Multi-label Classification Approach Research Articles

BranchLabelNet: Anatomical Human Airway Labeling Approach using a Dividing-and-Grouping Multi-Label Classification.

Anatomical airway labeling is crucial for precisely identifying airways displaying symptoms such as constriction, increased wall thickness, and modified branching patterns, facilitating the diagnosis and treatment of pulmonary ailments. This study introduces an innovative airway labeling methodology, BranchLabelNet, which accounts for the fractal nature of airways and inherent hierarchical branch nomenclature. In developing this methodology, branch-related parameters, including position vectors, generation levels, branch lengths, areas, perimeters, and more, are extracted from a dataset of 1000 chest computed tomography (CT) images. To effectively manage this intricate branch data, we employ an n-ary tree structure that captures the complicated relationships within the airway tree. Subsequently, we employ a divide-and-group deep learning approach for multi-label classification, streamlining the anatomical airway branch labeling process. Additionally, we address the challenge of class imbalance in the dataset by incorporating the Tomek Links algorithm to maintain model reliability and accuracy. Our proposed airway labeling method provides robust branch designations and achieves an impressive average classification accuracy of 95.94% across fivefold cross-validation. This approach is adaptable for addressing similar complexities in general multi-label classification problems within biomedical systems.

Retraction Note to: Leakage detection and localization on water transportation pipelines: a multi-label classification approach

Retraction Note to: Leakage detection and localization on water transportation pipelines: a multi-label classification approach

YOLIC: An efficient method for object localization and classification on edge devices

In the realm of Tiny AI, we introduce “You Only Look at Interested Cells” (YOLIC), an efficient method for object localization and classification on edge devices. Through seamlessly blending the strengths of semantic segmentation and object detection, YOLIC provides improved computational efficiency and precision compared to traditional methods. By adopting Cells of Interest for classification instead of individual pixels, YOLIC encapsulates relevant information, reduces computational load, and enables rough object shape inference. Importantly, the need for bounding box regression is obviated, as YOLIC capitalizes on the predetermined cell configuration that provides information about potential object location, size, and shape. To tackle the issue of single-label classification limitations, a multi-label classification approach is applied to each cell for effectively recognizing overlapping or closely situated objects. This paper presents extensive experiments on multiple datasets to demonstrate that YOLIC achieves detection performance comparable to the state-of-the-art YOLO algorithms while surpassing in speed, exceeding 30fps on a Raspberry Pi 4B CPU.

K1K2NN: A novel multi-label classification approach based on neighbors for predicting COVID-19 drug side effects

COVID-19, a novel ailment, has received comparatively fewer drugs for its treatment. Side Effects (SE) of a COVID-19 drug could cause long-term health issues. Hence, SE prediction is essential in COVID-19 drug development. Efficient models are also needed to predict COVID-19 drug SE since most existing research has proposed many classifiers to predict SE for diseases other than COVID-19. This work proposes a novel classifier based on neighbors named K1 K2 Nearest Neighbors (K1K2NN) to predict the SE of the COVID-19 drug from 17 molecules' descriptors and the chemical 1D structure of the drugs. The model is implemented based on the proposition that chemically similar drugs may be assigned similar drug SE, and co-occurring SE may be assigned to chemically similar drugs. The K1K2NN model chooses the first K1 neighbors to the test drug sample by calculating its similarity with the train drug samples. It then assigns the test sample with the SE label having the majority count on the SE labels of these K1 neighbor drugs obtained through a voting mechanism. The model then calculates the SE-SE similarity using the Jaccard similarity measure from the SE co-occurrence values. Finally, the model chooses the most similar K2 SE neighbors for those SE determined by the K1 neighbor drugs and assigns these SE to that test drug sample. The proposed K1K2NN model has showcased promising performance with the highest accuracy of 97.53% on chemical 1D drug structure and outperforms the state-of-the-art multi-label classifiers. In addition, we demonstrate the successful application of the proposed model on gene expression signature datasets, which aided in evaluating its performance and confirming its accuracy and robustness.

