Multi-label Classification Problem Research Articles

Tagging Multi-Label Categories to Points of Interest From Check-In Data

Category tag of Point Of Interest (POI) serves a crucial role in numerous Location Based Services (LBS) like finding a place of interest, POI recommendation, location-based advertisement, etc. However, it has been found that many POIs (around 30%) do not have any category information. Manual tagging of these categories is a very costly affair as it requires a physical visit to each POI. Hence, an automated method for category tagging of POIs has been identified as an important research problem. The problem of category tagging of POIs is still in its primary stage, requiring further exploration. In this work, we solve the problem in three broad steps i). feature identification, ii). feature extraction, and iii). tag assignment. For the first step, we consider sequential features, temporal features, and spatial features, which can be constructed using check-in data. For the second step, we generate POI embedding representing its features, using a graph-based unsupervised approach. For the final step, the problem is considered a multi-label classification problem. For this, we have used Classifier Chain algorithms which preserves inter-tag correlation. Comparison with state-of-the-art methodologies along with multiple variants of features and classification algorithms show a significant improvement of <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$5-34\%$</tex-math></inline-formula> by standard metric of average F1-score.

A Hard Knowledge Regularization Method with Probability Difference in Thorax Disease Images

The computer-aided thorax disease diagnosis suffers from the existing noisy labels in large-scale datasets. Especially, the fine-grained thorax images also show high inter-similarity, which leads to the classification task being more challenging. Previous works select the small-loss samples to optimize the deep networks but neglect the knowledge of the hard positive examples with large losses. To address the above problems, in this paper, we propose a novel Probability Difference Regularization method (PDR) to explore more knowledge from the hard positive examples for thorax disease diagnosis. PDR regularizes the deep network with the predicted probability discrepancy between the ground truth and the other classes. We first define a Probability Difference score as the difference between the predicted probability corresponding to the ground truth and the largest probability according to the other categories. Then the PDR regularizes the network by the negative of the PD score. Consequently, PDR benefits the classification in two folds. First, it could enlarge the predicted probability gap between the ground truth and other classes. Second, it enhances the learning of hard examples by introducing extra penalties for incorrect predictions during training. PDR is complimented for both multi-class and multi-label classification problems. We conduct experiments to validate the effectiveness of the proposed method on the ChestX-ray2017 dataset (which easily introduces noisy labels) and the ChestX-ray14 dataset (a real noisy dataset). Experimental results demonstrate that PDR consistently improves the performance of multi-class and multi-label thorax disease classification tasks.

Multi-Abnormality Attention Diagnosis Model Using One-vs-Rest Classifier in a Nuclear Power Plant

Multi-abnormal events, referring to the simultaneous occurrence of multiple single abnormal events in a nuclear power plant, have not been subject to consideration because multi-abnormal events are extremely unlikely to occur and indeed have not yet occurred. Such events, though, would be more challenging to diagnose than general single abnormal events, exacerbating the human error issue. This study introduces an efficient abnormality diagnosis model that covers multi-abnormality diagnosis using a one-vs-rest classifier and compares it with other artificial intelligence models. The multi-abnormality attention diagnosis model deals with multi-label classification problems, for which two methods are proposed. First, a method to effectively cluster single and multi-abnormal events is introduced based on the predicted probability distribution of each abnormal event. Second, a one-vs-rest classifier with high accuracy is employed as an efficient way to obtain knowledge on which particular multi-abnormal events are the most difficult to diagnose and therefore require the most attention to improve the multi-label classification performance in terms of data usage. The developed multi-abnormality attention diagnosis model can reduce human errors of operators due to excessive information and limited time when unexpected multi-abnormal events occur by providing diagnosis results as part of an operator support system.

Hygeia: A Multilabel Deep Learning-Based Classification Method for Imbalanced Electrocardiogram Data.

