Robust Features Research Articles

A general framework for generative self-supervised learning in non-invasive estimation of physiological parameters using photoplethysmography

Aligning physiological parameter labels with large-scale photoplethysmographic (PPG) data for deep learning is challenging and resource-intensive. While self-supervised representation learning (SSRL) can handle limited annotated data, the challenge lies in learning robust shared representations from vast unlabeled data and integrating various contextual cues to learn distinctive representations. To alleviate these challenges, a generative SSRL framework TS2TC is proposed to collaboratively utilize the temporal, spectrogram, and temporal-spectrogram mixed domains to explore and incorporate the unique features of PPG for universal and non-invasive physiological parameter estimation. Initially, a pretext task named Cross-Temporal Fusion Generative Anchor (CTFGA) is designed, modeling temporal dependencies and reconstructing independent segments at a coarse level to provide robust global feature extraction and local semantic contextual representation. The framework also includes sub-signals from PPG with diverse frequency scales and order derivatives reflecting hemodynamics to facilitate learning shared representations at varying semantic levels. Secondly, an advanced cognitive-inspired dual-process transfer (DPT) strategy is formulated, consisting of prior-dependent autonomous processes and posterior observation reasoning processes, to leverage the independent and integrated advantages of shared and specific representations. Furthermore, TS2TC introduces a novel bilinear temporal-spectrogram fusion method in the mixed domain, aligning latent representations from different domains, and establishing fine-grained contextual interactions at the feature level across multiple sources of information. Extensive experiments on physiological parameter estimation tasks showed that the joint performance of CTFGA and DPT outperforms standard generative learning significantly. TS2TC achieved an average 2.49% improvement in RMSE over the current state-of-the-art estimation methods with only 10% training data.

Zinc, Magnesium and Tantalum for biomedical applications: A comprehensive review

The historical development and biomedical applications of magnesium, tantalum, and zinc are examined in this integrated study. It traces the development of magnesium from its use in military applications through its integration into many businesses, with an emphasis on its use in orthopaedic implants. Along with early attempts and failures in orthopaedic implantation, the mechanical properties of magnesium alloys suitable for biodegradable osteosynthetic materials are investigated. Clinical cases highlighting the successes and difficulties of magnesium implants in bone restoration are presented. Magnesium alloys have recently played important roles in biomedicine, particularly in stents and scaffolds. This analysis highlights their biocompatibility and corrosion behaviour. The numerous biomedical applications of tantalum and zinc, such as those in implants, surgical equipment, and drug delivery, are then discussed. Tantalum's porosity, biocompatibility, and biomechanical qualities make it the ideal material for implants, producing positive results in bone, tissue, and dental applications. Zinc's robust antibacterial characteristics and promise in targeted drug release are highlighted. Innovative manufacturing techniques, composite optimisation, surface alterations, and thorough clinical assessments are among the future directions. Key areas of interest include standardised testing, tissue interactions, and regulatory frameworks. This paper highlights the crucial contributions of tantalum, magnesium, and zinc to the development of biomedical engineering and provides insights for improved patient care, innovation, and therapeutic efficacy.

Variant graph craft (VGC): a comprehensive tool for analyzing genetic variation and identifying disease-causing variants

BackgroundThe variant call format (VCF) file is a structured and comprehensive text file crucial for researchers and clinicians in interpreting and understanding genomic variation data. It contains essential information about variant positions in the genome, along with alleles, genotype calls, and quality scores. Analyzing and visualizing these files, however, poses significant challenges due to the need for diverse resources and robust features for in-depth exploration.ResultsTo address these challenges, we introduce variant graph craft (VGC), a VCF file visualization and analysis tool. VGC offers a wide range of features for exploring genetic variations, including extraction of variant data, intuitive visualization, and graphical representation of samples with genotype information. VGC is designed primarily for the analysis of patient cohorts, but it can also be adapted for use with individual probands or families. It integrates seamlessly with external resources, providing insights into gene function and variant frequencies in sample data. VGC includes gene function and pathway information from Molecular Signatures Database (MSigDB) for GO terms, KEGG, Biocarta, Pathway Interaction Database, and Reactome. Additionally, it dynamically links to gnomAD for variant information and incorporates ClinVar data for pathogenic variant information. VGC supports the Human Genome Assembly Hg37 and Hg38, ensuring compatibility with a wide range of data sets, and accommodates various approaches to exploring genetic variation data. It can be tailored to specific user needs with optional phenotype input data.ConclusionsIn summary, VGC provides a comprehensive set of features tailored to researchers working with genomic variation data. Its intuitive interface, rapid filtering capabilities, and the flexibility to perform queries using custom groups make it an effective tool in identifying variants potentially associated with diseases. VGC operates locally, ensuring data security and privacy by eliminating the need for cloud-based VCF uploads, making it a secure and user-friendly tool. It is freely available at https://github.com/alperuzun/VGC.

