Performance evaluation of seven multi-label classification methods on real-world patent and publication datasets

Purpose:Many science,technology and innovation(STI)resources are attached with several different labels.To assign automatically the resulting labels to an interested instance,many approaches with good performance on the benchmark datasets have been proposed for multi-label classification task in the literature.Furthermore,several open-source tools implementing these approaches have also been developed.However,the characteristics of real-world multi-label patent and publication datasets are not completely in line with those of benchmark ones.Therefore,the main purpose of this paper is to evaluate comprehensively seven multi-label classification methods on real-world datasets.Research limitations:Three real-world datasets differ in the following aspects:statement,data quality,and purposes.Additionally,open-source tools designed for multi-label classification also have intrinsic differences in their approaches for data processing and feature selection,which in turn impacts the performance of a multi-label classification approach.In the near future,we will enhance experimental precision and reinforce the validity of conclusions by employing more rigorous control over variables through introducing expanded parameter settings.Practical implications:The observed Macro F1 and Micro F1 scores on real-world datasets typically fall short of those achieved on benchmark datasets,underscoring the complexity of real-world multi-label classification tasks.Approaches leveraging deep learning techniques offer promising solutions by accommodating the hierarchical relationships and interdependencies among labels.With ongoing enhancements in deep learning algorithms and large-scale models,it is expected that the efficacy of multi-label classification tasks will be significantly improved,reaching a level of practical utility in the foreseeable future.Originality/value:(1)Seven multi-label classification methods are comprehensively compared on three real-world datasets.(2)The TextCNN and TextRCNN models perform better on small-scale datasets with more complex hierarchical structure of labels and more balanced document-label distribution.(3)The MLkNN method works better on the larger-scale dataset with more unbalanced document-label distribution.

Study on Multi-Label Classification of Medical Dispute Documents

The Internet of Medical Things(IoMT)will come to be of great importance in the mediation of medical disputes,as it is emerging as the core of intelligent medical treatment.First,IoMT can track the entire medical treatment process in order to provide detailed trace data in medical dispute resolution.Second,IoMT can infiltrate the ongoing treatment and provide timely intelligent decision support to medical staff.This information includes recommendation of similar historical cases,guidance for medical treatment,alerting of hired dispute profiteers etc.The multi-label classification of medical dispute documents(MDDs)plays an important role as a front-end process for intelligent decision support,especially in the recommendation of similar historical cases.However,MDDs usually appear as long texts containing a large amount of redundant information,and there is a serious distribution imbalance in the dataset,which directly leads to weaker classification performance.Accordingly,in this paper,a multi-label classification method based on key sentence extraction is proposed for MDDs.The method is divided into two parts.First,the attention-based hierarchical bi-directional long short-term memory(BiLSTM)model is used to extract key sentences from documents;second,random comprehensive sampling Bagging(RCS-Bagging),which is an ensemble multi-label classification model,is employed to classify MDDs based on key sentence sets.The use of this approach greatly improves the classification performance.Experiments show that the performance of the two models proposed in this paper is remarkably better than that of the baseline methods.

A Multi-Label Classification Method for Vehicle Video

In the last few years,smartphone usage and driver sleepiness have been unanimously considered to lead to numerous road accidents,which causes many scholars to pay attention to autonomous driving.For this complexity scene,one of the major challenges is mining information comprehensively from massive features in vehicle video.This paper proposes a multi-label classification method MCM-VV(Multi-label Classification Method for Vehicle Video)for vehicle video to judge the label of road condition for unmanned system.Method MCM-VV includes a process of feature extraction and a process of multi-label classification.During feature extraction,grayscale,lane line and the edge of main object are extracted after video preprocessing.During the multi-label classification,the algorithm DR-ML-KNN(Multi-label K-nearest Neighbor Classification Algorithm based on Dimensionality Reduction)learns the training set to obtain multi-label classifier,then predicts the label of road condition according to maximum a posteriori principle,finally outputs labels and adds the new instance to training set for the optimization of classifier.Experimental results on five vehicle video datasets show that the method MCM-VV is effective and efficient.The DR-ML-KNN algorithm reduces the runtime by 50%.It also reduces the time complexity and improves the accuracy.