Multi-label classification with imbalanced classes by fuzzy deep neural networks

Multi-label classification is an advantageous technique for managing uncertainty in classification problems where each data instance is associated with several labels simultaneously. Such situations are frequent in real-world scenarios, where decisions rely on imprecise or noisy data and adaptable classification methods are preferred. However, the problem of class imbalance represents a common characteristic of several multi-label datasets, in which the distribution of samples and their corresponding labels is non-uniform across the data space. In this paper, we propose a multi-label classification approach utilizing fuzzy logic in order to deal with the class imbalance problem. To eliminate the need for an expert to determine the logical rules of inference, deep neural networks are adopted, which have proven to be exceptionally effective for such problems. By combining both fuzzy inference systems and deep neural networks, the strengths and weaknesses of each approach can be mitigated. As a further development, a symbolic representation of time series is put in place to reduce data dimensionality and speed up the training procedure. This allows for more flexibility in model application, in particular with respect to time constraints arising from the causality of observed time series. Tests carried out on a multi-label classification dataset related to the current and voltage profiles of several household appliances show that the proposed model outperforms four baseline models for time series classification.

Enhancing Damage Localization in GFRP Composite Plates: A Novel Approach Using Feedback Optimization and Multi-Label Classification

Damage localization in GFRP (glass-fiber-reinforced polymer) composite plates is a crucial research area in marine engineering. This study introduces a feedback-based damage index (DI) combined with multi-label classification to enhance the accuracy of damage localization and address scenarios involving multiple damages. The research begins with the creation of a modal database for yachts’ GFRP composite plates using finite element modeling (FEM). A method for deriving a feedback-weighted matrix, based on the accuracy of the DI, is then developed. Sensitivity analysis reveals that the feedback DI is 50% more sensitive than the traditional DI, reducing false positives and missed detections. The associated feedback-weighted matrix depends solely on the structural shape, ensuring its transferability. To address the challenge for localizing multiple damages, a multi-label classification approach is proposed. The synergy between the feedback optimization and multi-label classification enables the rapid and precise localization of multiple damages in GFRP composite plates. Modal testing on damaged GFRP plates confirms the enhanced accuracy for combining the feedback DI with multi-label classification for pinpointing damage locations. Compared with traditional methods, this feedback DI method improves sensitivity, while multi-label classification effectively handles multiple damage scenarios, enhancing the overall efficiency of the damage diagnosis. The effectiveness of the proposed methods is validated through experimentation, offering robust theoretical support for composite plate damage diagnostics.

A new sentence embedding framework for the education and professional training domain with application to hierarchical multi-label text classification

In recent years, Natural Language Processing (NLP) has made significant advances through advanced general language embeddings, allowing breakthroughs in NLP tasks such as semantic similarity and text classification. However, complexity increases with hierarchical multi-label classification (HMC), where a single entity can belong to several hierarchically organized classes. In such complex situations, applied on specific-domain texts, such as the Education and professional training domain, general language embedding models often inadequately represent the unique terminologies and contextual nuances of a specialized domain. To tackle this problem, we present HMCCCProbT, a novel hierarchical multi-label text classification approach. This innovative framework chains multiple classifiers, where each individual classifier is built using a novel sentence-embedding method BERTEPro based on existing Transformer models, whose pre-training has been extended on education and professional training texts, before being fine-tuned on several NLP tasks. Each individual classifier is responsible for the predictions of a given hierarchical level and propagates local probability predictions augmented with the input feature vectors to the classifier in charge of the subsequent level. HMCCCProbT tackles issues of model scalability and semantic interpretation, offering a powerful solution to the challenges of domain-specific hierarchical multi-label classification. Experiments over three domain-specific textual HMC datasets indicate the effectiveness of HMCCCProbT to compare favorably to state-of-the-art HMC algorithms in terms of classification accuracy and also the ability of BERTEPro to obtain better probability predictions, well suited to HMCCCProbT, than three other vector representation techniques.

Multi-label Classification for Android Malware Based on Active Learning

The existing malware classification approaches (i.e., binary and family classification) can barely benefit subsequent analysis with their outputs. Even the family classification approaches suffer from lacking a formal naming standard and an incomplete definition of malicious behaviors. More importantly, the existing approaches are powerless for one malware with multiple malicious behaviors, while this is a very common phenomenon for Android malware in the wild. So that both of them actually cannot provide researchers with a direct and comprehensive enough understanding of malware. In this paper, we propose MLCDroid, an ML-based multi-label classification approach that can directly indicate the existence of pre-defined malicious behaviors. With an in-depth analysis, we summarize 6 basic malicious behaviors from real-world malware with security reports and construct a labeled dataset. We compare the results of 70 algorithm combinations to evaluate the effectiveness (best at 73.3%). Faced with the challenge of the expensive cost of data annotation, we further propose an active learning approach based on data augmentation, which can improve the overall accuracy to 86.7% with a data augmentation of 5,000+ high-quality samples from an unlabeled malware dataset. This is the first multi-label Android malware classification approach intending to provide more information on fine-grained malicious behaviors.

