Flat Classification Research Articles

Intelligent ultrasonic aspirator: Advancing tissue differentiation through hierarchical classification during hand-held resection

Modern neurosurgery strives to maximize tumor removal while preserving healthy tissue integrity. Accurate intraoperative differentiation between tumor and healthy tissue is crucial yet challenging. Often neurosurgeons rely on their experience and haptic feedback during palpation to distinguish between tumor and healthy tissue. A commonly used hand-held tool for tissue removal during neurosurgery is the ultrasonic aspirator, which changes its electrical properties as it interacts with tissue. The goal is to equip the ultrasonic aspirator with the ability to differentiate between different types of tissue while at the same time not interfering with the surgical workflow and providing comprehensible outcomes. To this end, a hierarchical classification approach is employed as a proof of concept, enabling precise identification of tissue stiffness during resection.The hierarchical approach is compared with the standard flat classification, commonly used in machine learning. Within the hierarchical approach, two strategies are employed: mandatory leaf-node predictions (MLNP) and non-mandatory leaf-node predictions (NMLNP). The NMLNP allows prediction to revert to a parent node when certainty is low. Data are acquired on three artificial tissue models – differing in stiffness – with an ultrasonic aspirator in a hand-held manner. The dataset comprises 1,821 data points for training and 186 for testing after balancing.The results indicate a slight performance advantage for the hierarchical classification MLNP approach over the flat classification approach in the absence of confidence thresholds, with weighted F2-scores of 0.781 and 0.762, respectively. However, the application of confidence thresholds results in both approaches exhibiting comparable performance, with the hierarchical NMLNP approach achieving a weighted F1-score of 0.920, thereby demonstrating superior overall performance. The effects of enforcing these thresholds and excluding data with low certainty are thoroughly investigated. This work emphasizes the feasibility of tissue differentiation using a hand-held ultrasound aspirator while resecting tissue. Moreover, it highlights the capability of hierarchical classification in advancing tissue differentiation accuracy during neurosurgical procedures, which could ultimately aid surgeons and enhance the safety of intraoperative workflows.

Attribute reduction for hierarchical classification based on improved fuzzy rough set

Attribute reduction plays a critical role in extracting valuable information from high-dimensional datasets. Compared to Pawlak rough set, fuzzy rough set can preserve more data information, making it a prominent focus in the research of attribute reduction. However, current fuzzy rough set-based attribute reduction focuses on flat classification, neglecting distinguishable stability information in hierarchical classification, which leads to insufficient data utilization and reduces the accuracy of attribute reduction. To address these issues, this paper presents two types of fuzzy rough set, named IFRS-I and IFRS-II. Especially, IFRS-I is an improved fuzzy rough set for flat classification, while IFRS-II is constructed based on IFRS-I for hierarchical classification. Unlike traditional fuzzy rough set, IFRS-II has the following two advantages: (1) a stability factor is designed to measure the stability difference among decision classes, (2) a tolerance index is designed to represent the tolerance distance between decision classes based on the approximate information of different decision classes in hierarchical classification. Finally, a stable and effective attribute reduction based on IFRS-II (ARIFRS-II) is designed for hierarchical classification. Experiments demonstrate that compared with the existing related algorithms, ARIFRS-II obtains a higher classification accuracy and stability, while maintaining a suitable number of subsets after reduction.

ENHANCING NON-NATIVE ACCENT RECOGNITION THROUGH A COMBINATION OF SPEAKER EMBEDDINGS, PROSODIC AND VOCAL SPEECH FEATURES

The transcription accuracy of automatic speech recognition (ASR) system may suffer when recognizing accented speech. The resulting bias in ASR system towards a specific accent due to under representation of that accent in the training dataset. Accent recognition of existing speech samples can help with the preparation of the training datasets, which is an important step toward closing the accent gap and eliminating biases in ASR system. For that we built a system to recognize accent from spoken speech data. In this study, we have explored some prosodic and vocal speech features as well as speaker embeddings for accent recognition on our custom English speech data that covers speakers from around the world with varying accents. We demonstrate that our selected speech features are more effective in recognizing nonnative accents. Additionally, we experimented with a hierarchical classification model for multi-level accent classification. To establish an accent hierarchy, we employed a bottom-up approach, combining regional accents and categorizing them as either native or non-native at the top level. Furthermore, we conducted a comparative study between flat classification and hierarchical classification using the accent hierarchy structure.

