Multi-label Classification Methods Research Articles

Automatic labeling of river restoration project documents based on project objectives and restoration methods

River restoration projects are widely implemented around the world. Such projects are usually complicated endeavors. Engineering, environmental, and social impacts must be considered under various constraints. Gaining lessons from existing projects would be valuable in new project planning. However, because such projects vary greatly in objectives and used methods, it is difficult to pinpoint relevant projects for reference, even if a large number of cases are collected in a decision-support system. In this study, machine-learning-based approaches were used to classify the description documents for river restoration projects. Based on the characteristics of such projects, a deep neural network (DNN) was developed to label project objectives, and a dictionary-based multilabel classification (MLC) method was developed to label project methods. The resulting labels were validated using 1400 project description documents. In labeling project objectives, the method resulted in a weighted average f1-score of 0.82 and 0.55 for the training and testing dataset, respectively. In labeling project methods, the f1-score was found to be 0.70. Both results indicate that the developed automatic labeling methods perform satisfactorily. The labels attached to the project documents enable project planners to conveniently find the relevant documents for reference and understand the relationships among the objectives and methods.

Explaining the performance of multilabel classification methods with data set properties

Meta learning generalizes the empirical experience with different learning tasks and holds promise for providing important empirical insight into the behavior of machine learning algorithms. In this paper, we present a comprehensive meta-learning study of data sets and methods for multilabel classification (MLC). MLC is a practically relevant machine learning task where each example is labeled with multiple labels simultaneously. Here, we analyze 40 MLC data sets by using 50 meta features describing different properties of the data. The main findings of this study are as follows. First, the most prominent meta features that describe the space of MLC data sets are the ones assessing different aspects of the label space. Second, the meta models show that the most important meta features describe the label space, and, the meta features describing the relationships among the labels tend to occur a bit more often than the meta features describing the distributions between and within the individual labels. Third, the optimization of the hyperparameters can improve the predictive performance, however, quite often the extent of the improvements does not always justify the resource utilization.

A flexible class of dependence-aware multi-label loss functions

The idea to exploit label dependencies for better prediction is at the core of methods for multi-label classification (MLC), and performance improvements are normally explained in this way. Surprisingly, however, there is no established methodology that allows to analyze the dependence-awareness of MLC algorithms. With that goal in mind, we introduce a class of loss functions that are able to capture the important aspect of label dependence. To this end, we leverage the mathematical framework of non-additive measures and integrals. Roughly speaking, a non-additive measure allows for modeling the importance of correct predictions of label subsets (instead of single labels), and thereby their impact on the overall evaluation, in a flexible way. The well-known Hamming and subset 0/1 losses are rather extreme special cases of this function class, which give full importance to single label sets or the entire label set, respectively. We present concrete instantiations of this class, which appear to be especially appealing from a modeling perspective. The assessment of multi-label classifiers in terms of these losses is illustrated in an empirical study, clearly showing their aptness at capturing label dependencies. Finally, while not being the main goal of this study, we also show some preliminary results on the minimization of this parametrized family of losses.

Sound-based multiple-equipment activity recognition using convolutional neural networks

Automatically recognizing activities of heavy construction equipment using sound data has recently received considerable attention as a promising research area in construction. Although existing methods are effective, they only focus on tracking the activities of one single piece of equipment. On construction job sites, multiple equipment sound signals are mixed in the environment; Thus, there is a need for a robust method to recognize these activities that are taking place simultaneously. To address this shortcoming, we proposed a multi-label multi-level sound classification method based on Short-Time Fourier Transform (STFT) and Convolutional Neural Network (CNN) that only requires a single-channel off-the-shelf microphone. In addition, we developed a data augmentation method to simulate real-world equipment sound mixtures. We tested the proposed method on both synthetic and real-world equipment sound mixtures. The results of our study showed that this method was effective in identifying activities of multiple pieces of equipment on real construction job sites without the need for separating sound signals in advance. Future studies can focus on other potential applications of sound signal processing in the construction domain, including analyzing engine abnormalities and monitoring environmental performance of the equipment.

