Study on Joint Method of 3D Acoustic Emission Source Localization Simplex and Grid Search Scanning

Acoustic emission(AE)source localization is a fundamental element of rock fracture damage imaging.To improve the efficiency and accuracy of AE source localization,this paper proposes a joint method comprising a three-dimensional(3D)AE source localization simplex method and grid search scanning.Using the concept of the geometry of simplexes,tetrahedral iterations were first conducted to narrow down the suspected source region.This is followed by a process of meshing the region and node searching to scan for optimal solutions,until the source location is determined.The resulting algorithm was tested using the artificial excitation source localization and uniaxial compression tests,after which the localization results were compared with the simplex and exhaustive methods.The results revealed that the localization obtained using the proposed method is more stable and can be effectively avoided compared with the simplex localization method.Furthermore,compared with the global scanning method,the proposed method is more efficient,with an average time of 10%–20%of the global scanning localization algorithm.Thus,the proposed algorithm is of great significance for laboratory research focused on locating rupture damages sustained by large-sized rock masses or test blocks.

A Robust Tuned Random Forest Classifier Using Randomized Grid Search to Predict Coronary Artery Diseases

Coronary artery disease(CAD)is one of themost authentic cardiovascular afflictions because it is an uncommonly overwhelming heart issue.The breakdown of coronary cardiovascular disease is one of the principal sources of death all over theworld.Cardiovascular deterioration is a challenge,especially in youthful and rural countries where there is an absence of humantrained professionals.Since heart diseases happen without apparent signs,high-level detection is desirable.This paper proposed a robust and tuned random forest model using the randomized grid search technique to predictCAD.The proposed framework increases the ability of CADpredictions by tracking down risk pointers and learning the confusing joint efforts between them.Nowadays,the healthcare industry has a lot of data but needs to gain more knowledge.Our proposed framework is used for extracting knowledge from data stores and using that knowledge to help doctors accurately and effectively diagnose heart disease(HD).We evaluated the proposed framework over two public databases,Cleveland and Framingham datasets.The datasets were preprocessed by using a cleaning technique,a normalization technique,and an outlier detection technique.Secondly,the principal component analysis(PCA)algorithm was utilized to lessen the feature dimensionality of the two datasets.Finally,we used a hyperparameter tuning technique,randomized grid search,to tune a random forest(RF)machine learning(ML)model.The randomized grid search selected the best parameters and got the ideal CAD analysis.The proposed framework was evaluated and compared with traditional classifiers.Our proposed framework’s accuracy,sensitivity,precision,specificity,and f1-score were 100%.The evaluation of the proposed framework showed that it is an unrivaled perceptive outcome with tuning as opposed to other ongoing existing frameworks.

基于Gridsearch-SVM梯形区域极点分类的故障诊断

针对一类线性定常系统,基于梯形区域极点配置,给出了执行器部件故障诊断的一种方法。首先,利用极点观测器,通过测量系统的状态,得到极点的动态信息;其次,根据模拟各通道执行器故障,实时采集闭环系统的极点信息,形成极点分类数据库;最后,利用支持向量机算法(Support Vector Machine,SVM)根据不同通道发生故障时极点所处位置不同,设计极点分类器,对极点进行分类,实现对系统的故障诊断。针对SVM中惩罚因子和核宽度系数需要依靠先验知识的缺陷,采用Grid search优化其参数,缩小寻优范围。仿真结果表明设计方案的可行性以及故障诊断的有效性。

基于Grid-Search_PSO优化SVM回归预测矿井涌水量

为了解决矿井涌水量预测难题,在Grid-Search_PSO优化SVM参数的基础上,采用SVM非线性回归预测法,对大海则煤矿1999~2008年7月份的矿井涌水量进行了预测。分析对比SVM回归预测法和ARIMA时间序列预测法预测结果的数据误差,发现SVM回归法预测值与实测值之间的偏差比ARIMA时间序列法要小很多。可见在影响矿井涌水量各种因素值具备的情况下,SVM非线性回归预测所建立的模型能够更准确地预测矿井的涌水量,在矿井安全生产中具有很大的应用价值。