Deep Attention-based Classification of Plant Images with Hierarchical Similarity and Imbalanced Distribution

—Standard datasets in deep learning-basedimage classification usually provide two favorable conditions for design: preservation of visual homogeneity of each category and uniform distribution of sample images. These conditions are not assured in a dataset of plant images. Two different species of plants under the same genus look very similar and the number of collectible images has a large variation over species.Visual similarity, however, can be turned into advantage in hierarchical approach, by assigning two-fold labels of species and genus, in two phases ofrough classification of genera and fine classification of species. We propose a hierarchical classification in which the concatenation scheme is augmented with a channel attention which focuses on the sibling relation of species. We compared our method with flat classification and conventional hierarchical classification. The test was on a PlantNet-300K dataset 300k images, composed of 303 genera and 1081 species. In experimental results, the channel attention layers lead to stable discerningof the minute difference among visually similar species. The proposed hierarchical classification method outperforms both the flat classification and the conventional hierarchical classification.

Analysis of automatic image classification methods for Urticaceae pollen classification

Pollen classification is considered an important task in palynology. In the Netherlands, two genera of the Urticaceae family, named Parietaria and Urtica, have high morphological similarities but induce allergy at a very different level. Therefore, distinction between these two genera is very important. Within this group, the pollen of Urtica membranacea is the only species that can be recognized easily under the microscope. For the research presented in this study, we built a dataset from 6472 pollen images and our aim was to find the best possible classifier on this dataset by analysing different classification methods, both machine learning and deep learning-based methods. For machine learning-based methods, we measured both texture and moment features based on images from the pollen grains. Varied feature selection techniques, classifiers as well as a hierarchical strategy were implemented for pollen classification. For deep learning-based methods, we compared the performance of six popular Convolutional Neural Networks: AlexNet, VGG16, VGG19, MobileNet V1, MobileNet V2 and ResNet50. Results show that compared with flat classification models, a hierarchical strategy yielded the highest accuracy with 94.5% among machine learning-based methods. Among deep learning-based methods, ResNet50 achieved an accuracy of 99.4%, slightly outperforming the other neural networks investigated. In addition, we investigated the influence on performance by changing the size of image datasets to 1000 and 500 images, respectively. Results demonstrated that on smaller datasets, ResNet50 still achieved the best classification performance. An ablation study was implemented to help understanding why the deep learning-based methods outperformed the other models investigated. Using Urticaceae pollen as an example, our research provides a strategy of selecting a classification model for pollen datasets with highly similar pollen grains to support palynologists and could potentially be applied to other image classification tasks.

Granularity Selection for Hierarchical Classification Based on Uncertainty Measure

Feature selection is an important preprocessing step for high-dimensional data mining and machine learning; it is viewed as the selection of the optimal granularity to describe the target concept in rough set theory. Currently, research on rough sets mainly focuses on granularity selection in flat classification scenarios, while organizing hundreds of labels for hierarchical classification (HC) can provide additional external information and achieve better performance in terms of both accuracy and efficiency. However, HC also faces the following problems: 1) the current measures’ failure to characterize the uncertainty in HC; 2) the inability to select the optimal granularity of the target concept in HC; and 3) no valid approach to select features in a decision system with hierarchical classification (HieDS). To address these problems, this article introduces HC into rough set theory and proposes an approach to granularity selection for HC. First, we introduce the knowledge distance to reflect the uncertainty of HC and define related important characteristic functions to describe a HieDS. Then, from the perspective of uncertainty, granularity selection for the target concept and feature selection are presented based on these characteristic functions. Finally, we experimentally realize granularity selection and demonstrate excellent performance of feature selection in a HieDS in terms of both feature selection and classification accuracy.