Electrocardiogram (ECG) is a common diagnostic indicator of heart disease in hospitals. Because of the low price and noninvasiveness of ECG diagnosis, it is widely used for prescreening and physical examination of heart diseases. In several studies on ECG analysis, only rough diagnoses are made to determine whether ECGs are abnormal or on a few kinds of ECG. In actual scenarios, doctors must analyze ECG samples in detail, which is a multilabel classification problem. Herein, we propose Hygeia, a multilabel deep learning-based ECG classification method that can analyze and classify 55 types of ECG. First, a guidance model is constructed to transform the multilabel classification problem into multiple interrelated two-classification models. This method ensures the good performance of each ECG analysis model, and the relationship between various types of ECG can be used in the analysis. The imbalance of samples in ECG datasets makes it difficult to analyze abnormal ECGs with high sensitivity and accuracy. We used data generation and mixed sampling methods for 11 ECG types with imbalanced problems to improve the average accuracy, sensitivity, F1 value, and accuracy from 87.74%, 43.11%, 0.3929, and 0.3929, to 92.68%, 96.92, 0.9287, and 99.47%, respectively. The average accuracy, sensitivity, F1 value, and accuracy of 44 of the 55 tags of the abnormal ECG analysis model are 99.69%, 95.81%, 0.9758, and 99.72%, respectively.

A Vision Transformer Model for Convolution-Free Multilabel Classification of Satellite Imagery in Deforestation Monitoring.

Understanding the dynamics of deforestation and land uses of neighboring areas is of vital importance for the design and development of appropriate forest conservation and management policies. In this article, we approach deforestation as a multilabel classification (MLC) problem in an endeavor to capture the various relevant land uses from satellite images. To this end, we propose a multilabel vision transformer model, ForestViT, which leverages the benefits of the self-attention mechanism, obviating any convolution operations involved in commonly used deep learning models utilized for deforestation detection. Experimental evaluation in open satellite imagery datasets yields promising results in the case of MLC, particularly for imbalanced classes, and indicates ForestViT's superiority compared with well-established convolutional structures (ResNET, VGG, DenseNet, and ModileNet neural networks). This superiority is more evident for minority classes.

DICNet: Deep Instance-Level Contrastive Network for Double Incomplete Multi-View Multi-Label Classification

In recent years, multi-view multi-label learning has aroused extensive research enthusiasm. However, multi-view multi-label data in the real world is commonly incomplete due to the uncertain factors of data collection and manual annotation, which means that not only multi-view features are often missing, and label completeness is also difficult to be satisfied. To deal with the double incomplete multi-view multi-label classification problem, we propose a deep instance-level contrastive network, namely DICNet. Different from conventional methods, our DICNet focuses on leveraging deep neural network to exploit the high-level semantic representations of samples rather than shallow-level features. First, we utilize the stacked autoencoders to build an end-to-end multi-view feature extraction framework to learn the view-specific representations of samples. Furthermore, in order to improve the consensus representation ability, we introduce an incomplete instance-level contrastive learning scheme to guide the encoders to better extract the consensus information of multiple views and use a multi-view weighted fusion module to enhance the discrimination of semantic features. Overall, our DICNet is adept in capturing consistent discriminative representations of multi-view multi-label data and avoiding the negative effects of missing views and missing labels. Extensive experiments performed on five datasets validate that our method outperforms other state-of-the-art methods.

Deep learning models for multilabel ECG abnormalities classification: A comparative study using TPE optimization

AbstractThe problem addressed in this study is the limitations of previous works that considered electrocardiogram (ECG) classification as a multiclass problem, despite many abnormalities being diagnosed simultaneously in real life, making it a multilabel classification problem. The aim of the study is to test the effectiveness of deep learning (DL)-based methods (Inception, MobileNet, LeNet, AlexNet, VGG16, and ResNet50) using three large 12-lead ECG datasets to overcome this limitation. The define-by-run technique is used to build the most efficient DL model using the tree-structured Parzen estimator (TPE) algorithm. Results show that the proposed methods achieve high accuracy and precision in classifying ECG abnormalities for large datasets, with the best results being 97.89% accuracy and 90.83% precision for the Ningbo dataset, classifying 42 classes for the Inception model; 96.53% accuracy and 85.67% precision for the PTB-XL dataset, classifying 24 classes for the Alex net model; and 95.02% accuracy and 70.71% precision for the Georgia dataset, classifying 23 classes for the Alex net model. The best results achieved for the optimum model that was proposed by the define-by-run technique were 97.33% accuracy and 97.71% precision for the Ningbo dataset, classifying 42 classes; 96.60% accuracy and 83.66% precision for the PTB-XL dataset, classifying 24 classes; and 94.32% accuracy and 66.97% precision for the Georgia dataset, classifying 23 classes. The proposed DL-based methods using the TPE algorithm provide accurate results for multilabel classification of ECG abnormalities, improving the diagnostic accuracy of heart conditions.