Grid-Search和PSO优化的SVM在Shibor回归预测中的应用研究

作为一种动态和非稳定时间序列,Shibor发展变化是随机波动的,难以准确预测Shibor的波动性.支持向量机(SVM)在回归预测非线性时间序列方面有很好地预测效果,SVM的预测精度和泛化能力的核心是参数的优化选择,分别用网格搜索法(Grid-Search)和粒子群(PSO)算法来优化SVM的参数c和g.从而将参数优化后的SVM非线性回归预测法与基于传统ARIMA时间序列预测结果进行对比分析.实验表明,优化后的SVM回归预测方法比ARIMA时间序列方法更精确,在实际中具有很大的应用价值.

Grid Search for Predicting Coronary Heart Disease by Tuning Hyper-Parameters

Diagnosing the cardiovascular disease is one of the biggest medical difficulties in recent years.Coronary cardiovascular(CHD)is a kind of heart and blood vascular disease.Predicting this sort of cardiac illness leads to more precise decisions for cardiac disorders.Implementing Grid Search Optimization(GSO)machine training models is therefore a useful way to forecast the sickness as soon as possible.The state-of-the-art work is the tuning of the hyperparameter together with the selection of the feature by utilizing the model search to minimize the false-negative rate.Three models with a cross-validation approach do the required task.Feature Selection based on the use of statistical and correlation matrices for multivariate analysis.For Random Search and Grid Search models,extensive comparison findings are produced utilizing retrieval,F1 score,and precision measurements.The models are evaluated using the metrics and kappa statistics that illustrate the three models’comparability.The study effort focuses on optimizing function selection,tweaking hyperparameters to improve model accuracy and the prediction of heart disease by examining Framingham datasets using random forestry classification.Tuning the hyperparameter in the model of grid search thus decreases the erroneous rate achieves global optimization.

METADATA EXPANDED SEMANTICALLY BASED RESOURCE SEARCH IN EDUCATION GRID

With the rapid increase of educational resources, how to search for necessary educational resource quickly is one of most important issues. Educational resources have the characters of distribution and heterogeneity, which are the same as the characters of Grid resources. Therefore, the technology of Grid resources search was adopted to implement the educational resources search. Motivated by the insufficiency of currently resources search methods based on metadata, a method of extracting semantic relations between words constituting metadata is proposed. We mainly focus on acquiring synonymy, hyponymy, hypernymy and parataxis relations. In our schema, we extract texts related to metadata that will be expanded from text spatial through text extraction templates. Next, metadata will be obtained through metadata extraction templates. Finally, we compute semantic similarity to eliminate false relations and construct a semantic expansion knowledge base. The proposed method in this paper has been applied on the education grid.

Research on Low Voltage Series Arc Fault Prediction Method Based on Multidimensional Time-Frequency Domain Characteristics

The load types in low-voltage distribution systems are diverse.Some loads have current signals that are similar to series fault arcs,making it difficult to effectively detect fault arcs during their occurrence and sustained combustion,which can easily lead to serious electrical fire accidents.To address this issue,this paper establishes a fault arc prototype experimental platform,selects multiple commonly used loads for fault arc experiments,and collects data in both normal and fault states.By analyzing waveform characteristics and selecting fault discrimination feature indicators,corresponding feature values are extracted for qualitative analysis to explore changes in timefrequency characteristics of current before and after faults.Multiple features are then selected to form a multidimensional feature vector space to effectively reduce arc misjudgments and construct a fault discrimination feature database.Based on this,a fault arc hazard prediction model is built using random forests.The model’s multiple hyperparameters are simultaneously optimized through grid search,aiming tominimize node information entropy and complete model training,thereby enhancing model robustness and generalization ability.Through experimental verification,the proposed method accurately predicts and classifies fault arcs of different load types,with an average accuracy at least 1%higher than that of the commonly used fault predictionmethods compared in the paper.

