Purpose-Intelligent diagnosis of equipment faults can effectively avoid the shutdown caused by equipment faults and improve the safety of the equipment.At present,the diagnosis of various kinds of bearing fault inform...Purpose-Intelligent diagnosis of equipment faults can effectively avoid the shutdown caused by equipment faults and improve the safety of the equipment.At present,the diagnosis of various kinds of bearing fault information,such as the occurrence,location and degree of fault,can be carried out by machine learning and deep learning and realized through the multiclassification method.However,the multiclassification method is not perfect in distinguishing similar fault categories and visual representation of fault information.To improve the above shortcomings,an end-to-end fault multilabel classification model is proposed for bearing fault diagnosis.Design/methodology/approach-In this model,the labels of each bearing are binarized by using the binary relevance method.Then,the integrated convolutional neural network and gated recurrent unit(CNN-GRU)is employed to classify faults.Different from the general CNN networks,the CNN-GRU network adds multiple GRU layers after the convolutional layers and the pool layers.Findings-The Paderborn University bearing dataset is utilized to demonstrate the practicability of the model.The experimental results show that the average accuracy in test set is 99.7%,and the proposed network is better than multilayer perceptron and CNN in fault diagnosis of bearing,and the multilabel classification method is superior to the multiclassification method.Consequently,the model can intuitively classify faults with higher accuracy.Originality/value-The fault labels of each bearing are labeled according to the failure or not,the fault location,the damage mode and the damage degree,and then the binary value is obtained.The multilabel problem is transformed into a binary classification problem of each fault label by the binary relevance method,and the predicted probability value of each fault label is directly output in the output layer,which visually distinguishes different fault conditions.展开更多
针对现有的特征选择模型未涉及特征和标记集之间的相关度,造成分类精度偏低等情况,提出了基于ReliefF和最大相关最小冗余(maximum Relevance and Minimum Redundancy,mRMR)的多标记特征选择.首先,运用互信息计算每个标记和标记集之间的...针对现有的特征选择模型未涉及特征和标记集之间的相关度,造成分类精度偏低等情况,提出了基于ReliefF和最大相关最小冗余(maximum Relevance and Minimum Redundancy,mRMR)的多标记特征选择.首先,运用互信息计算每个标记和标记集之间的相关度,使用每项相关度占其相关度之和的比例设计了标记权重,由此构建了特征和标记集间的相关度,初选与标记集相关度高的特征;其次,计算对象在特征上的距离,构建了新的特征权值更新公式,基于标记权重改进多标记ReliefF模型.然后,基于互信息和标记权重构建了最大相关性,设计了最小冗余性及其新的最大相关最小冗余评价准则,并将其应用于多标记特征选择,进一步剔除冗余特征;最后,设计了一种基于ReliefF和最大相关最小冗余的多标记特征选择算法,有效提高了多标记分类性能.在8个多标记数据集上测试所提算法的平均分类精度、覆盖率、汉明损失、1错误率和排序损失,实验结果证明了该算法的有效性.展开更多
From the beginning,the process of research and its publication is an ever-growing phenomenon and with the emergence of web technologies,its growth rate is overwhelming.On a rough estimate,more than thirty thousand res...From the beginning,the process of research and its publication is an ever-growing phenomenon and with the emergence of web technologies,its growth rate is overwhelming.On a rough estimate,more than thirty thousand research journals have been issuing around four million papers annually on average.Search engines,indexing services,and digital libraries have been searching for such publications over the web.Nevertheless,getting the most relevant articles against the user requests is yet a fantasy.It is mainly because the articles are not appropriately indexed based on the hierarchies of granular subject classification.To overcome this issue,researchers are striving to investigate new techniques for the classification of the research articles especially,when the complete article text is not available(a case of nonopen access articles).The proposed