Single-label Classification Research Articles

A multi-label classification system for anomaly classification in electrocardiogram.

Automatic classification of ECG signals has become a research hotspot, and most of the research work in this field is currently aimed at single-label classification. However, a segment of ECG signal may contain more than two cardiac diseases, and single-label classification cannot accurately judge all possibilities. Besides, single-label classification performs classification in units of segmented beats, which destroys the contextual relevance of signal data. Therefore, studying the multi-label classification of ECG signals becomes more critical. This study proposes a method based on the multi-label question transformation method-binary correlation and classifies ECG signals by constructing a deep sequence model. Binary correlation simplifies the learning difficulty of deep learning models and converts multi-label problems into multiple binary classification problems. The experimental results are as follows: F1 score is 0.767, Hamming Loss is 0.073, Coverage is 3.4, and Ranking Loss is 0.262. It performs better than existing work.

Hierarchical classification for account code suggestion

As part of invoice processing, businesses are required to manually classify each line item on an invoice to a specific financial account. This can be time-consuming and challenging when there is a large set of account codes to choose from. Failing to select the correct account will lead to errors in financial reporting which can be misleading for stakeholders and have adverse effects during a financial audit. The emergence of cloud-based accounting platforms has introduced potential areas for automated support across invoice processing tasks such as helping bookkeepers to select the correct financial account. Traditionally, account code suggestion is framed as a multi-class classification task, however, we explore the applicability of using a hierarchical single-label classifier. Account codes can be expressed as taxonomic classes, either explicitly through the chart of accounts or implicitly through associations with reconciled bank accounts. Our research provides evidence to support that the exploitation of hierarchical information from induced taxonomies can be highly advantageous for improving classification and recommendation performance. Furthermore, we introduce Top-K Parent Boosting, a novel post-processing strategy. We demonstrate the suitability of Top-K Parent Boosting for DAG structures and highlight its superiority in improving recommendation performance over former strategies.

Multi-label rhinitis prediction using ensemble neural network chain with pre-training

Rhinitis is a kind of respiratory disease that is difficult to cure. Timely and accurate prediction in its early stage is an effective method for diagnosis of rhinitis. Machine learning is often applied in predicting clinical rhinitis. However, those problems like multi-label features, class imbalance, and poor generalization performance usually occur on rhinitis prediction. This paper introduces an ensemble neural network chain model with pre-training on rhinitis multi-label classification. We apply stacked autoencoders for denoising and feature dimensionality reduction, add pre-training networks to extract global correlations, and build neural network chain to extract local relevant information for single-label classification. This proposed model can use both global and local label correlations to reduce the influence of unreasonable label sequences on classification. A total of 2231 clinical rhinitis cases from Shanghai Tongji Hospital affiliated to Tongji University is conducted for training and test. The cross-validation results show that the average Hamming Loss, accuracy, recall and F1-score is 0.0195, 87.88%, 92.32% and 92.88%, respectively. Compared to various typical multi-label classifiers, the proposed model achieves better generalization performance in evaluation measures. In addition, we calculate the feature importance of rhinitis based on the purity of splitting nodes in Random Forest and study the correlations between rhinitis features and classification, which have a good reference value for diagnosis and treatment of clinical rhinitis.

Identification of Geriatric Depression and Anxiety Using Activity Tracking Data and Minimal Geriatric Assessment Scales

The identification of geriatric depression and anxiety is important because such conditions are the most common comorbid mood problems that occur in older adults. The goal of this study was to build a machine learning framework that identifies geriatric mood disorders of depression and anxiety using low-cost activity trackers and minimal geriatric assessment scales. We collected activity tracking data from 352 mild cognitive impairment patients, from 60 to 90 in age, by having them wear activity trackers on their wrist for more than a month. We then extracted the features of 24-h activity rhythms and sleep patterns from the time-series activity tracking data. To increase the accuracy, we designed a novel method to incorporate additional features from questionnaire-based assessments of the geriatric depression scale and geriatric anxiety inventory into the activity tracking features. In the multi-label classification, we applied the binary relevance method to develop two single-label classifiers for depression and anxiety. The best hyper-parameters of classification algorithms for each label were selected by comparing the classification performance. We finally selected the combination of classifiers for depression and anxiety with the lowest Hamming loss as a multi-label classifier. This study successfully demonstrated the possibility of identifying geriatric depression and anxiety using low-cost activity trackers and minimal geriatric assessment scales for use in the real fields.