Multi-Label Classification of Chinese Rural Poverty Governance Texts Based on XLNet and Bi-LSTM Fused Hierarchical Attention Mechanism

Hierarchical multi-label text classification (HMTC) is a highly relevant and widely discussed topic in the era of big data, particularly for efficiently classifying extensive amounts of text data. This study proposes the HTMC-PGT framework for poverty governance’s single-path hierarchical multi-label classification problem. The framework simplifies the HMTC problem into training and combination problems of multi-class classifiers in the classifier tree. Each independent classifier in this framework uses an XLNet pretrained model to extract char-level semantic embeddings of text and employs a hierarchical attention mechanism integrated with Bi-LSTM (BiLSTM + HA) to extract semantic embeddings at the document level for classification purposes. Simultaneously, this study proposes that the structure uses transfer learning (TL) between classifiers in the classifier tree. The experimental results show that the proposed XLNet + BiLSTM + HA + FC + TL model achieves micro-P, micro-R, and micro-F1 values of 96.1%, which is 7.5~38.1% higher than those of other baseline models. The HTMC-PGT framework based on XLNet, BiLSTM + HA, and transfer learning (TL) between classifier tree nodes proposed in this study solves the hierarchical multi-label classification problem of poverty governance text (PGT). It provides a new idea for solving the traditional HMTC problem.

Knowledge graph embedding for profiling the interaction between transcription factors and their target genes.

Interactions between transcription factor and target gene form the main part of gene regulation network in human, which are still complicating factors in biological research. Specifically, for nearly half of those interactions recorded in established database, their interaction types are yet to be confirmed. Although several computational methods exist to predict gene interactions and their type, there is still no method available to predict them solely based on topology information. To this end, we proposed here a graph-based prediction model called KGE-TGI and trained in a multi-task learning manner on a knowledge graph that we specially constructed for this problem. The KGE-TGI model relies on topology information rather than being driven by gene expression data. In this paper, we formulate the task of predicting interaction types of transcript factor and target genes as a multi-label classification problem for link types on a heterogeneous graph, coupled with solving another link prediction problem that is inherently related. We constructed a ground truth dataset as benchmark and evaluated the proposed method on it. As a result of the 5-fold cross experiments, the proposed method achieved average AUC values of 0.9654 and 0.9339 in the tasks of link prediction and link type classification, respectively. In addition, the results of a series of comparison experiments also prove that the introduction of knowledge information significantly benefits to the prediction and that our methodology achieve state-of-the-art performance in this problem.

Unity in Diversity: Multilabel Emoji Identification in Tweets

Emojis or emoticons are not just a modern trend but have become an essential part of our day-to-day interactions. Predicting a suitable emoji for a given tweet is a challenging task because a wrong emoji prediction for a tweet can change the meaning of the message or can amplify the emotion of the message. This task is particularly challenging since it requires selecting an appropriate emoji from a huge list of prospective emojis that may or may not be equivalent to one another. Humans use multiple emojis to convey their emotions, thereby making the task a multilabel classification problem. In this article, we propose a multilabel emoji prediction system that predicts the appropriate emoji for a given tweet by using different state-of-the-art baselines. Due to the unavailability of a multi-emoji dataset, we create a large-scale multilabel emoji dataset named Mu-Emoji that comprises of more than 0.6 million tweets having varied emojis belonging to both positive and negative sentiments. For our proposed task, we employ graph attention network along with bidirectional encoder representations from transformer encoder for the accurate prediction of emojis. Qualitative and quantitative analyses show that our multilabel emoji prediction baselines perform well compared with the single-emoji prediction baselines for our proposed Mu-Emoji dataset. Our proposed framework also outperforms all the baselines for both single and multilabel emoji prediction tasks.

