基于k-fold交叉验证的代理模型序列采样方法

在代理模型序列采样框架下,针对现有研究中的不足之处,通过引入k-fold交叉验证计算样本的预测误差,并结合泰森多边形法和最大距离最小化准则,发展了一种适用于任意代理模型的k-fold CV-Voronoi自适应序列采样方法。相较于传统序列采样方法,本文方法具有计算简单和自适应性强等显著优势。通过数值算例和工程算例对比分析发现所提序列采样方法具有较高的近似精度和计算效率,此外,进一步讨论了k-fold交叉验证中k的不同取值对于代理模型精度的影响,总结出k的最优取值范围以供参考。

基于DnCNN 的侵彻过载时频去噪方法

目的提高从侵彻过载中准确估计刚体过载信号的能力。方法提出一种基于前馈去噪卷积神经网络(DnCNN)的侵彻过载时频去噪方法,该方法首先应用短时傅里叶变换(STFT)提取侵彻过载信号的时频图像,使DnCNN能够充分利用时频图像信息,估计出刚体过载时频图像。最后,通过逆STFT将时频图像转换回时域,得到估计的刚体过载信号。结果在5-Fold交叉验证中,所提方法在测试集上的平均绝对误差(MAE)为0.968%,Pearson相关系数(r)为90.35%。与低通滤波、总体经验模态分解(EEMD)和小波变换方法相比,所提方法的平均MAE分别降低了1.82%、1.00%、0.75%,平均相关系数r值分别提高了47.81%、17.48%、22.93%。结论所提方法可以从侵彻过载中准确估计出刚体过载信号,在去噪能力上优于低通滤波、EEMD和小波变换方法,且在去噪过程中,无需调整参数,能够自动完成去噪任务。

Prediction of geological characteristics from shield operational parameters by integrating grid search and K-fold cross validation into stacking classification algorithm

This study presents a framework for predicting geological characteristics based on integrating a stacking classification algorithm(SCA) with a grid search(GS) and K-fold cross validation(K-CV). The SCA includes two learner layers: a primary learner’s layer and meta-classifier layer. The accuracy of the SCA can be improved by using the GS and K-CV. The GS was developed to match the hyper-parameters and optimise complicated problems. The K-CV is commonly applied to changing the validation set in a training set. In general, a GS is usually combined with K-CV to produce a corresponding evaluation index and select the best hyper-parameters. The torque penetration index(TPI) and field penetration index(FPI) are proposed based on shield parameters to express the geological characteristics. The elbow method(EM) and silhouette coefficient(Si) are employed to determine the types of geological characteristics(K) in a Kmeans++ algorithm. A case study on mixed ground in Guangzhou is adopted to validate the applicability of the developed model. The results show that with the developed framework, the four selected parameters, i.e. thrust, advance rate, cutterhead rotation speed and cutterhead torque, can be used to effectively predict the corresponding geological characteristics.

The Distortion Theorems for k-fold Symmetric Quasi-convex Mappings along a Unit Direction in C^n

We obtain a distortion theorem of Jacobian matrix Jf（z） for k-fold symmetric quasi-convex f along a unit direction in C^n on the unit polydisc.

K-fold输入方式下的渝东北地区SPI指数干旱预测模型

文章基于丰都和万州2个站点,以支持向量机模型(SVM)为基础,采用粒子群算法(PSO)和遗传算法(GA)优化SVM模型,选用K-fold的参数输入方式,对渝东北地区SPI干旱指数进行了预测,得出了区域干旱预测的推荐模型。结果表明:不同模型对SPI指数的预测精度存在差异,其中PSO-SVM模型精度普遍优于其余模型,且考虑温度和日照时数的模型精度最优,在2个站点的GPI均排名第1,且泰勒图中与标准值最为接近。PSO-SVM模型可作为渝东北地区干旱预测的标准模型使用。

Performance Evaluation of Deep Dense Layer Neural Network for Diabetes Prediction

Diabetes is one of the fastest-growing human diseases worldwide and poses a significant threat to the population’s longer lives.Early prediction of diabetes is crucial to taking precautionary steps to avoid or delay its onset.In this study,we proposed a Deep Dense Layer Neural Network(DDLNN)for diabetes prediction using a dataset with 768 instances and nine variables.We also applied a combination of classical machine learning(ML)algorithms and ensemble learning algorithms for the effective prediction of the disease.The classical ML algorithms used were Support Vector Machine(SVM),Logistic Regression(LR),Decision Tree(DT),K-Nearest Neighbor(KNN),and Naïve Bayes(NB).We also constructed ensemble models such as bagging(Random Forest)and boosting like AdaBoost and Extreme Gradient Boosting(XGBoost)to evaluate the performance of prediction models.The proposed DDLNN model and ensemble learning models were trained and tested using hyperparameter tuning and K-Fold cross-validation to determine the best parameters for predicting the disease.The combined ML models used majority voting to select the best outcomes among the models.The efficacy of the proposed and other models was evaluated for effective diabetes prediction.The investigation concluded that the proposed model,after hyperparameter tuning,outperformed other learning models with an accuracy of 84.42%,a precision of 85.12%,a recall rate of 65.40%,and a specificity of 94.11%.