3D Convolution Recurrent Neural Networks for Multi-Label Earthquake Magnitude Classification

We examine a classification task in which signals of naturally occurring earthquakes are categorized ranging from minor to major, based on their magnitude. Generalized to a single-label classification task, most prior investigations have focused on assessing whether an earthquake’s magnitude falls into the minor or large categories. This procedure is often not practical since the tremor it generates has a wide range of variation in the neighboring regions based on the distance, depth, type of surface, and several other factors. We present an integrated 3-dimensional convolutional recurrent neural network (3D-CNN-RNN) trained to classify the seismic waveforms into multiple categories based on the problem formulation. Recent studies demonstrate using artificial intelligence-based techniques in earthquake detection and location estimation tasks with progress in collecting seismic data. However, less work has been performed in classifying the seismic signals into single or multiple categories. We leverage the use of a benchmark dataset comprising of earthquake waveforms having different magnitude and present 3D-CNN-RNN, a highly scalable neural network for multi-label classification problems. End-to-end learning has become a conventional approach in audio and image-related classification studies. However, for seismic signals classification, it has yet to be established. In this study, we propose to deploy the trained model on personal seismometers to effectively categorize earthquakes and increase the response time by leveraging the data-centric approaches. For this purpose, firstly, we transform the existing benchmark dataset into a series of multi-label examples. Secondly, we develop a novel 3D-CNN-RNN model for multi-label seismic event classification. Finally, we validate and evaluate the learned model with unseen seismic waveforms instances and report whether a specific event is associated with a particular class or not. Experimental results demonstrate the superiority and effectiveness of the proposed approach on unseen data using the multi-label classifier.

A random grouping-based self-regulating artificial bee colony algorithm for interactive feature detection

As the dimensionality and complexity of datasets increase, such as biological data, the demand for fast and efficient technologies to detect relevant feature information from these data is also increasing. Extensive progress has been made in the development of evolutionary algorithms (EAs), which can detect the association between a single feature and class label in high-dimensional data. However, when facing the high-dimensional problem caused by interactions between features, the search space of EAs increases exponentially with an increase in the number of features, resulting in unsatisfactory solution quality. Therefore, this study proposed a random grouping-based self-regulating artificial bee colony algorithm (RCABC). RCABC first decomposes all dataset features into a series of dynamic subsets using a dynamic random grouping (DRG) strategy. Thereafter, a self-regulating bee colony optimizer (S-Optimizer) is used to detect relevant interactive features in each subset. This study demonstrates the superiority of the proposed algorithm through experimental results on synthetic and real-world biological datasets.

EMBER: multi-label prediction of kinase-substrate phosphorylation events through deep learning.

Kinase-catalyzed phosphorylation of proteins forms the backbone of signal transduction within the cell, enabling the coordination of numerous processes such as the cell cycle, apoptosis, and differentiation. Although on the order of 105 phosphorylation events have been described, we know the specific kinase performing these functions for <5% of cases. The ability to predict which kinases initiate specific individual phosphorylation events has the potential to greatly enhance the design of downstream experimental studies, while simultaneously creating a preliminary map of the broader phosphorylation network that controls cellular signaling. We describe Embedding-based multi-label prediction of phosphorylation events (EMBER), a deep learning method that integrates kinase phylogenetic information and motif-dissimilarity information into a multi-label classification model for the prediction of kinase-motif phosphorylation events. Unlike previous deep learning methods that perform single-label classification, we restate the task of kinase-motif phosphorylation prediction as a multi-label problem, allowing us to train a single unified model rather than a separate model for each of the 134 kinase families. We utilize a Siamese neural network to generate novel vector representations, or an embedding, of peptide motif sequences, and we compare our novel embedding to a previously proposed peptide embedding. Our motif vector representations are used, along with one-hot encoded motif sequences, as input to a classification neural network while also leveraging kinase phylogenetic relationships into our model via a kinase phylogeny-weighted loss function. Results suggest that this approach holds significant promise for improving the known map of phosphorylation relationships that underlie kinome signaling. The data and code underlying this article are available in a GitHub repository at https://github.com/gomezlab/EMBER. Supplementary data are available at Bioinformatics online.

