Hierarchical Classification Task Research Articles

HCAM-CL: A Novel Method Integrating a Hierarchical Cross-Attention Mechanism with CNN-LSTM for Hierarchical Image Classification

Deep learning networks have yielded promising insights in the field of image classification. However, the hierarchical image classification (HIC) task, which involves assigning multiple, hierarchically organized labels to each image, presents a notable challenge. In response to this complexity, we developed a novel framework (HCAM-CL), which integrates a hierarchical cross-attention mechanism with a CNN-LSTM architecture for the HIC task. The HCAM-CL model effectively identifies the relevance between images and their corresponding labels while also being attuned to learning the hierarchical inter-dependencies among labels. Our versatile model is designed to manage both fixed-length and variable-length classification pathways within the hierarchy. In the HCAM-CL model, the CNN module is responsible for the essential task of extracting image features. The hierarchical cross-attention mechanism vertically aligns these features with hierarchical levels, uniformly weighing the importance of different spatial regions. Ultimately, the LSTM module is strategically utilized to generate predictive outcomes by treating HIC as a sequence generation challenge. Extensive experimental evaluations on CIFAR-10, CIFAR-100, and design patent image datasets demonstrate that our HCAM-CL framework consistently outperforms other state-of-the-art methods in hierarchical image classification.

Data Sorting Influence on Short Text Manual Labeling Quality for Hierarchical Classification

The precise categorization of brief texts holds significant importance in various applications within the ever-changing realm of artificial intelligence (AI) and natural language processing (NLP). Short texts are everywhere in the digital world, from social media updates to customer reviews and feedback. Nevertheless, short texts’ limited length and context pose unique challenges for accurate classification. This research article delves into the influence of data sorting methods on the quality of manual labeling in hierarchical classification, with a particular focus on short texts. The study is set against the backdrop of the increasing reliance on manual labeling in AI and NLP, highlighting its significance in the accuracy of hierarchical text classification. Methodologically, the study integrates AI, notably zero-shot learning, with human annotation processes to examine the efficacy of various data-sorting strategies. The results demonstrate how different sorting approaches impact the accuracy and consistency of manual labeling, a critical aspect of creating high-quality datasets for NLP applications. The study’s findings reveal a significant time efficiency improvement in terms of labeling, where ordered manual labeling required 760 min per 1000 samples, compared to 800 min for traditional manual labeling, illustrating the practical benefits of optimized data sorting strategies. Comparatively, ordered manual labeling achieved the highest mean accuracy rates across all hierarchical levels, with figures reaching up to 99% for segments, 95% for families, 92% for classes, and 90% for bricks, underscoring the efficiency of structured data sorting. It offers valuable insights and practical guidelines for improving labeling quality in hierarchical classification tasks, thereby advancing the precision of text analysis in AI-driven research. This abstract encapsulates the article’s background, methods, results, and conclusions, providing a comprehensive yet succinct study overview.

Dimensionality Reduction for Hierarchical Multi-Label Classification: A Systematic Mapping Study

Hierarchical multi-label classification problems typically deal with datasets with many attributes and labels, which can negatively impact the classifier performance. The application of dimensionality reduction methods can significantly improve the performance of classifiers. Dimensionality reduction can be performed by feature extraction or feature selection, according to the problem domain and datasets characteristics. This work carried out a systematic literature mapping to identify the approaches and techniques of dimensionality reduction that have been used in hierarchical multi-label classification tasks. Searches were performed on 7 important databases for the Computer Science field. From a list of 184 retrieved papers, 12 were selected for analysis, from which it was possible to determine a general overview of studies conducted from 2010 to 2022. It was identified that feature selection was the most frequent reduction method, with filter approach standing out. In addition, it was detected that most of the works used tree hierarchical structure. As its main outcome, this paper presents the state of the art of dimensionality reduction problem for hierarchical multi-label classification, indicating trends and research issues in the field.

Interpretable Detection of Diabetic Retinopathy, Retinal Vein Occlusion, Age-Related Macular Degeneration, and Other Fundus Conditions.