study aims to investigate the multilabel classification over the available metadata in the best possible way and to assess,“to what extent metadata-based features can perform in contrast to content-based approaches.”In this regard,novel techniques for investigating multilabel classification have been proposed,developed,and evaluated on metadata such as the Title and Keywords of the articles.The proposed technique has been assessed for two diverse datasets,namely,from the Journal of universal computer science(J.UCS)and the benchmark dataset comprises of the articles published by the Association for computing machinery(ACM).The proposed technique yields encouraging results in contrast to the state-ofthe-art techniques in the literature.展开更多
基于临床表现的疾病预测模型是临床决策支持系统(Clinical Decision Support System,CDSS)的一个重要研究内容.现有临床决策支持系统往往将临床病例作为训练数据集,以临床表现的描述文字为特征,采用统计机器学习方法构建疾病预测模型.然...基于临床表现的疾病预测模型是临床决策支持系统(Clinical Decision Support System,CDSS)的一个重要研究内容.现有临床决策支持系统往往将临床病例作为训练数据集,以临床表现的描述文字为特征,采用统计机器学习方法构建疾病预测模型.然而,在医疗领域往往存在着样本数据集不均衡的问题,导致模型的预测效果降低.欠采样技术是目前解决样本不均衡问题的常用手段.其主要采用一定的方法从多数类样本中抽取部分样本,与少数类样本组成平衡数据集后再构建模型.现有的欠采样方法往往可以显著提高模型对少数类样本的召回率,然而其通常也会造成模型准确率的降低,从而限制了预测模型的整体提升效果.为此,该文提出了一种新的基于迭代提升欠采样的集成分类方法(Under-Sampling with Iteratively Boosting,USIB),该方法迭代地从多数类样本中进行欠抽样,构建多组弱分类器,并采用加权组合方式将这些弱分类器构成一个强分类器,从而提升样本不平衡条件下单种疾病预测效果.另外,医学病例样本数据集通常是多类别、多标签的,为此,该文将多个单种疾病的预测模型进行组合构成一个多标签疾病预测模型,以满足临床意义上的多病种以及并发症的诊断.为了进一步提升多标签预测模型的效果,该文设计了一种基于标签最大互信息生成树的标签选择方法(Labels Selection method based on Maximum Mutual Information Spanning Tree,LS-MMIST),该方法根据原始数据集的分布构建标签之间的最大互信息生成树,在每一次的样本预测阶段,借助树中疾病标签之间的关系确定最终的预测标签集合.实验方面,该文首先选择三种公开的不均衡二分类数据集和我们私有的四种稀有疾病的数据集,对该文提出的迭代提升欠采样方法进行性能评估.其次,分别对比了该文提出的多标签预测模型与现有的多标签预测技术在中医和西医两种多标签数据集上的预测性能.实验结果显示,相对于目前主流的八种欠采样以及两种集成采样技术,该文提出的迭代提升欠采样方法在各个不均衡二分类数据集上的F1值平均提升22.58%;与现有的各种多标签预测技术相比,该文提出的多标签预测方法在西医和中医数据集上正确率分别提升6.30%和12.43%,召回率分别提升4.33%和5.86%,F1值分别提升5.48%和11.16%.展开更多
Multitasking and multioutput neural networks models jointly learn related classification tasks from a shared structure.Hard parameters sharing is a multitasking approach that shares hidden layers between multiple task...Multitasking and multioutput neural networks models jointly learn related classification tasks from a shared structure.Hard parameters sharing is a multitasking approach that shares hidden layers between multiple taskspecific outputs.The output layers’weights are essential in transforming aggregated neurons outputs into tasks labels.This paper redirects the multioutput network research to prove that the ensemble of output layers prediction can improve network performance in classifying multi-label classification tasks.The network’s output layers initialized with different weights simulate multiple semi-independent classifiers that can make non-identical label sets predictions for the same instance.The ensemble of a multi-output neural network that learns to classify the same multi-label classification task per output layer can outperform an individual output layer neural network.We propose an ensemble strategy of output layers components in the multi-output neural network for multi-label classification(ENSOCOM).The baseline and proposed models are selected based on the size of the hidden layer and the number of output layers to evaluate the proposed method comprehensively.The ENSOCOM method improved the performance of the neural networks on five different multi-label datasets based on several evaluation metrics.The methods presented in this work can substitute the standard labels representation and predictions generation of any neural network.展开更多
基金supported by the Mountain and Sea Talents Project of Shandong University of Science and Technology(grant numbers:01040055230)the National Nature Science Foundation of Shandong Province of China(Grant No.ZR2018MEE024).