Ensemble Learning for Nuclear Power Generation Forecasting Based on Deep Neural Networks and Support Vector Regression

Forecasting nuclear energy production is essential for market operations such as security, economic efficiency, resource optimization, grid stability, and the integration of renewable energy sources. Forecasting approaches allow nuclear power plants to operate consistently, contributing to the overall reliability and long-term viability of the energy system. It is noted that energy systems researchers are increasingly interested in machine learning models used to face the challenge of time series forecasting. This study evaluates a hybrid ensemble learning of three time series forecasting models including least-squares support vector regression, gated recurrent unit, and long short-term memory models applied to nuclear power time series forecasting on the dataset of French power plants from 2009 to 2020. Furthermore, this research evaluates forecasting results in which approaches are directed towards the optimized RreliefF (Robust relief Feature) selection algorithm using a hyperparameter optimization based on tree-structured Parzen estimator and following an ensemble learning approach, showing promising results in terms of performance metrics. The suggested ensemble learning model, which combines deep learning and the RreliefF algorithm using a hold-out, outperforms the other nine forecasting models in this study according to performance criteria such as 75% for the coefficient of determination, a root squared error average of 0.108, and an average absolute error of 0.080.

Intelligent integration of ANN and H‐infinity control for optimal enhanced performance of a wind generation unit linked to a power system

AbstractThis article focuses on utilizing intelligent H‐∞ synthesis to create a controller for a wind generation system linked to a power system via a static VAR compensator. The purpose of the control approach is twofold: firstly, to enhance the system's dynamic reactions to turbulent wind variations, and secondly, to elevate the quality of power generation. To achieve optimal control of the system, an Artificial Neural Network (ANN) is combined with the H‐∞ control method. This integration leverages the strengths of both ANN, which excels in modeling and optimization, and H‐∞, which prioritizes robustness to enhance dynamic performance. The resultant control strategy, connecting ANN and H‐∞, demonstrates the capability to deliver superior performance, precise tracking, and minimal overshooting. This approach is adaptive to changing control signals and exhibits robust characteristics, effectively managing uncertainties and disturbances. Through a simulation study, the effectiveness of this presented technique is showcased in enhancing the dynamic response of the system when compared to alternative control strategies.

Exploring Robust Features for Improving Adversarial Robustness.

While deep neural networks (DNNs) have revolutionized many fields, their fragility to carefully designed adversarial attacks impedes the usage of DNNs in safety-critical applications. In this article, we strive to explore the robust features that are not affected by the adversarial perturbations, that is, invariant to the clean image and its adversarial examples (AEs), to improve the model's adversarial robustness. Specifically, we propose a feature disentanglement model to segregate the robust features from nonrobust features and domain-specific features. The extensive experiments on five widely used datasets with different attacks demonstrate that robust features obtained from our model improve the model's adversarial robustness compared to the state-of-the-art approaches. Moreover, the trained domain discriminator is able to identify the domain-specific features from the clean images and AEs almost perfectly. This enables AE detection without incurring additional computational costs. With that, we can also specify different classifiers for clean images and AEs, thereby avoiding any drop in clean image accuracy.

Abstract P205: Single-nucleus Sequencing Reveals Endothelial Cell-specific Dysregulation in the Kidney in Multiple Models of Hypertension

The kidney plays a crucial role in the onset and progression of hypertension. To investigate the roles of different renal cell types in hypertension, we applied single-nucleus sequencing and spatial transcriptome sequencing to kidney samples from three well-established hypertension models: C57BL/6 mice treated with Ang II, the Dahl salt-sensitive (SS) rat on high-salt diets, and the spontaneously hypertensive rat (SHR), along with their respective controls including Sprague-Dawley (SD) and Wistar Kyoto (WKY) rats. Our dataset comprised 179,637 nuclei from 24 samples across 12 experimental conditions, identifying 17 major cell types including various epithelial cells, endothelial cells, vascular smooth muscle cells, fibroblasts, and immune cells. At baseline, differentially expressed genes between the SS and SD groups were specifically enriched in endothelial cell pathways related to vascular development. This included expression deficiencies in genes involved in angiogenesis in SS rats, such as Arhgap24 and Nox4. Compensatory expression changes in these genes were observed in the SS rats after a high-salt diet and in 26-week-old SHR, but not in their respective controls. These genes were also associated with multiple blood pressure-associated single-nucleotide polymorphisms (SNPs). Furthermore, changes in endothelial cell communication were most prominent upon stimuli, with impaired PTPRM (Protein Tyrosine Phosphatase Receptor Type M) signaling being a robust feature in hypertension models, involving angiogenic endothelial cells in the SS model and proliferating capillary endothelial cells in the SHR model. Our study highlights the critical role of renal endothelial cell angiogenic dysfunction in the pathogenesis of hypertension and suggests a link between specific renal endothelial cell subtype dysregulation and hypertension development.