Generalized multigranulation sequential three-way decision models for hierarchical classification

Hierarchical classification is an important research hotspot in machine learning due to the widespread existence of data with hierarchical class structures. The existing sequential three-way decision models mainly constructed the hierarchical condition information granules via concept hierarchy tree to discuss the three probabilistic regions for flat classification. However, in real-world applications, one may face not only the tree-structured data with hierarchical condition attributes but also more often the multi-level data with hierarchical decision attribute (hierarchical class labels). How to obtain acceptable decisions under different levels of granularity is the most important issue within the multi-level and multi-view data. To this end, we construct a generalized hierarchical decision table and propose a generalized hierarchical multigranulation sequential three-way decision model by combining multi-granularity and sequential three-way decisions. Specifically, we first design a generalized hierarchical decision table using concept hierarchy trees of all conditional attributes and decision attribute, and explore some basic properties. Then we decompose and aggregate condition and decision granules under different levels of granularity, propose the optimistic and pessimistic generalized hierarchical multigranulation three-way decision models to update the three probabilistic regions for flat and hierarchical classification, and discuss the relationships between these two models. Finally, the experimental results demonstrate that the proposed models are more suitable for different applications. These models will provide a novel insight and enrich the development of multigranulation three-way decisions from the perspective of multi-level and multi-view.

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.

SENTIMENT ATTRIBUTION ANALYSIS WITH HIERARCHICAL CLASSIFICATION AND AUTOMATIC ASPECT CATEGORIZATION ON ONLINE USER REVIEWS

Due to COVID-19 pandemic, most physical business transactions were pushed online. Online reviews became an excellent source for sentiment analysis to determine a customer's sentiment about a business. This insight is valuable asset for businesses, especially for tourism sector, to be harnessed for business intelligence and craft new marketing strategies. However, traditional sentiment analysis with flat classification and manual aspect categorization technique imposes challenges with non-opinionated reviews and outdated pre-defined aspect categories which limits businesses to filter relevant opinionated reviews and learn new aspects from reviews itself for aspect-based sentiment analysis. Therefore, this paper proposes sentiment attribution analysis with hierarchical classification and automatic aspect categorization to improve the social listening for diligent marketing and recommend potential business optimization to revive the business from surviving to thriving after this pandemic. Hierarchical classification is proposed using hybrid approach. While automatic aspect categorization is constructed with semantic similarity clustering and applied enhanced topic modelling on opinionated reviews. Experimental results on two real-world datasets from two different industries, Airline and Hotel, shows that the sentiment analysis with hierarchical classification outperforms the classification accuracy with a good F1-score compared to baseline papers. Automatic aspect categorization was found to be able to unhide the sentiment of the aspects which was not recognized in manual aspect categorization. Although it is accepted that the effectiveness of aspect-based sentiment analysis on flat classification and manual aspect categorization, none have assessed the effectiveness while using hierarchical classification with a hybrid approach and automatic aspect categorization.

Hierarchical classification of multi-corpus acoustic field recordings

Passive acoustic monitoring is one important technique for detecting long-term ecological change. Since audio data contains complex temporal and frequency information, deep learning is an ideal computational framework for automatic processing. In this work, the dataset consists of 64k annotated clips distributed across 23 classes that are derived from 17 000 h of acoustic data consisting of bio-, geo- and anthropophonies recorded at two different sites in the Capital Region of New York State. A hierarchical deep convolutional neural network with one local classifier per parent node provides fine, medium, and coarse-grained label predictions. If a fine-grained label is predicted incorrectly, a correct medium or coarse label still provides valuable taxonomic information. While the flat classifier performs similarly to the hierarchical for single-corpus training scenarios, it achieves higher medium-grained predictions for categories such as avian vocalization. For cross-corpus scenarios, the hierarchical classifier achieves a superior performance overall. These results highlight the importance of neural network architecture customization to suit a particular task and domain; hierarchical structures show potential in open set recognition tasks, where the entire set of possible classes is unknown. [Work supported by NSF Grant No. 1631674 and an RPI HASS Fellowship.]

