Proposed network structures and combined adaptive algorithms for electrocardiogram signal denoising

An electrocardiogram (ECG) signal is a record of the electrical activities of heart muscle and is used clinically to diagnose heart diseases. An ECG signal should be presented as clear as possible to support accurate decisions made by doctors. This article proposes different combinations of combined adaptive algorithms to derive different noise-cancelling structures to remove (denoise) different kinds of noise from ECG signals. The algorithms are applied to the following types of noise: power line interference, baseline wander, electrode motion artifact, and muscle artifacts. Moreover, the results of the suggested models and algorithms are compared with those of conventional denoising tools such as the discrete wavelet transform, an adaptive filter, and a multilayer neural network (NN) to ensure the superiority of the proposed combined structures and algorithms. Furthermore, the hybrid concept is based on dual, triple, and quadruple combinations of well-known algorithms that derive adaptive filters, such as the least mean squares, normalized least mean squares and recursive least squares algorithms. The combinations are formulated based on partial update, variable step-size (VSS), and second iterative VSS algorithms, which are considered in different combinations. In addition, biased NN and unbiased linear neural network (ULNN) structures are considered. The performance of the different structures and related algorithms are evaluated by measuring the post-signal-to-noise ratio, mean square error, and percentage root mean square difference.     

Deterministic and probabilistic ship pitch prediction using a multi-predictor integration model based on hybrid data preprocessing,reinforcement learning and improved QRNN

The deterministic and probabilistic prediction of ship motion is important for safe navigation and stable real-time operational control of ships at sea. However, the volatility and randomness of ship motion, the non-adaptive nature of single predictors and the poor coverage of quantile regression pose serious challenges to uncertainty prediction, making research in this field limited. In this paper, a multi-predictor integration model based on hybrid data preprocessing, reinforcement learning and improved quantile regression neural network (QRNN) is proposed to explore the deterministic and probabilistic prediction of ship pitch motion. To validate the performance of the proposed multi-predictor integrated prediction model, an experimental study is conducted with three sets of actual ship longitudinal motions during sea trials in the South China Sea. The experimental results indicate that the root mean square errors (RMSEs) of the proposed model of deterministic prediction are 0.0254°, 0.0359°, and 0.0188°, respectively. Taking series #2 as an example, the prediction interval coverage probabilities (PICPs) of the proposed model of probability predictions at 90%, 95%, and 99% confidence levels (CLs) are 0.9400, 0.9800, and 1.0000, respectively. This study signifies that the proposed model can provide trusted deterministic predictions and can effectively quantify the uncertainty of ship pitch motion, which has the potential to provide practical support for ship early warning systems.     

基于深度信念网络的列车故障音频诊断方法

铁路在交通运输行业有着举足轻重的地位，一旦列车发生故障将会导致严重的生命财产损失。由于列车发生故障的概率相对较低，因此难以捕获列车的故障样本。针对上述问题，提出了一种无监督学习的列车故障识别方法，通过检测列车音频信号来识别列车故障。该方法基于深度信念网络(DBN)，利用小波包分解提取检测信号的特征向量并将其作为DBN的输入，待网络充分训练后，由训练好的DBN识别当前列车的运行状况。现场监测实验结果表明，该方法能够在无监督的条件下有效识别列车故障，保障了列车的运行安全。     

Time-frequency domain causality of prime building cost and macroeconomic indicators in Ghana: implications for project selection

According to the Ghana Statistical Service, construction activity generated US$3.8 billion in 2014, representing about 12.7% of nominal GDP. A key factor that most investors in the construction sector consider in project selection is cost which has escalated over the years. Therefore, we examine the co-movements and causality in the time and frequency domains between the prime building cost index (PBCI) and its disaggregates on one hand and inflation and exchange rate on the other hand in Ghana. The findings revealed that the degree of co-movement between PBCI and inflation was significant at the 5% level and occurred over the long-run, indicating that construction cost drives inflation. The degree of co-movement between the prime build cost index and exchange rate occurred within the short term. These co-movements have policy implications for substituting inflation and exchange rates in project costing by investors in Ghana. The co-movement between the PBCI and inflation in the medium to higher frequencies suggests that inflation risk-averse investors should consider short-term projects. Again, the short to medium frequency co-movements between the PBCI and exchange rate indicates that investors should consider exchange rate risk in long-term projects.     