Diabetic retinopathy (DR), retinal vein occlusion (RVO), and age-related macular degeneration (AMD) pose significant global health challenges, often resulting in vision impairment and blindness. Automatic detection of these conditions is crucial, particularly in underserved rural areas with limited access to ophthalmic services. Despite remarkable advancements in artificial intelligence, especially convolutional neural networks (CNNs), their complexity can make interpretation difficult. In this study, we curated a dataset consisting of 15,089 color fundus photographs (CFPs) obtained from 8110 patients who underwent fundus fluorescein angiography (FFA) examination. The primary objective was to construct integrated models that merge CNNs with an attention mechanism. These models were designed for a hierarchical multilabel classification task, focusing on the detection of DR, RVO, AMD, and other fundus conditions. Furthermore, our approach extended to the detailed classification of DR, RVO, and AMD according to their respective subclasses. We employed a methodology that entails the translation of diagnostic information obtained from FFA results into CFPs. Our investigation focused on evaluating the models' ability to achieve precise diagnoses solely based on CFPs. Remarkably, our models showcased improvements across diverse fundus conditions, with the ConvNeXt-base + attention model standing out for its exceptional performance. The ConvNeXt-base + attention model achieved remarkable metrics, including an area under the receiver operating characteristic curve (AUC) of 0.943, a referable F1 score of 0.870, and a Cohen's kappa of 0.778 for DR detection. For RVO, it attained an AUC of 0.960, a referable F1 score of 0.854, and a Cohen's kappa of 0.819. Furthermore, in AMD detection, the model achieved an AUC of 0.959, an F1 score of 0.727, and a Cohen's kappa of 0.686. Impressively, the model demonstrated proficiency in subclassifying RVO and AMD, showcasing commendable sensitivity and specificity. Moreover, our models enhanced interpretability by visualizing attention weights on fundus images, aiding in the identification of disease findings. These outcomes underscore the substantial impact of our models in advancing the detection of DR, RVO, and AMD, offering the potential for improved patient outcomes and positively influencing the healthcare landscape.

Multisource neural network feature map fusion: An efficient strategy to detect plant diseases

The use of RGB cameras or multispectral imaging systems can provide a wide range of applications for crop monitoring, plant phenotyping and disease detection. Although several approaches have been proposed, they increasingly use convolutional neural network-based architectures, which have, however, become increasingly cumbersome for improving classification results and difficult to train with few labeled data. Other increasingly popular approaches consist of using an ensemble of convolutional neural networks, in which each model solves a different problem. Since the inference is time- and resource-consuming due to the execution of multiple models, recent works have focused on transferring knowledge from an ensemble of models to a compact model to obtain better performance. In this paper, we propose an original approach that improves both accuracy and speed by reusing feature maps extracted by heterogeneous models from different data. Linked to each model, a transformation block allows keeping the correct number of feature maps and changing their dimension if necessary. To generate the feature maps, we only need the first layers of the ensemble models, thus taking advantage of ensemble learning methods, while adding only a few layers of a second model dedicated to aggregation of features. This approach allows an ensemble of models to be combined with different architectures that can process different data, such as several representations of the same input image or multispectral images, while being fast enough at the inference stage. This approach is adapted to hierarchical classification tasks by re-exploiting the same feature maps with different transformation blocks, offering accuracy gains in tasks not handled by the ensemble model. The results are provided for the PlantVillage dataset, with RGB images converted to three different color spaces, and for a custom Grapevine Yellow dataset, with multispectral images acquired with two different multispectral cameras.

Pediatric Injury Surveillance From Uncoded Emergency Department Admission Records in Italy: Machine Learning-Based Text-Mining Approach.