Multi-label classification for multi-drug resistance prediction of Escherichia coli

Antimicrobial resistance (AMR) is a global health and development threat. In particular, multi-drug resistance (MDR) is increasingly common in pathogenic bacteria. It has become a serious problem to public health, as MDR can lead to the failure of treatment of patients. MDR is typically the result of mutations and the accumulation of multiple resistance genes within a single cell. Machine learning methods have a wide range of applications for AMR prediction. However, these approaches typically focus on single drug resistance prediction and do not incorporate information on accumulating antimicrobial resistance traits over time. Thus, identifying multi-drug resistance simultaneously and rapidly remains an open challenge. In our study, we could demonstrate that multi-label classification (MLC) methods can be used to model multi-drug resistance in pathogens. Importantly, we found the ensemble of classifier chains (ECC) model achieves accurate MDR prediction and outperforms other MLC methods. Thus, our study extends the available tools for MDR prediction and paves the way for improving diagnostics of infections in patients. Furthermore, the MLC methods we introduced here would contribute to reducing the threat of antimicrobial resistance and related deaths in the future by improving the speed and accuracy of the identification of pathogens and resistance.

LP-MLTSVM: Laplacian Multi-Label Twin Support Vector Machine for Semi-Supervised Classification

In the machine learning jargon, multi-label classification refers to a task where multiple mutually non-exclusive class labels are assigned to a single instance. Generally, the lack of sufficient labeled training data demanded by a classification task is met by an approach known as semi-supervised learning. This type of learning extracts the decision rules of classification by utilizing both labeled and unlabeled data. Regarding multi-label data, however, current semi-supervised learning methods are unable to classify them accurately. Therefore, with the goal of generalizing the state-of-the-art semi-supervised approaches to multi-label data, this paper proposes a novel two-stage method for multi-label semi-supervised classification. The first stage determines the label(s) of the unlabeled training data by means of a smooth graph constructed using the manifold regularization. In the second stage, thanks to the capability of the twin support vector machine to relax the requirement that hyperplanes should be parallel in classical SVM, we employ it to establish a multi-label classifier called LP-MLTSVM. In the experiments, this classifier is applied on benchmark datasets. The simulation results substantiate that compared to the existing multi-label classification algorithms, LP-MLTSVM shows superior performance in terms of the Hamming loss, average precision, coverage, ranking loss, and one-error metrics.

Multi-Label Classification and Deep Image Analysis Methods on Marine Microalgae and Rotifer Identification Using Transfer Learning and Two-Dimensional Convolutional Neural Networks

Multi-Label Classification and Deep Image Analysis Methods on Marine Microalgae and Rotifer Identification Using Transfer Learning and Two-Dimensional Convolutional Neural Networks

Multilabel 12-Lead ECG Classification Based on Leadwise Grouping Multibranch Network

The 12-lead electrocardiogram (ECG) is widely used in the clinical diagnosis of cardiovascular disease, and deep learning has become an effective approach to automatic ECG classification. Generally, current research simply regards the 12-lead ECG signal as an ordinary 2-D array and does not specifically consider the intrinsic relationship between different leads when building the neural networks. However, ECG classes, from the biomedical perspective, mainly show specific patterns on one or several leads rather than all 12 leads, which suggests that it would be more efficient to learn class-specific intrinsic features from corresponding leads. To make use of such domain knowledge, in this study, we present a multilabel 12-lead ECG classification method based on the leadwise grouping multibranch network. A simple yet effective leadwise grouping strategy is proposed to incorporate domain knowledge to ECG classification models. Meanwhile, a multibranch network is designed accordingly, and spatial and temporal features are extracted by a BranchNet for each branch, which corresponds to one lead group. Moreover, an extended focal loss is presented to solve the class imbalance problem for multilabel classification. The proposed method was evaluated on two large-scale real-world ECG databases and yielded values of 0.9599, 0.7920, 0.7490, 0.5537, 0.1282, and 1.5354 for the area under receiver operating characteristic curve (AUROC), area under precision–recall curve (AUPRC), F1, accuracy (Acc), one-error (OE), and coverage (Cove), respectively, on the PhysioNet/Computing in Cardiology Challenge 2020 (CinC2020) database and values of 0.9531, 0.8975, 0.8102, 0.7484, 0.1791, and 0.5392 on the Shandong Provincial Hospital (SPH) database. The results are better than the existing work and are reached with fewer parameters and lower computational cost, demonstrating the effectiveness of the proposed method and leadwise grouping strategy.

