Auto machine learning-based modelling and prediction of excavationinduced tunnel displacement

The influence of a deep excavation on existing shield tunnels nearby is a vital issue in tunnelling engineering.Whereas,there lacks robust methods to predict excavation-induced tunnel displacements.In this study,an auto machine learning(AutoML)-based approach is proposed to precisely solve the issue.Seven input parameters are considered in the database covering two physical aspects,namely soil property,and spatial characteristics of the deep excavation.The 10-fold cross-validation method is employed to overcome the scarcity of data,and promote model’s robustness.Six genetic algorithm(GA)-ML models are established as well for comparison.The results indicated that the proposed AutoML model is a comprehensive model that integrates efficiency and robustness.Importance analysis reveals that the ratio of the average shear strength to the vertical effective stress E_(ur)/σ′_(v),the excavation depth H,and the excavation width B are the most influential variables for the displacements.Finally,the AutoML model is further validated by practical engineering.The prediction results are in a good agreement with monitoring data,signifying that our model can be applied in real projects.

Application of deep autoencoder model for structural condition monitoring

Damage detection in structures is performed via vibra-tion based structural identification. Modal information, such as fre-quencies and mode shapes, are widely used for structural dama-ge detection to indicate the health conditions of civil structures.The deep learning algorithm that works on a multiple layer neuralnetwork model termed as deep autoencoder is proposed to learnthe relationship between the modal information and structural stiff-ness parameters. This is achieved via dimension reduction of themodal information feature and a non-linear regression against thestructural stiffness parameters. Numerical tests on a symmetri-cal steel frame model are conducted to generate the data for thetraining and validation, and to demonstrate the efficiency of theproposed approach for vibration based structural damage detec-tion.

Application of Seasonal Auto-regressive Integrated Moving Average Model in Forecasting the Incidence of Hand-foot-mouth Disease in Wuhan,China

Outbreaks of hand-foot-mouth disease（HFMD） have occurred many times and caused serious health burden in China since 2008. Application of modern information technology to prediction and early response can be helpful for efficient HFMD prevention and control. A seasonal auto-regressive integrated moving average（ARIMA） model for time series analysis was designed in this study. Eighty-four-month（from January 2009 to December 2015） retrospective data obtained from the Chinese Information System for Disease Prevention and Control were subjected to ARIMA modeling. The coefficient of determination（R^2）, normalized Bayesian Information Criterion（BIC） and Q-test P value were used to evaluate the goodness-of-fit of constructed models. Subsequently, the best-fitted ARIMA model was applied to predict the expected incidence of HFMD from January 2016 to December 2016. The best-fitted seasonal ARIMA model was identified as（1,0,1）（0,1,1）12, with the largest coefficient of determination（R^2=0.743） and lowest normalized BIC（BIC=3.645） value. The residuals of the model also showed non-significant autocorrelations（P_（Box-Ljung（Q））=0.299）. The predictions by the optimum ARIMA model adequately captured the pattern in the data and exhibited two peaks of activity over the forecast interval, including a major peak during April to June, and again a light peak for September to November. The ARIMA model proposed in this study can forecast HFMD incidence trend effectively, which could provide useful support for future HFMD prevention and control in the study area. Besides, further observations should be added continually into the modeling data set, and parameters of the models should be adjusted accordingly.

Settlement Prediction for Buildings Surrounding Foundation Pits Based on a Stationary Auto-regression Model

To ensure the safety of buildings surrounding foundation pits, a study was made on a settlement monitoring and trend prediction method. A statistical testing method for analyzing the stability of a settlement monitoring datum has been discussed. According to a comprehensive survey, data of 16 stages at operating control point, were verified by a standard t test to determine the stability of the operating control point. A stationary auto-regression model, AR(p), used for the observation point settlement prediction has been investigated. Given the 16 stages of the settlement data at an observation point, the applicability of this model was analyzed. Settlement of last four stages was predicted using the stationary auto-regression model AR (1); the maximum difference between predicted and measured values was 0.6 mm, indicating good prediction results of the model. Hence, this model can be applied to settlement predictions for buildings surrounding foundation pits.

A Study of Wind Statistics Through Auto-Regressive and Moving-Average (ARMA) Modeling

Statistical properties of winds near the Taichung Harbour are investigated. The 26 years'incomplete data of wind speeds, measured on an hourly basis, are used as reference. The possibility of imputation using simulated results of the Auto-Regressive (AR), Moving-Average (MA), and/ or Auto-Regressive and Moving-Average (ARMA) models is studied. Predictions of the 25-year extreme wind speeds based upon the augmented data are compared with the original series. Based upon the results, predictions of the 50- and 100-year extreme wind speeds are then made.

