Small-time scale network traffic prediction based on a local support vector machine regression model

In this paper we apply the nonlinear time series analysis method to small-time scale traffic measurement data. The prediction-based method is used to determine the embedding dimension of the traffic data. Based on the reconstructed phase space, the local support vector machine prediction method is used to predict the traffic measurement data, and the BIC-based neighbouring point selection method is used to choose the number of the nearest neighbouring points for the local support vector machine regression model. The experimental results show that the local support vector machine prediction method whose neighbouring points are optimized can effectively predict the small-time scale traffic measurement data and can reproduce the statistical features of real traffic measurements.

A Hierarchical Clustering and Fixed-Layer Local Learning Based Support Vector Machine Algorithm for Large Scale Classification Problems

It is a challenging topic to develop an efficient algorithm for large scale classification problems in many applications of machine learning. In this paper, a hierarchical clustering and fixed- layer local learning （HCFLL） based support vector machine（SVM） algorithm is proposed to deal with this problem. Firstly, HCFLL hierarchically dusters a given dataset into a modified clustering feature tree based on the ideas of unsupervised clustering and supervised clustering. Then it locally trains SVM on each labeled subtree at a fixed-layer of the tree. The experimental results show that compared with the existing popular algorithms such as core vector machine and decision.tree support vector machine, HCFLL can significantly improve the training and testing speeds with comparable testing accuracy.

DIAGNOSTICS OF FATIGUE CRACK IN ULTERIOR PLACES OF LARGER-SCALE OVERLOADED SUPPORTING SHAFT BASED ON TIME SERIES AND NEURAL NETWORKS

To improve the diagnosis accuracy and self-adaptability of fatigue crack in ulterior place of the supporting shaft, time series and neural network are attempted to be applied in research on diag-nosing the fatigue crack’s degree based on analyzing the vibration characteristics of the supporting shaft. By analyzing the characteristic parameter which is easy to be detected from the supporting shaft’s exterior, the time series model parameter which is hypersensitive to the situation of fatigue crack in ulterior place of the supporting shaft is the target input of neural network, and the fatigue crack’s degree value of supporting shaft is the output. The BP network model can be built and net-work can be trained after the structural parameters of network are selected. Furthermore, choosing the other two different group data can test the network. The test result will verify the validity of the BP network model. The result of experiment shows that the method of time series and neural network are effective to diagnose the occurrence and the development of the fatigue crack’s degree in ulterior place of the supporting shaft.

Designing a Scale to Assess Breastfeeding Support among Public Health Nurses in Japan

Background: Promoting breastfeeding support by public health nurses (PHN) requires first that the support which they currently provide to be assessed. However, there is no assessment tool for this purpose. The aim of this study was therefore to develop a scale to assess breastfeeding support currently provided by PHN. Methods: We developed the Practice of Breastfeeding Support Scale (PBSS) for PHN based on the results of a previous study. The content validity of the PBSS was established through discussion with three other researchers. A pilot study was conducted to confirm face validity. To confirm reliability and validity, an anonymous, self-reported questionnaire was sent to PHN working in municipal offices. The statistical analyses included the Kaiser-Meyer-Olkin (KMO), Barlett’s Test of Sphericity, exploratory factor analysis (EFA), Cronbach’s alpha and correlation coefficient. Results: 768 PHN participated in this study. Cronbach’s alpha of PBSS was 0.85. The KMO measure was 0.892, and Bartlett’s Test of Sphericity was p Conclusion: The reliability and validity of PBSS were confirmed. These findings suggested that the PBSS has the potential to help promote breastfeeding support by PHN by clarifying their current breastfeeding support practices and related factors.