HEMDAG: a family of modular and scalable hierarchical ensemble methods to improve Gene Ontology term prediction.

Automated protein function prediction is a complex multi-class, multi-label, structured classification problem in which protein functions are organized in a controlled vocabulary, according to the Gene Ontology (GO). 'Hierarchy-unaware' classifiers, also known as 'flat' methods, predict GO terms without exploiting the inherent structure of the ontology, potentially violating the True-Path-Rule (TPR) that governs the GO, while 'hierarchy-aware' approaches, even if they obey the TPR, do not always show clear improvements with respect to flat methods, or do not scale well when applied to the full GO. To overcome these limitations, we propose Hierarchical Ensemble Methods for Directed Acyclic Graphs (HEMDAG), a family of highly modular hierarchical ensembles of classifiers, able to build upon any flat method and to provide 'TPR-safe' predictions, by leveraging a combination of isotonic regression and TPR learning strategies. Extensive experiments on synthetic and real data across several organisms firstly show that HEMDAG can be used as a general tool to improve the predictions of flat classifiers, and secondly that HEMDAG is competitive versus state-of-the-art hierarchy-aware learning methods proposed in the last CAFA international challenges. Fully tested R code freely available at https://anaconda.org/bioconda/r-hemdag. Tutorial and documentation at https://hemdag.readthedocs.io. Supplementary data are available at Bioinformatics online.

A Tidal Flat Wetlands Delineation and Classification Method for High-Resolution Imagery

As an important part of coastal wetlands, tidal flat wetlands provide various significant ecological functions. Due to offshore pollution and unreasonable utilization, tidal flats have been increasingly threatened and degraded. Therefore, it is necessary to protect and restore this important wetland by monitoring its distribution. Considering the multiple sizes of research objects, remote sensing images with high resolutions have unique resolution advantages to support the extraction of tidal flat wetlands for subsequent monitoring. The purpose of this study is to propose and evaluate a tidal flat wetland delineation and classification method from high-resolution images. First, remote sensing features and geographical buffers are used to establish a decision tree for initial classification. Next, a natural shoreline prediction algorithm is designed to refine the range of the tidal flat wetland. Then, a range and standard deviation descriptor is constructed to extract the rock marine shore, a category of tidal flat wetlands. A geographical analysis method is considered to distinguish the other two categories of tidal flat wetlands. Finally, a tidal correction strategy is introduced to regulate the borderline of tidal flat wetlands to conform to the actual situation. The performance of each step was evaluated, and the results of the proposed method were compared with existing available methods. The results show that the overall accuracy of the proposed method mostly exceeded 92% (all higher than 88%). Due to the integration and the performance superiority compared to existing available methods, the proposed method is applicable in practice and has already been applied during the construction project of Hengqin Island in China.