A Novel Dual Attention Approach for DNN Based Automated Diabetic Retinopathy Grading

ABSTRACTDiabetic retinopathy (DR) poses a serious threat to vision, emphasising the need for early detection. Manual analysis of fundus images, though common, is error‐prone and time‐intensive. Existing automated diagnostic methods lack precision, particularly in the early stages of DR. This paper introduces the Soft Convolutional Block Attention Module‐based Network (Soft‐CBAMNet), a deep learning network designed for severity detection, which features Soft‐CBAM attention to capture complex features from fundus images. The proposed network integrates both the convolutional block attention module (CBAM) and the soft‐attention components, ensuring simultaneous processing of input features. Following this, attention maps undergo a max‐pooling operation, and refined features are concatenated before passing through a dropout layer with a dropout rate of 50%. Experimental results on the APTOS dataset demonstrate the superior performance of Soft‐CBAMNet, achieving an accuracy of 85.4% in multiclass DR grading. The proposed architecture has shown strong robustness and general feature learning capability, achieving a mean AUC of 0.81 on the IDRID dataset. Soft‐CBAMNet's dynamic feature extraction capability across all classes is further justified by the inspection of intermediate feature maps. The model excels in identifying all stages of DR with increased precision, surpassing contemporary approaches. Soft‐CBAMNet presents a significant advancement in DR diagnosis, offering improved accuracy and efficiency for timely intervention.

A hybrid approach for power quality event identification in power systems: Elasticnet Regression decomposition and optimized probabilistic neural networks

The transformation of traditional grid networks towards smart-grid and microgrid concepts raises many critical issues, and quality in the power supply is one of the prominent ones that needs further research. Developing and applying power quality (PQ) recognition methods with efficient and reliable analysis are essential to the fast-growing issues related to modern smart power distribution systems. In this regard, a hybrid algorithm is proposed for PQ events detection and classification using Elasticnet Regression-based Variational Mode Decomposition (ER-VMD) and Salp Swarm Algorithm optimized Probabilistic Neural Network (SSA-PNN). The Elasticnet Regression (ER) process is suggested to modify the conventional VMD approach instead of the Tikhonov Regularization (TR) method to enhance performance and obtain better band-limited intrinsic mode functions. This idea results in robust and effective reconstruction features and helps to obtain accurate classification using the classifier. In the classification stage, a Salp Swarm Algorithm (SSA) based PNN is used for the PQ event, considering the relevant features obtained from ER-VMD. The system parameters often influence PNN performance, and SSA is used to determine the ideal values to improve the PNN's capacity for more accurate classification. The numerical values of the accuracy percentage, percentage of sensitivity, and percentage of specificity in the case of real-time data are found as 98.58, 100, and 98.46, respectively. The acquired comparison findings demonstrate the effectiveness and robustness of the proposed technique in terms of rapid learning speed, smaller computational complexity, robust performance for anti-noise conditions, and accurate identification and categorization.

An Efficient Mixed-Integer Programming Model for Nonintrusive Load Monitoring With Distributionally Robust Feature Extraction

An Efficient Mixed-Integer Programming Model for Nonintrusive Load Monitoring With Distributionally Robust Feature Extraction

A Hybrid Convolutional Neural Network Model for the Classification of Multi‐Class Skin Cancer

ABSTRACTSkin cancer is a significant public health issue, making accurate and early diagnosis crucial. This study proposes a novel and efficient hybrid deep‐learning model for accurate skin cancer diagnosis. The model first employs DeepLabV3+ for precise segmentation of skin lesions in dermoscopic images. Feature extraction is then carried out using three pretrained models: MobileNetV2, EfficientNetB0, and DenseNet201 to ensure balanced performance and robust feature learning. These extracted features are then concatenated, and the ReliefF algorithm is employed to select the most relevant features. Finally, obtained features are classified into eight categories: actinic keratosis, basal cell carcinoma, benign keratosis, dermatofibroma, melanoma, melanocytic nevus, squamous cell carcinoma, and vascular lesion using the kNN algorithm. The proposed model achieves an F1 score of 93.49% and an accuracy of 94.42% on the ISIC‐2019 dataset, surpassing the best individual model, EfficientNetB0, by 1.20%. Furthermore, the evaluation of the PH2 dataset yielded an F1 score of 94.43% and an accuracy of 94.44%, confirming its generalizability. These findings signify the potential of the proposed model as an expedient, accurate, and valuable tool for early skin cancer detection. They also indicate combining different CNN models achieves superior results over the results obtained from individual models.