Nearest neighbor search algorithm based on multiple background grids for fluid simulation

The core of smoothed particle hydrodynamics （SPH） is the nearest neighbor search subroutine. In this paper, a nearest neighbor search algorithm which is based on multiple background grids and support variable smooth length is introduced. Through tested on lid driven cavity flow, it is clear that this method can provide high accuracy. Analysis and experiments have been made on its parallelism, and the results show that this method has better parallelism and with adding processors its accuracy become higher, thus it achieves that efficiency grows in pace with accuracy.

Risk assessment of rockburst using SMOTE oversampling and integration algorithms under GBDT framework

Rockburst is a common geological disaster in underground engineering,which seriously threatens the safety of personnel,equipment and property.Utilizing machine learning models to evaluate risk of rockburst is gradually becoming a trend.In this study,the integrated algorithms under Gradient Boosting Decision Tree(GBDT)framework were used to evaluate and classify rockburst intensity.First,a total of 301 rock burst data samples were obtained from a case database,and the data were preprocessed using synthetic minority over-sampling technique(SMOTE).Then,the rockburst evaluation models including GBDT,eXtreme Gradient Boosting(XGBoost),Light Gradient Boosting Machine(LightGBM),and Categorical Features Gradient Boosting(CatBoost)were established,and the optimal hyperparameters of the models were obtained through random search grid and five-fold cross-validation.Afterwards,use the optimal hyperparameter configuration to fit the evaluation models,and analyze these models using test set.In order to evaluate the performance,metrics including accuracy,precision,recall,and F1-score were selected to analyze and compare with other machine learning models.Finally,the trained models were used to conduct rock burst risk assessment on rock samples from a mine in Shanxi Province,China,and providing theoretical guidance for the mine's safe production work.The models under the GBDT framework perform well in the evaluation of rockburst levels,and the proposed methods can provide a reliable reference for rockburst risk level analysis and safety management.

基于自动终止准则改进的kd-tree粒子近邻搜索研究

对于大规模运动模拟问题而言,近邻点的搜索效率将对整体的运算效率产生显著影响。本文基于关联性分析建立kd-tree的最大深度dmax与粒子总数N的自适应关系式,提出了kd-tree自动终止准则,即ATC-kd-tree,同时还考虑了叶子节点大小阈值n_(0)对近邻搜索效率的影响。试验表明,ATC-kd-tree具有更高的近邻搜索效率,相较于不使用自动终止准则的kd-tree搜索效率最高提升46%,且适用性更强,可求解不同N值的近邻搜索问题,解决了粒子总数N发生改变时需要再次率定最大深度dmax的问题。同时,本文还提出了网格搜索法组合坐标下降法的两步参数优化算法GSCD法。通过2维阿米巴虫形状的参数优化试验发现,GSCD法可更为快速地率定ATC-kd-tree的可变参数,其优化效率比网格搜索法最高提升了205%,相较于改进网格搜索法最高提升了90%。研究结果表明,ATC-kd-tree和GSCD法不仅提高了近邻搜索的效率,也为复杂运动中近邻粒子搜索问题提供了一种更为高效的解决方案,能够显著降低计算资源的消耗,进一步提升模拟的精度和效率。

基于机器学习算法的糖尿病预测

糖尿病是一种无法根治的慢性疾病,早发现、早干预、早治疗能够延缓病情进展,提高患者的治疗效率。构建基于决策树、逻辑回归、XGBoost等六种机器学习分类算法的预测模型,实现糖尿病风险预测。该模型以皮马印第安人糖尿病数据集为研究对象,通过数据预处理、数据特征分析构建有效数据集,采用网格搜索方法进行交叉验证寻找算法的最佳参数组合,构建超参数及基于超参数的分类模型,并对模型的预测性能进行评价。实验结果表明,该模型拥有良好的糖尿病风险预测性能。