Region-level arabic dialect identification using deep learning models

The automatic classification of the Arabic language dialects is the preliminary step towards establishing many dialectal-sensitive Arabic natural language processing tasks. Arabic dialect identification entails predicting the dialects associated with specific textual inputs and classifying them under their respected labels. In this paper, we propose a novel approach by merging several distinct datasets to obtain a large, diverse, and bias-free dialectal corpus. Our dataset is a collection of parallel sentences translated into multiple dialects (MADAR), as well as tweets gathered from Twitter users (NADI-2020, NADI-2021, QADI, &amp; ARAP-Tweet 2.0). The collected dataset is classified into seven labels: Gulf, Levant, Iraq, Maghreb, Nile Basin, Yemen, and Modern Standard Arabic. The merged dataset was cleansed to produce Arabic sentences free of punctuation, non-Arabic characters, numbers, repeating characters, empty lines, and elongation characters. We obtained a high dialectal classification accuracy using a new Word2vec embedding model on the merged dialectal dataset. Seven deep learning systems were trained on a balanced subset of the dataset. These models are Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), Bidirectional-LSTM (BILSTM), Bidirectional-GRU (BIGRU), Convolutional-LSTM (CLSTM), and Convolutional-GRU (CGRU). Single-label classification tests ran on these trained models acquired a minimum accuracy of 77.90% (CNN) and a maximum accuracy of 81.52% (BILSTM). We further evaluated the accuracy of tests ran for short and long sentences with 87.52% attained accuracy for classifying short sentences with CGRU and 94.06% for long sentences using BIGRU, both of which are indications of proposed approach efficacy to move forward.

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.

A Convolutional Neural Network-Based Framework for Classification of Protein Localization Using Confocal Microscopy Images

Understanding protein subcellular localization is vital and indispensable in proteomics research. Molecular biology and computer science developments have enabled the use of computational approaches to identify proteins in cells. An excellent method for locating proteins is confocal microscopy, used by the Human Protein Atlas (HPA). It can help researchers better understand human pathology and help physicians automate medical imaging interpretation by classifying human proteins. Human protein Atlas comprises millions of images annotated with single or multiple labels. However, only a few approaches are developed for automatic prediction of protein localization, and they focus mainly on single-label classification. Therefore, a recognition system for multi-label classification of HPA with acceptable performance should be developed. Hence, this study aims to develop a deep learning-based system for the multi-label classification of HPA. Specifically, two architectures have been proposed in this work for automatically extracting features from the images and predicting the localization of the proteins in 28 subcellular compartments. First, a convolutional neural network has been proposed, which has been trained from scratch and second an ensemble-based model using transfer learning architectures has been proposed. The results shows that both the models perform well in protein localization classification tasks for major cellular organelles. Yet, in this study, the proposed convolutional network outperforms the ensemble model in classification of images with multiple simultaneous protein localizations. The models were evaluated on 3 performance criteria: recall, precision and f1-score. The proposed convolutional neural network beats the ensemble model by achieving recall of 0.75, precision of 0.75 and f1-score of 0.74.

Seeking Subjectivity in Visual Emotion Distribution Learning.

Visual Emotion Analysis (VEA), which aims to predict people's emotions towards different visual stimuli, has become an attractive research topic recently. Rather than a single label classification task, it is more rational to regard VEA as a Label Distribution Learning (LDL) problem by voting from different individuals. Existing methods often predict visual emotion distribution in a unified network, neglecting the inherent subjectivity in its crowd voting process. In psychology, the Object-Appraisal-Emotion model has demonstrated that each individual's emotion is affected by his/her subjective appraisal, which is further formed by the affective memory. Inspired by this, we propose a novel Subjectivity Appraise-and-Match Network (SAMNet) to investigate the subjectivity in visual emotion distribution. To depict the diversity in crowd voting process, we first propose the Subjectivity Appraising with multiple branches, where each branch simulates the emotion evocation process of a specific individual. Specifically, we construct the affective memory with an attention-based mechanism to preserve each individual's unique emotional experience. A subjectivity loss is further proposed to guarantee the divergence between different individuals. Moreover, we propose the Subjectivity Matching with a matching loss, aiming at assigning unordered emotion labels to ordered individual predictions in a one-to-one correspondence with the Hungarian algorithm. Extensive experiments and comparisons are conducted on public visual emotion distribution datasets, and the results demonstrate that the proposed SAMNet consistently outperforms the state-of-the-art methods. Ablation study verifies the effectiveness of our method and visualization proves its interpretability.

