Improved neural networks based on genetic algorithm for pulse recognition

Pulse diagnosis is an important part of Chinese medicine and has played an important role in the development of Chinese medical science. However, the pulse is traditionally determined by cutting it off, which leads to a lack of objective standard pulse identification methods and affects their accuracy and feasibility. This research has studied and discussed the processing and identification of four kinds of pulse: normal pulse, wiry pulse, smooth pulse, and thready pulse. Four frequency-domain characteristics of the pulse wave and six kinds of wavelet scale energy characteristic information were extracted, and a three-layer BP (backprocessing) neural network was established. The LM (Levenberg–Marquard) algorithm and a genetic algorithm were used to improve the BP neural network, to train on and predict experimental samples, and to obtain classification accuracies of 90% and 95% respectively. Moreover, improved BP neural network based on a genetic algorithm has shown highly superior performance in terms of convergence speed and low error rate.     

非定常Navier-Stokes方程基于两重网格离散的有限元并行算法

基于两重网格离散和区域分解技巧，提出三种求解非定常Navier-Stokes方程的有限元并行算法.算法的基本思想是在每一时间迭代步，在粗网格上采用Oseen迭代法求解非线性问题，在细网格上分别并行求解Oseen、Newton、Stokes线性问题以校正粗网格解.对于空间变量采用有限元离散，时间变量采用向后Euler格式离散.数值实验验证了算法的有效性.     

Investigation on the effect of density ratio on the convergence behavior of partitioned method for fluid–structure interaction simulation

In order to investigate the effect of density ratio of fluid and solid on the convergence behavior of partitioned FSI algorithm, three strong-coupling partitioned algorithms (fixed-point method with a constant under-relaxation parameter, Aitken’s method and Quasi-Newton inverse least squares (QN-ILS) method) have been considered in the context of finite element method. We have employed the incompressible Navier–Stokes equations for a Newtonian fluid domain and the total Lagrangian formulation for a non-linear motion of solid domain. Linear-elastic (hyper-elastic) model has been employed for solid material with small (large) deformation. A pulsatile inlet-flow interacting with a 2D circular channel of linear-elastic material and a pressure wave propagation in a 3D flexible vessel have been simulated. Both linear-elastic and hyper-elastic (Mooney–Rivlin) models have been adopted for the 3D flexible vessel. From the present numerical experiments, we have found that QN-ILS outperforms the others leading to a robust convergence regardless of the density ratio for both linear-elastic and hyper-elastic models. On the other hand, the performances of the fixed-point method with a constant under-relaxation parameter and the Aitken’s method depend strongly on the density ratio, relaxation parameter selected for coupling iteration, and degree of deformation. Although the QN-ILS of this work is still slower than a monolithic method for serial computation, it has an advantage of easier parallelization due to the modularity of the partitioned FSI algorithm.     

带有潜伏期的狂犬病模型及控制策略研究

研究建立了狗与人两个群体的SEIR狂犬病模型,把狂犬病潜伏期阶段的传染性加入到模型中,利用遗传算法对1996年到2015年的数据进行拟合,估出了中国狂犬病的基本再生数R0≈1.66,证明了狂犬病无病平衡点的全局稳定性以及模型的一致持续性.根据数值模拟结果,发现处于潜伏期的犬类对人类狂犬病造成威胁.因此控制狂犬病的一个关键措施就是要做好犬的管理,减少与犬只的接触,这对抑制狂犬病的爆发有着重要的作用,也为我国狂犬病的控制提供了可靠的理论依据.     

新组合模型在光电功率预测中的应用

为提高光伏预测要求的精准性,文章提出一种新算法将神经网络和ARMA算法改进组合,构成NEW ARMA-BP模型算法.以某30兆瓦的光伏电站采集的输出功率为输入样本,基于ARMA和BP神经网络算法在Matlab环境下依次搭建了相应的预测模型,预估光伏短期输出量.采用"误差正态检验图"判断基于两种不同算法的误差水平,依据两种单模型预测误差,运用所提出的新方法计算权值并获得新的预测值.基于Matlab的仿真结论验证了组合预测在光伏输出预测领域的适用性.     

A survey on HHL algorithm: From theory to application in quantum machine learning

The Harrow-Hassidim-Lloyd (HHL) algorithm is a method to solve the quantum linear system of equations that may be found at the core of various scientific applications and quantum machine learning models including the linear regression, support vector machines and recommender systems etc. After reviewing the necessary background on elementary quantum algorithms, we provide detailed account of how HHL is exploited in different quantum machine learning (QML) models, and how it provides the desired quantum speedup in all these models. At the end, we briefly discuss some of the remaining challenges ahead for HHL-based QML models and related methods.     

