Underwater Image Classification Based on EfficientnetB0 and Two-Hidden-Layer Random Vector Functional Link

The ocean plays an important role in maintaining the equilibrium of Earth’s ecology and providing humans access to a wealth of resources.To obtain a high-precision underwater image classification model,we propose a classification model that combines an EfficientnetB0 neural network and a two-hidden-layer random vector functional link network(EfficientnetB0-TRVFL).The features of underwater images were extracted using the EfficientnetB0 neural network pretrained via ImageNet,and a new fully connected layer was trained on the underwater image dataset using the transfer learning method.Transfer learning ensures the initial performance of the network and helps in the development of a high-precision classification model.Subsequently,a TRVFL was proposed to improve the classification property of the model.Net construction of the two hidden layers exhibited a high accuracy when the same hidden layer nodes were used.The parameters of the second hidden layer were obtained using a novel calculation method,which reduced the outcome error to improve the performance instability caused by the random generation of parameters of RVFL.Finally,the TRVFL classifier was used to classify features and obtain classification results.The proposed EfficientnetB0-TRVFL classification model achieved 87.28%,74.06%,and 99.59%accuracy on the MLC2008,MLC2009,and Fish-gres datasets,respectively.The best convolutional neural networks and existing methods were stacked up through box plots and Kolmogorov-Smirnov tests,respectively.The increases imply improved systematization properties in underwater image classification tasks.The image classification model offers important performance advantages and better stability compared with existing methods.

Fully Distributed Learning for Deep Random Vector Functional-Link Networks

In the contemporary era, the proliferation of information technology has led to an unprecedented surge in data generation, with this data being dispersed across a multitude of mobile devices. Facing these situations and the training of deep learning model that needs great computing power support, the distributed algorithm that can carry out multi-party joint modeling has attracted everyone’s attention. The distributed training mode relieves the huge pressure of centralized model on computer computing power and communication. However, most distributed algorithms currently work in a master-slave mode, often including a central server for coordination, which to some extent will cause communication pressure, data leakage, privacy violations and other issues. To solve these problems, a decentralized fully distributed algorithm based on deep random weight neural network is proposed. The algorithm decomposes the original objective function into several sub-problems under consistency constraints, combines the decentralized average consensus (DAC) and alternating direction method of multipliers (ADMM), and achieves the goal of joint modeling and training through local calculation and communication of each node. Finally, we compare the proposed decentralized algorithm with several centralized deep neural networks with random weights, and experimental results demonstrate the effectiveness of the proposed algorithm.

基于Vector Random Decrement技术和特征系统实现算法ERA的模态参数识别

现代的大型复杂结构,如大坝、高层建筑、桥梁及海洋平台等,处于复杂的环境载荷作用下,这些环境载荷往往是无法测量的。在仅有输出响应时,应用随机减量法RDT获得自由衰减响应信号,而后用时域复指数拟合法、ITD法、特征系统实现算法ERA等算法获得结构的模态参数是一种有效的方法。但在数据量有限时,随机减量函数的平均次数过少,导致RD函数的收敛性较差。为此提出了利用Vector Random Decrement技术(VRDT)提取自由衰减响应信号,而后利用特征系统实现算法ERA求得模态参数的方法,新算法能够有效地提高模态参数识别精度。数值算例验证了所提算法的有效性。

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.

Dispersion of the Mechanical Parts Performance Indicators Based on the Concept of Random Vector

To solve the precision and reliability problem of various machinery equipments and military vehicles, some military organisations, the industrial sector and the academia at home and abroad begin to pay attention to the statistical distribution of machining dimensions, material properties and service loads, and the system reliability optimization design with constraints and reliability optimization design of various mechanical parts is studied in this way. However, the above researches focus on solving the strength and the life problem, and no studies have been done on the discrete degree and discrete pattern of other performance indicators. The concept of using a random vector to describe the mechanical parts performance indicators is presented; characteristics between the value of the vector variance matrix determinant and the sum of the diagonal covariance matrix in describing the performance indicators of vector dispersion are studied and compared. A clutch diaphragm spring is set as an example, the geometric dimension indicator is described with random vector, and the applicability of using variance matrix determinant and variance matrix trace of geometric dimension vector to describe discrete degree of random vector is studied by using Monte-Carlo simulation method and component discrete degree perturbation method. Also, the effects of different components of diaphragm spring geometric dimension vector on the value of covariance matrix determinant and the sum of covariance matrix diagonal of diaphragm spring performance indicators vector are analyzed. The present study shows that the impacts of the dispersion of diaphragm spring cone angle on every performance dispersion are all ranked first, and far exceed that of other dimension dispersion. So it must be strictly controlled in the production process. The result of the research work provides a reference for the design of diaphragm spring, and also it presents a proper method for researching the performance of other mechanical parts.

