REG4)和卷曲类受体7(FZD7),在其外显子区域均检测到了SNP位点;除MEIS1、PCGF1、PZD7基因外,其他基因均存在非同义突变位点,且KSR1基因存在获得终止密码子的突变,CAMP基因存在获得终止密码子的突变和缺失终止密码子的突变;与红安格斯牛相比,晋南牛存在6个特有的受选择基因:CATHL1、CATHL4、CAMP、MEIS1、PCGF1、PZD7,主要与抗病性、生长和骨骼肌发育等相关。【结论】本研究从全基因组水平探究了晋南牛的遗传结构及选择信号特点,筛选出6个可能与晋南牛经济性状相关的候选基因,为后续晋南牛保种选育、特色性状形成的分子机制研究提供理论参考。

基于灰狼算法和极限学习机的风速多步预测

为了提高风速的多步预测水平,提出了一种基于数据信号分解和灰狼算法优化极限学习机的混合预测模型。首先,使用具有自适应噪声的完全集成经验模态分解算法将原始风速时间序列分解为若干本征模态函数和一个残差序列,并使用偏自相关函数法对模型输入进行特征选择;其次,在分解子序列上分别建立模型并进行预测,构造多输入多输出策略的极限学习机神经网络,使用灰狼优化算法求解其中的最优化隐含层权值和偏置;最后,对子序列进行重构并得到最终的预测结果。使用时间分辨率为15 min的多组实测资料开展模拟实验,所提模型在3个风电场的均方根误差分别为0.859、0.925、0.927 m/s,均低于其他对比模型,验证了该模型在未来4 h风速预测即16步预测中的有效性。