Multilabel Classifier Chains Algorithm Based on Maximum Spanning Tree and Directed Acyclic Graph

The classifier chains algorithm is aimed at solving the multilabel classification problem by composing the labels into a randomized label order. The classification effect of this algorithm depends heavily on whether the label order is optimal. To obtain a better label ordering, the authors propose a multilabel classifier chains algorithm based on a maximum spanning tree and a directed acyclic graph. The algorithm first uses Pearson's correlation coefficient to calculate the correlation between labels and constructs the maximum spanning tree of labels, then calculates the mutual decision difficulty between labels to transform the maximum spanning tree into a directed acyclic graph, and it uses topological ranking to output the optimized label ordering. Finally, the authors use the classifier chains algorithm to train and predict against this label ordering. Experimental comparisons were conducted between the proposed algorithm and other related algorithms on seven datasets, and the proposed algorithm ranked first and second in six evaluation metrics, accounting for 76.2% and 16.7%, respectively. The experimental results demonstrated the effectiveness of the proposed algorithm and affirmed its contribution in exploring and utilizing label-related information.

FlexER: Flexible Entity Resolution for Multiple Intents

Entity resolution, a longstanding problem of data cleaning and integration, aims at identifying data records that represent the same real-world entity. Existing approaches treat entity resolution as a universal task, assuming the existence of a single interpretation of a real-world entity and focusing only on finding matched records, separating corresponding from non-corresponding ones, with respect to this single interpretation. However, in real-world scenarios, where entity resolution is part of a more general data project, downstream applications may have varying interpretations of real-world entities relating, for example, to various user needs. In what follows, we introduce the problem of multiple intents entity resolution (MIER), an extension to the universal (single intent) entity resolution task. As a solution, we propose FlexER, utilizing contemporary solutions to universal entity resolution tasks to solve MIER. FlexER addresses the problem as a multi-label classification problem. It combines intent-based representations of tuple pairs using a multiplex graph representation that serves as an input to a graph neural network (GNN). FlexER learns intent representations and improves the outcome to multiple resolution problems. A large-scale empirical evaluation introduces a new benchmark and, using also two well-known benchmarks, shows that FlexER effectively solves the MIER problem and outperforms the state-of-the-art for a universal entity resolution.

Decision system for copper flotation backbone process

This study proposed a decision system that can output the flotation backbone flowchart using the natural properties of copper ore. The proposed decision system includes three decision tasks: product scheme, flotation scheme and grinding scheme. Each decision task is a multi-label classification problem. To improve the classification effect of each sub-label, extreme gradient boosting (XGBoost) is used as a subclassifier, because of its ability to deal with small and high-dimensional samples. To selectively utilize the relations between the sub-labels in the same task, a modified classifier chain (MCC) was proposed. To specifically use the effect of a front-end task on a back-end task, the decision system connects the MCC-XGBoost corresponding to the three tasks in series. Accordingly, the outputs of a front-end task becomes the candidate features of a back-end task. To improve the recall rates of minority classes, the classification thresholds are customized using the Yoden index. Finally, the high performance of the decision system was demonstrated by hypothesis testing.

Multi-Label Classification Based on Associations

Associative classification (AC) has been shown to outperform other methods of single-label classification for over 20 years. In order to create rules that are both more precise and simpler to grasp, AC combines the rules of mining associations with the task of classification. However, the current state of knowledge and the views of various specialists indicate that the issue of multi-label classification (MLC) cannot be solved by any AC method. Since this is the case, adapting or using an AC algorithm to manage multi-label datasets is one of the most pressing issues. To solve the MLC issue, this research proposes modifying the classification based on associations (msCBA) method by extending its capabilities to consider more than one class label in the consequent of its rules and modifying its rules order procedure to fit the nature of the multi-label dataset. The proposed algorithm outperforms several other MLC algorithms from various learning techniques across a variety of performance measuresand using six datasets with different domains. The main findings of this research are the significance of utilizing the local dependencies among labels compared to global dependencies, and the important rule of AC in solving the problem of MLC.