Unintentional injury is the leading cause of death in young children. Emergency department (ED) diagnoses are a useful source of information for injury epidemiological surveillance purposes. However, ED data collection systems often use free-text fields to report patient diagnoses. Machine learning techniques (MLTs) are powerful tools for automatic text classification. The MLT system is useful to improve injury surveillance by speeding up the manual free-text coding tasks of ED diagnoses. This research aims to develop a tool for automatic free-text classification of ED diagnoses to automatically identify injury cases. The automatic classification system also serves for epidemiological purposes to identify the burden of pediatric injuries in Padua, a large province in the Veneto region in the Northeast Italy. The study includes 283,468 pediatric admissions between 2007 and 2018 to the Padova University Hospital ED, a large referral center in Northern Italy. Each record reports a diagnosis by free text. The records are standard tools for reporting patient diagnoses. An expert pediatrician manually classified a randomly extracted sample of approximately 40,000 diagnoses. This study sample served as the gold standard to train an MLT classifier. After preprocessing, a document-term matrix was created. The machine learning classifiers, including decision tree, random forest, gradient boosting method (GBM), and support vector machine (SVM), were tuned by 4-fold cross-validation. The injury diagnoses were classified into 3 hierarchical classification tasks, as follows: injury versus noninjury (task A), intentional versus unintentional injury (task B), and type of unintentional injury (task C), according to the World Health Organization classification of injuries. The SVM classifier achieved the highest performance accuracy (94.14%) in classifying injury versus noninjury cases (task A). The GBM method produced the best results (92% accuracy) for the unintentional and intentional injury classification task (task B). The highest accuracy for the unintentional injury subclassification (task C) was achieved by the SVM classifier. The SVM, random forest, and GBM algorithms performed similarly against the gold standard across different tasks. This study shows that MLTs are promising techniques for improving epidemiological surveillance, allowing for the automatic classification of pediatric ED free-text diagnoses. The MLTs revealed a suitable classification performance, especially for general injuries and intentional injury classification. This automatic classification could facilitate the epidemiological surveillance of pediatric injuries by also reducing the health professionals' efforts in manually classifying diagnoses for research purposes.

A Comparative Study of Traditional, Ensemble and Neural Network-Based Natural Language Processing Algorithms

Accurate data analysis is an important part of data-driven financial audits. Given the increased data availability and various systems from which audit files are generated, RCSFI provides a way for standardization on behalf of analysis. This research attempted to automate this hierarchical text classification task in order to save financial auditors time and avoid errors. Several studies have shown that ensemble-based models and neural-network-based natural language processing (NLP) techniques achieved encouraging results for classification problems in various domains. However, there has been limited empirical research comparing the performance of both of the aforementioned techniques in a hierarchical multi-class classification setting. Moreover, neural-network- based NLP techniques have commonly been applied to English datasets and not to Dutch financial datasets. Additionally, this research took the implementation of hierarchical approaches into account for the traditional and ensemble-based models and found that the performance did not increase when implementing the included hierarchical approaches. DistilBERT achieved the highest scores on level 1-2-3-4 and outperformed the traditional and ensemble-based models. The model obtained a F1 of 94.50% for level 1-2-3-4. DistilBERT also outperformed BERTje at level 1-2-3-4 despite BERTje being specifically pre-trained on Dutch datasets.

Evaluating hierarchical machine learning approaches to classify biological databases.

The rate of biological data generation has increased dramatically in recent years, which has driven the importance of databases as a resource to guide innovation and the generation of biological insights. Given the complexity and scale of these databases, automatic data classification is often required. Biological data sets are often hierarchical in nature, with varying degrees of complexity, imposing different challenges to train, test and validate accurate and generalizable classification models. While some approaches to classify hierarchical data have been proposed, no guidelines regarding their utility, applicability and limitations have been explored or implemented. These include ‘Local’ approaches considering the hierarchy, building models per level or node, and ‘Global’ hierarchical classification, using a flat classification approach. To fill this gap, here we have systematically contrasted the performance of ‘Local per Level’ and ‘Local per Node’ approaches with a ‘Global’ approach applied to two different hierarchical datasets: BioLip and CATH. The results show how different components of hierarchical data sets, such as variation coefficient and prediction by depth, can guide the choice of appropriate classification schemes. Finally, we provide guidelines to support this process when embarking on a hierarchical classification task, which will help optimize computational resources and predictive performance.

