Real-Time Spreading Thickness Monitoring of High-core Rockfill Dam Based on K-nearest Neighbor Algorithm

During the storehouse surface rolling construction of a core rockfilldam, the spreading thickness of dam face is an important factor that affects the construction quality of the dam storehouse' rolling surface and the overallquality of the entire dam. Currently, the method used to monitor and controlspreading thickness during the dam construction process is artificialsampling check after spreading, which makes it difficult to monitor the entire dam storehouse surface. In this paper, we present an in-depth study based on real-time monitoring and controltheory of storehouse surface rolling construction and obtain the rolling compaction thickness by analyzing the construction track of the rolling machine. Comparatively, the traditionalmethod can only analyze the rolling thickness of the dam storehouse surface after it has been compacted and cannot determine the thickness of the dam storehouse surface in realtime. To solve these problems, our system monitors the construction progress of the leveling machine and employs a real-time spreading thickness monitoring modelbased on the K-nearest neighbor algorithm. Taking the LHK core rockfilldam in Southwest China as an example, we performed real-time monitoring for the spreading thickness and conducted real-time interactive queries regarding the spreading thickness. This approach provides a new method for controlling the spreading thickness of the core rockfilldam storehouse surface.

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.

Nearest neighbor search algorithm for GBD tree spatial data structure

This paper describes the nearest neighbor (NN) search algorithm on the GBD(generalized BD) tree. The GBD tree is a spatial data structure suitable for two-or three-dimensional data and has good performance characteristics with respect to the dynamic data environment. On GIS and CAD systems, the R-tree and its successors have been used. In addition, the NN search algorithm is also proposed in an attempt to obtain good performance from the R-tree. On the other hand, the GBD tree is superior to the R-tree with respect to exact match retrieval, because the GBD tree has auxiliary data that uniquely determines the position of the object in the structure. The proposed NN search algorithm depends on the property of the GBD tree described above. The NN search algorithm on the GBD tree was studied and the performance thereof was evaluated through experiments.

Basic Tenets of Classification Algorithms K-Nearest-Neighbor, Support Vector Machine, Random Forest and Neural Network: A Review

In this paper, sixty-eight research articles published between 2000 and 2017 as well as textbooks which employed four classification algorithms: K-Nearest-Neighbor (KNN), Support Vector Machines (SVM), Random Forest (RF) and Neural Network (NN) as the main statistical tools were reviewed. The aim was to examine and compare these nonparametric classification methods on the following attributes: robustness to training data, sensitivity to changes, data fitting, stability, ability to handle large data sizes, sensitivity to noise, time invested in parameter tuning, and accuracy. The performances, strengths and shortcomings of each of the algorithms were examined, and finally, a conclusion was arrived at on which one has higher performance. It was evident from the literature reviewed that RF is too sensitive to small changes in the training dataset and is occasionally unstable and tends to overfit in the model. KNN is easy to implement and understand but has a major drawback of becoming significantly slow as the size of the data in use grows, while the ideal value of K for the KNN classifier is difficult to set. SVM and RF are insensitive to noise or overtraining, which shows their ability in dealing with unbalanced data. Larger input datasets will lengthen classification times for NN and KNN more than for SVM and RF. Among these nonparametric classification methods, NN has the potential to become a more widely used classification algorithm, but because of their time-consuming parameter tuning procedure, high level of complexity in computational processing, the numerous types of NN architectures to choose from and the high number of algorithms used for training, most researchers recommend SVM and RF as easier and wieldy used methods which repeatedly achieve results with high accuracies and are often faster to implement.

A Study of EM Algorithm as an Imputation Method: A Model-Based Simulation Study with Application to a Synthetic Compositional Data

Compositional data, such as relative information, is a crucial aspect of machine learning and other related fields. It is typically recorded as closed data or sums to a constant, like 100%. The statistical linear model is the most used technique for identifying hidden relationships between underlying random variables of interest. However, data quality is a significant challenge in machine learning, especially when missing data is present. The linear regression model is a commonly used statistical modeling technique used in various applications to find relationships between variables of interest. When estimating linear regression parameters which are useful for things like future prediction and partial effects analysis of independent variables, maximum likelihood estimation (MLE) is the method of choice. However, many datasets contain missing observations, which can lead to costly and time-consuming data recovery. To address this issue, the expectation-maximization (EM) algorithm has been suggested as a solution for situations including missing data. The EM algorithm repeatedly finds the best estimates of parameters in statistical models that depend on variables or data that have not been observed. This is called maximum likelihood or maximum a posteriori (MAP). Using the present estimate as input, the expectation (E) step constructs a log-likelihood function. Finding the parameters that maximize the anticipated log-likelihood, as determined in the E step, is the job of the maximization (M) phase. This study looked at how well the EM algorithm worked on a made-up compositional dataset with missing observations. It used both the robust least square version and ordinary least square regression techniques. The efficacy of the EM algorithm was compared with two alternative imputation techniques, k-Nearest Neighbor (k-NN) and mean imputation (), in terms of Aitchison distances and covariance.