Visualization of atomic scale reaction dynamics of supported nanocatalysts during oxidation and ammonia synthesis using in-situ environmental(scanning) transmission electron microscopy

Reaction dynamics in gases at operating temperatures at the atomic level are the basis of heterogeneous gas-solid catalyst reactions and are crucial to the catalyst function.Supported noble metal nanocatalysts such as platinum are of interest in fuel cells and as diesel oxidation catalysts for pollution control,and practical ruthenium nanocatalysts are explored for ammonia synthesis.Graphite and graphitic carbons are of interest as supports for the nanocatalysts.Despite considerable literature on the catalytic processes on graphite and graphitic supports,reaction dynamics of the nanocatalysts on the supports in different reactive gas environments and operating temperatures at the single atom level are not well understood.Here we present real time in-situ observations and analyses of reaction dynamics of Pt in oxidation,and practical Ru nanocatalysts in ammonia synthesis,on graphite and related supports under controlled reaction environments using a novel in-situ environmental(scanning) transmission electron microscope with single atom resolution.By recording snapshots of the reaction dynamics,the behaviour of the catalysts is imaged.The images reveal single metal atoms,clusters of a few atoms on the graphitic supports and the support function.These all play key roles in the mobility,sintering and growth of the catalysts.The experimental findings provide new structural insights into atomic scale reaction dynamics,morphology and stability of the nanocatalysts.

POSITIVE DEFINITE KERNEL IN SUPPORT VECTOR MACHINE(SVM)

The relationship among Mercer kernel, reproducing kernel and positive definite kernel in support vector machine （SVM） is proved and their roles in SVM are discussed. The quadratic form of the kernel matrix is used to confirm the positive definiteness and their construction. Based on the Bochner theorem, some translation invariant kernels are checked in their Fourier domain. Some rotation invariant radial kernels are inspected according to the Schoenberg theorem. Finally, the construction of discrete scaling and wavelet kernels, the kernel selection and the kernel parameter learning are discussed.

Target classification using SIFT sequence scale invariants

On the basis of scale invariant feature transform（SIFT） descriptors,a novel kind of local invariants based on SIFT sequence scale（SIFT-SS） is proposed and applied to target classification.First of all,the merits of using an SIFT algorithm for target classification are discussed.Secondly,the scales of SIFT descriptors are sorted by descending as SIFT-SS,which is sent to a support vector machine（SVM） with radial based function（RBF） kernel in order to train SVM classifier,which will be used for achieving target classification.Experimental results indicate that the SIFT-SS algorithm is efficient for target classification and can obtain a higher recognition rate than affine moment invariants（AMI） and multi-scale auto-convolution（MSA） in some complex situations,such as the situation with the existence of noises and occlusions.Moreover,the computational time of SIFT-SS is shorter than MSA and longer than AMI.

Large scale classification with local diversity AdaBoost SVM algorithm

Local diversity AdaBoost support vector machine（LDAB-SVM） is proposed for large scale dataset classification problems.The training dataset is split into several blocks firstly, and some models based on these dataset blocks are built.In order to obtain a better performance, AdaBoost is used in each model building.In the boosting iteration step, the component learners which have higher diversity and accuracy are collected via the kernel parameters adjusting.Then the local models via voting method are integrated.The experimental study shows that LDAB-SVM can deal with large scale dataset efficiently without reducing the performance of the classifier.

Model selection for SVM using mutative scale chaos optimization algorithm

This paper proposes a new search strategy using mutative scale chaos optimization algorithm （MSCO） for model selection of support vector machine （SVM）. It searches the parameter space of SVM with a very high efficiency and finds the optimum parameter setting for a practical classification problem with very low time cost. To demonstrate the performance of the proposed method it is applied to model selection of SVM in ultrasonic flaw classification and compared with grid search for model selection. Experimental results show that MSCO is a very powerful tool for model selection of SVM, and outperforms grid search in search speed and precision in ultrasonic flaw classification.

Construction of Compactly Supported Bivariate Orthogonal Wavelets

For a given compactly supported scaling fun ct ion supported over [0,3]×[0,3], we present an algorithm to construct compac t ly supported orthogonal wavelets. By this algorithm, the symbol function of the associated wavelets can be constructed explicitly.

