Domain Classification Research Articles

Bearing fault diagnosis based on a multiple-constraint modal-invariant graph convolutional fusion network

Multisensor data fusion method can improve the accuracy of bearing fault diagnosis, in order to address the problems of single-sensor data types and the insufficient exploration of redundancy and complementarity between different modal data in most existing multisensor data fusion methods for bearing fault diagnosis, a bearing fault diagnosis method based on a Multiple-Constraint Modal-Invariant Graph Convolutional Fusion Network (MCMI-GCFN) is proposed in this paper. Firstly, a Convolutional Autoencoder (CAE) and Squeeze-and-Excitation Block (SE block) are used to extract features of raw current and vibration signals. Secondly, the model introduces source domain classifiers and domain discriminators to capture modal invariance between different modal data based on domain adversarial training, making use of the redundancy and complementarity between multimodal data. Then, the spatial aggregation property of Graph Convolutional Neural Networks (GCN) is utilized to capture the dependency relationship between current and vibration modes with similar time step features for accurately fusing contextual semantic information. Finally, the validation is conducted on the public bearing damage current and vibration dataset from Paderborn University. The experimental results showed that the delivered fusion method achieved a bearing fault diagnosis accuracy of 99.6 %, which was about 9 %–11.4 % better than that with nonfusion methods.

SKZC: self-distillation and k-nearest neighbor-based zero-shot classification

Zero-shot learning represents a formidable paradigm in machine learning, wherein the crux lies in distilling and generalizing knowledge from observed classes to novel ones. The objective is to identify unfamiliar objects that were not included in the model’s training, leveraging learned patterns and knowledge from previously encountered categories. As a crucial subtask of open-world object detection, zero-shot classification can also provide insights and solutions for this field. Despite its potential, current zero-shot classification models often suffer from a performance gap due to limited transfer ability and discriminative capability of learned representations. In pursuit of advancing the subpar state of zero-shot object classification, this paper introduces a novel model for image classification which can be applied to object detection, namely, self-distillation and k-nearest neighbor-based zero-shot classification method. First, we employ a diffusion detector to identify potential objects in images. Then, self-distillation and distance-based classifiers are used for distinguishing unseen objects from seen classes. The k-nearest neighbor-based cluster heads are designed to cluster the unseen objects. Extensive experiments and visualizations were conducted on publicly available datasets on the efficacy of the proposed approach. Precisely, our model demonstrates performance improvement of over 20% compared to contrastive clustering. Moreover, it achieves a precision of 0.910 and a recall of 0.842 on CIFAR-10 datasets, a precision of 0.737, and a recall of 0.688 on CIFAR-100 datasets for the macro average. Compared to a more recent model (SGFR), our model realized improvements of 10.9%, 13.3%, and 7.8% in Sacc, Uacc, and H metrics, respectively. This study aims to introduce fresh ideas into the domain of zero-shot image classification, and it can be applied to open-world object detection tasks. Our code is available at https://www.github.com/CmosWolf1/Code_implementation_for_paper_SKZC.

A modified vision transformer architecture with scratch learning capabilities for effective fire detection

Fire is considered to be one of the major influencing factors that cause fatalities, property damage, and economic, and ecological disruption. To perform the early detection of fire using data from vision sensors and prevent or reduce the damage that fires cause, deep learning models have been widely adopted to overcome the limitations of conventional methods. However, mainstream convolutional neural network (CNN) models have limited generalisation abilities in unseen scenarios and struggle to obtain a good trade-off among the accuracy, inference speed, and model size. Currently, vision transformers (ViT) outperform conventional CNN models; however, they are computationally expensive and required more data for training. They provide a limited performance for small and medium-sized datasets, which are very common in the fire scene classification domain. In this work, we employ a novel ViT architecture by combining shifted patch tokenisation and local self-attention modules for efficient fire scene classification and enable the model to learn from scratch even on small and medium-sized datasets. Furthermore, to make the model suitable for real-time inferencing, we modify the transformer encoder and eventually achieve a reduced number of floating-point operations and a reduced model size. Additionally, in this work, a medium-scale fire dataset is developed that contains complex real-world scenarios. Our model is assessed on three benchmark and a self-created datasets using several evaluation metrics, including a novel cross-corpse evaluation metric, as well as a robustness evaluation metric. The experimental results indicate that our model achieved an overwhelmingly better performance compared to existing methods in terms of the accuracy and model complexity.