Application of Auto-regressive Linear Model in Understanding the Effect of Climate on Malaria Vectors Dynamics in the Three Gorges Reservoir

It is important to understand the dynamics of malaria vectors in implementing malaria control strategies. Six villages were selected from different sections in the Three Gorges Reservoir fc,r exploring the relationship between the climatic ｜：actors and its malaria vector density from 1997 to 2007 using the auto-regressive linear model regressi^n method. The result indicated that both temperature and precipitation were better modeled as quadratic rather than linearly related to the density of Anopheles sinensis.

Parametric SNR Estimation Based on Auto-Regressive Model in AWGN Channels

Signal-to-noise ratio（SNR）estimation for signal which can be modeled by Auto-regressive（AR）process is studied in this paper.First,the conventional frequency domain method is introduced to estimate the SNR for the received signal in additive white Gauss noise（AWGN）channel.Then a parametric SNR estimation algorithm is proposed by taking advantage of the AR model information of the received signal.The simulation results show that the proposed parametric method has better performance than the conventional frequency doma in method in case of AWGN channel.

BUILDING OF A SIMPLE MODEL OF AUTO-OLT IN DOGS AND ITS SIGNIFICANCE

AIM: we recommend a method of Simple auto-oLT model in dogs.METHODS:The model was ligated all ligaments or connective tissues of the liver,only reserved the vascular construction,that was the suprahepatic and infrahepatic inferior vena cava,portal vein,hepatic artery or common bile duct.the operation was similar to the orthotopic liver transplantation except vascular anastomoses,the dog liver underwent the warm or cold ischemia and the reperfusated injurous process.RESULTS: The imitability was exactly good and the operation was simple and safe. Because the hepatic vessels of the going out or coming in was clamped block and might open or blind the blood flow whenever necessary,the model might control the warm or cold ischemic time accurately,and eliminate the influence or the complications due to vascular anastomoses.CONCLUSIONS: The model avoided many-sided Influences of the traditional OLT and was a good method to study hepatic artery or portal vein ischemic injury and created a new way to explore the pathogenesis or some complications in the OLT.

Improved Water Network Macroscopic Model Utilising Auto-Control Adjusting Valve by PLS

In order to overcome the low precision and weak applicability problems of the current municipal water network state simulation model, the water network structure is studied. Since the telemetry system has been applied increasingly in the water network, and in order to reflect the network operational condition more accurately, a new water network macroscopic model is developed by taking the auto-control adjusting valve opening state into consideration. Then for highly correlated or collinear independent variables in the model, the partial least squares (PLS) regression method provides a model solution which can distinguish between the system information and the noisy data. Finally, a hypothetical water network is introduced for validating the model. The simulation results show that the relative error is less than 5.2%, indicating that the model is efficient and feasible, and has better generalization performance.

Various Methods for Constructing Auto-Bcklund Transformations for a Generalized Variable-Coefficient Korteweg-de Vries Model from Plasmas and Fluid Dynamics

<Abstract>In this paper,under the Painlevé-integrable condition,the auto-Bcklund transformations in different forms for a variable-coefficient Korteweg-de Vries model with physical interests are obtained through various methods including the Hirota method,truncated Painlevé expansion method,extended variable-coefficient balancing-act method,and Lax pair.Additionally,the compatibility for the truncated Painlevé expansion method and extended variable-coefficient balancing-act method is testified.

基于深度学习的桡动脉脉搏波重构方法

目的:针对从指端脉搏波重构出桡动脉脉搏波的难题,提出一种基于深度学习的重构方法。方法:使用四通道数据采集系统PowerLab分别无创采集指端脉搏波和桡动脉脉搏波,对脉搏波信号噪声源进行分析,利用去基线算法、小波变换去噪算法、归一化预处理算法,得到稳定的信号波形。设计变分自编码器(VAE)网络模型结构参数,利用十折交叉验证法对744例受试者数据进行训练,建立桡动脉脉搏波预测模型。设置学习率、随机失活、正则化项共3项超参数,对VAE网络模型进行优化。结果:186例受试者桡动脉脉搏波重构和同步检测结果表明:低阻型和高阻型指端脉搏波经VAE网络模型建模后5%K差、20%K差、K差总方差、FIT分别为49.10%、96.70%、89.74和75.80%;低阻型和高阻型指端脉搏波经VAE网络优化模型建模后5%K差、20%K差、K差总方差、FIT分别为48.50%、94.50%、73.74和66.30%。结论:VAE网络模型建模及其优化方法可用于桡动脉脉搏波重构,重构精度较高,并具有较强的鲁棒性和泛化能力。