Developing a Warning Model of Potentially Inappropriate Medications in Older Chinese Outpatients in Tertiary Hospitals: A Machine-Learning Study.

Due to multiple comorbid illnesses, polypharmacy, and age-related changes in pharmacokinetics and pharmacodynamics in older adults, the prevalence of potentially inappropriate medications (PIMs) is high, which affects the quality of life of older adults. Building an effective warning model is necessary for the early identification of PIMs to prevent harm caused by medication in geriatric patients. The purpose of this study was to develop a machine learning-based model for the warning of PIMs in older Chinese outpatients. This retrospective study was conducted among geriatric outpatients in nine tertiary hospitals in Chengdu from January 2018 to December 2018. The Beers criteria 2019 were used to assess PIMs in geriatric outpatients. Three problem transformation methods were used to tackle the multilabel classification problem in prescriptions. After the division of patient prescriptions into the training and test sets (8:2), we adopted six widely used classification algorithms to conduct the classification task and assessed the discriminative performance by the accuracy, precision, recall, F1 scores, subset accuracy (ss Acc), and Hamming loss (hm) of each model. The results showed that among 11,741 older patient prescriptions, 5816 PIMs were identified in 4038 (34.39%) patient prescriptions. A total of 41 types of PIMs were identified in these prescriptions. The three-problem transformation methods included label power set (LP), classifier chains (CC), and binary relevance (BR). Six classification algorithms were used to establish the warning models, including Random Forest (RF), Light Gradient Boosting Machine (LightGBM), eXtreme Gradient Boosting (XGBoost), CatBoost, Deep Forest (DF), and TabNet. The CC + CatBoost model had the highest accuracy value (97.83%), recall value (89.34%), F1 value (90.69%), and ss Acc value (97.79%) with a good precision value (92.18%) and the lowest hm value (0.0006). Therefore, the CC + CatBoost model was selected to predict the occurrence of PIM in geriatric Chinese patients. This study's novelty establishes a warning model for PIMs in geriatric patients by using machine learning. With the popularity of electronic patient record systems, sophisticated computer algorithms can be implemented at the bedside to improve medication use safety in geriatric patients in the future.

Spatiotemporal self-supervised representation learning from multi-lead ECG signals

Automatic analysis of electrocardiogram(ECG) signals is one of the applications in the medical domain where deep learning methods demonstrate impressive performance. However, label scarcity remains a critical obstacle limiting the development and clinical application of deep learning methods. Self-supervised pretraining exhibits its potential to alleviate this issue. Motivated by the idea that multi-lead ECG signals gathered simultaneously represent similar underlying cardiac status, we propose ECG-MAE, a novel generative self-supervised pretraining approach. Specifically, an efficient encoder is designed to learn spatiotemporal representations by reconstructing 12-lead ECG signals that have been randomly masked in both time and lead dimensions. Experiments on a multi-label classification problem reveal that our pretrained model obtains a macro-averaged AUC of 0.9474, exceeding prior studies. We observe enhanced downstream performance and label efficiency compared with purely supervised models, allowing us to train more powerful models with the same amount of data and diagnose rare diseases beyond the reach of conventional methods.

Deep learning for understanding multilabel imbalanced Chest X-ray datasets

Over the last few years, convolutional neural networks (CNNs) have dominated the field of computer vision thanks to their ability to extract features and their outstanding performance in classification problems, for example in the automatic analysis of X-rays. Unfortunately, these neural networks are considered black-box algorithms, i.e. it is impossible to understand how the algorithm has achieved the final result. To apply these algorithms in different fields and test how the methodology works, we need to use eXplainable AI techniques. Most of the work in the medical field focuses on binary or multiclass classification problems. However, in many real-life situations, such as chest X-rays, radiological signs of different diseases can appear at the same time. This gives rise to what is known as ”multilabel classification problems”. A disadvantage of these tasks is class imbalance, i.e. different labels do not have the same number of samples. The main contribution of this paper is a Deep Learning methodology for imbalanced, multilabel chest X-ray datasets. It establishes a baseline for the currently underutilised PadChest dataset and a new eXplainable AI technique based on heatmaps. This technique also includes probabilities and inter-model matching. The results of our system are promising, especially considering the number of labels used. Furthermore, the heatmaps match the expected areas, i.e. they mark the areas that an expert would use to make a decision.