Structural homology-based identification of BEN domain proteins in Poxviruses

BEND family transcription factors directly interact with DNA through BEN domains and have been found across metazoan species. Interestingly, certain insect and mammalian viruses have also hijacked Bend genes into their genome. However, the phylogenetic classification and evolution of these viral BEN domains remain unclear. Building on our previous finding that in silico method accurately determine the 3D model of BEN domains, we used AlphaFold2 to predict the tertiary structures of poxviral BEN domains for comprehensive homologous comparison.We revealed that the majority of poxviral BEN modules exhibit characteristics of type II BEN. Additionally, electrostatic surface potential analysis found various poxviral BEN domains, including the first BEN of OPG067 in Orthopoxvirus, the third BEN of OPG067 in Yatapoxvirus and the third BEN of MC036R in MCV, have positively charged protein surfaces, indicating a structural basis for DNA loading. Notably, MC036R shares structural resemblance with human BEND3, as they both contain four BEN domains and an intrinsically disordered region. In summary, our discoveries provide deeper insights into the functional roles of BEN proteins within poxviruses.

Accurate multiclassification and segmentation of gastric cancer based on a hybrid cascaded deep learning model with a vision transformer from endoscopic images

Compared with other forms of cancer, gastric cancer has high mortality and incidence rates, making it a major cause of death worldwide. Accurate diagnosis is crucial in the treatment of stomach cancer. Researchers have used deep learning techniques facilitated by developments in artificial intelligence to classify and segment endoscopic images of stomach cancer. Most recentresearch examining endoscopic images of stomach cancer has used a binary classification system, whichis insufficient for practical use. False-positives and computational costs become problematic when segmentation is applied to all the images of healthy patients obtained throughout the evaluation. Hence, the expected level of performance has not been attained in the real-time multiclassification and segmentation of stomach cancer. In this study, we present a deep learning-based technique for multiclassification of endoscopic images by combiningmodified GoogLeNet and vision transformer (ViT) models and identifying invasive areas based on Faster R-CNN. The classification of endoscopic images into three categories, namely, normal, early gastric cancer, and advanced gastric cancer, is accomplished by using a hybrid approach including modified GoogLeNet and vision transformer (ViT) models. Gastric cancer regionsare then identified and segmented in the endoscopic images using the Faster R-CNN method. The Faster R-CNN algorithm is used with an endoscopic image as input, resulting in the generation of a bounding box and label image that accurately represents the gastric cancerous area. The proposed model achieved an accuracy, sensitivity and F1-score of 97.4%, 97.5% and 95.9%, respectively, for the classification of noncancerous, early gastric cancer and advanced gastric cancer. Furthermore, the performance of the segmentation method was also validated based on evaluation metrics and achieved 96.7%, 96.6% and 95.5% accuracy, sensitivity and F1-score, respectively, for the segmentation of noncancerous, early gastric cancer and advanced gastric cancer tissues. In conclusion, the method proposed in this study demonstrates enhanced global classification and detection performance compared to existing state-of-the-art algorithms. This finding underscores the significant potential of the proposed methodin the domain of gastric endoscopic image classification and segmentation.

Maximal Condorcet domains. A further progress report

Condorcet domains are sets of preference orders such that the majority relation corresponding to any profile of preferences from the domain is acyclic. The best known examples in economics are the single-peaked, the single-crossing, and the group separable domains. We survey the latest developments in the area since Monjardet's magisterial overview (2009), provide some new results and offer two conjectures concerning unsolved problems. The main goal of the presentation is to illuminate the rich internal structure of the class of maximal Condorcet domains. In an appendix, we present the complete classification of all maximal Condorcet domains on four alternatives obtained by Dittrich (2018).