The Estimation of Radial Exponential Random Vectors in Additive White Gaussian Noise

Image signals are always disturbed by noise during their transmission, such as in mobile or network communication. The received image quality is significantly influenced by noise. Thus, image signal denoising is an indispensable step during image processing. As we all know, most commonly used methods of image denoising is Bayesian wavelet transform estimators. The Performance of various estimators, such as maximum a posteriori (MAP), or minimum mean square error (MMSE) is strongly dependent on correctness of the proposed model for original data distribution. Therefore, the selection of a proper model for distribution of wavelet coefficients is important in wavelet-based image denoising. This paper presents a new image denoising algorithm based on the modeling of wavelet coefficients in each subband with multivariate Radial Exponential probability density function (PDF) with local variances. Generally these multivariate extensions do not result in a closed form expression, and the solution requires numerical solutions. However, we drive a closed form MMSE shrinkage functions for a Radial Exponential random vectors in additive white Gaussian noise (AWGN). The estimator is motivated and tested on the problem of wavelet-based image denoising. In the last, proposed, the same idea is applied to the dual-tree complex wavelet transform (DT-CWT), This Transform is an over-complete wavelet transform.

The Comparison between Random Forest and Support Vector Machine Algorithm for Predicting β-Hairpin Motifs in Proteins

Based on the research of predictingβ-hairpin motifs in proteins, we apply Random Forest and Support Vector Machine algorithm to predictβ-hairpin motifs in ArchDB40 dataset. The motifs with the loop length of 2 to 8 amino acid residues are extracted as research object and thefixed-length pattern of 12 amino acids are selected. When using the same characteristic parameters and the same test method, Random Forest algorithm is more effective than Support Vector Machine. In addition, because of Random Forest algorithm doesn’t produce overfitting phenomenon while the dimension of characteristic parameters is higher, we use Random Forest based on higher dimension characteristic parameters to predictβ-hairpin motifs. The better prediction results are obtained;the overall accuracy and Matthew’s correlation coefficient of 5-fold cross-validation achieve 83.3% and 0.59, respectively.

Efficient Global Threshold Vector Outlyingness Ratio Filter for the Removal of Random Valued Impulse Noise

This research paper proposes a filter to remove Random Valued Impulse Noise (RVIN) based on Global Threshold Vector Outlyingness Ratio (GTVOR) that is applicable for real time image processing. This filter works with the algorithm that breaks the images into various decomposition levels using Discrete Wavelet Transform (DWT) and searches for the noisy pixels using the outlyingness of the pixel. This algorithm has the capability of differentiating high frequency pixels and the “noisy pixel” using the threshold as well as window adjustments. The damage and the loss of information are prevented by means of interior mining. This global threshold based algorithm uses different thresholds for different quadrants of DWT and thus helps in recovery of noisy image even if it is 90% affected. Experimental results exhibit that this method outperforms other existing methods for accurate noise detection and removal, at the same time chain of connectivity is not lost.

Computational Intensity Prediction Model of Vector Data Overlay with Random Forest Method

Spatial analysis is the core of geographic information system(GIS),of which,spatial overlay of vector data is a major job.Computational intensity of the spatial overlay has a direct effect on the overall performance of the GIS.High precision modeling for the computational intensity and analysis of the vector data overlay has been a challenging task.Thus,the paper proposes a novel approach,which utilizes self-learning and self-training features of optimized random forest algorithm to the vector data overlay analysis.Simulation experiments show that the proposed model is superior to non-optimized random forest algorithm and support vector machine model with higher prediction precision and is also capable of eliminate redundant computational intensity features.