Managing of Smart Micro-Grid Connected Scheme Using Group Search Optimization

This article introduces a group search optimization (GSO) based tuning model for modelling and managing Smart Micro-Grids connected system. In existing systems, typically tuned PID controllers are engaged to point out the load frequency control (LFC) problems through different tuning techniques. Though, inappropriately tuned PID controller may reveal pitiable dynamical reply and also incorrect option of integral gain may even undermine the complete system. This research is used to explain about an optimized energy management system through Group Search Optimization (GSO) for building incorporation in smart micro-grids (MGs) with zero grid-impact. The essential for this technique is to develop the MG effectiveness, when the complete PI controller requires to be tuned. Consequently, we proposed that the proposed GSO based algorithm with appropriate explanation or member representation, derivation of fitness function, producer process, scrounger process, and ranger process. An entire and adaptable design of MATLAB/SIMULINK also proposed. The related solutions and practical test verifications are given. This paper verified that the proposed method was effective in Micro-Grid (MG) applications. The comparison results demonstrate the advantage of the proposed technique and confirm its potential to solve the problem.

基于多源数据的特长隧道驾驶疲劳模型

为研究驾驶人在特长隧道内驾驶疲劳演变过程及其影响因素,基于实车试验采集的多源数据,对特长隧道内驾驶疲劳分类判别以及驾驶疲劳影响因素关系模型展开了研究。通过差异显著性分析和相关性分析筛选出闭眼百分率P80、瞳孔直径变异系数和加速度作为疲劳敏感性指标,并分析了各指标随行驶时间累积的变化规律。为构建驾驶疲劳分类判别模型,基于卡罗林斯卡嗜睡量表(Karolinska sleeping scale,KSS)主观疲劳检测结果,将疲劳程度划分清醒状态、半疲劳状态和疲劳状态,采用构造多类分类器的方法将不同疲劳状态样本进行组合分类,利用网格搜索法进行分类模型的参数寻优,并将筛选出的疲劳敏感性指标作为分类模型的输入变量,建立了基于网格搜索法的多分类支持向量机疲劳状态判别模型(GS-M-SVMs模型)。然后根据疲劳状态分类判别模型,利用有序多分类Logistic模型建立了特长隧道疲劳程度与影响因素的关系模型,对特长隧道内驾驶疲劳影响因素进行了探究。研究结果表明:疲劳敏感性指标变化规律可有效表征特长隧道内驾驶疲劳演变过程,而GS-M-SVMs模型分类检测准确率达到90.75%,对疲劳程度的分类识别效果较好,并且累积行驶时间和隧道长度显著影响驾驶人的疲劳程度,其模型回归系数分别为2.634和0.395,表明累积行驶时间是驾驶人在特长隧道路段中疲劳程度加重的最主要因素,隧道照度和隧道线形等因素并无显著影响。

基于GS-SVR的架空输电线路工程投资估算预测研究

传统的投资估算编制模式存在过度依赖定额的现象,随着大量工程造价数据的积累,利用其实现投资估算,以弥补传统定额计价模式的不足,能够对建设项目工程造价起到总体控制作用。文章以架空输电线路工程为例,基于支持向量回归机(Support Vector Regression,SVR)研究架空输电线路工程投资估算问题。结果表明:通过选取影响架空输电线路工程投资估算的主要指标,构建基于SVR的架空输电线路工程投资估算模型,并利用改进的网格搜索法(Grid Search,GS)优化模型参数,得到基于GS-SVR的投资估算预测模型;与传统的线性回归和SVR模型相比,GS-SVR模型表现出更为良好的性能。