面向短文本的增强上下文神经主题模型

目前的主题模型大多数基于自身文本的词共现信息进行建模,并没有引入主题的稀疏约束来提升模型的主题抽取能力,此外短文本本身存在词共现稀疏的问题,该问题严重影响了短文本主题建模的准确性。针对以上问题,提出了一种增强上下文神经主题模型(enhanced context neural topic model,ECNTM)。ECNTM基于主题控制器对主题进行稀疏性约束,过滤掉不相关的主题,同时模型的输入变成BOW向量和SBERT句子嵌入的拼接,在高斯解码器中,通过在嵌入空间中将单词上的主题分布处理为多元高斯分布或高斯混合分布,显式地丰富了短文本有限的上下文信息,解决了短文本词共现特征稀疏问题。在WS、Reuters、KOS、20 NewsGroups四个公开数据集上的实验结果表明,该模型在困惑度、主题一致性以及文本分类准确率上相较基准模型均有明显提升,证明了引入主题稀疏约束特性以及丰富的上下文信息到短文本主题建模的有效性。

序列稀疏自回归方法及其在美股做空数据分析上的应用

采用序列稀疏回归的思路来处理向量自回归模型,并设计适用于大规模时间序列数据分析的序列稀疏自回归方法。研究表明:从因子角度刻画向量自回归模型可以有效地将稀疏矩阵估计问题分解成稀疏奇异向量的估计问题,从而极大地提高了计算效率。以1523家美股上市公司1973年1月—2014年12月的做空数据为例,利用此方法探索公司之间的大规模做空关联网络。研究发现:此方法可以有效地恢复股票做空份额(即某一公司的空头股份数量)与股票收益率之间隐藏的关联网络,对于股票风险溢价研究具有一定启发意义。

一种基于指令MKS的自动向量化代价模型

自动向量化代价模型是编译器进行自动向量化优化时的重要组成部分,其作用是评估代码在应用向量化转换后能否获得性能提升。当代价模型不准确时,编译器会应用负收益的向量化转换,从而降低程序的执行效率。针对GCC编译器默认代价模型的不精确问题,以Intel Xeon Silver 4214R CPU为平台,提出了一种基于指令MKS的自动向量化代价模型。该模型充分考虑了指令的机器模式、运算类型以及运算强度等,并使用梯度下降算法自动搜索不同指令类型的近似代价。在SPEC2006以及SPEC2017上进行了单线程测试,实验结果表明,该模型能够减少收益评估错误的情况。与默认代价模型生成的向量程序相比,GCC编译器添加MKS代价模型后,在SPEC2006课题上最高获得了4.72%的提速,在SPEC2017课题上最高获得了7.08%的提速。

基于水电储能调节的风光水发电联合优化调度策略

为缓解新能源装机容量扩大引起的弃风弃光现象,在已有梯级水电上下电站之间加入储能泵站,提出风光水储短期优化调度策略。构建以风光水储系统负荷跟踪误差最小、梯级水电站发电量最大和梯级水电站发电耗水量最小的多目标优化调度模型;提出基于季节性自回归移动平均(seasonal auto-regressive lntegrated moving average, SARIMA)模型和Copula函数的风光出力预测模型作为优化调度模型的边界条件,通过SARIMA预测模型将风光出力历史数据分解为季节性分量、趋势分量以及随机噪声余项进行全天96个调度时段风光出力预测,并叠加上基于Copula函数生成风光出力预测误差,然后通过拉丁超立方采样以及K-means聚类进行场景生成和缩减得到5个风光出力场景。选取风光典型日出力数据为例进行算例分析,算例结果表明:所提预测模型较SARIMA模型可以显著提高预测准确度,模型预测风光出力均方根误差从33.34、229.49 MW分别下降至0.697、9.534 MW;所提优化调度策略可以在全年丰、平、枯水期有效减少弃风弃光现象,并可将过剩新能源中的50%转化为上级水库储存水能。

基于SARIMA和SVR组合模型的转向架系统寿命评估

随着地铁运营时间和里程的增加,地铁车辆逐渐接近其理论寿命,为确保车辆运行安全性,需对其重要子系统进行健康状态及剩余寿命评估。文中选取车辆转向架系统作为研究对象,提出了一种基于协方差优选法的季节性回归移动平均(SARIMA)和支持向量回归(SVR)的组合模型对转向架寿命进行评估。首先,将车辆转向架系统历史故障率转化为健康指数,然后基于协方差优选法将SARIMA和SVR进行赋权组合,根据转向架系统历史健康指数进行预测,最后建立历史和预测的健康指数与运行时间的数学模型,分析得到转向架系统的剩余寿命。以某地铁车辆转向架系统为例进行算例分析及验证,结果表明组合模型可更准确地预测其健康状态,为有关维修部门开展维修维护策略提供理论依据,估计得出其剩余寿命,为车辆寿命后期退役及延寿决策提供理论数据分析支撑。