Feature Selection for Multi-label Classification Using Neighborhood Preservation

Multi-label learning deals with data associated with a set of labels simultaneously. Dimensionality reduction is an important but challenging task in multi-label learning. Feature selection is an efficient technique for dimensionality reduction to search an optimal feature subset preserving the most relevant information. In this paper, we propose an effective feature evaluation criterion for multi-label feature selection, called neighborhood relationship preserving score. This criterion is inspired by similarity preservation, which is widely used in single-label feature selection. It evaluates each feature subset by measuring its capability in preserving neighborhood relationship among samples. Unlike similarity preservation, we address the order of sample similarities which can well express the neighborhood relationship among samples, not just the pairwise sample similarity. With this criterion, we also design one ranking algorithm and one greedy algorithm for feature selection problem. The proposed algorithms are validated in six publicly available data sets from machine learning repository. Experimental results demonstrate their superiorities over the compared state-of-the-art methods.

Coupled Attribute Similarity Learning on Categorical Data for Multi-Label Classification

In this paper a novel coupled attribute similarity learning method is proposed with the basis on the multi-label categorical data（CASonMLCD）.The CASonMLCD method not only computes the correlations between different attributes and multi-label sets using information gain,which can be regarded as the important degree of each attribute in the attribute learning method,but also further analyzes the intra-coupled and inter-coupled interactions between an attribute value pair for different attributes and multiple labels.The paper compared the CASonMLCD method with the OF distance and Jaccard similarity,which is based on the MLKNN algorithm according to 5common evaluation criteria.The experiment results demonstrated that the CASonMLCD method can mine the similarity relationship more accurately and comprehensively,it can obtain better performance than compared methods.

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.

Classification research of TCM pulse conditions based on multi-label voice analysis

Objective To explore the feasibility of remotely obtaining complex information on traditional Chinese medicine(TCM)pulse conditions through voice signals.Methods We used multi-label pulse conditions as the entry point and modeled and analyzed TCM pulse diagnosis by combining voice analysis and machine learning.Audio features were extracted from voice recordings in the TCM pulse condition dataset.The obtained features were combined with information from tongue and facial diagnoses.A multi-label pulse condition voice classification DNN model was built using 10-fold cross-validation,and the modeling methods were validated using publicly available datasets.Results The analysis showed that the proposed method achieved an accuracy of 92.59%on the public dataset.The accuracies of the three single-label pulse manifestation models in the test set were 94.27%,96.35%,and 95.39%.The absolute accuracy of the multi-label model was 92.74%.Conclusion Voice data analysis may serve as a remote adjunct to the TCM diagnostic method for pulse condition assessment.

Inverse design of nonlinear phononic crystal configurations based on multi-label classification learning neural networks

Phononic crystals,as artificial composite materials,have sparked significant interest due to their novel characteristics that emerge upon the introduction of nonlinearity.Among these properties,second-harmonic features exhibit potential applications in acoustic frequency conversion,non-reciprocal wave propagation,and non-destructive testing.Precisely manipulating the harmonic band structure presents a major challenge in the design of nonlinear phononic crystals.Traditional design approaches based on parameter adjustments to meet specific application requirements are inefficient and often yield suboptimal performance.Therefore,this paper develops a design methodology using Softmax logistic regression and multi-label classification learning to inversely design the material distribution of nonlinear phononic crystals by exploiting information from harmonic transmission spectra.The results demonstrate that the neural network-based inverse design method can effectively tailor nonlinear phononic crystals with desired functionalities.This work establishes a mapping relationship between the band structure and the material distribution within phononic crystals,providing valuable insights into the inverse design of metamaterials.