基于参数调优Xgboost算法的多余物信号检测技术

密封继电器在航空航天领域有着非常关键的作用,继电器内部的多余物严重影响着它的可靠性和稳定性。现在的密封继电器多余物检测技术大多采用微粒碰撞噪声检测法(PIND),这种传统的检测技术保障了航天系统的可靠性和稳定性,但对于密封继电器多余物信号判断的准确率只能达到75%。实验使用基于参数调优的Xgboost算法对检测信号进行分类,首先,通过对比多余物信号和组件信号的时域和频域波形提取出13个特征构建训练样本,然后通过网格搜索和k折交叉检验结合的方法,搜索出Xgboost树的最大深度和每棵树随机采样的最好比例,进行模型训练和模型调整。结果表明,基于参数调优的Xgboost算法在密封继电器多余物的判断上,准确率最高可以提升到90%,精确率和召回率等各项分类指标也有大幅度提升。

基于改进BP神经网络的变电站检修运维成本预测

变电站的检修运维成本受众多复杂因素影响,且检修费用数据记录具有模糊性和波动性。为解决检修费用记录不明的问题,首先对变电站检修条目划分并采用水平和垂直方向的数据分析方法进行处理,再利用BP神经网络预测检修运维成本。为提高BP神经网络预测精度,采用K-fold交叉验证对原始数据训练模型进行精准调整,应用遗传算法对BP神经网路的初始值和阀值进行调整和改进,从而建立基于遗传算法的改进BP神经网络检修运维成本预测方法。以某地市变电站为例进行变电检修运维成本预测,对比分析显示所提方法能有效提高模型预测精准度,从而为电网给变电站拨付检修费用提供参考价值。

分类器准确率评估的研究

由于机器学习中过度拟合问题的广泛存在,使得对分类器进行准确率评估显得十分重要。在对现有的两种评估方法—"k-fold交叉验证"和"随机子抽样"进行研究之后,设计出一种新的评估方法,旨在综合已有两种方法的优点,寻找一种更合理的评估方法,并以决策树构造的分类器进行验证。实验结果表明,在训练样本不多的情况下,新的评估方法应用到分类器的训练中,可有效地提高分类器的分类精度。

Prediction of undrained shear strength using extreme gradient boosting and random forest based on Bayesian optimization

Accurate assessment of undrained shear strength(USS)for soft sensitive clays is a great concern in geotechnical engineering practice.This study applies novel data-driven extreme gradient boosting(XGBoost)and random forest(RF)ensemble learning methods for capturing the relationships between the USS and various basic soil parameters.Based on the soil data sets from TC304 database,a general approach is developed to predict the USS of soft clays using the two machine learning methods above,where five feature variables including the preconsolidation stress(PS),vertical effective stress(VES),liquid limit(LL),plastic limit(PL)and natural water content(W)are adopted.To reduce the dependence on the rule of thumb and inefficient brute-force search,the Bayesian optimization method is applied to determine the appropriate model hyper-parameters of both XGBoost and RF.The developed models are comprehensively compared with three comparison machine learning methods and two transformation models with respect to predictive accuracy and robustness under 5-fold cross-validation(CV).It is shown that XGBoost-based and RF-based methods outperform these approaches.Besides,the XGBoostbased model provides feature importance ranks,which makes it a promising tool in the prediction of geotechnical parameters and enhances the interpretability of model.

