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.

BARN:Behavior-Aware Relation Network for multi-label behavior detection in socially housed macaques

Quantification of behaviors in macaques provides crucial support for various scientific disciplines,including pharmacology,neuroscience,and ethology.Despite recent advancements in the analysis of macaque behavior,research on multi-label behavior detection in socially housed macaques,including consideration of interactions among them,remains scarce.Given the lack of relevant approaches and datasets,we developed the Behavior-Aware Relation Network(BARN)for multi-label behavior detection of socially housed macaques.Our approach models the relationship of behavioral similarity between macaques,guided by a behavior-aware module and novel behavior classifier,which is suitable for multi-label classification.We also constructed a behavior dataset of rhesus macaques using ordinary RGB cameras mounted outside their cages.The dataset included 65?913 labels for19 behaviors and 60?367 proposals,including identities and locations of the macaques.Experimental results showed that BARN significantly improved the baseline SlowFast network and outperformed existing relation networks.In conclusion,we successfully achieved multilabel behavior detection of socially housed macaques with both economic efficiency and high accuracy.

Spatial Correlation Module for Classification of Multi-Label Ocular Diseases Using Color Fundus Images

To prevent irreversible damage to one’s eyesight,ocular diseases(ODs)need to be recognized and treated immediately.Color fundus imaging(CFI)is a screening technology that is both effective and economical.According to CFIs,the early stages of the disease are characterized by a paucity of observable symptoms,which necessitates the prompt creation of automated and robust diagnostic algorithms.The traditional research focuses on image-level diagnostics that attend to the left and right eyes in isolation without making use of pertinent correlation data between the two sets of eyes.In addition,they usually only target one or a few different kinds of eye diseases at the same time.In this study,we design a patient-level multi-label OD(PLML_ODs)classification model that is based on a spatial correlation network(SCNet).This model takes into consideration the relevance of patient-level diagnosis combining bilateral eyes and multi-label ODs classification.PLML_ODs is made up of three parts:a backbone convolutional neural network(CNN)for feature extraction i.e.,DenseNet-169,a SCNet for feature correlation,and a classifier for the development of classification scores.The DenseNet-169 is responsible for retrieving two separate sets of attributes,one from each of the left and right CFI.After then,the SCNet will record the correlations between the two feature sets on a pixel-by-pixel basis.After the attributes have been analyzed,they are integrated to provide a representation at the patient level.Throughout the whole process of ODs categorization,the patient-level representation will be used.The efficacy of the PLML_ODs is examined using a soft margin loss on a dataset that is readily accessible to the public,and the results reveal that the classification performance is significantly improved when compared to several baseline approaches.

Intelligent Traffic Surveillance through Multi-Label Semantic Segmentation and Filter-Based Tracking

Road congestion,air pollution,and accident rates have all increased as a result of rising traffic density andworldwide population growth.Over the past ten years,the total number of automobiles has increased significantly over the world.In this paper,a novel method for intelligent traffic surveillance is presented.The proposed model is based on multilabel semantic segmentation using a random forest classifier which classifies the images into five classes.To improve the results,mean-shift clustering was applied to the segmented images.Afterward,the pixels given the label for the vehicle were extracted and blob detection was applied to mark each vehicle.For the validation of each detection,a vehicle verification method based on the structural similarity index is proposed.The tracking of vehicles across the image frames is done using the Identifier(ID)assignment technique and particle filter.Also,vehicle counting in each frame along with trajectory estimation was done for each object.Our proposed system demonstrated a remarkable vehicle detection rate of 0.83 over Vehicle Aerial Imaging from Drone(VAID),0.86 over AU-AIR,and 0.75 over the Unmanned Aerial Vehicle Benchmark Object Detection and Tracking(UAVDT)dataset during the experimental evaluation.The proposed system can be used for several purposes,such as vehicle identification in traffic,traffic density estimation at intersections,and traffic congestion sensing on a road.