Multi-Label Emotion Classification on Code-Mixed Text: Data and Methods

The multi-label emotion classification task aims to identify all possible emotions in a written text that best represent the author’s mental state. In recent years, multi-label emotion classification attracted the attention of researchers due to its potential applications in e-learning, health care, marketing, etc. There is a need for standard benchmark corpora to develop and evaluate multi-label emotion classification methods. The majority of benchmark corpora were developed for the English language (monolingual corpora) using tweets. However, the multi-label emotion classification problem is not explored for code-mixed text, for example, English and Roman Urdu, although the code-mixed text is widely used in Facebook posts/comments, tweets, SMS messages, particularly by the South Asian community. For filling this gap, this study presents a large benchmark corpus for the multi-label emotion classification task, which comprises 11,914 code-mixed (English and Roman Urdu) SMS messages. Each code-mixed (English and Roman Urdu) SMS message manually annotated using a set of 12 emotions, including anger, anticipation, disgust, fear, joy, love, optimism, pessimism, sadness, surprise, trust, and neutral (no emotion). As a secondary contribution, we applied and compared state-of-the-art classical machine learning (content-based methods – three word n-gram features and eight character n-gram features), deep learning (CNN, RNN, Bi-RNN, GRU, Bi-GRU, LSTM, and Bi-LSTM), and transfer learning-based methods (BERT and XLNet) on our proposed corpus. After our extensive experimentation, the best results were obtained using state-of-the-art classical machine learning methods on word uni-gram (Micro Precision = 0.67, Micro Recall = 0.54, Micro F <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sub> = 0.67) with a combination of OVR multi-label and SVC single-label machine learning algorithms. Our proposed corpus is free and publicly available for research purposes to foster research in an under-resourced language (Roman Urdu).

On the Effects of Different Types of Label Noise in Multi-Label Remote Sensing Image Classification

The development of accurate methods for multi-label classification (MLC) of remote sensing (RS) images is one of the most important research topics in RS. To address MLC problems, the use of deep neural networks that require a high number of reliable training images annotated by multiple land-cover class labels (multi-labels) has been found popular in RS. However, collecting such annotations is time-consuming and costly. A common procedure to obtain annotations at zero labeling cost is to rely on thematic products or crowdsourced labels. As a drawback, these procedures come with the risk of label noise that can distort the learning process of the MLC algorithms. In the literature, most label noise robust methods are designed for single-label classification (SLC) problems in computer vision (CV), where each image is annotated by a single label. Unlike SLC, label noise in MLC can be associated with: 1) subtractive label-noise (a land cover class label is not assigned to an image while that class is present in the image); 2) additive label-noise (a land cover class label is assigned to an image although that class is not present in the given image); and 3) mixed label-noise (a combination of both). In this paper, we investigate three different noise robust CV SLC methods and adapt them to be robust for multi-label noise scenarios in RS. During experiments, we study the effects of different types of multi-label noise and evaluate the adapted methods rigorously. To this end, we also introduce a synthetic multi-label noise injection strategy that is more adequate to simulate operational scenarios compared to the uniform label noise injection strategy, in which the labels of absent and present classes are flipped at uniform probability. Further, we study the relevance of different evaluation metrics in MLC problems under noisy multi-labels.

High-Dimensional Multi-Label Data Stream Classification With Concept Drifting Detection

Multi-label data streams such as Web texts and images have been popular on the Web. These data present the characteristics of multiple label, high dimensionality, high volume, high velocity and especial concept drift etc. Thus, multi-label data stream classification is a very challenging and significant task especially in the handling of high-dimensional data with concept drifts. However, this challenge has received little attention from the research community. Therefore, we propose the max-relevance and min-redundancy based algorithm adaptation approach for the efficient and effective classification on multi-label data streams with high-dimensional attributes and concept drifts .<xref ref-type="fn" rid="fn1">¹</xref><fn id="fn1"><label>1.</label> Source codes and data sets are available at below. https://github.com/peipeilihfut/MLStreamClassification </fn> In order to reduce the impact from the high-dimensional data with noisy attributes, we first refine the minimal-redundancy-maximal-relevance criterion based on mutual information to select qualified features in multi-label data streams. Secondly, we propose the data distribution based concept drifting detection approach to distinguish concept drifts hidden in data streams. Finally, we build an incremental ensemble classification model for efficiently classifying multi-label data streams. Extensive studies show that our approach can get optimal subsets of features while maintaining a good performance in the multi-label classification, as compared to several state-of-the-art multi-label feature selection algorithms using two efficient multi-label classification methods as base classifiers. Meanwhile, our approach is superior to three well-known multi-label data stream classification approaches in the effectiveness and efficiency.