Application of Artificial Neural Networks in Soil Science Research

Artificial Neural Networks utilize high-performance computation and large data technology, allowing research to generate new prospects in agriculture. ANN is currently a preferred technique for crop yield prediction, forecasting, and classification in biological science domains. Among different agriculture fields, soil science research plays a vital role in understanding and managing the complex processes occurring within the soil environment as oil is a complex system with dynamic surface layers that differ from the other parts of the matrix. Due to the increasing accessibility of innovative computing techniques, Artificial Neural Networks (ANNs) have developed into useful tools for modeling and forecasting soil-related activities. The numerous applications of ANNs in soil science research, with a focus on how well they can classify soils, assess soil fertility, forecast soil erosion, and estimate soil moisture. They are vital tools for identifying soil types, evaluating fertility levels, predicting erosion, and soil moisture estimation. ANN models were effective at predicting soil characteristics like pH, organic carbon concentration, and clay content. By training on vast datasets that contain the chemical, biological, and physical properties of soil, ANNs are able to accurately predict different soil types and enable land-use planning, precision farming, and environmental management. This mini-review focuses on ANN approaches that possess the potential to increase our understanding of soil science and encourage informed decisions for soil management and conservation.

Genetic Programming-Based Evolutionary Deep Learning for Data-Efficient Image Classification

Data-efficient image classification is a challenging task that aims to solve image classification using small training data. Neural network-based deep learning methods are effective for image classification, but they typically require large-scale training data and have major limitations such as requiring expertise to design network architectures and having poor interpretability. Evolutionary deep learning is a recent hot topic that combines evolutionary computation with deep learning. However, most evolutionary deep learning methods focus on evolving architectures of neural networks, which still suffer from limitations such as poor interpretability. To address this, this paper proposes a new genetic programming-based evolutionary deep learning approach to data-efficient image classification. The new approach can automatically evolve variable-length models using many important operators from both image and classification domains. It can learn different types of image features from colour or gray-scale images, and construct effective and diverse ensembles for image classification. A flexible multi-layer representation enables the new approach to automatically construct shallow or deep models/trees for different tasks and perform effective transformations on the input data via multiple internal nodes. The new approach is applied to solve five image classification tasks with different training set sizes. The results show that it achieves better performance in most cases than deep learning methods for data-efficient image classification. A deep analysis shows that the new approach has good convergence and evolves models with high interpretability, different lengths/sizes/shapes, and good transferability.

Adversarial Danger Identification on Temporally Dynamic Graphs.

Multivariate time series forecasting plays an increasingly critical role in various applications, such as power management, smart cities, finance, and healthcare. Recent advances in temporal graph neural networks (GNNs) have shown promising results in multivariate time series forecasting due to their ability to characterize high-dimensional nonlinear correlations and temporal patterns. However, the vulnerability of deep neural networks (DNNs) constitutes serious concerns about using these models to make decisions in real-world applications. Currently, how to defend multivariate forecasting models, especially temporal GNNs, is overlooked. The existing adversarial defense studies are mostly in static and single-instance classification domains, which cannot apply to forecasting due to the generalization challenge and the contradiction issue. To bridge this gap, we propose an adversarial danger identification method for temporally dynamic graphs to effectively protect GNN-based forecasting models. Our method consists of three steps: 1) a hybrid GNN-based classifier to identify dangerous times; 2) approximate linear error propagation to identify the dangerous variates based on the high-dimensional linearity of DNNs; and 3) a scatter filter controlled by the two identification processes to reform time series with reduced feature erasure. Our experiments, including four adversarial attack methods and four state-of-the-art forecasting models, demonstrate the effectiveness of the proposed method in defending forecasting models against adversarial attacks.

Attention Mechanisms in Clinical Text Classification: A Comparative Evaluation.

Attention mechanisms are now a mainstay architecture in neural networks and improve the performance of biomedical text classification tasks. In particular, models that perform automated medical encoding of clinical documents make extensive use of the label-wise attention mechanism. A label-wise attention mechanism increases a model's discriminatory ability by using label-specific reference information. This information can either be implicitly learned during training or explicitly provided through embedded textual code descriptions or information on the code hierarchy; however, contemporary studies arbitrarily select the type of label-specific reference information. To address this shortcoming, we evaluated label-wise attention initialized with either implicit or explicit label-specific reference information against two common baseline methods-target-attention and text-encoder architecture-specific methods-to generate document embeddings across four text-encoder architectures-a convolutional neural network, two recurrent neural networks, and a transformer. We also present an extension of label-wise attention that can embed the information on the code hierarchy. We performed our experiments on the MIMIC III dataset, which is a standard dataset in the clinical text classification domain. Our experiments showed that using pretrained reference information and the hierarchical design helped improve classification performance. These performance improvements had less impact on larger datasets and label spaces across all text-encoder architectures. In our analysis, we used an attention mechanism's energy scores to explain the perceived differences in performance and interpretability between the text-encoder architectures and types of label-attention.