Multi-Label Image Classification Based on Object Detection and Dynamic Graph Convolutional Networks

Multi-label image classification is recognized as an important task within the field of computer vision,a discipline that has experienced a significant escalation in research endeavors in recent years.The widespread adoption of convolutional neural networks(CNNs)has catalyzed the remarkable success of architectures such as ResNet-101 within the domain of image classification.However,inmulti-label image classification tasks,it is crucial to consider the correlation between labels.In order to improve the accuracy and performance of multi-label classification and fully combine visual and semantic features,many existing studies use graph convolutional networks(GCN)for modeling.Object detection and multi-label image classification exhibit a degree of conceptual overlap;however,the integration of these two tasks within a unified framework has been relatively underexplored in the existing literature.In this paper,we come up with Object-GCN framework,a model combining object detection network YOLOv5 and graph convolutional network,and we carry out a thorough experimental analysis using a range of well-established public datasets.The designed framework Object-GCN achieves significantly better performance than existing studies in public datasets COCO2014,VOC2007,VOC2012.The final results achieved are 86.9%,96.7%,and 96.3%mean Average Precision(mAP)across the three datasets.

Point Cloud Classification Using Content-Based Transformer via Clustering in Feature Space

Recently, there have been some attempts of Transformer in 3D point cloud classification. In order to reduce computations, most existing methods focus on local spatial attention,but ignore their content and fail to establish relationships between distant but relevant points. To overcome the limitation of local spatial attention, we propose a point content-based Transformer architecture, called PointConT for short. It exploits the locality of points in the feature space(content-based), which clusters the sampled points with similar features into the same class and computes the self-attention within each class, thus enabling an effective trade-off between capturing long-range dependencies and computational complexity. We further introduce an inception feature aggregator for point cloud classification, which uses parallel structures to aggregate high-frequency and low-frequency information in each branch separately. Extensive experiments show that our PointConT model achieves a remarkable performance on point cloud shape classification. Especially, our method exhibits 90.3% Top-1 accuracy on the hardest setting of ScanObjectN N. Source code of this paper is available at https://github.com/yahuiliu99/PointC onT.

Intrahepatic portal venous systems in adult patients with cavernous transformation of portal vein: Imaging features and a new classification

Background: Cavernous transformation of the portal vein(CTPV) due to portal vein obstruction is a rare vascular anomaly defined as the formation of multiple collateral vessels in the hepatic hilum. This study aimed to investigate the imaging features of intrahepatic portal vein in adult patients with CTPV and establish the relationship between the manifestations of intrahepatic portal vein and the progression of CTPV. Methods: We retrospectively analyzed 14 CTPV patients in Beijing Tsinghua Changgung Hospital. All patients underwent both direct portal venography(DPV) and computed tomography angiography(CTA) to reveal the manifestations of the portal venous system. The vessels measured included the left portal vein(LPV), right portal vein(RPV), main portal vein(MPV) and the portal vein bifurcation(PVB). Results: Nine males and 5 females, with a median age of 40.5 years, were included in the study. No significant difference was found in the diameters of the LPV or RPV measured by DPV and CTA. The visualization in terms of LPV, RPV and PVB measured by DPV was higher than that by CTA. There was a significant association between LPV/RPV and PVB/MPV in term of visibility revealed with DPV( P = 0.01), while this association was not observed with CTA. According to the imaging features of the portal vein measured by DPV, CTPV was classified into three categories to facilitate the diagnosis and treatment. Conclusions: DPV was more accurate than CTA for revealing the course of the intrahepatic portal vein in patients with CTPV. The classification of CTPV, that originated from the imaging features of the portal vein revealed by DPV, may provide a new perspective for the diagnosis and treatment of CTPV.