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

PurposeIntelligent 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/approachIn 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.FindingsThe 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/valueThe 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.

Hierarchical GAN-Tree and Bi-Directional Capsules for multi-label image classification

Compared with the flat multi-label image classification, the hierarchical structure reserves a richer source of structural information to represent complicated relationships between labels in the real world. However, existing multi-label image classification methods focus on the accuracy of label prediction, ignoring the structural information embedded in the hierarchical label space. Furthermore, they hardly form the relevant visual feature space corresponding to the hierarchical label structure. In this paper, we propose a novel hierarchical framework based on the feature and label structural information named Hierarchical GAN-Tree and Bi-Directional Capsules (HGT&BC) to address these problems. We conduct Hierarchical GAN-Tree for feature space representation and Hierarchical Bi-Directional Capsules for label space classification, respectively. Hierarchical GAN-Tree generates hierarchical feature space using the unsupervised divisive clustering pattern according to the hierarchical structure, alleviating the mode-collapse of generators and the overfitting manifestation of conventional GANs. Hierarchical Bi-Directional Capsules utilize the hierarchical label structure in iterations of top-down and bottom-up processes: the top-down process integrates hierarchical relationships into the probability computation to enhance partial hierarchical relationships; the bottom-up process modifies the dynamic routing mechanism between capsules to represent semantic objects for the comprehensive global hierarchical classifiers. Owing to the two components, HGT&BC successfully expresses the hierarchical relationships in both feature and label space and improves the performance of multi-label image classification. Extensive experimental results on four benchmark datasets demonstrate the effectiveness and efficiency of our hierarchical framework in practice.

Research on Multi-label Text Classification Method Based on tALBERT-CNN

Single-label classification technology has difficulty meeting the needs of text classification, and multi-label text classification has become an important research issue in natural language processing (NLP). Extracting semantic features from different levels and granularities of text is a basic and key task in multi-label text classification research. A topic model is an effective method for the automatic organization and induction of text information. It can reveal the latent semantics of documents and analyze the topics contained in massive information. Therefore, this paper proposes a multi-label text classification method based on tALBERT-CNN: an LDA topic model and ALBERT model are used to obtain the topic vector and semantic context vector of each word (document), a certain fusion mechanism is adopted to obtain in-depth topic and semantic representations of the document, and the multi-label features of the text are extracted through the TextCNN model to train a multi-label classifier. The experimental results obtained on standard datasets show that the proposed method can extract multi-label features from documents, and its performance is better than that of the existing state-of-the-art multi-label text classification algorithms.

Research on multi-label classification method of transformer based on DBSCAN (Density-Based Spatial Clustering of Applications with Noise) clustering algorithm

With the improvement of the intelligent level of power grid and the enhancement of the integrated characteristics of power grid, the degree of discretization of massive data of power equipment gradually increases, which brings great challenges to the safe and stable operation of power grid. How to process and analyze data effectively has become an important research content. Transformer is an important electrical equipment, therefore it is of great significance to monitor the operation status of transformer, to construct transformer operation characteristic label system based on multi-source heterogeneous data, and to realize multi-label classification function. In this paper, a transformer multi-label classification method of transformer based on DBSCAN(Density-Based Spatial Clustering of Applications with Noise) clustering algorithm is proposed, which can accurately identify outliers as Noise without input of the number of clustering to be divided, realize the key feature mining of transformer state, and to realize to provide flexible information association and historical data for dispatch and control operators.