High temperature thermal behaviour modeling of large-scale fused silica optics for laser facility

High temperature annealing is often used for the stress control of optical materials.However,weight and viscosity at high temperature may destroy the surface morphology,especially for the large-scale,thin and heavy optics used for large laser facilities.It is necessary to understand the thermal behaviour and design proper support systems for large-scale optics at high temperature.In this work,three support systems for fused silica optics are designed and simulated with the finite element method.After the analysis of the thermal behaviours of different support systems,some advantages and disadvantages can be revealed.The results show that the support with the optical surface vertical is optimal because both pollution and deformation of optics could be well controlled during annealing at high temperature.Annealing process of the optics irradiated by CO2 laser is also simulated.It can be concluded that high temperature annealing can effectively reduce the residual stress.However,the effects of annealing on surface morphology of the optics are complex.Annealing creep is closely related to the residual stress and strain distribution.In the region with large residual stress,the creep is too large and probably increases the deformation gradient which may affect the laser beam propagation.

老年期精神分裂症社会支持度及其影响因素:基于144名连续抽样住院患者的横断面研究

目的:探讨老年期精神分裂住院患者社会支持度及影响因素。方法:采用连续抽样的方法招募了2021年3月至2023年12月广州医科大学附属脑科医院老年精神科的144例精神分裂症住院患者作为研究对象,使用社会支持度量表(SSRS)调查患者社会支持情况,收集数据包括基本资料、精神症状情况等。结果:144例老年精神分裂症患者的SSRS总分为28.29±5.67,单因素分析结果显示,老年期精神分裂症患者社会支持的影响因素为病程,婚姻状况与照顾者(P<0.05)。多元线性回归结果显示,老年期精神分裂症患者的社会支持主要与主要照顾者(他人照顾)(β=2.836,95%CI:0.515~5.158,P=0.017),婚姻状况(无伴侣)(β=-2.725,95%CI:-4.627~-0.824,P=0.005),简明精神病量表(BPRS)中的敌对猜疑因素(β=-0.488,95%CI:-0.739~-0.250,P<0.001)有关。结论:受他人照顾、有伴侣与精神行为症状中的敌对猜疑是老年期精神分裂住院患者社会支持度的主要影响因素。

粉煤灰基陶瓷膜支撑体的制备与尺寸放大试验

选取固体废物粉煤灰作为支撑体骨料,TiO_(2)为烧结助剂,羧甲基纤维素(CMC)为黏结剂,木炭粉为造孔剂,采用固态粒子烧结法制得初始陶瓷膜支撑体样品,并对其进行等比尺寸(直径)放大制备。探究支撑体尺寸放大制备中烧结温度、造孔剂添加量、尺寸(直径)放大倍数等因素对支撑体性能的影响,对物质组成、微观形貌、抗折强度、纯水通量、酸碱腐蚀率及孔径分布等性能进行表征。结果表明:最高烧结温度为1 050℃,造孔剂木炭粉添加量为15%(质量分数),放大到原尺寸(直径)的2倍时,所制得支撑体性能最佳,其内部孔隙均匀,颈型结构明显,纯水通量为4 728.26 L/(m^(2)·h·MPa),抗折强度为25.15 MPa,中值孔径为3.06μm,孔隙率为38.56%,酸、碱质量损失率分别为0.33%、0.25%。