Customizable HMM-based measures to accurately compare tree sets

Trees have been topics of much interest since many decades due to various emerging applications using data represented as trees. Several techniques have been developed to compare two trees. But there is a serious lack of metrics to compare weighted trees. Existing approaches do not also allow to explicitly specify the targeted nodes properties on which the comparison should be performed. Furthermore, the problem of comparing two tree sets is not specifically addressed by existing techniques. This paper attempts to solve these problems by first proposing a distance and a similarity for the comparison of two finite sets of rooted ordered trees which can be labeled or not, as well as weighted or unweighted. To achieve this goal, a hidden Markov model is associated with each tree set for each targeted nodes property. The model associated with a tree set T for the targeted nodes property p learns how much the nodes of the trees in T verify property p. The resulting models are finally compared to derive a distance and similarity between the two sets of trees. The previous measures are then generalized for the comparison of unrooted and unordered trees. Flat classification experiments were carried out on two synthetic databases named FirstLast-L and FirstLast-LW available online. They both contain four classes of 100 rooted ordered trees whose specific and non-trivial nodes properties are clearly defined. When the distance proposed in this paper is selected as metric for the Nearest Neighbor classifier, a perfect accuracy of $$100\%$$ is obtained for these two databases. This performance is $$41\%$$ higher than the accuracy exhibited when the widespread tree Edit distance is selected for FirstLast-L.

Hierarchical deep learning models using transfer learning for disease detection and classification based on small number of medical images

Deep learning is being employed in disease detection and classification based on medical images for clinical decision making. It typically requires large amounts of labelled data; however, the sample size of such medical image datasets is generally small. This study proposes a novel training framework for building deep learning models of disease detection and classification with small datasets. Our approach is based on a hierarchical classification method where the healthy/disease information from the first model is effectively utilized to build subsequent models for classifying the disease into its sub-types via a transfer learning method. To improve accuracy, multiple input datasets were used, and a stacking ensembled method was employed for final classification. To demonstrate the method’s performance, a labelled dataset extracted from volumetric ophthalmic optical coherence tomography data for 156 healthy and 798 glaucoma eyes was used, in which glaucoma eyes were further labelled into four sub-types. The average weighted accuracy and Cohen’s kappa for three randomized test datasets were 0.839 and 0.809, respectively. Our approach outperformed the flat classification method by 9.7% using smaller training datasets. The results suggest that the framework can perform accurate classification with a small number of medical images.

Learn class hierarchy using convolutional neural networks

A large amount of research on Convolutional Neural Networks (CNN) has focused on flat Classification in the multi-class domain. In the real world, many problems are naturally expressed as hierarchical classification problems, in which the classes to be predicted are organized in a hierarchy of classes. In this paper, we propose a new architecture for hierarchical classification, introducing a stack of deep linear layers using cross-entropy loss functions combined to a center loss function. The proposed architecture can extend any neural network model and simultaneously optimizes loss functions to discover local hierarchical class relationships and a loss function to discover global information from the whole class hierarchy while penalizing class hierarchy violations. We experimentally show that our hierarchical classifier presents advantages to the traditional classification approaches finding application in computer vision tasks. The same approach can also be applied to some CNN for text classification.

HMATC: Hierarchical multi-label Arabic text classification model using machine learning

Multi-label classification assigns multiple labels to each document concurrently. Many real-world classification problems tend to employ high-dimensional label spaces, which can be naturally structured in a hierarchy. In this type of problem, each instance may belong to multiple labels and labels are organized in a hierarchical structure. It presents a more complex problem than flat classification, given that the classification algorithm has to take into account hierarchical relationships between labels and be able to predict multiple labels for the same instance. Few studies have investigated multi-label text classification for the Arabic language. Most of these studies have focused mainly on flat classification and have neglected the hierarchical structure. Therefore, this paper explores the hierarchical multi-label classification in the context of the Arabic language. It proposes a hierarchical multi-label Arabic text classification (HMATC) model with a machine learning approach. The impact of feature selection methods and feature set dimensions on classification performance are also investigated. In addition, the Hierarchy Of Multilabel ClassifiER (HOMER) algorithm is optimized via examination of different sets of multi-label classifiers, clustering algorithms and different numbers of clusters to improve the hierarchical classification. Moreover, this study contributes to existing research by introducing a hierarchical multi-label Arabic dataset in an appropriate format for hierarchical classification and making it publicly available. The results reveal that the proposed model outperforms all models considered in the experiments in terms of the computational cost, which consumed less cost (2 h) compared with other evaluated models. In addition, it shows a significant improvement compared with the state-of-the-art model (Fatwa model) in terms of Hamming loss (0.004), hierarchical loss (1.723), multi-label accuracy (0.758), subset accuracy (0.292), micro-averaged precision (0.879), micro-averaged recall (0.828), and micro-averaged F-measure (0.853).