A multi-label emoji classification method using balanced pointwise mutual information-based feature selection

The availability of social media such as twitter allows users to express their feeling, emotions and opinions toward a topic. Emojis are graphic symbols that are regarded as the new generation of emoticons and an effective way of conveying feelings and emotions in social media. With the surging popularity of Emojis, the researchers in the area of Emotion Classification strive to understand the emotion correlated to each Emoji. Two of the most the successful approaches in emoji analysis rely on: 1) official Unicode description and 2) manually built emoji lexicons. Since the use of emoji is socially determined, the former approach is not aligned with intended semantic and usage, which leads researchers to opt for emoji lexicons. To overcome problem of lexicon-based approach, we proposed a method to classify emojis automatically. Therefore, we present a modified Pointwise Mutual Information (PMI) method, called Balanced Pointwise Mutual Information-Based (B-PMI), to develop a balanced weighted emoji classification based on the semantic similarity. Further, deep neural network is used to represent emoji in vector form (emoji embedding) to extend the pre-trained word embeddings. We carefully evaluated the proposed method in multiple twitter datasets that are employed in sentiment and emotion classification using machine learning (ML) and deep learning (DL) approaches. In both approaches, extending word embedding with the proposed emoji embedding improved results. The DL-based approach achieved the highest f1-score of 70.01% for sentiment classification, and accuracy score of 56.36% for emotion classification. ML-based approach obtained accuracy score of 52.17% in emotion classification.

Multi-Keyword Classification: A Case Study in Finnish Social Sciences Data Archive

In this paper, we consider the task of assigning relevant labels to studies in the social science domain. Manual labelling is an expensive process and prone to human error. Various multi-label text classification machine learning approaches have been proposed to resolve this problem. We introduce a dataset obtained from the Finnish Social Science Archive and comprised of 2968 research studies’ metadata. The metadata of each study includes attributes, such as the “abstract” and the “set of labels”. We used the Bag of Words (BoW), TF-IDF term weighting and pretrained word embeddings obtained from FastText and BERT models to generate the text representations for each study’s abstract field. Our selection of multi-label classification methods includes a Naive approach, Multi-label k Nearest Neighbours (ML-kNN), Multi-Label Random Forest (ML-RF), X-BERT and Parabel. The methods were combined with the text representation techniques and their performance was evaluated on our dataset. We measured the classification accuracy of the combinations using Precision, Recall and F1 metrics. In addition, we used the Normalized Discounted Cumulative Gain to measure the label ranking performance of the selected methods combined with the text representation techniques. The results showed that the ML-RF model achieved a higher classification accuracy with the TF-IDF features and, based on the ranking score, the Parabel model outperformed the other methods.

Non-intrusive energy estimation using random forest based multi-label classification and integer linear programming

Home energy management system is proposed to reduce the influences caused by the high ratio penetration of renewable energy generation, through managing and dispatching the residential power and energy consumption in the demand side. Being aware of how the electric energy is consumed is a key step of this system. Non-intrusive Load Monitoring is regarded as the most potential method to address this problem, which aims to separate individual appliances in households by decomposing the total power consumption. In recent years, NILM is framed as a multi-label classification problem and many researches has been investigated in this field. In this paper, a non-intrusive method which can identify appliances power usage information from the total power consumption is proposed and thoroughly investigated. Firstly, the random k-labelset multi-label classification algorithm is enhanced by introducing random forest algorithm as base classifier. Then, grid search method and cross validation method are integrated to determine the optimal paraments set. This algorithm is used to achieve the appliances identification. Finally, based on the identification result, the integer linear programming is employed for power estimation of each appliance, especially multi-state appliances. Experimental results on low voltage networks simulator demonstrate that the proposed method has a high identification accuracy compared with the traditional random k-labelset multi-label classification methods with other base classifiers, and it is capable of identifying the power usages of different appliances accurately. The desirable performance of power estimation has broadened the applications of machine learning based non-intrusive energy monitoring.

Optimal Granularity Selection in Multi-label Decision Table

To solve the problem of granularity selection in multi-label decision classification, a global and object-based optimal granularity selection method is proposed. Firstly, the granularity partitioning of multi-label decision tables is analyzed based on multiple granularity levels and the granulation roughness measurement method of multi-label decision tables is introduced. Then the general optimal granularity selection method is discussed for coordinated decision tables and uncoordinated decision tables. Finally, in view of the limitation that the global optimal granularity selection cannot make every object reach the optimal granularity, and the uncertainty of some objects in the uncoordinated decision table regarding the classification of decision markers, the local optimal granularity selection method of objects is discussed, and the effectiveness of the method is verified by an example.

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.