Deep ocular tumor classification model using cuckoo search algorithm and Caputo fractional gradient descent

While digital ocular fundus images are commonly used for diagnosing ocular tumors, interpreting these images poses challenges due to their complexity and the subtle features specific to tumors. Automated detection of ocular tumors is crucial for timely diagnosis and effective treatment. This study investigates a robust deep learning system designed for classifying ocular tumors. The article introduces a novel optimizer that integrates the Caputo fractional gradient descent (CFGD) method with the cuckoo search algorithm (CSA) to enhance accuracy and convergence speed, seeking optimal solutions. The proposed optimizer’s performance is assessed by training well-known Vgg16, AlexNet, and GoogLeNet models on 400 fundus images, equally divided between benign and malignant classes. Results demonstrate the significant potential of the proposed optimizer in improving classification accuracy and convergence speed. In particular, the mean accuracy attained by the proposed optimizer is 86.43%, 87.42%, and 87.62% for the Vgg16, AlexNet, and GoogLeNet models, respectively. The performance of our optimizer is compared with existing approaches, namely stochastic gradient descent with momentum (SGDM), adaptive momentum estimation (ADAM), the original cuckoo search algorithm (CSA), Caputo fractional gradient descent (CFGD), beetle antenna search with ADAM (BASADAM), and CSA with ADAM (CSA-ADAM). Evaluation criteria encompass accuracy, robustness, consistency, and convergence speed. Comparative results highlight significant enhancements across all metrics, showcasing the potential of deep learning techniques with the proposed optimizer for accurately identifying ocular tumors. This research contributes significantly to the development of computer-aided diagnosis systems for ocular tumors, emphasizing the benefits of the proposed optimizer in medical image classification domains.

Multi-domain stain normalization for digital pathology: A cycle-consistent adversarial network for whole slide images

The variation in histologic staining between different medical centers is one of the most profound challenges in the field of computer-aided diagnosis. The appearance disparity of pathological whole slide images causes algorithms to become less reliable, which in turn impedes the wide-spread applicability of downstream tasks like cancer diagnosis. Furthermore, different stainings lead to biases in the training which in case of domain shifts negatively affect the test performance. Therefore, in this paper we propose MultiStain-CycleGAN, a multi-domain approach to stain normalization based on CycleGAN. Our modifications to CycleGAN allow us to normalize images of different origins without retraining or using different models. We perform an extensive evaluation of our method using various metrics and compare it to commonly used methods that are multi-domain capable. First, we evaluate how well our method fools a domain classifier that tries to assign a medical center to an image. Then, we test our normalization on the tumor classification performance of a downstream classifier. Furthermore, we evaluate the image quality of the normalized images using the Structural similarity index and the ability to reduce the domain shift using the Fréchet inception distance. We show that our method proves to be multi-domain capable, provides a very high image quality among the compared methods, and can most reliably fool the domain classifier while keeping the tumor classifier performance high. By reducing the domain influence, biases in the data can be removed on the one hand and the origin of the whole slide image can be disguised on the other, thus enhancing patient data privacy.

Domain Adaptation Curriculum Learning for Scene Text Detection in Inclement Weather Conditions

AbstractScene text detection has been widely studied on haze‐free images with reliable ground truth annotation. However, detecting scene text in inclement weather conditions remains a major challenge due to the severe domain distribution mismatch problem. This paper introduces a domain adaptation curriculum learning method to address this problem. The scene text detector is self‐trained in an easy‐to‐hard manner using the pseudo‐labels predicted from foggy images. Thus, our method reduces the pseudo‐labeling noise level. Then, a feature alignment module is introduced to help the network learn domain‐invariant features by training a domain classifier. Experimental results show that our method improved significantly on both synthetic foggy data sets and natural foggy data sets, outperforming many state‐of‐the‐art scene text detectors. © 2024 Institute of Electrical Engineers of Japan and Wiley Periodicals LLC.