X射线荧光光谱结合支持向量机对眼药水塑料瓶的分类研究

为建立一种快速、准确、无损的眼药水塑料瓶的分类方法,利用X射线荧光光谱,在电流为200μA、电压为50 kV、功率为10 W、测试时间为60 s的条件下,对33个不同厂家、不同品牌、不同批次的眼药水塑料瓶样品进行检验,根据人工分类与系统聚类的方法将33个样品分为4类后,分别采用一对一法构建多元分类器和K-fold交叉验证2种方法构建支持向量机模型,前者预测准确率为66.67%,后者预测准确率为84.8%。采用K-fold交叉验证的方法构建支持向量机,能够较为准确地鉴别未知眼药水塑料瓶的类别,该方法可为公安办案提供参考。

Brain Cancer Tumor Classification from Motion-Corrected MRI Images Using Convolutional Neural Network

Detection of brain tumors in MRI images is the first step in brain cancer diagnosis.The accuracy of the diagnosis depends highly on the expertise of radiologists.Therefore,automated diagnosis of brain cancer from MRI is receiving a large amount of attention.Also,MRI tumor detection is usually followed by a biopsy(an invasive procedure),which is a medical procedure for brain tumor classification.It is of high importance to devise automated methods to aid radiologists in brain cancer tumor diagnosis without resorting to invasive procedures.Convolutional neural network(CNN)is deemed to be one of the best machine learning algorithms to achieve high-accuracy results in tumor identification and classification.In this paper,a CNN-based technique for brain tumor classification has been developed.The proposed CNN can distinguish between normal(no-cancer),astrocytoma tumors,gliomatosis cerebri tumors,and glioblastoma tumors.The implemented CNN was tested on MRI images that underwent a motion-correction procedure.The CNN was evaluated using two performance measurement procedures.The first one is a k-fold cross-validation testing method,in which we tested the dataset using k=8,10,12,and 14.The best accuracy for this procedure was 96.26%when k=10.To overcome the over-fitting problem that could be occurred in the k-fold testing method,we used a hold-out testing method as a second evaluation procedure.The results of this procedure succeeded in attaining 97.8%accuracy,with a specificity of 99.2%and a sensitivity of 97.32%.With this high accuracy,the developed CNN architecture could be considered an effective automated diagnosis method for the classification of brain tumors from MRI images.

基于K-CV参数优化的SVR煤炭含碳量预测

煤炭的含碳量是衡量煤质的重要指标,传统的检测方法操作复杂、成本高,现有的预测模型精度有待进一步提高,为解决上述问题,提出一种基于K-fold Cross Validation(K-CV)参数优化的支持向量回归(SVR)预测模型。以煤炭质量检测中心提供的80组原始数据作为实验对象,选取其中的50组作为训练集,剩余的30组作为测试集。以训练集作为K-CV方法的样本数据寻找最优参数,以最优参数为基础建立SVR预测模型,并通过测试集对模型进行验证,结果表明含碳量预测的平均相对误差达到0.38%,该模型预测精度较高,具有良好的泛化性能。

Analyzing Some Elements of Technological Singularity Using Regression Methods

Technological advancement has contributed immensely to human life and society.Technologies like industrial robots,artificial intelligence,and machine learning are advancing at a rapid pace.While the evolution of Artificial Intelligence has contributed significantly to the development of personal assistants,automated drones,smart home devices,etc.,it has also raised questions about the much-anticipated point in the future where machines may develop intelligence that may be equal to or greater than humans,a term that is popularly known as Technological Singularity.Although technological singularity promises great benefits,past research works on Artificial Intelligence(AI)systems going rogue highlight the downside of Technological Singularity and assert that it may lead to catastrophic effects.Thus,there is a need to identify factors that contribute to technological advancement and may ultimately lead to Technological Singularity in the future.In this paper,we identify factors such as Number of scientific publications in Artificial Intelligence,Number of scientific publications in Machine Learning,Dynamic RAM(Random Access Memory)Price,Number of Transistors,and Speed of Computers’Processors,and analyze their effects on Technological Singularity using Regression methods(Multiple Linear Regression and Simple Linear Regression).The predictive ability of the models has been validated using PRESS and k-fold cross-validation.Our study shows that academic advancement in AI and ML and Dynamic RAM prices contribute significantly to Technological Singularity.Investigating the factors would help researchers and industry experts comprehend what leads to Technological Singularity and,if needed,how to prevent undesirable outcomes.

Artificial Neural Network-based prediction of glacial debris flows in the ParlungZangbo Basin, southeastern Tibetan Plateau,China

Accurate prediction on geological hazards can prevent disaster events in advance and greatly reduce property losses and life casualties.Glacial debris flows are the most serious hazards in southeastern Tibet in China due to their complexity in formation mechanism and the difficulty in prediction.Data collected from 102 glacier debris flow events from 31 gullies since 1970 and regional meteorological data from 1970 to 2019 in ParlungZangbo River Basin in southeastern Tibet were used for Artificial Neural Network(ANN)-based prediction of glacial debris flows.The formation mechanism of glacial debris flows in the ParlungZangbo Basin was systematically analyzed,and the calculations involving the meteorological data and disaster events were conducted by using the statistical methods and two layers fully connected neural networks.The occurrence probabilities and scales of glacial debris flows(small,medium,and large)were predicted,and promising results have been achieved.Through the proposed model calculations,a prediction accuracy of 78.33%was achieved for the scale of glacial debris flows in the study area.The prediction accuracy for both large-and medium-scale debris flows are higher than that for small-scale debris flows.The debris flow scale and the probability of occurrence increase with increasing rainfall and temperature.In addition,the K-fold cross-validation method was used to verify the reliability of the model.The average accuracy of the model calculated under this method is about 93.3%,which validates the proposed model.Practices have proved that the combination of ANN and disaster events can provide sound prediction on geological hazards under complex conditions.