SCIDA: Self-Correction Integrated Domain Adaptation From Single- to Multi-Label Aerial Images

Most publicly available datasets for image classification are with single labels, while images are inherently multi-labeled in our daily life. Such an annotation gap makes many pre-trained single-label classification models fail in practical scenarios. This annotation issue is more concerned for aerial images: Aerial data collected from sensors naturally cover a relatively large land area with multiple labels, while annotated aerial datasets, which are publicly available (e.g., UCM, AID), are single-labeled. As manually annotating multi-label aerial images would be time/labor-consuming, we propose a novel self-correction integrated domain adaptation (SCIDA) method for automatic multi-label learning. SCIDA is weakly supervised, i.e., automatically learning the multi-label image classification model from using massive, publicly available single-label images. To achieve this goal, we propose a novel Label-Wise self-Correction (LWC) module to better explore underlying label correlations. This module also makes the unsupervised domain adaptation (UDA) from single- to multi-label data possible. For model training, the proposed model only uses single-label information yet requires no prior knowledge of multi-labeled data; and it predicts labels for multi-label aerial images. In our experiments, trained with single-labeled MAI-AID-s and MAI-UCM-s datasets, the proposed model is tested directly on our collected Multi-scene Aerial Image (MAI) dataset.

ANALYSIS OF THE PROBLEM OF MULTIVALUED OF CLASS LABELS ON THE SECURITY OF COMPUTER NETWORKS

Modern computer networks have a complex infrastructure that requires constant monitoring to detect anomalous conditions that can cause malfunctions, which is unacceptable for large-scale distributed networks. An important problem in the intelligent processing of syslog data is the existence of multilabel datasets. Among the Russian language scientific publications, the problem under consideration in the context of information security of computer networks is not presented. The purpose of the research work is to increase the security of computer networks through the use of multi-label learning methods in solving the problem of classifying system log class labels. In this paper, a comparative analysis of single-label and multi-label classifiers in a computational experiment on the Mean accuracy metric was carried out. According to the results of the analysis, 80% of single-label classifiers were inferior in classification accuracy according to the Mean accuracy multi-label metric to their counterparts, which may indicate a strong influence of multi-label class labels on the models under consideration. The considered structure of experimental data in a tabular form is influenced by the multi-label problem much more strongly than it can be estimated by a standard frequency check, which actualizes further research in this direction.

A Supervised Learning Framework for Joint Estimation of Angles-of-Arrival and Number of Sources

Machine learning is a promising technique for angle-of-arrival (AOA) estimation of waves impinging a sensor array. However, the majority of the methods proposed so far only consider a known, fixed number of impinging waves, i.e., a fixed number of sources (NOS). This paper proposes a machine-learning-based estimator designed for the case when the NOS is variable and hence unknown a priori. The proposed estimator comprises a framework of single-label classifiers. Each classifier predicts if waves are present within certain randomly selected segments of the array’s field of view (FOV), resulting from discretising the FOV with a certain (FOV) resolution. The classifiers’ predictions are combined into a probabilistic angle spectrum, whereupon the NOS and the AOAs are estimated jointly by applying a probability threshold whose optimal level is learned from data. The estimator’s performance is assessed using a new performance metric: the joint AOA estimation success rate. Numerical simulations show that for low SNR (−10 dB), a low FOV resolution (2°) yields a higher success rate than a high resolution (1°), whereas the opposite applies for mid (0 dB) and high (10 dB) SNRs. In nearly all simulations, except one at low SNR and a high FOV resolution, the proposed estimator outperforms the MUSIC algorithm if the maximum allowed AOA estimation error is approximately equal to (or larger than) the FOV resolution.

A combinatorial optimization approach for multi-label associative classification

Mining associations between variables corresponding to multiple class labels (or outcomes) is prevalent in various applied domains, such as medical diagnosis, text mining, e-commence, and social behavior analysis. While most associative classification algorithms have been developed to discover association rules of binary variables for single-label classification problem, there are limited methods designed for the problem, called multi-label classification, that accounts for multi-labels. In this study, we consider the multi-label classification problem as a multi-class classification problem and formulate it as a 0–1 integer optimization model. We then leverage combinatorial optimization and association rule techniques to solve this hard problem. More specifically, we propose a ranking metric for selecting and aggregating stronger rules to form an optimal multi-label classifier. The computational results for multiple real applications show that our algorithm is able to identify significant association rules between key variables and multiple labels, and in turn achieves a competitive classification performance compared to state-of-the-art machine learning methods such as logistic regression, decision trees, and random forest. Moreover, we design a user-interface tool interfaced with the developed algorithm and demonstrate a medical diagnosis problem to predict multiple high-risk subgroups during emergency care in practice.