A Novel Deep Learning Approach for Myocardial Infarction Detection and Multi-Label Classification

A Novel Deep Learning Approach for Myocardial Infarction Detection and Multi-Label Classification

An analysis of annual reports from the sustainable development goals perspective

Purpose The sustainable development goals (SDGs) are introduced to guide achieving the sustainable goals and tackle the global problems. United Nations members may perform activities to achieve the predetermined goals and report on their SDG activities. The comprehension and commitment of several stakeholders are essential for the effective implementation of the SDGs. Countries encourage their stakeholders to perform and report their activities to meet the SDGs. The purpose of this study is to investigate the extent to which corporations’ annual reports address the SDGs to assess and comprehend their level of commitment to, priority of and integration of SDGs within their reporting structure. This research makes it easier to evaluate corporations’ sustainability performance and contributions to global sustainability goals by looking at the extent to which they address the SDGs. Design/methodology/approach In the study, it is revealed to what extent the reports meet the SDGs with the multilabel text classification approach. The SDG classification is carried out by examining the report with the help of a text analysis tool based on an enhanced version of gradient boosting. The implementation of a machine learning-based model allowed it to determine which SDGs are associated with the company’s operations without the requirement for the report’s authors to perform so. Therefore, instead of reading the texts to seek for “SDG” evidence as typically occurs in the literature, SDG proof was searched in relevant texts. Findings To show the feasibility of the study, the annual reports of the leading companies in Turkey are examined, and the results are interpreted. The study produced results including insights into the sustainable practices of businesses, priority SDG selection, benchmarking and business comparison, gaps and improvement opportunities identification and representation of the SDGs’ importance. Originality/value The findings of the analysis of annual reports indicate which SDGs they are concerned about. A gap in the literature can be noticed in the analysis of annual reports of companies that fall under a particular framework. In addition, it has sparked the idea of conducting research on a global scale and in a time series. With the aid of this research, decision-making procedures can be guided, and advancements toward the SDGs can be achieved.

Evaluating machine learning architectures for sound event detection for signals with variable signal-to-noise-ratios in the Beaufort Sea.

This paper explores the challenging polyphonic sound event detection problem using machine learning architectures applied to data recorded in the Beaufort Sea during the Canada Basin Acoustic Propagation Experiment. Four candidate architectures were investigated and evaluated on nine classes of signals broadcast from moored sources that were recorded on a vertical line array of hydrophones over the course of the yearlong experiment. These signals represent a high degree of variability with respect to time-frequency characteristics, changes in signal-to-noise ratio (SNR) associated with varying signal levels as well as fluctuating ambient sound levels, and variable distributions, which resulted in class imbalances. Within this context, binary relevance, which decomposes the multi-label learning task into a number of independent binary learning tasks, was examined as an alternative to the conventional multi-label classification (MLC) approach. Binary relevance has several advantages, including flexible, lightweight model configurations that support faster model inference. In the experiments presented, binary relevance outperformed conventional MLC approach on classes with the most imbalance and lowest SNR. A deeper investigation of model performance as a function of SNR showed that binary relevance significantly improved recall within the low SNR range for all classes studied.

EnML: Multi-label Ensemble Learning for Urdu Text Classification

Exponential growth of electronic data requires advanced multi-label classification approaches for the development of natural language processing (NLP) applications such as recommendation systems, drug reaction detection, hate speech detection, and opinion recognition/mining. To date, several machine and deep learning–based multi-label classification methodologies have been proposed for English, French, German, Chinese, Arabic, and other developed languages. Urdu is the 11th largest language in the world and has no computer-aided multi-label textual news classification approach. Unlike other languages, Urdu is lacking multi-label text classification datasets that can be used to benchmark the performance of existing machine and deep learning methodologies. With an aim to accelerate and expedite research for the development of Urdu multi-label text classification–based applications, this article provides multiple contributions as follows: First, it provides a manually annotated multi-label textual news classification dataset for the Urdu language. Second, it benchmarks the performance of traditional machine learning approaches particularly by adapting three data transformation approaches along with three top-performing machine learning classifiers and four algorithm adaptation-based approaches. Third, it benchmarks performance of 16 existing deep learning approaches and the four most widely used language models. Finally, it provides an ensemble approach that reaps the benefits of three different deep learning architectures to precisely predict different classes associated with a particular Urdu textual document. Experimental results reveal that proposed ensemble approach performance values (87% accuracy, 92% F1-score, and 8% hamming loss) are significantly higher than adapted machine and deep learning–based approaches.