Loose to compact feature alignment for domain adaptive object detection

Recently, great achievements have been made for deep learning based object detection methods. But their performance drops significantly when domain shifts occur. To address this problem, in this work we propose a loose to compact feature alignment method under an unsupervised domain adaptation framework. The entire feature alignment is performed in a divide and conquer manner, so as to distribute the alignment difficulties at two steps. At the first step, we loosen the goal at both image and instance levels. At the image level, a new Mask Guided Foreground Alignment (MGFA) module is proposed to make the alignment focus more on easier foreground regions, leaving the more diverse and more difficult background regions to the second step; at the instance level, we propose a Class-Wise Instance Alignment (CWIA) module with separated domain classifiers for different categories so as to ease the alignment. At the second step, the alignment is performed per pixel and per instance, achieving a more compact and better aligned feature space. We conduct experiments on three different adaptation scenarios, where we achieve comparable results, demonstrating the effectiveness of our proposed method.

Harnessing the Power of Beta Scoring in Deep Active Learning for Multi-Label Text Classification

Within the scope of natural language processing, the domain of multi-label text classification is uniquely challenging due to its expansive and uneven label distribution. The complexity deepens due to the demand for an extensive set of annotated data for training an advanced deep learning model, especially in specialized fields where the labeling task can be labor-intensive and often requires domain-specific knowledge. Addressing these challenges, our study introduces a novel deep active learning strategy, capitalizing on the Beta family of proper scoring rules within the Expected Loss Reduction framework. It computes the expected increase in scores using the Beta Scoring Rules, which are then transformed into sample vector representations. These vector representations guide the diverse selection of informative sample, directly linking this process to the model's expected proper score. Comprehensive evaluations across both synthetic and real datasets reveal our method's capability to often outperform established acquisition techniques in multi-label text classification, presenting encouraging outcomes across various architectural and dataset scenarios.

MCSSME: Multi-Task Contrastive Learning for Semi-supervised Singing Melody Extraction from Polyphonic Music

Singing melody extraction is an important task in the field of music information retrieval (MIR). The development of data-driven models for this task have achieved great successes. However, the existing models have two major limitations: firstly, most of the existing singing melody extraction models have formulated this task as a pixel-level prediction task. The lack of labeling data has limited the model for further improvements. Secondly, the generalization of the existing models are prone to be disturbed by the music genres. To address the issues mentioned above, in this paper, we propose a multi-Task contrastive learning framework for semi-supervised singing melody extraction, termed as MCSSME. Specifically, to deal with data scarcity limitation, we propose a self-consistency regularization (SCR) method to train the model on the unlabeled data. Transformations are applied to the raw signal of polyphonic music, which makes the network to improve its representation capability via recognizing the transformations. We further propose a novel multi-task learning (MTL) approach to jointly learn singing melody extraction and classification of transformed data. To deal with generalization limitation, we also propose a contrastive embedding learning, which strengthens the intra-class compactness and inter-class separability. To improve the generalization on different music genres, we also propose a domain classification method to learn task-dependent features by mapping data from different music genres to shared subspace. MCSSME evaluates on a set of well-known public melody extraction datasets with promising performances. The experimental results demonstrate the effectiveness of the MCSSME framework for singing melody extraction from polyphonic music using very limited labeled data scenarios.

Performance Analysis of Random Forest on Quartile Classification Journal

Journals play a pivotal role in disseminating scientific knowledge, housing a multitude of valuable research articles. In this digital age, the evaluation of journals and their quality is essential. The SCImago Journal Rank (SJR) stands as one of the prominent platforms for ranking journals, categorizing them into five index classes: Q1, Q2, Q3, Q4, and NQ. Determining these index classes often relies on classification methodologies. This research, drawing inspiration from the Cross-Industry Standard Process for Data Mining (CRISP-DM), seeks to employ the Random Forest method to classify journals, thus contributing to the refinement of journal ranking processes. Random Forest stands out as a robust choice due to its remarkable ability to mitigate overfitting, a common challenge in machine learning classification tasks. In the context of approximating SJR index classes, Random Forest, when utilizing the Gini index, exhibits promise, albeit with an initial accuracy rate of 62.12%. The Gini index, an impurity measure, enables Random Forest to make informed decisions while classifying journals into their respective SJR index classes. However, it is worth noting that this accuracy rate represents a starting point, and further refinement and feature engineering may enhance the model's performance. This research underscores the significance of machine learning techniques in the domain of journal classification and journal-ranking systems. By harnessing the power of Random Forest, this study aims to facilitate more accurate and efficient categorization of journals, thereby aiding researchers, academics, and institutions in identifying and accessing high-quality scientific literature.