基于不规则区域划分方法的k-Nearest Neighbor查询算法

随着越来越多的数据累积,对数据处理能力和分析能力的要求也越来越高.传统k-Nearest Neighbor(k NN)查询算法由于其容易导致计算负载整体不均衡的规则区域划分方法及其单个进程或单台计算机运行环境的较低数据处理能力.本文提出并详细介绍了一种基于不规则区域划分方法的改进型k NN查询算法,并利用对大规模数据集进行分布式并行计算的模型Map Reduce对该算法加以实现.实验结果与分析表明,Map Reduce框架下基于不规则区域划分方法的k NN查询算法可以获得较高的数据处理效率,并可以较好的支持大数据环境下数据的高效查询.

Comparison of Two Quantum Nearest Neighbor Classifiers on IBM’s Quantum Simulator

Today computers are used to store data in memory and then process them. In our big data era, we are facing the challenge of storing and processing the data simply due to their fast ever growing size. Quantum computation offers solutions to these two prominent issues quantum mechanically and beautifully. Through careful design to employ superposition, entanglement, and interference of quantum states, a quantum algorithm can allow a quantum computer to store datasets of exponentially large size as linear size and then process them in parallel. Quantum computing has found its way in the world of machine learning where new ideas and approaches are in great need as the classical computers have reached their capacity and the demand for processing big data grows much faster than the computing power the classical computers can provide today. Nearest neighbor algorithms are simple, robust, and versatile supervised machine learning algorithms, which store all training data points as their learned “model” and make the prediction of a new test data point by computing the distances between the query point and all the training data points. Quantum counterparts of these classical algorithms provide efficient and elegant ways to deal with the two major issues of storing data in memory and computing the distances. The purpose of our study is to select two similar quantum nearest neighbor algorithms and use a simple dataset to give insight into how they work, highlight their quantum nature, and compare their performances on IBM’s quantum simulator.

ML组合的CYGNSS海面风速反演质量控制模型

卷积神经网络(CNN)可用于气旋全球导航卫星系统(CYGNSS)的海面风速反演。虽然在模型训练前设置了质量控制指标来检测和削弱CYGNSS的异常观测数据,但CYGNSS观测数据中仍存在异常值导致模型反演精度降低,甚至出现错误反演结果。因此,提出一种基于机器学习(ML)组合的海面风速反演模型。在基于CNN回归模型的CYGNSS反演海面风速基础上,ML分类模型生成CNN回归结果的质量标志位,该标志位可以检测并删除CNN回归结果的异常值,进一步提高风速反演结果的数据质量,ML分类模型能够更好地考虑各种数据误差之间的相互作用,而不是单独使用每个条件的阈值,以达到更优的海面风速反演精度的效果。实验对比了Logistic回归(LR)、决策树(DT)、朴素贝叶斯模型、K最邻近(KNN)算法、神经网络(NN)模型、支持向量机(SVM)算法等6个分类模型,其中,基于KNN算法的分类模型对风速反演质量控制的效果最优。所提风速反演组合模型显著提高了反演结果的精度,在0~20 m/s区间内,异常样本过滤率为81.27%,在所有被过滤的数据中,过滤正确率为86.03%;风速反演误差的均方根误差从无ML分类模型的1.7 m/s降低到有ML分类模型的1.44 m/s,其中,训练样本为0~10 m/s的反演结果精度提升效果较为明显,证明了所提风速反演组合模型对风速质量控制的有效性。

基于沙地猫群优化–最小二乘支持向量机的动态NOx排放预测

针对火电机组频繁调峰导致机组燃烧状态不稳,进而导致锅炉出口NOx浓度波动范围大的问题,提出一种基于沙地猫群优化(sand cat sarm optimization,SCSO)的最小二乘支持向量机(leastsquaressupportvectormachine,LSSVM) NOx动态预测模型。首先利用k近邻互信息计算时间延迟的同时筛选辅助变量。然后,基于SCSO算法进行输入变量阶次的选择。使用包含辅助变量时间延迟和阶次的信息作为模型的输入,SCSO算法优化最小二乘支持向量机参数,建立动态NOx排放最小二乘支持向量机预测模型(SCSO-LSSVM动态软测量模型)。最后将模型与未加入迟延的LSSVM模型,加入迟延的LSSVM模型和粒子群优化算法(particle swarm optimization,PSO)优化最小二乘支持向量机参数的动态软测量模型进行对比验证。结果表明,相较于其他模型,该文建立SCSO-LSSVM动态软测量模型均方根误差、平均绝对误差、平均绝对误差最小,预测精度最高,而且在NOx浓度剧烈波动时也能够较好地预测NOx浓度,具有很好的动态特性。