Hydrodynamic Performance Analysis of a Submersible Surface Ship and Resistance Forecasting Based on BP Neural Networks

This paper investigated the resistance performance of a submersible surface ship(SSS)in different working cases and scales to analyze the hydrodynamic performance characteristics of an SSS at different speeds and diving depths for engineering applications.First,a hydrostatic resistance performance test of the SSS was carried out in a towing tank.Second,the scale effect of the hydrodynamic pressure coefficient and wave-making resistance was analyzed.The differences between the three-dimensional real-scale ship resistance prediction and numerical methods were explained.Finally,the advantages of genetic algorithm(GA)and neural network were combined to predict the resistance of SSS.Back propagation neural network(BPNN)and GA-BPNN were utilized to predict the SSS resistance.We also studied neural network parameter optimization,including connection weights and thresholds,using K-fold cross-validation.The results showed that when a SSS sails at low and medium speeds,the influence of various underwater cases on resistance is not obvious,while at high speeds,the resistance of water surface cases increases sharply with an increase in speed.After improving the weights and thresholds through K-fold cross-validation and GA,the prediction results of BPNN have high consistency with the actual values.The research results can provide a theoretical reference for the optimal design of the resistance of SSS in practical applications.

Stacking Learning在高光谱图像分类中的应用

高光谱图像分类研究中,集成学习能够显著地提高分类效果。但是传统的并行多分类系统对基础分类器有较高要求,即要求差异性及分类均衡。为了解决这一问题,采用Stacking Learning的堆栈式学习方式,首先使用K-Fold和交叉验证的方式进行数据分割和训练,将原始特征进行特征变换,重新构建二级特征。再使用新特征进行对Meta分类器进行训练得到判决分类器,用于样本的最后分类判断。实验结果表明,采用的Stacking Learning方法不依赖基础分类器,且相比较于传统的多分类系统具有更高的精度和良好的稳定性。

基于粒子群优化算法的LightGBM超短期负荷预测研究

针对当前超短期负荷预测模型的不足,提出了一种基于粒子群优化算法的LightGBM超短期负荷预测模型,实现了LightGBM模型参数的自适应调整,可针对不同时空下负荷的规律特点调整模型参数,提高了模型的可推广性。仿真结果表明,提出的模型能有效提高负荷预测的准确度。

Artificial intelligence model validation before its application in clinical diagnosis assistance

The process of selecting an artificial intelligence(AI)model to assist clinical diagnosis of a particular pathology and its validation tests is relevant since the values of accuracy,sensitivity and specificity may not reflect the behavior of the method in a real environment.Here,we provide helpful considerations to increase the success of using an AI model in clinical practice.

Classification and Diagnosis of Lymphoma’s Histopathological Images Using Transfer Learning

Current cancer diagnosis procedure requires expert knowledge and is time-consuming,which raises the need to build an accurate diagnosis support system for lymphoma identification and classification.Many studies have shown promising results using Machine Learning and,recently,Deep Learning to detect malignancy in cancer cells.However,the diversity and complexity of the morphological structure of lymphoma make it a challenging classification problem.In literature,many attempts were made to classify up to four simple types of lymphoma.This paper presents an approach using a reliable model capable of diagnosing seven different categories of rare and aggressive lymphoma.These Lymphoma types are Classical Hodgkin Lymphoma,Nodular Lymphoma Predominant,Burkitt Lymphoma,Follicular Lymphoma,Mantle Lymphoma,Large B-Cell Lymphoma,and T-Cell Lymphoma.Our proposed approach uses Residual Neural Networks,ResNet50,with a Transfer Learning for lymphoma’s detection and classification.The model used results are validated according to the performance evaluation metrics:Accuracy,precision,recall,F-score,and kappa score for the seven multi-classes.Our algorithms are tested,and the results are validated on 323 images of 224×224 pixels resolution.The results are promising and show that our used model can classify and predict the correct lymphoma subtype with an accuracy of 91.6%.