胚胎移植女性孕早期睡眠质量及关联因素分析

背景胚胎移植女性经受了身体和心理的双重挑战,孕早期的生活质量,尤其是睡眠质量会受到较大的影响。目的分析胚胎移植女性孕早期睡眠质量及相关影响因素。方法选取2022年6—12月于河北医科大学第二医院生殖医学科进行体外受精-胚胎移植(in vitro fertilization-embryo transfer,IVF-ET)助孕成功的患者,在其移植后45 d返院复查B超时进行问卷调查,调查内容包括匹兹堡睡眠质量指数(Pittsburgh sleep quality index,PSQI)、焦虑自评量表(self-rating anxiety scale,SAS)、抑郁自评量表(self-rating depression scale,SDS)、中文简化版心理弹性量表(Connor Davidson resilience scale,CD-RISC)和社会支持评定量表。以PSQI>7分为判断睡眠障碍的标准,通过多因素Logistic回归模型分析睡眠质量与各个影响因素的关系,并使用信息增益算法对影响睡眠质量的主要因素进行影响程度评估。结果发放问卷336份,回收325份,回收率96.7%。325例IVF-ET孕妇年龄(32.46±4.52)岁,睡眠质量总分为(7.79±3.63)分,其中126例孕妇总分≤7分为睡眠正常组,199例孕妇总分>7分为睡眠障碍组(61.23%,199/325)。相关心理学评估:焦虑自评量表(43.75±8.86)分;抑郁自评量表(50.89±10.54)分;心理弹性量表总分(64.18±11.34),其中坚韧性(32.66±10.28)分,力量性(21.75±6.37)分,乐观性(9.74±3.26)分;社会支持评定量表总分为(42.27±4.93)分,其中客观支持(9.15±2.13)分,主观支持(25.30±4.26)分,对支持的利用度(7.82±1.91)分。Logistic回归结果提示,年龄越大、越焦虑,越容易出现睡眠障碍;文化程度中,以初中及以下人群作为参照,高中或中专学历的人群更不容易出现睡眠障碍;心理弹性水平越高,睡眠障碍出现概率越低(P均<0.05)。信息增益分析结果显示,影响睡眠质量的因素按影响力大小依次为心理弹性中的坚韧性(1.186)、社会支持量表中的主观支持分(0.807)、心理弹性量表中的力量性(0.806)、心理弹性量表中的乐观性(0.510)、社会支持量表中的对支持的利用度(0.422)、文化程度(0.419)、客观支持分(0.391)、职业(0.216)、婆媳关系(0.213)、SAS(0.192)、SDS(0.162)、第几次移植(0.146)、年龄(0.117)、第几次取卵(0.108)、社会支持总分(0.107)、现有子女个数(0.088)、月收入(0.082)、夫妻关系(0.051)、居住地(0.035)。结论胚胎移植女性在孕早期睡眠质量较差;患者的不良心理状态对睡眠有负面影响,而心理弹性和社会支持对睡眠质量则起到了积极的正面影响,临床可以从改善患者心理弹性状态、增加社会支持方向入手,帮助IVF-ET孕妇从孕早期开始改善睡眠质量,从而提高生活质量,保证母婴健康。

RMAPS模式预报总辐射的3种订正方法应用

为降低光伏功率预测中预报总辐射误差且探讨各类订正方法的适用性,分季节对比分析逐步回归、支持向量机(SVM)和相似误差订正(AnBC)方法对快速更新多尺度分析和预报系统短期预报总辐射的订正效果.结果表明,订正后明显降低了预报误差,一定程度上改善了预报总辐射分布较分散和偏大的情况.酒泉鸿坤光伏电站秋季逐步回归订正效果相对最佳(平均绝对偏差(M_(AE))降低4.56 W/m^(2)),冬季、夏季和春季均是AnBC效果相对最佳(M_(AE)依次降低10.33、12.71、44.27 W/m^(2));敦煌电建汇能光伏电站秋季和冬季均是SVM订正效果相对最佳(M_(AE)分别降低4.73和7.85 W/m^(2)),夏季和春季均是AnBC效果相对最佳(M_(AE)分别降低16.24和34.17 W/m^(2)).两座电站逐小时误差分布显示AnBC效果相对最佳;就各季节相对最佳订正方法而言,订正后春季提高时次百分比最高(酒泉鸿坤为73.88%,电建汇能为77.28%).晴天SVM订正效果最明显,非晴天AnBC效果最明显.

基于空间投影和聚类划分的SVR加速算法

数据不仅能产生价值,还对统计学的科学发展提供了动力。随着科技的飞速发展,海量数据得以涌现,但大规模的数据会导致很多传统处理方法很难满足各领域对数据分析的需求。面对海量数据时代学习算法的低效性,分治法通常被认为是解决这一问题最直接、最广泛使用的策略。SVR是一种强大的回归算法,在模式识别和数据挖掘等领域有广泛应用。然而在处理大规模数据时,SVR训练效率低。为此,该文利用分治思想提出一种基于空间投影和聚类划分的SVR加速算法(PKM-SVR)。利用投影向量将数据投影到二维空间;利用聚类方法将数据空间划分为k个互不相交的区域;在每个区域上训练SVR模型;利用每个区域的SVR模型预测落入同一区域的待识别样本。在标准数据集上与传统的数据划分方法进行对比实验,实验结果表明该算法训练速度较快,并表现出更好的预测性能。