A Multilabel Approach for Fault Detection and Classification of Transmission Lines using Binary Relevance

In Contemporary automation systems, Fault detection and classification of electrical transmission lines in grid systems are given top priority. The broad application of Machine Learning (ML) methods has enabled the substitute of conventional methods of fault identification and classification. These methods are more effective ones that can identify faults early on using a significant quantity of sensory data. So detecting simultaneous failures is difficult in the context of distracting the noise and several faults in the transmission lines. This study contributes by offering a unique way for concurrently detecting and classifying several faults using a multilabel classification approach based on binary relevance classifiers. The proposed binary relevance multilabel detection and classification models’ performances are examined. Under both ideal and problematic circumstances, faults in the dataset are collected. A variety of multilabel fault types detection and classification determines the suggested method’s effectiveness.

Predicting and characterising persuasion strategies in misinformation content over social media based on the multi-label classification approach

Persuasion aims at affecting the audience’s attitude and behaviour through a series of messages containing persuasion strategies. In the context of misinformation spread, identifying the persuasion strategies is important in order to warn people to be aware of the analogous persuasion attempts in the future. In this work, we address the prediction of persuasion strategies in micro-blogging posts through a multi-label classification approach based on a variety of lexical and semantic features. We conduct our experiments using a set of well-known multi-label classification algorithms, including multi-label decision tree, multi-label k-nearest neighbours, multi-label random forest, binary relevance and classifier chains. The results show that the model incorporating classifier chains and XGBoost algorithm achieves the best subset accuracy of 0.779 and the highest macro F1-score of 0.847. In addition, we evaluated and compared the features’ importance for different persuasion strategies and analysed the major errors of miss-out prediction. The findings of this article provide a benchmark for the multi-label classification of persuasion strategies in micro-blogging posts and lead to a better understanding of different persuasion attempts contained in social media misinformation.

Automated labelling of radiology reports using natural language processing: Comparison of traditional and newer methods

AbstractAutomated labelling of radiology reports using natural language processing allows for the labelling of ground truth for large datasets of radiological studies that are required for training of computer vision models. This paper explains the necessary data preprocessing steps, reviews the main methods for automated labelling and compares their performance. There are four main methods of automated labelling, namely: (1) rules‐based text‐matching algorithms, (2) conventional machine learning models, (3) neural network models and (4) Bidirectional Encoder Representations from Transformers (BERT) models. Rules‐based labellers perform a brute force search against manually curated keywords and are able to achieve high F1 scores. However, they require proper handling of negative words. Machine learning models require preprocessing that involves tokenization and vectorization of text into numerical vectors. Multilabel classification approaches are required in labelling radiology reports and conventional models can achieve good performance if they have large enough training sets. Deep learning models make use of connected neural networks, often a long short‐term memory network, and are similarly able to achieve good performance if trained on a large data set. BERT is a transformer‐based model that utilizes attention. Pretrained BERT models only require fine‐tuning with small data sets. In particular, domain‐specific BERT models can achieve superior performance compared with the other methods for automated labelling.

Distributed Online Multi-Label Learning with Privacy Protection in Internet of Things

With the widespread use of end devices, online multi-label learning has become popular as the data generated by users using the Internet of Things devices have become huge and rapidly updated. However, in many scenarios, the user data are often generated in a geographically distributed manner that is often inefficient and difficult to centralize for training machine learning models. At the same time, current mainstream distributed learning algorithms always require a centralized server to aggregate data from distributed nodes, which inevitably causes risks to the privacy of users. To overcome this issue, we propose a distributed approach for multi-label classification, which trains the models in distributed computing nodes without sharing the source data from each node. In our proposed method, each node trains its model with its local online data while it also learns from the neighbour nodes without transferring the training data. As a result, our proposed method achieved the online distributed approach for multi-label classification without losing performance when taking existing centralized algorithms as a reference. Experiments show that our algorithm outperforms the centralized online multi-label classification algorithm in F1 score, being 0.0776 higher in macro F1 score and 0.1471 higher for micro F1 score on average. However, for the Hamming loss, both algorithms beat each other on some datasets, and our proposed algorithm loses 0.005 compared to the centralized approach on average, which can be neglected. Furthermore, the size of the network and the degree of connectivity are not factors that affect the performance of this distributed online multi-label learning algorithm.