基于加权实例推理的缓倾斜综采工作面液压支架选型研究

为实现地质构造简单的缓倾斜综采工作面液压支架智能化选型,提出了一种基于加权实例推理的液压支架选型方法。首先,建立了液压支架选型实例库;其次,采用粗糙集理论和序关系分析法进行权重构造;另外,将液压支架的条件属性分为3种类型计算相似度;最后通过匹配实例选型。以某煤矿选型方案为例,并以50组液压支架的属性数据进行验证。结果表明,该方法的准确率为88%,能够为液压支架的智能化选型提供较好的参考依据。

零件加工隐性工艺知识获取方法研究

随着制造业数字化工艺的深入应用,如何高效利用积累的工艺知识,已成为提升工艺设计效率与质量的关键,然而隐性工艺知识却存在难以获取、描述与转化的技术瓶颈,严重阻碍智能化工艺设计模式推广。为此,提出了一种复杂零件加工的隐性工艺知识获取方法。首先,利用等宽法对结构化工艺数据进行离散化处理,构建基于文本挖掘的隐性工艺知识获取流程,并通过产生式规则对隐性工艺知识表达;然后,基于案例推理和规则推理融合的知识推理方法,并采用最近邻算法实现隐性工艺知识的识别;最后,以船用柴油机缸盖类复杂加工零件为验证对象,对加工隐性工艺知识获取方法进行了有效验证。

求解带容量约束车辆路径问题的改进遗传算法

为解决传统遗传算法求解带容量约束的车辆路径问题时收敛速度慢和局部搜索能力差的问题,对传统遗传算法提出一种改进策略。使用基于贪婪策略的启发式交叉算子加强算法接近最优解的能力,加快算法收敛速度,在变异操作中,引入最近邻搜索算子,缩小基因变异范围,使用单点局部插入算子提高算法的局部优化能力。采用精英选择和轮盘赌法结合的选择策略,保持种群多样性以加强算法的全局搜索能力。实例计算测试表明,与传统遗传算法相比,所提算法求解平均偏差降低了70.25%,求解时间减少了87.41%;与ALNS和AGGWOA算法相比,有更高的求解质量和更好的稳定性。

基于参数自适应DBSCAN算法的浮标位置数据异常检测

针对遥测遥控系统采集浮标位置数据时易受外在因素的干扰,提出了一种K近邻优化的参数自适应DBSCAN算法,来检测浮标位置数据中的异常点。通过分析数据集的分布特性生成最优邻域距离值ε和邻域内样本点数量MinPts列表,引入卡林斯基-哈拉巴斯指数对列表中的参数进行评分,将最高评分对应的参数作为最优参数,实现DBSCAN算法的自适应聚类。实验结果表明,新算法能够自适应选择最优参数,对浮标遥测位置数据的异常点进行有效检测。

基于IKNN和LOF的变压器回复电压数据清洗方法研究

基于回复电压极化谱提取特征参量是目前广泛应用的变压器油纸绝缘状态评估方法,但极化谱易受工况干扰、人工失误等因素影响而出现特征数据异常的情况,严重降低评估准确性。针对上述问题,该文提出了一种基于局部离群因子(LOF)和改进K最近邻(IKNN)的回复电压数据清洗方法。首先,选取回复电压极化谱的回复电压极大值Urmax、初始斜率Sr与主时间常数tcdom作为老化特征参量,并基于LOF算法对非标准极化谱中的异常特征量数据进行识别与筛除。其次,利用模糊C均值(FCM)聚类算法减小噪声点对KNN算法的干扰,并通过加权欧氏距离标度突出各特征量间的关联性,进而构建出基于IKNN的数据填补模型架构以实现特征缺失数据的填补。最后,代入多组实测数据验证所提数据清洗方法的实效性。结果表明,数据清洗后的状态评估准确率相较于原有数据上升了50%左右,有效提高了变压器回复电压数据质量,为准确感知变压器运行状况奠定坚实的基础。

基于字典分级和属性加权的密文排序检索方案

可搜索加密支持用户在不解密原始数据的前提下对加密数据执行检索操作.现有的多关键词排序可搜索加密方案,其索引和陷门构建的时间成本通常依赖于由全局关键词字典张成的向量空间.为了减少用户端的计算开销和通信成本,进一步提升数据使用者对检索结果的满意度,提出了一种支持细粒度访问控制的多关键词密文排序检索方案.该方案首先设计基于互信息的字典剥离机制差异化全局字典中的关键词,得到两个信息量不同的附属子字典,进一步在低维子字典空间上生成索引和陷门;其次,引入文档访问策略中属性的权重,将其作为排序标准之一,使数据使用者获得更为相关的结果;最后,检索时利用筛选向量对数据进行初次过滤并借助属性匹配完成二次剔除,从而避免检索过程中不必要的计算.