频带能量与样本熵在注意力脑电信号中的对比研究

脑电波是一种复杂的生物电信号,可反应出大脑内部的活动及注意力等精神状态。基于此,论文设计了注意力相关的脑电实验,并完成了受试者脑电数据的采集,对所采集的脑电数据分别从以下两种角度进行研究:从时频分析的角度,采用db4小波基对原始脑电信号进行7层小波包分解,提取了β波/θ波能量占比作为特征量;从非线性动力学的角度,提取脑电信号的样本熵作为特征,并分别对各受试者进行注意力的分级研究。通过对比分析,结果表明两者都能从一定程度上表征注意力水平的状况,但样本熵对于多级注意力的区分度更好。     

基于人脸视频的心率参数提取

为了在舒适非接触环境下检测被试者的心率变化,本文设计了一种通过普通摄像头来检测心率参数的信号处理系统。首先,将KLT(Kanade-Lucas-Tomasi)算法跟踪识别到的人脸视频图像转换到YCbCr颜色空间来进行皮肤检测,并同时转换到Cg颜色通道来提取高质量的光电容积脉搏波(Photoplethysmography, PPG)信号。然后,用Morlet复小波作为母波绘制PPG信号的小波能量谱图。最后根据心率信号的生理特性,去除伪点噪声,提取随时间变化的心率参数。实验结果表明,该方法在静息状态下的测量结果同标准仪器测量结果的平均绝对值误差|M_e|小于2 bpm(beats per minute),误差的标准差SD_e小于2.5 bpm,RMSE均小于2.6 bpm;头部运动状态下两种测量方法的|M_e|均小于2.3 bpm,SD_e均小于2.9 bpm,RMSE均小于2.9 bpm。对两种测量方法进行Bland-Altman一致性分析,其测量结果显示静息状态下差值的均数■为0.295 7 bpm,95%置信区间为-3.340 1~3.931 4 bpm;头部运动状态下■为0.383 2 bpm,95%置信区间为-3.677 1~4.443 5 bpm,表明本文提出的非接触式方法的测量结果同标准仪器的测量结果具有高度的一致性。     

基于小波分析的谐波在线监测系统

针对传统谐波在线监测系统存的结果不准确，无法描述谐波动态变化特点，设计了基于小波分析的谐波在线监测系统。首先设计了谐波在线监测系统的硬件模块，然后谐波在线监测系统的软件模块，依据小波变换分析谐波信号特征，得到的谐波变化率，从而谐波在线监测系统的监测结果，最后采用具体实验进行了谐波在线监测系统性能的仿真实验，由实验结果可知，该系统的谐波监测精度高，可以有效检测各种谐波分量，保证电力系统稳定运行。     

1958～2017年右江出口径流量演变特征分析

为了分析右江1958~2017年出口径流量演变特征，选用线性趋势法、累积平距法、Morlet小波分析法、Mann-Kendall突变检验法等多种方法，从全年、汛期、枯水期三种情况分析了右江出口径流量的变化趋势性、周期性、突变性等特点，并探讨了不同情况演变特征差异的原因、水利枢纽建设的影响、近期变化的趋势。结果表明，年均径流量和汛期平均径流量序列整体呈下降趋势，枯水期平均流量序列整体呈上升趋势；年均径流量和汛期平均径流量序列第一主周期均为37年，枯水期平均径流量序列第一主周期为10年；由于金鸡滩水利枢纽施工建设，年均径流量序列在2004~2007年持续突变，汛期平均径流量序列在2007年发生突变，枯水期平均径流量未发生突变；三种情况演变特征存在差异性主要原因是人类对径流量的利用主要在枯水期；近期年均径流量将继续处于偏多状态，汛期平均径流量将由偏少状态转为偏多状态，枯水期平均径流量将持续保持偏少状态。     

基于小波时频图和卷积神经网络的断路器故障诊断分析

高压断路器操动机构振动信号为非平稳性信号,蕴含着丰富的操动机构工作状态的信息,对操动机构工作状态的检验辨识具有重大意义。提出一种基于小波时频图和卷积神经网络的断路器故障诊断方法。对操动机构振动信号进行连续小波变换生成时频图(CWT),并对时频图进行统一压缩预处理;将预处理后的时频图作为特征图输入卷积神经网络AlexNet模型;通过对网络参数的调整,逐步改进网络模型,有监督地实现对操动机构故障状态的辨识诊断。结果表明,该方法能够有效地运用于断路器操动机构故障辨识诊断,与小波频带能量-RBF、小波频带能量-SVM的故障识别相比,故障识别准确率最高。     

基于十字形阵列和2D-MUSIC算法的Lamb波检测

采用由压电传感器组成的十字形阵列进行Lamb波信号的激励和接收，提出一种二维多重信号分类（2D-MUSIC）方法对铝板中的缺陷进行定位检测。选用合适的频率激励产生单一模态信号，可避免多模态的影响，降低Lamb波的频散；利用2D-MUSIC算法对接收信号进行分段处理，并结合反射信号和二维导向矢量对铝板中的缺陷进行定位。结果表明，提出的2D-MUSIC算法对铝板中的缺陷定位比传统MUSIC算法更精准。