偏置剪枝叠式自编码回声状态网络的时序预测

针对大多数模型对时间序列预测数据的预测准确率较低,为提升时间序列的预测精度,提出一种基于Biased Drop-weight的偏置剪枝叠式自编码回声状态网络(BD-AE-SGESN)的深度模型。以叠式ESN为多层深度网络框架,提出一种生成式AE算法生成每一层的输入权值,利用BD算法根据输入权重激活值进行剪枝。对比实验结果表明,该模型能够有效提升预测准确率,在3个不同的数据上,相比其它模型有着较小的预测误差和较高的稳定度。

脑卒中住院患者性别、年龄及时空分布特征:基于宁夏地区19万例患者数据

背景脑卒中是血液无法流入大脑而导致脑组织受损的一种急性脑血管疾病,其致残率、致死率以及复发率较高,宁夏地区相关研究多为脑卒中临床相关分析,缺乏对近年宁夏地区脑卒中住院情况的变化趋势分析。目的分析宁夏地区脑卒中住院患者疾病流行特征及分布情况,为制定脑卒中综合防治措施提供依据。方法收集宁夏地区共55家中医及西医医院的病案首页数据,筛选出2013—2019年出院且主要诊断为脑卒中[国际疾病分类(ICD)-10编码为I60~I63]的数据进行分析。应用SPSS 24.0软件采用χ^(2)检验对性别及年龄进行差异性分析,应用地理信息系统采用全局空间自相关分析方法对宁夏地区2013—2019年脑卒中住院率数据的分布进行分析。结果最终纳入190634例脑卒中患者数据。2013—2019年宁夏地区脑卒中住院率呈逐年上升趋势(住院率分别为24.302/10000、30.045/10000、34.949/10000、39.397/10000、44.049/10000、47.617/10000、52.944/10000,χ_(趋势)^(2)=5.982,P=0.014),且在每年的寒冷季节住院率较高,每年3月份有1个明显的高峰,之后稍有下降。2013—2019年宁夏地区脑卒中住院患者中,缺血性脑卒中167194例,出血性脑卒中23440例;缺血性脑卒中和出血性脑卒中患者不同性别、年龄比较,差异有统计学意义(χ^(2)=473.533、7518.543,P<0.05);且从数据上看,缺血性脑卒中和出血性脑卒中男性、≥60岁住院患者所占比例均超过50%。全局空间自相关分析结果显示,2013年、2018年和2019年脑卒中住院率存在空间聚集性(P<0.05)。空间分布图显示,宁夏地区住院的脑卒中患者主要集中在宁夏中北部。结论2013—2019年宁夏地区脑卒中患者住院率表现为不断上升且存在不同程度的聚集性,住院率较高的地区集中在宁夏中北部。

中国旅游经济韧性与旅游发展质量的关系研究

旅游经济韧性和旅游发展质量是旅游业持续健康发展的两个重要方面,探究二者关系对于旅游经济快速恢复并走上高质量发展道路具有重要意义。文章以中国30个省区为研究对象,运用熵权TOPSIS法对2009—2019年旅游经济韧性与旅游发展质量进行测度,通过耦合协调度模型、空间自相关和PVAR模型等方法探究二者关系。结果表明:(1)各省区旅游经济韧性与旅游发展质量水平稳步上升,两系统发展水平均呈“由西向东”逐渐递增的空间格局。(2)旅游经济韧性与旅游发展质量耦合协调水平总体显著提升,低度协调和中度协调区主要分布在西北地区,高度协调区数量大幅增长并向内陆扩张,极度协调区始终位于东部沿海一线;耦合协调亚类型划分中,“低度协调—旅游经济韧性滞后型”省区数量缩减最为明显,中度协调类型省区中旅游经济韧性滞后问题始终广泛存在,“高度协调—旅游经济韧性滞后型”省区数量显著增加,广东成为唯一“极度协调—旅游发展质量滞后型”省区。(3)旅游经济韧性与旅游发展质量耦合协调度存在全局空间集聚现象且逐步增强;局部空间自相关中,各类型集聚区整体变化不大,存在一定程度的路径依赖和空间锁定。(4)在互动关系方面,分别以全国范围和东部、中部地区为研究对象时发现,旅游发展质量对旅游经济韧性存在单向正面效应,而西部地区旅游经济韧性对旅游发展质量起单向促进作用。