A note on higher-order vertices of higher-spin fields in flat and (A)dS space

In this work we classify (homogeneous) solutions to the Noether procedure in (A)dS for an arbitrary number of external legs and in general dimensions, analysing also the corresponding deformations of gauge symmetries. This builds upon the corresponding flat space classification [1], which we review and give its relation with the (A)dS result presented here. The role of dimensional dependent identities is studied in detail, which we find do not lead to new solutions for couplings involving more than three fields. For spins one and two our formalism recovers the Yang-Mills and Gravity examples.

Exploring a knowledge-based approach to predicting NACE codes of enterprises based on web page texts

Classification of enterprises by main economic activity according to NACE codes is a challenging but important task for national statistical institutes. Since manual editing is time-consuming, we investigated the automatic prediction from dedicated website texts using a knowledge-based approach. To that end, concept features were derived from a set of domain-specific keywords. Furthermore, we compared flat classification to a specific two-level hierarchy which was based on an approach used by manual editors. We limited ourselves to Naïve Bayes and Support Vector Machines models and only used texts from the main web pages. As a first step, we trained a filter model that classifies whether websites contain information about economic activity. The resulting filtered data set was subsequently used to predict 111 NACE classes. We found that using concept features did not improve the model performance compared to a model with character n-grams, i.e. non-informative features. Neither did the two-level hierarchy improve the performance relative to a flat classification. Nonetheless, prediction of the best three NACE classes clearly improved the overall prediction performance compared to a top-one prediction. We conclude that more effort is needed in order to achieve good results with a knowledge-based approach and discuss ideas for improvement.

Uncertainty-aware integration of local and flat classifiers for food recognition

Food image recognition has recently attracted the attention of many researchers, due to the challenging problem it poses, the ease collection of food images, and its numerous applications to health and leisure. In real applications, it is necessary to analyze and recognize thousands of different foods. For this purpose, we propose a novel prediction scheme based on a class hierarchy that considers local classifiers, in addition to a flat classifier. In order to make a decision about which approach to use, we define different criteria that take into account both the analysis of the Epistemic Uncertainty estimated from the ‘children’ classifiers and the prediction from the ‘parent’ classifier. We evaluate our proposal using three Uncertainty estimation methods, tested on two public food datasets. The results show that the proposed method reduces parent-child error propagation in hierarchical schemes and improves classification results compared to the single flat classifier, meanwhile maintains good performance regardless the Uncertainty estimation method chosen.

Human experts vs. machines in taxa recognition

The step of expert taxa recognition currently slows down the response time of many bioassessments. Shifting to quicker and cheaper state-of-the-art machine learning approaches is still met with expert scepticism towards the ability and logic of machines. In our study, we investigate both the differences in accuracy and in the identification logic of taxonomic experts and machines. We propose a systematic approach utilizing deep Convolutional Neural Nets and extensively evaluate it over a multi-pose taxonomic dataset with hierarchical labels specifically created for this comparison. We also study the prediction accuracy on different ranks of taxonomic hierarchy in detail. We compare the results of Convolutional Neural Networks to human experts and support vector machines. Our results revealed that human experts using actual specimens yield the lowest classification error (CE¯=6.1%). However, a much faster, automated approach using deep Convolutional Neural Nets comes close to human accuracy (CE¯=11.4%) when a typical flat classification approach is used. Contrary to previous findings in the literature, we find that for machines following a typical flat classification approach commonly used in machine learning performs better than forcing machines to adopt a hierarchical, local per parent node approach used by human taxonomic experts (CE¯=13.8%). Finally, we publicly share our unique dataset to serve as a public benchmark dataset in this field.