Prediction of Alzheimer’s Using Random Forest with Radiomic Features

Alzheimer’s disease is a non-reversible,non-curable,and progressive neurological disorder that induces the shrinkage and death of a specific neuronal population associated with memory formation and retention.It is a frequently occurring mental illness that occurs in about 60%–80%of cases of dementia.It is usually observed between people in the age group of 60 years and above.Depending upon the severity of symptoms the patients can be categorized in Cognitive Normal(CN),Mild Cognitive Impairment(MCI)and Alzheimer’s Disease(AD).Alzheimer’s disease is the last phase of the disease where the brain is severely damaged,and the patients are not able to live on their own.Radiomics is an approach to extracting a huge number of features from medical images with the help of data characterization algorithms.Here,105 number of radiomic features are extracted and used to predict the alzhimer’s.This paper uses Support Vector Machine,K-Nearest Neighbour,Gaussian Naïve Bayes,eXtreme Gradient Boosting(XGBoost)and Random Forest to predict Alzheimer’s disease.The proposed random forest-based approach with the Radiomic features achieved an accuracy of 85%.This proposed approach also achieved 88%accuracy,88%recall,88%precision and 87%F1-score for AD vs.CN,it achieved 72%accuracy,73%recall,72%precisionand 71%F1-score for AD vs.MCI and it achieved 69%accuracy,69%recall,68%precision and 69%F1-score for MCI vs.CN.The comparative analysis shows that the proposed approach performs better than others approaches.

基于机器学习的“一带一路”投资国别风险预测研究

“一带一路”倡议提出十年间,中国对沿线国家的投资规模持续扩大。然而,企业在抓住机遇,进行“一带一路”沿线国家投资的同时,也需要重点关注“一带一路”投资国别风险。本文从政治、经济、社会和对华关系4个维度构建“一带一路”投资国别风险预测指标体系;运用灰色关联分析计算样本国家的综合风险评价值;基于2012~2022年间“一带一路”沿线国家的数据,利用机器学习构建GA-BP神经网络、支持向量回归和随机森林3种预测模型;通过对比预测精度,确定最佳预测模型,利用2021年的指标数据,对2022年的投资国别风险进行预测。研究结果表明:(1)在“一带一路”投资国别风险的研究背景下,支持向量回归模型预测效果最优,证明机器学习模型能够有效应用于风险管理领域;(2)“一带一路”投资国别风险存在明显的地区差异,中东欧地区和东南亚地区投资国别风险普遍较低,而南亚地区投资国别风险普遍较高,但都存在特例。本文研究结果可为“走出去”企业在“一带一路”沿线国家的投资决策提供参考。

基于多查询的社交网络关键节点挖掘算法

关键节点挖掘是复杂网络领域的研究重点和热点。针对社交网络中关键嫌疑人挖掘问题,提出基于多查询的社交网络关键节点挖掘算法。该算法将已知嫌疑人作为查询节点,提取其所在的局部拓扑结构,并计算局部拓扑结构中非查询节点的关键程度,从中选择关键程度较高的节点进行推荐。针对现有方法中关键节点计算复杂度高、已知查询节点信息难以有效利用的问题,提出一个两阶段的基于多查询的社交网络关键节点挖掘算法,整合多查询节点的局部拓扑信息和全局节点聚合特征信息,将计算范围从全局缩减到局部,进而对相关节点的关键程度进行量化。具体而言,利用带重启策略的随机游走算法获得多个查询节点的局部拓扑结构;为了得到节点的嵌入向量,基于graphsage模型构建一种无监督的图神经网络模型,该模型结合节点的自身特征和邻居聚合特征来生成嵌入向量,从而为算法框架的相似度计算提供信息输入。基于与查询节点特征的相似性,衡量局部拓扑中节点的关键程度。实验结果显示,所提算法在时间效率和结果有效性方面均优于传统关键节点挖掘算法。