文摘Purpose-Intelligent diagnosis of equipment faults can effectively avoid the shutdown caused by equipment faults and improve the safety of the equipment.At present,the diagnosis of various kinds of bearing fault information,such as the occurrence,location and degree of fault,can be carried out by machine learning and deep learning and realized through the multiclassification method.However,the multiclassification method is not perfect in distinguishing similar fault categories and visual representation of fault information.To improve the above shortcomings,an end-to-end fault multilabel classification model is proposed for bearing fault diagnosis.Design/methodology/approach-In this model,the labels of each bearing are binarized by using the binary relevance method.Then,the integrated convolutional neural network and gated recurrent unit(CNN-GRU)is employed to classify faults.Different from the general CNN networks,the CNN-GRU network adds multiple GRU layers after the convolutional layers and the pool layers.Findings-The Paderborn University bearing dataset is utilized to demonstrate the practicability of the model.The experimental results show that the average accuracy in test set is 99.7%,and the proposed network is better than multilayer perceptron and CNN in fault diagnosis of bearing,and the multilabel classification method is superior to the multiclassification method.Consequently,the model can intuitively classify faults with higher accuracy.Originality/value-The fault labels of each bearing are labeled according to the failure or not,the fault location,the damage mode and the damage degree,and then the binary value is obtained.The multilabel problem is transformed into a binary classification problem of each fault label by the binary relevance method,and the predicted probability value of each fault label is directly output in the output layer,which visually distinguishes different fault conditions.
文摘针对现有的特征选择模型未涉及特征和标记集之间的相关度,造成分类精度偏低等情况,提出了基于ReliefF和最大相关最小冗余(maximum Relevance and Minimum Redundancy,mRMR)的多标记特征选择.首先,运用互信息计算每个标记和标记集之间的相关度,使用每项相关度占其相关度之和的比例设计了标记权重,由此构建了特征和标记集间的相关度,初选与标记集相关度高的特征;其次,计算对象在特征上的距离,构建了新的特征权值更新公式,基于标记权重改进多标记ReliefF模型.然后,基于互信息和标记权重构建了最大相关性,设计了最小冗余性及其新的最大相关最小冗余评价准则,并将其应用于多标记特征选择,进一步剔除冗余特征;最后,设计了一种基于ReliefF和最大相关最小冗余的多标记特征选择算法,有效提高了多标记分类性能.在8个多标记数据集上测试所提算法的平均分类精度、覆盖率、汉明损失、1错误率和排序损失,实验结果证明了该算法的有效性.
文摘From the beginning,the process of research and its publication is an ever-growing phenomenon and with the emergence of web technologies,its growth rate is overwhelming.On a rough estimate,more than thirty thousand research journals have been issuing around four million papers annually on average.Search engines,indexing services,and digital libraries have been searching for such publications over the web.Nevertheless,getting the most relevant articles against the user requests is yet a fantasy.It is mainly because the articles are not appropriately indexed based on the hierarchies of granular subject classification.To overcome this issue,researchers are striving to investigate new techniques for the classification of the research articles especially,when the complete article text is not available(a case of nonopen access articles).The proposed study aims to investigate the multilabel classification over the available metadata in the best possible way and to assess,“to what extent metadata-based features can perform in contrast to content-based approaches.”In this regard,novel techniques for investigating multilabel classification have been proposed,developed,and evaluated on metadata such as the Title and Keywords of the articles.The proposed technique has been assessed for two diverse datasets,namely,from the Journal of universal computer science(J.UCS)and the benchmark dataset comprises of the articles published by the Association for computing machinery(ACM).The proposed technique yields encouraging results in contrast to the state-ofthe-art techniques in the literature.