Image emotion distribution learning based on enhanced fuzzy KNN algorithm with sparse learning

With the trend of people expressing opinions and emotions via images online, increasing attention has been paid to affective analysis of visual content. Traditional image affective analysis mainly focuses on single-label classification, but an image usually evokes multiple emotions. To this end, emotion distribution learning is proposed to describe emotions more explicitly. However, most current studies ignore the ambiguity included in emotions and the elusive correlations with complex visual features. Considering that emotions evoked by images are delivered through various visual features, and each feature in the image may have multiple emotion attributes, this paper develops a novel model that extracts multiple features and proposes an enhanced fuzzy k-nearest neighbor (EFKNN) to calculate the fuzzy emotional memberships. Specifically, the multiple visual features are converted into fuzzy emotional memberships of each feature belonging to emotion classes, which can be regarded as an intermediate representation to bridge the affective gap. Then, the fuzzy emotional memberships are fed into a fully connected neural network to learn the relationships between the fuzzy memberships and image emotion distributions. To obtain the fuzzy memberships of test images, a novel sparse learning method is introduced by learning the combination coefficients of test images and training images. Extensive experimental results on several datasets verify the superiority of our proposed approach for emotion distribution learning of images.

Dual class representation learning for few-shot image classification

Few-shot learning (FSL) models are trained on base classes that have many training examples and evaluated on novel classes that have very few training examples. Since these models cannot be properly fine-tuned on the novel classes using the few training examples, FSL methods use the features extracted by the model trained on the base classes for evaluating it on the novel classes. In this work, we propose a novel few-shot learning approach that focuses on making the network representations generic, to improve its novel class performance. Specifically, our proposed approach introduces dual class information for the base class training images using a base class label and a self-supervised class label. The self-supervised classes are synthesized by applying transformations that alter the image structure and are not dependent on the base classes. Our approach trains the network to recognize both types of classes simultaneously for each training image. This process incorporates the class-invariant information of the self-supervised classes into the model representations and helps the model learn generic features which in turn improves its novel class performance. We also propose a novel approach for creating self-supervised classes that helps the network incorporate a deeper understanding of the structure of the objects and their parts. This approach significantly outperforms existing self-supervision methods in this setting. We empirically demonstrate on multiple datasets that our approach is very effective in addressing the few-shot learning problem and significantly outperforms the single class representation learning approach that uses a single image class label per training image.

Multi-label semantic feature fusion for remote sensing image captioning

For remote sensing image (RSI) captioning tasks, two-stage RSI captioning methods have achieved high performance because they introduce the results of other RSI tasks, such as image classification as prior information. However, most previous works treat image classification in the two-stage RSI captioning method as a single-label classification task, which cannot adequately describe the entire contents of complex RSIs and may cause semantic ambiguity. To settle this problem and further refine image feature representation, we introduce multi-label classification into two-stage RSI captioning to provide sufficient and accurate prior semantic information and propose a multi-label semantic feature fusion (MLSFF) framework. Specifically, we design a robust multi-label semantic attribute extractor to extract multi-label semantic attributes of RSIs. To obtain discriminative feature representations for RSI captioning, we propose two cross-modal semantic feature fusion operators that fuse the extracted semantic attributes and the image feature extracted by the convolutional neural network. The results of extensive numerical experiments show that the proposed method can achieve state-of-the-art performance on the UCM-Captions, Sydney-Captions, and RSICD datasets. Specifically, on the UCM-Captions dataset, our method achieves a gain of 8.2% in Sm score over the SAT (LAM) method (Zhang et al., 2019c). On the Sydney-Captions dataset, our method improves the Sm score by 17.4% compared with the TCE loss-based method (Li et al., 2020a). On the RSICD, our method outperforms the multi-level attention method (Li et al., 2020b) by 3.2% in terms of the Sm score. Code is available at https://github.com/xtye5025/MLSFF.

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.

Multi-Self-Attention for Aspect Category Detection and Biomedical Multilabel Text Classification with BERT

Multilabel classification is one of the most challenging tasks in natural language processing, posing greater technical difficulties than single-label classification. At the same time, multilabel classification has more natural applications. For individual labels, the whole piece of text has different focuses or component distributions, which require full use of local information of the sentence. As a widely adopted mechanism in natural language processing, attention becomes a natural choice for the issue. This paper proposes a multilayer self-attention model to deal with aspect category and word attention at different granularities. Combined with the BERT pretraining model, it achieves competitive performance in aspect category detection and electronic medical records’ classification.