Education-to-Skill Mapping Using Hierarchical Classification and Transformer Neural Network

Skills gained from vocational or higher education form an essential component of country’s economy, determining the structure of the national labor force. Therefore, knowledge on how people’s education converts to jobs enables data-driven choices concerning human resources within an ever-changing job market. Moreover, the relationship between education and occupation is also relevant in times of global crises, such as the COVID-19 pandemic. Healthcare system overload and skill shortage on one hand, and job losses related to lock-downs on the other, have exposed a necessity to identify target groups with relevant education backgrounds in order to facilitate their occupational transitions. However, the relationship between education and employment is complex and difficult to model. This study aims to propose the methodology that would allow us to model education-to-skill mapping. Multiple challenges arising from administrative datasets, namely imbalanced data, complex labeling, hierarchical structure and textual data, were addressed using six neural network-based algorithms of incremental complexity. The final proposed mathematical model incorporates the textual data from descriptions of education programs that are transformed into embeddings, utilizing transformer neural networks. The output of the final model is constructed as the hierarchical classification task. The effectiveness of the proposed model is demonstrated using experiments on national level data, which covers whole population of Lithuania. Finally, we provide the recommendations for the usage of proposed model. This model can be used for practical applications and scenario forecasting. Some possible applications for such model usage are demonstrated and described in this article. The code for this research has been made available on GitHub.

A taxonomy, data set, and benchmark for detecting and classifying malevolent dialogue responses

AbstractConversational interfaces are increasingly popular as a way of connecting people to information. With the increased generative capacity of corpus‐based conversational agents comes the need to classify and filter out malevolent responses that are inappropriate in terms of content and dialogue acts. Previous studies on the topic of detecting and classifying inappropriate content are mostly focused on a specific category of malevolence or on single sentences instead of an entire dialogue. We make three contributions to advance research on the malevolent dialogue response detection and classification (MDRDC) task. First, we define the task and present a hierarchical malevolent dialogue taxonomy. Second, we create a labeled multiturn dialogue data set and formulate the MDRDC task as a hierarchical classification task. Last, we apply state‐of‐the‐art text classification methods to the MDRDC task, and report on experiments aimed at assessing the performance of these approaches.

Kernelized fuzzy rough sets based online streaming feature selection for large-scale hierarchical classification

In recent years, many online streaming feature selection approaches focus on flat data, which means that all data are taken as a whole. However, in the era of big data, not only the feature space of data has unknown and evolutionary characteristics, but also the label space of data exists hierarchical structure. To address this problem, an online streaming feature selection framework for large-scale hierarchical classification task is proposed. The framework consists of three parts: (1) a new hierarchical data-oriented kernelized fuzzy rough model with sibling strategy is constructed, (2) the online important feature is selected based on feature correlation analysis, and (3) the online redundant feature is deleted based on feature redundancy. Finally, an empirical study using several hierarchical classification data sets manifests that the proposed method outperforms other state-of-the-art online streaming feature selection methods.

A knowledge-based approach to hierarchical classification: A voting metaphor

The paper proposes a new approach to hierarchical classification based on condition-action rules that represent expert knowledge in a given domain. The approach adopts a voting metaphor: each rule is regarded as a voter that expresses a preference for a given category to be assigned to an item to be classified; the category that receives more votes wins. Novel performance measures of hierarchical classifiers are also introduced that aim at overcoming the limitations of the current concepts of precision and recall. The proposed approach can be applied to any hierarchical classification task, for which expert knowledge is available. The viability of the approach and its performance are shown through a real-size application concerning the e-mail dispatching task inside a large public administration. The results obtained demonstrate that the proposed knowledge-based approach to hierarchical classification can reach a performance level comparable to that of human experts, if not even better.