融合动态K近邻Slope_One的协同过滤推荐算法

传统协同过滤推荐算法存在数据稀疏的问题,这会导致算法精确度不足。Slope_One算法简单高效,可以预测用户对某个物品的评分。因此,论文提出融合动态K近邻Slope_One的协同过滤推荐算法,提高推荐算法的精确度。首先利用改进余弦相似度公式计算用户相似度,筛选出K个近邻用户进行平均评分偏差计算,利用Slope_One算法预测相应的用户评分并对评分矩阵进行有效填充,然后在新的评分矩阵上,利用基于物品的协同过滤算法进行推荐。

一种改进的局部均值伪近邻算法

针对基于局部均值的伪近邻分类算法(LMPNN)易受近邻参数k和噪声点影响的问题,提出了一种改进的局部均值伪近邻分类算法(IPLMPNN)。利用双层搜索规则确定待测样本的最近邻,提高近邻集的选择质量;为了克服主观赋权法的不利影响,并且加强每个局部均值向量对分类的作用,引入注意力机制计算距离加权系数;使用改进的调和平均距离计算待测样本与局部均值向量之间的加权多调和平均距离,由此查找伪近邻点对待测样本进行分类。利用UCI和KEEL中的多个数据集对IPLMPNN算法进行仿真实验,并与8种相关算法进行比较。实验结果表明,IPLMPNN算法取得了令人满意的分类结果。

基于稳定AP选择的动态室内定位方法

在室内复杂多变环境下,基于接收信号强度指示(Received Signal Strength Indication,RSSI)的位置指纹算法得到了广泛研究。其中,在线阶段的匹配算法通常采用加权K近邻(Weighted K-Nearest Neighbor,WKNN)算法,但该算法往往采用固定k值方法存在较大的定位误差,具有一定的局限性,并且离线阶段构建位置指纹数据库时并没有考虑到无线接入点(Access Point,AP)信号的波动性。因此,存在大量不同AP的冗余信息,对定位效果产生较大影响。针对上述问题,提出一种基于稳定AP选择的动态室内定位方法。首先,通过高斯滤波对RSSI值进行预处理,滤除随机干扰;然后,通过优选AP算法计算AP的稳定度,筛选出关键AP用于定位;最后,利用距离阈值动态调整k值,并对权重系数进行改善,实现了对WKNN算法的改进。实验结果表明,基于稳定AP选择的动态室内定位方法可以有效去除冗余AP信息,并实现动态k值方案,在定位精度上优于K近邻(K-Nearest Neighbors,KNN)算法、加权K近邻算法和改进的加权K近邻算法,平均定位误差分别降低了26.13%、21.29%和9.89%,定位误差在1.5 m内的累积分布概率达到了60.41%,分别提升了25%、16.66%和8.33%,定位效果提升明显。

基于最邻近算法的数据中台内生性数据安全交互系统

数据中台是一种可实现数据采集、清洗、存储的架构,使其优化内部数据的管理效果,提升数据价值的释放。但由于数据中台架构较为复杂,导致数据安全交互时效性下降。为解决此问题,基于最邻近算法设计一种新的数据中台内生性数据安全交互系统。设置入口节点和出口节点协调模式,抑制混乱传输现象,通过业务服务和数据存储双中台架构搭建硬件结构。利用最邻近算法排序处理数据,设定准确度阈值,分析密钥参数,实现安全交互。实验结果表明,该方法的精准度在99%以上,交互时间显著缩短,对于数据中台有积极的推动作用。

基于Bi-LSTM神经网络的室内可见光定位方法

双向长短时记忆(Bi-LSTM)神经网络由于超参数众多,难以获得最优系统模型。同时,考虑到灰狼优化(GWO)算法可能过早收敛的情况,提出了一种采用GWO结合粒子群(GWO-PSO)算法优化Bi-LSTM神经网络的单灯定位方法。通过优化网络中的学习率、隐藏神经元个数等超参数,提高系统的稳定性和定位精度。最后,采用加权K邻近(WKNN)算法对误差较大的点进行优化,以获得更精确的定位位置。仿真结果表明,在3 m×3.6 m×3 m的室内环境中,所提定位方法的平均定位误差为3.57 cm,其中90%的定位误差在6 cm内。