Gate-Attention and Dual-End Enhancement Mechanism for Multi-Label Text Classification

In the realm of Multi-Label Text Classification(MLTC),the dual challenges of extracting rich semantic features from text and discerning inter-label relationships have spurred innovative approaches.Many studies in semantic feature extraction have turned to external knowledge to augment the model’s grasp of textual content,often overlooking intrinsic textual cues such as label statistical features.In contrast,these endogenous insights naturally align with the classification task.In our paper,to complement this focus on intrinsic knowledge,we introduce a novel Gate-Attention mechanism.This mechanism adeptly integrates statistical features from the text itself into the semantic fabric,enhancing the model’s capacity to understand and represent the data.Additionally,to address the intricate task of mining label correlations,we propose a Dual-end enhancement mechanism.This mechanism effectively mitigates the challenges of information loss and erroneous transmission inherent in traditional long short term memory propagation.We conducted an extensive battery of experiments on the AAPD and RCV1-2 datasets.These experiments serve the dual purpose of confirming the efficacy of both the Gate-Attention mechanism and the Dual-end enhancement mechanism.Our final model unequivocally outperforms the baseline model,attesting to its robustness.These findings emphatically underscore the imperativeness of taking into account not just external knowledge but also the inherent intricacies of textual data when crafting potent MLTC models.

Multi-label dimensionality reduction and classification with extreme learning machines

In the need of some real applications, such as text categorization and image classification, the multi-label learning gradually becomes a hot research point in recent years. Much attention has been paid to the research of multi-label classification algorithms. Considering the fact that the high dimensionality of the multi-label datasets may cause the curse of dimensionality and wil hamper the classification process, a dimensionality reduction algorithm, named multi-label kernel discriminant analysis （MLKDA）, is proposed to reduce the dimensionality of multi-label datasets. MLKDA, with the kernel trick, processes the multi-label integrally and realizes the nonlinear dimensionality reduction with the idea similar with linear discriminant analysis （LDA）. In the classification process of multi-label data, the extreme learning machine （ELM） is an efficient algorithm in the premise of good accuracy. MLKDA, combined with ELM, shows a good performance in multi-label learning experiments with several datasets. The experiments on both static data and data stream show that MLKDA outperforms multi-label dimensionality reduction via dependence maximization （MDDM） and multi-label linear discriminant analysis （MLDA） in cases of balanced datasets and stronger correlation between tags, and ELM is also a good choice for multi-label classification.

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.

Radar emitter multi-label recognition based on residual network

In low signal-to-noise ratio(SNR)environments,the traditional radar emitter recognition(RER)method struggles to recognize multiple radar emitter signals in parallel.This paper proposes a multi-label classification and recognition method for multiple radar-emitter modulation types based on a residual network.This method can quickly perform parallel classification and recognition of multi-modulation radar time-domain aliasing signals under low SNRs.First,we perform time-frequency analysis on the received signal to extract the normalized time-frequency image through the short-time Fourier transform(STFT).The time-frequency distribution image is then denoised using a deep normalized convolutional neural network(DNCNN).Secondly,the multi-label classification and recognition model for multi-modulation radar emitter time-domain aliasing signals is established,and learning the characteristics of radar signal time-frequency distribution image dataset to achieve the purpose of training model.Finally,time-frequency image is recognized and classified through the model,thus completing the automatic classification and recognition of the time-domain aliasing signal.Simulation results show that the proposed method can classify and recognize radar emitter signals of different modulation types in parallel under low SNRs.

Multi-label learning algorithm with SVM based association

Multi-label learning is an active research area which plays an important role in machine learning. Traditional learning algorithms, however, have to depend on samples with complete labels. The existing learning algorithms with missing labels do not consider the relevance of labels, resulting in label estimation errors of new samples. A new multi-label learning algorithm with support vector machine(SVM) based association(SVMA) is proposed to estimate missing labels by constructing the association between different labels. SVMA will establish a mapping function to minimize the number of samples in the margin while ensuring the margin large enough as well as minimizing the misclassification probability. To evaluate the performance of SVMA in the condition of missing labels, four typical data sets are adopted with the integrity of the labels being handled manually. Simulation results show the superiority of SVMA in dealing with the samples with missing labels compared with other models in image classification.