Cost-sensitive hierarchical classification for imbalance classes

The hierarchical classification with an imbalance class problem is a challenge for in machine learning, and is caused by data with an uneven distribution. Learning from an imbalanced dataset can lead to performance degradation of the classifier. Cost-sensitive learning is a useful solution for handling the gap probability of majority and minority classes. This paper proposes a cost-sensitive hierarchical classification for imbalance classes (CSHCIC), constructing a cost-sensitive factor to balance the relationship between majority and minority classes. First, we divide a large hierarchical classification task into several small subclassification tasks by class hierarchy. Second, we establish a cost-sensitive factor by more precisely using the number of different samples of subclassifications. Then, we calculate the probability of every node using logistic regression. Lastly, we update the cost-sensitive factor using the flexibility factor and the number of samples. The experimental results show that the cost-sensitive hierarchical classification method achieves excellent performance on handling imbalance class datasets. The running time cost of the proposed method is smaller than most state-of-the-art methods.

Multi-Label Arabic Text Classification: An Overview

There is a massive growth of text documents on the web. This led to the increasing need for methods that can organize and classify electronic documents (instances) automati-cally. Multi-label classification task is widely used in real-world problems and it has been applied on di˙erent applications. It assigns multiple labels for each document simultaneously. Few and insuÿcient research studies have investigated the multi-label text classification problem in the Arabic language. Therefore, this survey paper aims to present an extensive review of the existing multi-label classification methods and techniques that can deal with multi-label problem. Besides, we focus on Arabic language by covering the relevant applications of multi-label classification on the Arabic text, and identify the main challenges faced by these studies. Furthermore, this survey presents an experimental comparisons of di˙erent multi-label classification methods applied for the Arabic context and points out some baseline results. We found that further investigations are also needed to improve the multi-label classification task in the Arabic language, especially the hierarchical classification task.

A hierarchical multi-label classification method based on neural networks for gene function prediction

abstractGene function prediction is used to assign biological or biochemical functions to genes, which continues to be a challenging problem in modern biology. Genes may exhibit many functions simultaneously, and these functions are organized into a hierarchy, such as a directed acyclic graph (DAG) for Gene Ontology (GO). Because of these characteristics, gene function prediction can be seen as a typical hierarchical multi-label classification (HMC) task. A novel HMC method based on neural networks is proposed in this article for predicting gene function based on GO. The proposed method belongs to a local approach by transferring the HMC task to a set of subtasks. There are three strategies implemented in this method to improve its performance. First, to tackle the imbalanced data set problem when building the training data set for each class, negative instances selecting policy and SMOTE approach are used to preprocess each imbalanced training data set. Second, a particular multi-layer perceptron (MLP) is designed for each node in GO. Third, a post processing method based on the Bayesian network is used to guarantee that the results are consistent with the hierarchy constraint. The experimental results indicate that the proposed HMC-MLPN method is a promising method for gene function prediction based on a comparison with two other state-of-the-art methods.

Review on hierarchical learning methods for large-scale classification task

Hierarchical classification is a task that uses hierarchy of categories in data. It can handle large-scale data. In recent years, significant research has emerged in this field, which is receiving increasingly more attention. In this paper, we first introduce the definition of hierarchical classification and thereafter review the important studies on several basic issues in large-scale hierarchical classification tasks based on different problem-solving strategies. First, we define the hierarchy formally and introduce some hierarchical evaluation metrics. Second, we explain how to construct the hierarchy, how to learn classifiers and perform feature selection using the information in the hierarchy, and how to design stopping strategies and introduce some representative studies on each issue. Finally, we summarize the features of large-scale hierarchical classification task and discuss the possible future work in this field.

HMC-ReliefF: Feature ranking for hierarchical multi-label classification

In machine learning, the growing complexity of the available data poses an increased challenge for its analysis. The rising complexity is both in terms of the data becoming more high-dimensional as well as the data having a more intricate structure. This emphasizes the need for developing machine learning algorithms that are able to tackle both the high-dimensionality and the complex structure of the data. Our work in this paper focuses on the development and analysis of the HMCReliefF algorithm, which is a feature relevance (ranking) algorithm for the task of Hierarchical Multi-label Classification (HMC). The basis of the algorithm is the RReliefF algorithm for regression that is adapted for hierarchical multi-label target variables. We perform an extensive experimental investigation of the HMC-ReliefF algorithm on several datasets from the domains of image annotation and functional genomics. We analyse the algorithm?s performance in terms of accuracy in a filterlike setting and also in terms of ranking stability for various parameter values. The results show that the HMC-ReliefF can successfully detect relevant features from the data that can be further used for constructing accurate predictive models. Additionally, the stability analysis helps to determine the preferred parameter values for obtaining not just accurate, but also a stable algorithm output.