A Novel Framework for Learning and Classifying the Imbalanced Multi-Label Data

A generalization of supervised single-label learning based on the assumption that each sample in a dataset may belong to more than one class simultaneously is called multi-label learning.The main objective of this work is to create a novel framework for learning and classifying imbalancedmulti-label data.This work proposes a framework of two phases.The imbalanced distribution of themulti-label dataset is addressed through the proposed Borderline MLSMOTE resampling method in phase 1.Later,an adaptive weighted l21 norm regularized(Elastic-net)multilabel logistic regression is used to predict unseen samples in phase 2.The proposed Borderline MLSMOTE resampling method focuses on samples with concurrent high labels in contrast to conventional MLSMOTE.The minority labels in these samples are called difficult minority labels and are more prone to penalize classification performance.The concurrentmeasure is considered borderline,and labels associated with samples are regarded as borderline labels in the decision boundary.In phase II,a novel adaptive l21 norm regularized weighted multi-label logistic regression is used to handle balanced data with different weighted synthetic samples.Experimentation on various benchmark datasets shows the outperformance of the proposed method and its powerful predictive performances over existing conventional state-of-the-art multi-label methods.

Classification of Sailboat Tell Tail Based on Deep Learning

The tell tail is usually placed on the triangular sail to display the running state of the air flow on the sail surface.It is of great significance to make accurate judgement on the drift of the tell tail of the sailboat during sailing for the best sailing effect.Normally it is difficult for sailors to keep an eye for a long time on the tell sail for accurate judging its changes,affected by strong sunlight and visual fatigue.In this case,we adopt computer vision technology in hope of helping the sailors judge the changes of the tell tail in ease with ease.This paper proposes for the first time a method to classify sailboat tell tails based on deep learning and an expert guidance system,supported by a sailboat tell tail classification data set on the expert guidance system of interpreting the tell tails states in different sea wind conditions,including the feature extraction performance.Considering the expression capabilities that vary with the computational features in different visual tasks,the paper focuses on five tell tail computing features,which are recoded by an automatic encoder and classified by a SVM classifier.All experimental samples were randomly divided into five groups,and four groups were selected from each group as the training set to train the classifier.The remaining one group was used as the test set for testing.The highest resolution value of the ResNet network was 80.26%.To achieve better operational results on the basis of deep computing features obtained through the ResNet network in the experiments.The method can be used to assist the sailors in making better judgement about the tell tail changes during sailing.

Empowering Diagnosis: Cutting-Edge Segmentation and Classification in Lung Cancer Analysis

Lung cancer is a leading cause of global mortality rates.Early detection of pulmonary tumors can significantly enhance the survival rate of patients.Recently,various Computer-Aided Diagnostic(CAD)methods have been developed to enhance the detection of pulmonary nodules with high accuracy.Nevertheless,the existing method-ologies cannot obtain a high level of specificity and sensitivity.The present study introduces a novel model for Lung Cancer Segmentation and Classification(LCSC),which incorporates two improved architectures,namely the improved U-Net architecture and the improved AlexNet architecture.The LCSC model comprises two distinct stages.The first stage involves the utilization of an improved U-Net architecture to segment candidate nodules extracted from the lung lobes.Subsequently,an improved AlexNet architecture is employed to classify lung cancer.During the first stage,the proposed model demonstrates a dice accuracy of 0.855,a precision of 0.933,and a recall of 0.789 for the segmentation of candidate nodules.The suggested improved AlexNet architecture attains 97.06%accuracy,a true positive rate of 96.36%,a true negative rate of 97.77%,a positive predictive value of 97.74%,and a negative predictive value of 96.41%for classifying pulmonary cancer as either benign or malignant.The proposed LCSC model is tested and evaluated employing the publically available dataset furnished by the Lung Image Database Consortium and Image Database Resource Initiative(LIDC-IDRI).This proposed technique exhibits remarkable performance compared to the existing methods by using various evaluation parameters.