Label Pair of Instances-Based Safe Screening for Multilabel Rank Support Vector Machine

Rank support vector machine (RSVM) is widely used in multilabel classification problems. However, as the number of labels and instances soars, the training efficiency of the model will be greatly reduced. Unfortunately, few effective methods can solve this problem. In this article, we propose a safe screening rule (SSR) for RSVM to improve its training speed. This is the first attempt to construct SSR for multilabel learning problems. SSR for RSVM can screen and delete most of the instances based on their relevant–irrelevant label pairs, which is the biggest difference in the existing SSR. After this process, the scale of RSVM can be substantially reduced before solving it. The sequential version of SSR for RSVM is further introduced to accelerate the whole parameter tuning process. One important advantage of SSR is that it is safe, which means we can obtain the same optimal solution as the original problem by utilizing it. Extensive experiments with five benchmark datasets, three large-scale datasets, and one type 2 diabetes dataset show that our approach is efficient and safe.

TSMC-Net: Deep-Learning Multigas Classification Using THz Absorption Spectra.

The identification of gas mixture speciation from a complex multicomponent absorption spectrum is a problem in gas sensing that can be addressed using machine-learning approaches. Here, we report on a deep convolutional neural network for multigas classification using terahertz (THz) absorption spectra, THz spectra mixture classifier network or TSMC-Net. TSMC-Net has been developed to identify eight volatile organic compounds in mixtures based on their fingerprint rotational absorption spectra in the 220-330 GHz frequency range. A data set consisting of simulated absorption spectra for randomly generated mixtures, with absorption greater than thresholds representing detectable limits and annotated with multiple labels, was prepared for model development. The supervised multilabel classification problem, i.e., the identification of individual gases in a mixture, is converted to a supervised multiclass classification problem via label powerset conversion. The trained model is validated and tested against simulated spectra for gas mixtures, with and without white Gaussian noise. The trained model exhibits high precision, recall, and accuracy for each pure compound. Class activation maps illustrate the complex decision-making process of the model and highlight relevant frequency regions that are needed to identify unique mixtures. Finally, the model was demonstrated against measured THz absorption spectra for pure species and mixtures, acquired using a microelectronics-based THz absorption spectrometer. The data set generation strategy and deep convolutional neural network approach are generalized and can be extrapolated to other spectroscopy types, frequency ranges, and sensors.

Towards private stylists via personalized compatibility learning

Personalized outfit compatibility learning is an emerging yet challenging task. Most of the existing methods focus on general outfit compatibility learning. Although a few works have been proposed for personalized fashion compatibility, they either considered user preference on fashion items with specific patterns or design elements or recommended outfits based on the overall visual similarity according to the users’ preferred collections. This paper adopts physical and fashion attributes for effective personalized fashion compatibility evaluation and recommendation. The physical attributes are concluded into seven aspects: body shape, skin color, hairstyle, hair color, height, breast size (breasts), and color contrast. The personalized outfit compatibility problem in this paper is a multi-label classification problem and formulated as an optimization function with outfit images, fashion attributes, and physical attributes as input. It is the first attempt to solve the problem by discovering the correlation between visual image features, fashion attributes, and physical attributes. Specifically, the correlation is learned with two transformer encoders by updating attention weights of different embedding pairs during the training process. The model can not only predict the fashion attributes of the outfit’s top, bottom, shoes, and bag items, but also predict the incompatible physical attributes of an individual towards the given outfit. It can be used to recommend outfits that best fit an individual and the predicted fashion attributes can be used for result explanation. The O4U dataset, which contains rich annotations of fashion item attributes and human physical attributes of the outfits, is used to evaluate the performance of the proposed method. The quantitative and qualitative results show that the proposed method outperforms state-of-the-art methods for personalized outfit compatibility evaluation.