CNN-RNN: a large-scale hierarchical image classification framework

Objects are often organized in a semantic hierarchy of categories, where fine-level categories are grouped into coarse-level categories according to their semantic relations. While previous works usually only classify objects into the leaf categories, we argue that generating hierarchical labels can actually describe how the leaf categories evolved from higher level coarse-grained categories, thus can provide a better understanding of the objects. In this paper, we propose to utilize the CNN-RNN framework to address the hierarchical image classification task. CNN allows us to obtain discriminative features for the input images, and RNN enables us to jointly optimize the classification of coarse and fine labels. This framework can not only generate hierarchical labels for images, but also improve the traditional leaf-level classification performance due to incorporating the hierarchical information. Moreover, this framework can be built on top of any CNN architecture which is primarily designed for leaf-level classification. Accordingly, we build a high performance network based on the CNN-RNN paradigm which outperforms the original CNN (wider-ResNet) and also the current state-of-the-art. In addition, we investigate how to utilize the CNN-RNN framework to improve the fine category classification when a fraction of the training data is only annotated with coarse labels. Experimental results demonstrate that CNN-RNN can use the coarse-labeled training data to improve the classification of fine categories, and in some cases it even surpasses the performance achieved by fully annotated training data. This reveals that, CNN-RNN can alleviate the challenge of specialized and expensive annotation of fine labels.

A Hierarchical Multi-Label Classification Algorithm for Gene Function Prediction

Gene function prediction is a complicated and challenging hierarchical multi-label classification (HMC) task, in which genes may have many functions at the same time and these functions are organized in a hierarchy. This paper proposed a novel HMC algorithm for solving this problem based on the Gene Ontology (GO), the hierarchy of which is a directed acyclic graph (DAG) and is more difficult to tackle. In the proposed algorithm, the HMC task is firstly changed into a set of binary classification tasks. Then, two measures are implemented in the algorithm to enhance the HMC performance by considering the hierarchy structure during the learning procedures. Firstly, negative instances selecting policy associated with the SMOTE approach are proposed to alleviate the imbalanced data set problem. Secondly, a nodes interaction method is introduced to combine the results of binary classifiers. It can guarantee that the predictions are consistent with the hierarchy constraint. The experiments on eight benchmark yeast data sets annotated by the Gene Ontology show the promising performance of the proposed algorithm compared with other state-of-the-art algorithms.

초등학생의 인지양식에 따른 안구운동기반 생물분류 사고과정 모형 개발

The purpose of this study was to develop eye-movement based classifying thinking model by identifying the differences in eye movement pattern shown in classification process between the elementary students who have analytic cognitive style and wholistic cognitive style. The subjects for the research consisted of 25 analytic students and 13 wholistic students. First, the participants were asked to solve the eye-tracking problem. After that, they gave an interview about the eye-tracking problem. Finally, they answered CSA test. The findings of this study were fourfold. First, 5 tasks were developed for revealed differences in classification process between students` cognitive style. The tasks were consisted of 4 non-hierarchical classification tasks and 1 hierarchical classification task. Second, there was a signi-ficant difference in students` fixation duration by students` cognitive style. Analytic students spent little time on sca-nning details and found the features successfully. They made different classification standard according to their cognitive style. Analytic students interested in features` detail, while wholistic students interested in salient features. Third, in-terviewing revealed the differences in the process of making standards. Finally, ECTM was developed. There were two steps in this model- Cognition of Elements and Making Stan-dards. This study developed eye-movement based classifying model by analyzing the differences in classifying process between analytic students and wholistic students. It suggested that classification should be taught differently by students` cognitive style and it should be taught following stage.