基于星载激光雷达数据的森林地上生物量估算方法比较

近年来,星载激光雷达数据已被广泛用于大尺度森林地上生物量估计,但由于其激光光斑采样点不连续,通常使其需要与辅助数据相结合来估算森林地上生物量的连续分布,且估算方法仍存在许多不确定性。研究以祁连山国家公园为样本,结合星载激光雷达ICESat/GLAS数据、Landsat OLI数据和样地调查数据建立了3种基于非参数化算法(普通克里金插值(Ordinary Kriging,OK),支持向量回归(Support Vector regression,SVR)和随机森林(Random forest,RF))的森林地上生物量估算模型,以森林资源清查数据独立验证各模型估计精度。结果发现:3种模型的均方根误差(RMSE)从低到高依次为SVR(19.053 t·hm^(-2))、RF(21.074 t·hm^(-2))和OK(26.362 t·hm^(-2)),平均相对误差(MRE)从低到高依次为SVR(31.890%)、RF(33.314%)和OK(55.398%),且除OK模型外,SVR与RF模型的总体相对误差(TRE)都在可接受的范围内。进一步对SVR与RF模型生成的森林地上生物量空间分布的准确性进行验证,发现相较RF模型,SVR模型生成的森林地上生物量空间分布与森林资源清查数据更为接近。SVR森林地上生物量估计模型在数量精度和分布精度上都表现更优。结果可为今后基于星载激光雷达数据的森林地上生物量估算提供借鉴。

基于图像处理的水培生菜冠层图像叶面积估测研究

为实现精准、高效、无损地获取植物工厂环境下水培生菜相关长势参数叶面积(Leaf area,LA),基于数字图像处理和机器学习回归方法建立单株水培生菜冠层图像LA估测模型。首先,通过智能手机获取2个生菜品种不同生长期的冠层可见光图像,利用Photoshop图像处理软件将原始图像统一剪裁为900像素×900像素大小,采用中值滤波(MedianBlur)法对剪裁后的图像进行去噪运算,将RGB图像转化为HSV颜色空间,再采用mask掩膜法分割彩色图像;然后,利用图像法获取单株生菜LA实测值,构建以LA实测值为因变量,以生菜冠层投影面积(Projected leaf area,PLA)为自变量的线性回归(Linear regression,LR)模型和以全局图像特征(颜色、形状、纹理等)为自变量的支持向量回归(Support vector regression,SVR)、多元线性回归(Multiple linear regression,MLR)和随机森林(Random forest,RF)等LA估测模型进行对比分析;最后,采用决定系数(Coefficient of determination,R^(2))和均方根误差(Root mean square error,RMSE)评估模型的准确性。结果表明:RF模型估测效果最好,对于生菜品种‘绿萝’单株LA估测结果的R^(2)为0.9714、RMSE为8.89 cm2,对于品种‘碧霄’估测结果的R^(2)为0.9201、RMSE为23.34 cm2。本研究验证了RF回归模型能够较准确地估测生菜单株叶面积,可为植物工厂水培生菜LA无损估测提供新的解决方案和研究基础。

三种机器学习模型用于空气质量等级预测的比较研究——以保定市为例

目的 利用支持向量机(support vector machine, SVM)、随机森林(random forest, RF)和多层感知器(multilayer perceptron, MLP)三种机器学习方法分别构建保定市未来三日空气质量等级预测模型,通过对参数调优和预测结果比较选择三种模型中的最佳模型。方法 基于保定市2014—2022年的空气污染物日均浓度监测数据和同期气象数据,采用SVM、RF和MLP三种机器学习模型,利用前四日数据为未来三日分别构建了每日的空气质量等级预测模型并评估特征变量的重要性。对模型参数进行调优,采取十折交叉验证法进行验证,通过准确率和AUC等指标来评估模型性能。结果 SVM模型未来三日准确率分别为69.8%、63.5%、62.3%,AUC分别为77.4、70.8、70.7;RF模型未来三日准确率分别为75.9%、68.2%、67.1%,AUC分别为0.84、0.74、0.72;MLP模型未来三日准确率分别为73.2%、66.4%、65.7%,AUC为0.83、0.74、0.73,综合对比RF模型表现最优;空气质量特征变量重要性高于气象因素特征变量。结论 通过对比研究,RF机器学习模型能够相对有效地预测未来一日空气污染等级,并提供空气质量等级预警。