XTM: A Novel Transformer and LSTM-Based Model for Detection and Localization of Formally Verified FDI Attack in Smart Grid

The modern smart grid (SG) is mainly a cyber-physical system (CPS), combining the traditional power system infrastructure with information technologies. SG is frequently threatened by cyber attacks such as False Data Injection (FDI), which manipulates the states of power systems by adding malicious data. To maintain a reliable and secure operation of the smart grid, it is crucial to detect FDI attacks in the system along with their exact location. The conventional Bad Data Detection (BDD) algorithm cannot detect such stealthy attacks. So, motivated by the most recent deep learning (DL) developments and data-driven solutions, a new transformer-based model named XTM is proposed to detect and identify the exact locations of data intrusions in real-time scenarios. XTM, which combines the transformer and long short-term memory (LSTM), is the first hybrid DL model that explores the performance of transformers in this particular research field. First, a new threshold selection scheme is introduced to detect the presence of FDI, replacing the need for conventional BDD. Then, the exact intrusion point of the attack is located using a multilabel classification approach. A formally verified constraints satisfaction-based attack vector model was used to manipulate the data set. In this work, considering the temporal nature of power system, both hourly and minutely sensor data are used to train and evaluate the proposed model in the IEEE-14 bus system, achieving a detection accuracy of almost 100%. The row accuracy (RACC) metric was also evaluated for the location detection module, with values of 92.99% and 99.99% for the hourly and minutely datasets, respectively. Moreover, the proposed technique was compared with other deep learning models as well, showing that the proposed model outperforms the state-of-the-art methods mentioned in the literature.

Investigating Reasons for Disagreement in Natural Language Inference

AbstractWe investigate how disagreement in natural language inference (NLI) annotation arises. We developed a taxonomy of disagreement sources with 10 categories spanning 3 high- level classes. We found that some disagreements are due to uncertainty in the sentence meaning, others to annotator biases and task artifacts, leading to different interpretations of the label distribution. We explore two modeling approaches for detecting items with potential disagreement: a 4-way classification with a “Complicated” label in addition to the three standard NLI labels, and a multilabel classification approach. We found that the multilabel classification is more expressive and gives better recall of the possible interpretations in the data.

Multi-label sub-pixel classification of red and black soil over sparse vegetative areas using AVIRIS-NG airborne hyperspectral image

The limited spatial resolution of the hyperspectral (Hx) images corrupts the spectral information of pure materials and their distribution in an image. The accuracy of characterising or classifying the soil using Hx or Mx images decreases when surfaces are covered by vegetation. In the presence of vegetation, a single pixel can be labelled as either vegetation or a specific soil type. In this context, we have studied the usefulness of the multi-label classification (MLC) approach to classify the soil colour in the presence of vegetation cover. We have evaluated its performance on airborne Hx (Airborne Visible InfraRed Imaging Spectrometer - Next Generation, AVIRIS-NG) images acquired over Berambadi catchment, Karnataka, India. The potential of MLC to classify soil types using simulated Sentinel-2 images (Sen-S) was also explored in this study. The surface soil colour in the Berambadi catchment was classified into two soil types (“black” and “red” soils). The proposed MLC approach consists of (1) simulating the mixed spectra of vegetation, red soil, black soil and non-photosynthesis-vegetation (NPV) using linear-mixture-model (LMM) and bi-linear-mixture-model (BLM) to generate a well-balanced calibration data set, and (2) labelling of each pixel into multiple classes using MLC approaches. Performances of classical and deep-neural-network (DNN) based MLC models were compared to identify the best performing model. Our results showed significant performance for the cost-sensitive-multi-label-embedding (CLEMS) model when applied to both AVIRIS-NG (OA=97%) and Sen-S (OA=93%) images. The proposed method requires a limited number of ground-truth samples, and it is operationally practical for large Hx and Mx images.

A novel strategy for locational detection of false data injection attack

State estimation algorithms furnish an effective approach in monitoring and control of critical infrastructures like smart grid in real-time. Recently, false data injection attack (FDIA) has shown its detrimental effects by bypassing the conventional bad data detection test. The current trend in the detection technique of such class of attack remains localised in their presence detection within the measurement set whereas their exact locations of intrusions remain unknown. To palliate this issue, this work showcases an effective implementation of deep learning models to determine the exact intrusion points in real-time. Such novel deep learning models along with the conventional bad data detector can effectively identify the presence of any unstructured and structured false data injections within the measurement set, hence providing a cost-effective strategy. These deep learning models can effectively capture the inconsistency with co-occurrence dependency of the potential attack vectors within the measurement set, thus providing a multilabel classification approach. Moreover, such class of deep learning architectures being model free endow the grid operators with real-time detection without any preliminary statistical assumptions of the grid. An extensive analysis on the standard IEEE test bench showcases the efficacy of such class of detection policy undergoing varying attack and noise margins.