Analytical solution of stochastic differential equation by multilayer perceptron neural network approximation of Fokker–Planck equation

The Fokker–Planck equation is a useful tool to analyze the transient probability density function of the states of a stochastic differential equation. In this paper, a multilayer perceptron neural network is utilized to approximate the solution of the Fokker–Planck equation. To use unconstrained optimization in neural network training, a special form of the trial solution is considered to satisfy the initial and boundary conditions. The weights of the neural network are calculated by Levenberg–Marquardt training algorithm with Bayesian regularization. Three practical examples demonstrate the efficiency of the proposed method.     

卷积神经网络用于近红外光谱古筝面板木材分级

目前,我国乐器制作行业在古筝面板用木材等级的筛选上主要依赖于技师主观评判,但此法缺少科学理论的依据,效率低,客观性及出材率的提高等方面受到限制,无法满足乐器市场的大量需求。实现古筝面板用木材快速、智能化的分级工作是一个急需解决的课题。近红外光谱非常适用于测量含氢的有机物质。古筝面板木材主要化学成分的化学键均由含氢基团组成,不同等级板材的化学成分存在差异,这些差异反映在近红外光谱中,为判断木材等级提供了可能。同时卷积神经网络对非线性数据具有较强的特征提取能力,所以提出一种应用卷积神经网络模型对光谱数据进行分析的方法,进而判别木材的等级。应用了Savitzky Golay一阶、二阶微分两种预处理方法和核主成分分析、连续投影算法两种数据压缩方法,通过所设计的卷积神经网络模型以样本识别准确率和模型构建过程中的损失值作为判定指标选出最佳预处理和数据压缩方法。为了提高模型提取分析光谱数据的能力和避免过拟合现象,应用了多通道卷积核、批量归一化和early stopping策略,将通过两层卷积层提取的特征信息送入全连接层,从而充分提取剩余信息,通过Softmax函数获得板材的最终预测等级,从而确定了最终模型。最终Savitzky Golay一阶微分和核主成分分析为最佳数据处理方法,同时得出用于区分不同等级的古筝面板用木材的主要关键谱带,分别为1 163~1 243, 1 346~1 375和1 525~1 584 nm。将该模型应用于测试集样本,古筝面板用木材的等级识别准确率为95.5%。实验结果表明所提出的方法可以高效地处理光谱数据,有效识别区分不同等级的古筝面板用木材的关键特征,从而为广阔的乐器市场提供一定的技术支持。     

吸收峰混叠的太赫兹光谱区间组合特征提取算法

太赫兹光谱是物质识别的前沿方法之一。由于不同物质的分子组成或结构各异,许多物质的太赫兹吸收谱会在特定频率上出现吸收峰,可以作为混合物成分检测的重要特征。有效准确地提取这些吸收峰的参数,是提高识别率的关键。多峰拟合算法将光谱曲线拟合成若干个标准峰函数之和,能够同时提取到吸收峰的频率、峰高、峰宽等信息。但是该算法以寻峰算法结果为基础确定吸收峰的大致位置和数量,寻峰结果不一定是最优的拟合结果,而且很难准确识别定位混叠状态的吸收峰。为了提高混叠光谱中吸收峰的识别定位精度,提出以大幅度平滑后的曲线波谷为分界点,将预处理后的光谱分成若干个子区间。然后将子区间组合起来进行多峰拟合,通过遗传算法得到最优的拟合子区间组合和吸收峰频率近似值,拟合时每个子区间中通过峰数递增最优化方法确定拟合的吸收峰数,最后微调优化得到最优的吸收峰频率、峰高值。为了实现物质的识别,通过密度聚类算法得到同一类纯净物在多次测量中的共同吸收峰,以此作为标准数据,通过提出的基于吸收峰特征的光谱匹配算法实现了纯净物和不同含量混合物的快速识别。对10类纯净物的实际光谱数据进行拟合聚类,得到其吸收峰参数,结果与太赫兹光谱数据库一致。通过识别算法对纯净物测试集进行识别的识别率为100%,证明了特征提取和物质识别算法的有效性。对于含有混叠峰的混合物光谱,二阶导数法对葡萄糖-乳糖混合物光谱中被掩盖吸收峰(1.280 THz)的识别率仅为70%,提取到的频率平均值为1.316 THz;而该算法提高识别率至95%,频率平均值为1.281 THz,该算法提高了对混叠峰的分辨能力,能够精确定位混叠峰。对10类纯净物构成的6类不同程度混叠的二元混合物前二、三识别率分别达到90.8%和98.3%,提取到的特征能够有效应用于混合物的成分检测。该算法能够以纯净物数据为标准数据实现成分各异的混合物成分检测,对于太赫兹光谱混合物成分检测有重要意义。