基于GEE的中国不同生态系统林火驱动力研究

针对同时对大尺度范围内的不同生态系统林火驱动力研究的难题,提出一种基于谷歌地球引擎(google earth engine,GEE)实现大范围不同生态系统林火驱动力的分析方法。首先基于GEE在线获取中国4个主要不同生态系统林火数据集、Sentinel-2卫星影像和驱动因子等信息,再通过Sentinel-2影像提取的归一化燃烧率差值筛选真实林火点,然后利用随机森林、支持向量机和增强回归树法对林火点分类并评价其表现,最后筛选最佳方法进行林火驱动力重要性分析。研究结果表明:随机森林预测林火的精度最高,均超过92%;山西省长治市和内蒙古大兴安岭地区林火最重要的驱动力分别为人口分布和最高温度,而四川省凉山彝族自治州和江西省赣州市林火发生最重要的两个驱动因子均为帕默尔干旱指数和土壤湿度。研究证明基于GEE的方法可有效地同时实现大范围内中国不同生态系统林火驱动力研究。

基于RF-SFLA-SVM的装配式建筑高空作业工人不安全行为预警

为有效预警装配式建筑高空作业工人不安全行为的发生趋势或状态,增强对装配式建筑工人不安全行为(PBWUBs)的管控,采用随机森林(RF)-混合蛙跳算法(SFLA)-支持向量机(SVM)模型,开展工人不安全行为预警研究。首先,采用SHEL模型分析处于高空作业危险中的PBWUBs的影响因素,并通过RF确定关键预警指标;然后,采用SFLA对SVM的参数进行寻优改进;最后,利用RF-SFLA-SVM预警高空作业PBWUBs,提出应对措施,并与其他预警模型对比。研究结果表明:基于RF-SFLA-SVM预警高空作业PBWUBs,准确率最高,为91.67%,与其他模型的预警性能相比,最高提升14%。研究结果可为高空作业PBWUBs的防控提供参考。

基于ERF和BO-SVC的交流接触器触头故障识别方法

针对交流接触器各状态样本不均衡导致故障状态识别精度低和特征冗余度高的问题,文中提出一种基于嵌入式随机森林(embedded random forest,ERF)和贝叶斯优化非线性支持向量机(Bayesian optimization-support vector classification,BO-SVC)的复合识别方法。首先,通过交流接触器全寿命试验平台提取接触器状态特征,并针对各状态样本间不均衡导致识别精度低现象,提出一种基于权重法的样本均衡处理策略。然后,使用ERF对均衡后样本进行特征选择和降维,提取最能表征触头状态变化规律的最优特征。最后,将最优特征输入到BO-SVC识别模型,与另外2种代表性模型作为对比,以精确率、召回率和F1-分数3个指标对各模型性能进行评估。在3个指标上,文中方法的结果分别达到95.22%、98.91%和97.01%,均高于对比模型。以F1-分数为指标,在4组样本上对各模型性能进行测试,结果表明文中方法的F1-分数平均高出对比模型0.56%和27.28%,验证文中研究有效解决了交流接触器特征冗余和故障识别精度低的问题。

基于小波压缩深度学习重构的多图像光学加密

为解决多图像加密算法密文体积大、加密效果差、重构效果不理想等问题,提出一种基于小波压缩和深度学习重构的多图像光学加密方法。利用小波压缩提取多图像的低频部分,将重排后的新图放入改进的FDT-DRPE光学加密系统中得到密文;利用矢量分解和螺旋相位变换克服FDT-DRPE不敏感问题;构造的L_S混沌系统提高密钥敏感性。提出新型深度学习网络模型BHCN,解决传统图像重构精度不高问题。实验结果表明,密文体积可压缩至原图的1/4,重构图像的峰值信噪比为34.57 dB,结构相似性为0.9521,与同类文献相比,速度更快,重构效果更好,安全性更高。

基于随机森林和支持向量机的Mo-Nb合金本构模型

在变形温度为900~1200℃、应变速率为0.01~10 s^(-1)条件下,采用Gleeble-3800型热模拟试验机对Mo-Nb合金进行等温恒应变速率压缩实验,研究Mo-Nb合金的流动应力行为,并采用随机森林和支持向量机的方法建立该合金的本构关系模型。结果表明:Mo-Nb合金是负温度和正应变速率敏感型材料,其流动应力随变形温度升高和应变速率降低而减小;随机森林和支持向量机本构关系模型的训练样本的相关系数和平均相对误差分别为0.989、0.998及2.41%、0.94%,测试样本的相关系数和平均相对误差分别为0.991、0.996及2.47%、1.4%,二者都具有较好的预测能力;支持向量机本构关系模型精度高于随机森林,因此,支持向量机本构关系模型更适于预测Mo-Nb合金的流动应力。