浅析震源位置准确度及其影响因素

地震定位是地震学研究的基础,然而地震定位和地震学研究之间存在“供给”矛盾.不同研究对地震位置准确度级别的要求不尽相同,震源机制和壳幔结构研究要求震源位置的准确度为千米级别,工业生产活动和诱发地震研究要求震源位置的准确度为百米级别.然而,地震监测台网给出的地震位置准确度仅为数千米.诸多地震定位方法从不同方面对地震定位过程进行优化和改进,但它们的侧重点不尽相同.总体而言,已有的定位方法对地震位置的准确度关注程度尚显不足.在大量的地震定位实践中,前人获得了用于优化地震位置准确度的若干经验法则,这些经验法则不但存在地区差异,而且还有一定的适用条件,经验法则仍需要被进一步地优化和修正.本文简要分析地震定位准确度的多方面影响因素,有针对性地开展研究,在地震定位算法和控制观测数据质量方面获得一定的研究进展;在地震定位耦合关系方面补充了定位速度模型、发震位置和发震时刻三者之间的制约关系;在地震定位流程方面提出了使用逐步消元定位的建议.

基于聚类和GBDT的镀锌钢卷力学性能预测

热镀锌钢卷力学性能影响因素之间关系复杂,限制了模型精度的提升。采用k-means算法利用化学成分属性对镀锌钢卷数据集进行聚类,将数据聚成三种模式簇实现样本的优选。利用梯度提升树算法,开展各模式数据集与不划分模式的全数据集下的力学性能建模研究,最后结合网格搜索与交叉验证方法进行模型参数优化。研究结果表明,分模式下模型MAE误差相比于全数据集建模平均减小0.85 MPa。参数优化后,各模式下MAE误差平均减少5.19 MPa,RMSE误差平均减少3.63 MPa,提高了预测模型精度。

Grid和P2P混合环境中一种基于信任的资源搜索机制

Grid和P2P两种分布式计算模式中的资源搜索算法均假设节点提供可靠的资源,但Grid和P2P混合计算环境的动态、异构、自组织等特点使得一些节点存在冒名和提供虚假服务等行为。本文对基于经验和最好邻居搜索机制进行改进,引入信任因子,提出了基于信任的资源搜索机制。该机制有效抑制了欺骗行为,提高了资源搜索的可靠性和安全性。

基于改进人工鱼群算法的蠕虫机器人路径规划

针对人工鱼群算法在机器人路径规划中存在路径长、精度不高、易陷入局部最优等问题,提出了一种改进的人工鱼群算法,旨在提高算法效率及精度。首先,在算法觅食行为中加入寻优循环,减少算法在路径规划中选取位置点的随机性,使机器人能够更快地走向目标点;其次,融合禁忌搜索算法,通过引入禁忌表来记录算法陷入局部最优的路径,使算法在选取新位置点时能够避开局部最优区域,避免算法在局部过度循环,同时对规划出的路径进行优化处理,删去重复栅格点之间的路径,保证路径中没有重复的栅格点;最后,将改进后的人工鱼群算法应用在一种新型的三维栅格地图中。实验结果表明:相较于其他对比算法,在地图1、2、3中改进人工鱼群算法所取得的平均路径长度分别减少了10%、15%、30%,在复杂地图中路径规划的成功率提高了75%。

GSM-SVM在地震震级预测中的应用

针对地震震级影响因子众多且关系重复等问题,为合理预测地震震级,提出了基于网格搜索法优化支持向量机(support vector machine,SVM)的地震震级预测模型。选取地震累积频度、累积释放能量、b值、异常震群个数、地震条带个数、活动周期和相关区震级等7个影响因子,利用主成分分析法(principal component analysis,PCA)去除因子间的冗余信息,降低输入维数,并利用网格搜索法(grid search method,GSM)确定SVM参数C和g,建立震级预测模型,并对测试样本进行预测,与遗传算法(genetic algorithm,GA)和粒子群算法(particle swarm optimization,PSO)预测结果相对比,结果表明:PCA-GSM-SVM模型预测结果平均相对误差为1.29%,具有较高的预测精度。