Multi-Label Learning Based on Transfer Learning and Label Correlation

In recent years,multi-label learning has received a lot of attention.However,most of the existing methods only consider global label correlation or local label correlation.In fact,on the one hand,both global and local label correlations can appear in real-world situation at same time.On the other hand,we should not be limited to pairwise labels while ignoring the high-order label correlation.In this paper,we propose a novel and effective method called GLLCBN for multi-label learning.Firstly,we obtain the global label correlation by exploiting label semantic similarity.Then,we analyze the pairwise labels in the label space of the data set to acquire the local correlation.Next,we build the original version of the label dependency model by global and local label correlations.After that,we use graph theory,probability theory and Bayesian networks to eliminate redundant dependency structure in the initial version model,so as to get the optimal label dependent model.Finally,we obtain the feature extraction model by adjusting the Inception V3 model of convolution neural network and combine it with the GLLCBN model to achieve the multi-label learning.The experimental results show that our proposed model has better performance than other multi-label learning methods in performance evaluating.

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.

Novel Apriori-Based Multi-Label Learning Algorithm by Exploiting Coupled Label Relationship

It is a key challenge to exploit the label coupling relationship in multi-label classification（MLC）problems.Most previous work focused on label pairwise relations,in which generally only global statistical information is used to analyze the coupled label relationship.In this work,firstly Bayesian and hypothesis testing methods are applied to predict the label set size of testing samples within their k nearest neighbor samples,which combines global and local statistical information,and then apriori algorithm is used to mine the label coupling relationship among multiple labels rather than pairwise labels,which can exploit the label coupling relations more accurately and comprehensively.The experimental results on text,biology and audio datasets shown that,compared with the state-of-the-art algorithm,the proposed algorithm can obtain better performance on 5 common criteria.

Multi-Label Chinese Comments Categorization: Comparison of Multi-Label Learning Algorithms

Multi-label text categorization refers to the problem of categorizing text througha multi-label learning algorithm. Text classification for Asian languages such as Chinese isdifferent from work for other languages such as English which use spaces to separate words.Before classifying text, it is necessary to perform a word segmentation operation to converta continuous language into a list of separate words and then convert it into a vector of acertain dimension. Generally, multi-label learning algorithms can be divided into twocategories, problem transformation methods and adapted algorithms. This work will usecustomer's comments about some hotels as a training data set, which contains labels for allaspects of the hotel evaluation, aiming to analyze and compare the performance of variousmulti-label learning algorithms on Chinese text classification. The experiment involves threebasic methods of problem transformation methods: Support Vector Machine, Random Forest,k-Nearest-Neighbor;and one adapted algorithm of Convolutional Neural Network. Theexperimental results show that the Support Vector Machine has better performance.

iATC_Deep-mISF: A Multi-Label Classifier for Predicting the Classes of Anatomical Therapeutic Chemicals by Deep Learning

The recent worldwide spreading of pneumonia-causing virus, such as Coronavirus, COVID-19, and H1N1, has been endangering the life of human beings all around the world. To provide useful clues for developing antiviral drugs, information of anatomical therapeutic chemicals is vitally important. In view of this, a CNN based predictor called “iATC_Deep-mISF” has been developed. The predictor is particularly useful in dealing with the multi-label systems in which some chemicals may occur in two or more different classes. To maximize the convenience for most experimental scientists, a user-friendly web-server for the new predictor has been established at http://www.jci-bioinfo.cn/iATC_Deep-mISF/, which will become a very powerful tool for developing effective drugs to fight pandemic coronavirus and save the mankind of this planet.

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.