Comprehensive understanding of glioblastoma molecular phenotypes:classification,characteristics,and transition

Among central nervous system-associated malignancies,glioblastoma(GBM)is the most common and has the highest mortality rate.The high heterogeneity of GBM cell types and the complex tumor microenvironment frequently lead to tumor recurrence and sudden relapse in patients treated with temozolomide.In precision medicine,research on GBM treatment is increasingly focusing on molecular subtyping to precisely characterize the cellular and molecular heterogeneity,as well as the refractory nature of GBM toward therapy.Deep understanding of the different molecular expression patterns of GBM subtypes is critical.Researchers have recently proposed tetra fractional or tripartite methods for detecting GBM molecular subtypes.The various molecular subtypes of GBM show significant differences in gene expression patterns and biological behaviors.These subtypes also exhibit high plasticity in their regulatory pathways,oncogene expression,tumor microenvironment alterations,and differential responses to standard therapy.Herein,we summarize the current molecular typing scheme of GBM and the major molecular/genetic characteristics of each subtype.Furthermore,we review the mesenchymal transition mechanisms of GBM under various regulators.

Curve Classification Based onMean-Variance Feature Weighting and Its Application

The classification of functional data has drawn much attention in recent years.The main challenge is representing infinite-dimensional functional data by finite-dimensional features while utilizing those features to achieve better classification accuracy.In this paper,we propose a mean-variance-based(MV)feature weighting method for classifying functional data or functional curves.In the feature extraction stage,each sample curve is approximated by B-splines to transfer features to the coefficients of the spline basis.After that,a feature weighting approach based on statistical principles is introduced by comprehensively considering the between-class differences and within-class variations of the coefficients.We also introduce a scaling parameter to adjust the gap between the weights of features.The new feature weighting approach can adaptively enhance noteworthy local features while mitigating the impact of confusing features.The algorithms for feature weighted K-nearest neighbor and support vector machine classifiers are both provided.Moreover,the new approach can be well integrated into existing functional data classifiers,such as the generalized functional linear model and functional linear discriminant analysis,resulting in a more accurate classification.The performance of the mean-variance-based classifiers is evaluated by simulation studies and real data.The results show that the newfeatureweighting approach significantly improves the classification accuracy for complex functional data.

A Robust Approach for Multi Classification-Based Intrusion Detection through Stacking Deep Learning Models

Intrusion detection is a predominant task that monitors and protects the network infrastructure.Therefore,many datasets have been published and investigated by researchers to analyze and understand the problem of intrusion prediction and detection.In particular,the Network Security Laboratory-Knowledge Discovery in Databases(NSL-KDD)is an extensively used benchmark dataset for evaluating intrusion detection systems(IDSs)as it incorporates various network traffic attacks.It is worth mentioning that a large number of studies have tackled the problem of intrusion detection using machine learning models,but the performance of these models often decreases when evaluated on new attacks.This has led to the utilization of deep learning techniques,which have showcased significant potential for processing large datasets and therefore improving detection accuracy.For that reason,this paper focuses on the role of stacking deep learning models,including convolution neural network(CNN)and deep neural network(DNN)for improving the intrusion detection rate of the NSL-KDD dataset.Each base model is trained on the NSL-KDD dataset to extract significant features.Once the base models have been trained,the stacking process proceeds to the second stage,where a simple meta-model has been trained on the predictions generated from the proposed base models.The combination of the predictions allows the meta-model to distinguish different classes of attacks and increase the detection rate.Our experimental evaluations using the NSL-KDD dataset have shown the efficacy of stacking deep learning models for intrusion detection.The performance of the ensemble of base models,combined with the meta-model,exceeds the performance of individual models.Our stacking model has attained an accuracy of 99%and an average F1-score of 93%for the multi-classification scenario.Besides,the training time of the proposed ensemble model is lower than the training time of benchmark techniques,demonstrating its efficiency and robustness.

