A Novel Metadata Based Multi-Label Document Classification Technique

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.

ENSOCOM: Ensemble of Multi-Output Neural Network’s Components for Multi-Label Classification

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.

The multilabel fault diagnosis model of bearing based on integrated convolutional neural network and gated recurrent unit

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.