融合多特征信息与GWO-SVM的机械关键设备故障诊断

为了提高机械关键设备故障诊断的精度,建立机械关键设备故障诊断模型。文章提出一种融合机械关键设备故障信号多特征信息与灰狼优化算法(Grey Wolf Optimization Algorithm,GWO)改进支持向量机(Support Vector Machine,SVM)(GWO-SVM)的机械关键设备故障诊断模型。首先,提取机械关键设备故障信号的时域特征、频域特征和多尺度加权排列熵特征,分别对比不同特征的机械关键设备故障诊断结果。其次,为提高SVM模型性能,运用GWO算法对SVM模型的惩罚参数P和核函数参数g进行优化选择,提出一种融合多特征信息与GWO-SVM的机械设备故障诊断模型。与GA-SVM、PSO-SVM和SVM相比,基于GWO-SVM的机械设备故障诊断模型的诊断精度最高。这里算法可以有效提高机械关键设备故障诊断正确率,为机械关键设备故障诊断提供了新的方法。

基于声信号的离心泵故障诊断研究

各种原因使得工业现场设备状态监测的首选测量信号是声信号时,提出一种基于声信号的设备状态监测方法显得尤为必要。以某型离心泵为依据对象,对现场采集的声信号提取梅尔倒谱系数(MFCC)作为信号的初始特征,然后计算这些MFCC初始特征的散布熵(DE)值,并通过主成分分析法(PCA)对矩阵进行降维,从而构造特征矩阵。利用蝙蝠优化算法(BA)对支持向量机(SVM)的惩罚系数与核函数参数进行优化,对离心泵的多种故障工况开展诊断,并与多种诊断方法进行比较。实验结果表明,经过BA优化后的模型在诊断准确率上提高了21.7%;在该模型的基础上利用DE对MFCC提取的信号进行深度挖掘,使模型诊断的准确率提高2.05%。

以农业服务规模化促进农业提质增效——基于322家合作社、家庭农场等典型案例分析

土地规模与服务规模是推进我国农业适度规模经营的两种重要途径,基于322家典型案例分析发现,各地区都在积极探索把以“土地流转”方式联农带农逐渐转变为以“经营托管”方式联农带农。在典型案例中,种植类合作社(占比40%)和农机合作社(占比15%)以“生产托管”方式联农带农,不断尝试通过节约劳动型的机械技术和节约土地型的生物、化学和信息技术扩大服务规模,依托“N+服务”模式,使服务逐步延伸到耕、种、防、收、烘、储、销等农业生产全过程;养殖类合作社(占比约20%)采用“技术+服务”方式逐步形成“统一综合服务+分户饲养+拓展种植”的种养结合循环发展模式,提高了经济效益、社会效益和生态效益。通过调研案例发现,面向小农户的农业社会化服务供给不足、服务效率低、服务水平低的情况普遍存在,仅依靠市场自身发展扩大农业服务规模、提升农业服务效率和水平的能力和空间有限,还需在增服务、增效率、提水平等方面进一步加大政策扶持力度,夯实推进农业服务规模化发展的政策基础,转变农业生产运营模式和服务模式,探索土地规模化与服务规模化协调发展机制,稳步扩大农业服务规模,打造新型农业社会化组织队伍,促进农业发展提质增效。

乡村儿童学校教育支持的理路、困境与路径选择——兼论乡村小规模学校的价值意蕴

为乡村儿童提供接受学校教育支持的机会,革新乡村儿童学校教育支持的手段,精准乡村儿童学校教育支持分类需求,是乡村振兴背景下完善乡村儿童学校教育支持体系的理路。乡村小规模学校的萎缩难以为乡村儿童提供充足的教育机会,乡村学校教育在“升学至上”的追求中逐渐迷失自我,乡村儿童学校教育精准支持若有若无,是乡村儿童学校教育支持面临的主要困境。可从关注乡村教育定位与发展入手,发挥乡村小规模学校的独特优势,实施乡村儿童学校教育支持的分类保障,完善乡村振兴进程中乡村儿童学校教育支持体系。