Depression Intensity Classification from Tweets Using Fast Text Based Weighted Soft Voting Ensemble

Predicting depression intensity from microblogs and social media posts has numerous benefits and applications,including predicting early psychological disorders and stress in individuals or the general public.A major challenge in predicting depression using social media posts is that the existing studies do not focus on predicting the intensity of depression in social media texts but rather only perform the binary classification of depression and moreover noisy data makes it difficult to predict the true depression in the social media text.This study intends to begin by collecting relevant Tweets and generating a corpus of 210000 public tweets using Twitter public application programming interfaces(APIs).A strategy is devised to filter out only depression-related tweets by creating a list of relevant hashtags to reduce noise in the corpus.Furthermore,an algorithm is developed to annotate the data into three depression classes:‘Mild,’‘Moderate,’and‘Severe,’based on International Classification of Diseases-10(ICD-10)depression diagnostic criteria.Different baseline classifiers are applied to the annotated dataset to get a preliminary idea of classification performance on the corpus.Further FastText-based model is applied and fine-tuned with different preprocessing techniques and hyperparameter tuning to produce the tuned model,which significantly increases the depression classification performance to an 84%F1 score and 90%accuracy compared to baselines.Finally,a FastText-based weighted soft voting ensemble(WSVE)is proposed to boost the model’s performance by combining several other classifiers and assigning weights to individual models according to their individual performances.The proposed WSVE outperformed all baselines as well as FastText alone,with an F1 of 89%,5%higher than FastText alone,and an accuracy of 93%,3%higher than FastText alone.The proposed model better captures the contextual features of the relatively small sample class and aids in the detection of early depression intensity prediction from tweets with impactful performances.

Classification and rating of disintegrated dolomite strata for slope stability analysis

Although disintegrated dolomite,widely distributed across the globe,has conventionally been a focus of research in underground engineering,the issue of slope stability issues in disintegrated dolomite strata is gaining increasing prominence.This is primarily due to their unique properties,including low strength and loose structure.Current methods for evaluating slope stability,such as basic quality(BQ)and slope stability probability classification(SSPC),do not adequately account for the poor integrity and structural fragmentation characteristic of disintegrated dolomite.To address this challenge,an analysis of the applicability of the limit equilibrium method(LEM),BQ,and SSPC methods was conducted on eight disintegrated dolomite slopes located in Baoshan,Southwest China.However,conflicting results were obtained.Therefore,this paper introduces a novel method,SMRDDS,to provide rapid and accurate assessment of disintegrated dolomite slope stability.This method incorporates parameters such as disintegrated grade,joint state,groundwater conditions,and excavation methods.The findings reveal that six slopes exhibit stability,while two are considered partially unstable.Notably,the proposed method demonstrates a closer match with the actual conditions and is more time-efficient compared with the BQ and SSPC methods.However,due to the limited research on disintegrated dolomite slopes,the results of the SMRDDS method tend to be conservative as a safety precaution.In conclusion,the SMRDDS method can quickly evaluate the current situation of disintegrated dolomite slopes in the field.This contributes significantly to disaster risk reduction for disintegrated dolomite slopes.

Learning feature alignment and dual correlation for few‐shot image classification

Few‐shot image classification is the task of classifying novel classes using extremely limited labelled samples.To perform classification using the limited samples,one solution is to learn the feature alignment(FA)information between the labelled and unlabelled sample features.Most FA methods use the feature mean as the class prototype and calculate the correlation between prototype and unlabelled features to learn an alignment strategy.However,mean prototypes tend to degenerate informative features because spatial features at the same position may not be equally important for the final classification,leading to inaccurate correlation calculations.Therefore,the authors propose an effective intraclass FA strategy that aggregates semantically similar spatial features from an adaptive reference prototype in low‐dimensional feature space to obtain an informative prototype feature map for precise correlation computation.Moreover,a dual correlation module to learn the hard and soft correlations was developed by the authors.This module combines the correlation information between the prototype and unlabelled features in both the original and learnable feature spaces,aiming to produce a comprehensive cross‐correlation between the prototypes and unlabelled features.Using both FA and cross‐attention modules,our model can maintain informative class features and capture important shared features for classification.Experimental results on three few‐shot classification benchmarks show that the proposed method outperformed related methods and resulted in a 3%performance boost in the 1‐shot setting by inserting the proposed module into the related methods.