文摘目的研究使用En Vision多标记读板仪检测细胞内钙信号的可行性。方法分别用卡巴胆碱和凝血酶刺激LN229、SKN-MC细胞或者磷脂酶C抑制剂U73122预处理的LN229细胞,使用En Vision多标记读板仪检测细胞内钙信号强度的变化。结果卡巴胆碱诱导的LN229细胞内钙信号变化呈现浓度依赖性;卡巴胆碱和凝血酶诱导的细胞内钙信号变化趋势不同;凝血酶诱导的钙信号变化具有细胞特异性;U73122对凝血酶诱导的钙信号的抑制作用呈现剂量依赖性。结论 En Vision多标记读板仪作为细胞内钙信号检测仪器,具有快速、可重复性好和灵敏度高等优势,适用于钙信号相关的研究和小分子抑制剂的筛选等领域的工作。
文摘基于临床表现的疾病预测模型是临床决策支持系统(Clinical Decision Support System,CDSS)的一个重要研究内容.现有临床决策支持系统往往将临床病例作为训练数据集,以临床表现的描述文字为特征,采用统计机器学习方法构建疾病预测模型.然而,在医疗领域往往存在着样本数据集不均衡的问题,导致模型的预测效果降低.欠采样技术是目前解决样本不均衡问题的常用手段.其主要采用一定的方法从多数类样本中抽取部分样本,与少数类样本组成平衡数据集后再构建模型.现有的欠采样方法往往可以显著提高模型对少数类样本的召回率,然而其通常也会造成模型准确率的降低,从而限制了预测模型的整体提升效果.为此,该文提出了一种新的基于迭代提升欠采样的集成分类方法(Under-Sampling with Iteratively Boosting,USIB),该方法迭代地从多数类样本中进行欠抽样,构建多组弱分类器,并采用加权组合方式将这些弱分类器构成一个强分类器,从而提升样本不平衡条件下单种疾病预测效果.另外,医学病例样本数据集通常是多类别、多标签的,为此,该文将多个单种疾病的预测模型进行组合构成一个多标签疾病预测模型,以满足临床意义上的多病种以及并发症的诊断.为了进一步提升多标签预测模型的效果,该文设计了一种基于标签最大互信息生成树的标签选择方法(Labels Selection method based on Maximum Mutual Information Spanning Tree,LS-MMIST),该方法根据原始数据集的分布构建标签之间的最大互信息生成树,在每一次的样本预测阶段,借助树中疾病标签之间的关系确定最终的预测标签集合.实验方面,该文首先选择三种公开的不均衡二分类数据集和我们私有的四种稀有疾病的数据集,对该文提出的迭代提升欠采样方法进行性能评估.其次,分别对比了该文提出的多标签预测模型与现有的多标签预测技术在中医和西医两种多标签数据集上的预测性能.实验结果显示,相对于目前主流的八种欠采样以及两种集成采样技术,该文提出的迭代提升欠采样方法在各个不均衡二分类数据集上的F1值平均提升22.58%;与现有的各种多标签预测技术相比,该文提出的多标签预测方法在西医和中医数据集上正确率分别提升6.30%和12.43%,召回率分别提升4.33%和5.86%,F1值分别提升5.48%和11.16%.
基金The authors would like to thank the Deanship of Scientific Research at UmmAl-Qura University for supporting this work by Grant Code: (22UQU4340018DSR02).
文摘Multitasking and multioutput neural networks models jointly learn related classification tasks from a shared structure.Hard parameters sharing is a multitasking approach that shares hidden layers between multiple taskspecific outputs.The output layers’weights are essential in transforming aggregated neurons outputs into tasks labels.This paper redirects the multioutput network research to prove that the ensemble of output layers prediction can improve network performance in classifying multi-label classification tasks.The network’s output layers initialized with different weights simulate multiple semi-independent classifiers that can make non-identical label sets predictions for the same instance.The ensemble of a multi-output neural network that learns to classify the same multi-label classification task per output layer can outperform an individual output layer neural network.We propose an ensemble strategy of output layers components in the multi-output neural network for multi-label classification(ENSOCOM).The baseline and proposed models are selected based on the size of the hidden layer and the number of output layers to evaluate the proposed method comprehensively.The ENSOCOM method improved the performance of the neural networks on five different multi-label datasets based on several evaluation metrics.The methods presented in this work can substitute the standard labels representation and predictions generation of any neural network.
文摘Rakel(Random k-labelsets)算法从原始标签集中随机选择一部分标签子集,并且使用LP(Label Powerset)算法训练相应的多标签子分类器。由于随机选择标签的原因,导致LP子分类器预测性能不好。本文基于标签的共现关系选择成对标签来训练LP分类器,提出PwRakel(Pairwise Random k-labelsets)算法。该算法通过挖掘标签相关性扩展训练集,有效提高分类性能。实验结果表明,所提出的算法与Rakel算法以及其他算法对比,分类准确度更高。