Multi-label local discriminative embedding

Multi-label classification problems arise frequently in text categorization, and many other related applications. Like conventional categorization problems, multi-label categorization tasks suffer from the curse of high dimensionality. Existing multi-label dimensionality reduction methods mainly suffer from two limitations. First, latent nonlinear structures are not utilized in the input space. Second, the label information is not fully exploited. This paper proposes a new method, multi-label local discriminative embedding (MLDE), which exploits latent structures to minimize intraclass distances and maximize interclass distances on the basis of label correlations. The latent structures are extracted by constructing two sets of adjacency graphs to make use of nonlinear information. Non-symmetric label correlations, which are the case in real applications, are adopted. The problem is formulated into a global objective function and a linear mapping is achieved to solve out-of-sample problems. Empirical studies across 11 Yahoo sub-tasks, Enron and Bibtex are conducted to validate the superiority of MLDE to state-of-art multi-label dimensionality reduction methods.

ML-ANet:A Transfer Learning Approach Using Adaptation Network for Multi-label Image Classification in Autonomous Driving

To reduce the discrepancy between the source and target domains,a new multi-label adaptation network(ML-ANet)based on multiple kernel variants with maximum mean discrepancies is proposed in this paper.The hidden representations of the task-specific layers in ML-ANet are embedded in the reproducing kernel Hilbert space(RKHS)so that the mean-embeddings of specific features in different domains could be precisely matched.Multiple kernel functions are used to improve feature distribution efficiency for explicit mean embedding matching,which can further reduce domain discrepancy.Adverse weather and cross-camera adaptation examinations are conducted to verify the effectiveness of our proposed ML-ANet.The results show that our proposed ML-ANet achieves higher accuracies than the compared state-of-the-art methods for multi-label image classification in both the adverse weather adaptation and cross-camera adaptation experiments.These results indicate that ML-ANet can alleviate the reliance on fully labeled training data and improve the accuracy of multi-label image classification in various domain shift scenarios.

Pedestrian attribute classification with multi-scale and multi-label convolutional neural networks

Pedestrian attribute classification from a pedestrian image captured in surveillance scenarios is challenging due to diverse clothing appearances,varied poses and different camera views. A multiscale and multi-label convolutional neural network( MSMLCNN) is proposed to predict multiple pedestrian attributes simultaneously. The pedestrian attribute classification problem is firstly transformed into a multi-label problem including multiple binary attributes needed to be classified. Then,the multi-label problem is solved by fully connecting all binary attributes to multi-scale features with logistic regression functions. Moreover,the multi-scale features are obtained by concatenating those featured maps produced from multiple pooling layers of the MSMLCNN at different scales. Extensive experiment results show that the proposed MSMLCNN outperforms state-of-the-art pedestrian attribute classification methods with a large margin.

Multi-label learning of face demographic classification for correlation analysis

In this paper, we utilize the framework of multi-label learning for face demographic classification. We also attempt t;o explore the suitable classifiers and features for face demographic classification. Three most popular demographic information, gender, ethnicity and age are considered in experiments. Based on the results from demographic classification, we utilize statistic analysis to explore the correlation among various face demographic information. Through the analysis, we draw several conclusions on the correlation and interaction among these high-level face semantic, and the obtained results can be helpful in automatic face semantic annotation and other face analysis tasks.

Stable Label-Specific Features Generation for Multi-Label Learning via Mixture-Based Clustering Ensemble

Multi-label learning deals with objects associated with multiple class labels,and aims to induce a predictive model which can assign a set of relevant class labels for an unseen instance.Since each class might possess its own characteristics,the strategy of extracting label-specific features has been widely employed to improve the discrimination process in multi-label learning,where the predictive model is induced based on tailored features specific to each class label instead of the identical instance representations.As a representative approach,LIFT generates label-specific features by conducting clustering analysis.However,its performance may be degraded due to the inherent instability of the single clustering algorithm.To improve this,a novel multi-label learning approach named SENCE(stable label-Specific features gENeration for multi-label learning via mixture-based Clustering Ensemble)is proposed,which stabilizes the generation process of label-specific features via clustering ensemble techniques.Specifically,more stable clustering results are obtained by firstly augmenting the original instance repre-sentation with cluster assignments from base clusters and then fitting a mixture model via the expectation-maximization(EM)algorithm.Extensive experiments on eighteen benchmark data sets show that SENCE performs better than LIFT and other well-established multi-label learning algorithms.