A dual-weighted adversarial network for partial domain fault diagnosis of machinery

Domain adaptation provides a promising approach to cross-domain fault diagnosis of rotating machinery. While many current methods focus on scenarios where the source and target domains share identical label spaces, a prevalent situation in industrial production involves the target domain being a subset of the source domain, known as partial domain adaptation (PDA). The main challenge in PDA is the label mismatches caused by outlier classes, making the alignment between domains particularly difficult. To this end, a dual-weighted adversarial network is proposed in this paper. Specifically, a bilateral class weighting strategy (BCWS) is developed, which can effectively suppress negative migration at the decision boundary while improving the robustness of adversarial training by applying bilateral weighting to both the source and target domains. Moreover, a collaborative framework is developed to facilitate positive migration. The constructed global perceptual module (GPM) is highly correlated with the improved adversarial loss function, which adaptively adjusts the input feature map according to the accuracy of the target domain classification and pays more attention to the domain-invariant features. Experimental results for two cases, namely across different operating conditions and across different rotating components, verify the effectiveness and superiority of the proposed method for the PDA problem.

DBL-Net: A dual-branch learning network with information from spatial and frequency domains for tumor segmentation and classification in breast ultrasound image

Breast cancer is a common malignancy, ranking as one of the most prevalent cancers among women globally. Improving treatment success rates for breast cancer are crucially dependent on early detection and accurate diagnosis. Ultrasound imaging, as a non-invasive and low-radiation imaging technique, plays a significant role in early breast cancer detection. However, due to the characteristics of fuzzy tumor boundaries and irregular shapes of the tumor, accurate breast tumor classification and segmentation remain challenging tasks. This paper introduces a novel approach for breast ultrasound image segmentation and classification tasks. Firstly, we study the potential value of frequency domain information in breast image analysis and propose the DBL-Net, a multi-task learning network for simultaneous tumor segmentation and tumor classification. Secondly, we customize a Spatial-Frequency Domain Feature Encoding module (S-FEM) to better encode and fuse spatial and frequency domain features of breast ultrasound images. Furthermore, we design a Representational Perception Enhancer (RPE) to improve the feature representation capabilities and prediction accuracy of the model. Finally, We have carried out a comprehensive series of tests on the BUS dataset, and the findings clearly indicate that our method outperforms the current state-of-the-art methods.

Glacier: guided locally constrained counterfactual explanations for time series classification

In machine learning applications, there is a need to obtain predictive models of high performance and, most importantly, to allow end-users and practitioners to understand and act on their predictions. One way to obtain such understanding is via counterfactuals, that provide sample-based explanations in the form of recommendations on which features need to be modified from a test example so that the classification outcome of a given classifier changes from an undesired outcome to a desired one. This paper focuses on the domain of time series classification, more specifically, on defining counterfactual explanations for univariate time series. We propose Glacier, a model-agnostic method for generating locally-constrained counterfactual explanations for time series classification using gradient search either on the original space or on a latent space that is learned through an auto-encoder. An additional flexibility of our method is the inclusion of constraints on the counterfactual generation process that favour applying changes to particular time series points or segments while discouraging changing others. The main purpose of these constraints is to ensure more reliable counterfactuals, while increasing the efficiency of the counterfactual generation process. Two particular types of constraints are considered, i.e., example-specific constraints and global constraints. We conduct extensive experiments on 40 datasets from the UCR archive, comparing different instantiations of Glacier against three competitors. Our findings suggest that Glacier outperforms the three competitors in terms of two common metrics for counterfactuals, i.e., proximity and compactness. Moreover, Glacier obtains comparable counterfactual validity compared to the best of the three competitors. Finally, when comparing the unconstrained variant of Glacier to the constraint-based variants, we conclude that the inclusion of example-specific and global constraints yields a good performance while demonstrating the trade-off between the different metrics.