An efficient corn leaf disease prediction using Adaptive Color Edge Segmentation with Resnext101 model

Corn leaf disease prediction is essential in ensuring agricultural productivity and food security. Although classical segmentation and classification techniques have been used to identify diseases, they often fail to deal with complex leaf structures. Thus, deep learning has attracted growing attention for automatically learning discriminative features from data. This paper proposes a new approach to predicting corn leaf disease using deep learning and classical segmentation techniques for improved accuracy and efficiency. The proposed work presents an adaptive colour edge segmentation method improved by a hill-climbing search for robust feature extraction according to the diversified nature of corn leaves. With the help of stochastic hill climbing, the segmentation process is optimized by adaptively changing parameters to get better segmentation accuracy. After that, features are extracted and provided as input into a ResNeXt-101 model for disease classification. The novel activation function in ResNeXt-101 combines the Adam optimizer with a Gaussian-based GELU to enhance nonlinearity to the smooth activation of GELU. The results obtained from experiments show that the proposed approach is practical. The ResNeXt-101 model has achieved overwhelming performance, with 99% for testing accuracy and a minimum loss of 0.01, proving its superior generalization capability and robustness. The proposed work was performed with no overfitting and free from local minima during the training process.

Cross-domain additive learning of new knowledge rather than replacement.

In medical clinical scenarios for reasons such as patient privacy, information protection and data migration, when domain adaptation is needed for real scenarios, the source-domain data is often inaccessible and only the pre-trained source model on the source-domain is available. Existing solutions for this type of problem tend to forget the rich task experience previously learned on the source domain after adapting, which means that the model simply overfits the target-domain data when adapting and does not learn robust features that facilitate real task decisions. We address this problem by exploring the particular application of source-free domain adaptation in medical image segmentation and propose a two-stage additive source-free adaptation framework. We generalize the domain-invariant features by constraining the core pathological structure and semantic consistency between different perspectives. And we reduce the segmentation generated by locating and filtering elements that may have errors through Monte-Carlo uncertainty estimation. We conduct comparison experiments with some other methods on a cross-device polyp segmentation and a cross-modal brain tumor segmentation dataset, the results in both the target and source domains verify that the proposed method can effectively solve the domain offset problem and the model retains its dominance on the source domain after learning new knowledge of the target domain.This work provides valuable exploration for achieving additive learning on the target and source domains in the absence of source data and offers new ideas and methods for adaptation research in the field of medical image segmentation.

A new insight to investigate the developmental resilience of Chengdu-Chongqing twin-city economic circle based on ecological niche theory

ABSTRACT Enhancing the resilience of urban agglomerations is crucial for regional sustainable development. By analyzing the regional resilience of Chengdu-Chongqing Twin Cities Economic Circle (CCEC) from 2006 to 2018, this paper explores the development level of regional resilience, and tries to apply the new perspective of niche related method to the research of regional resilience. Based on the urban resilience theory and the ecological niche theory, this paper constructs the regional resilience index (RRI) from the four dimensions of ecology, economy, society and resources, and selects the suitability, robustness and diversity indicators to construct the regional resilience evaluation index system. The results show that the regional suitability of the central urban area shows a positive trend, showing that the suitability of urban development in the core area is better, and the suitability of urban development in the second edge area is weaker. From the perspective of regional robustness characteristics, the differences in the four dimensions of ecology, economy, society and resources are on the rise, and there are certain risks of system robustness. From the characteristics of regional diversity, the interaction between cities at the same level is more frequent, the competition between core cities is fierce, the secondary cities are homogeneous, the system function and structure similarity within the region is high, and the diversity of regional resilience is poor. Finally, the current situation of resilience in the CCEC region is discussed and suggestions for optimization are made.

DeepFeature: Guiding adversarial testing for deep neural network systems using robust features

With the deployment of Deep Neural Network (DNN) systems in security-critical fields, more and more researchers are concerned about DNN robustness. Unfortunately, DNNs are vulnerable to adversarial attacks and produce completely wrong outputs. This inspired numerous testing works devoted to improving the adversarial robustness of DNNs. Coverage and uncertainty criteria were proposed to guide sample selections for DNN retraining. However, they are greatly limited to evaluating DNN abnormal behaviors rather than locating the root cause of adversarial vulnerability. This work aims to bridge this gap. We propose an adversarial testing framework, DeepFeature, using robust features. DeepFeature generates robust features related to the model decision-making. It locates the weak features within these features that fail to be transformed by the DNN. They are the main culprits of vulnerability. DeepFeature selects diverse samples containing weak features for adversarial retraining. Our evaluation shows that DeepFeature significantly improves overall robustness, average improved by 77.83%, and individual robustness, average improved by 42.81‰, of the models in adversarial testing. Compared with coverage and uncertainty criteria, these two performances are improved by 3.93% and 15.00% in DeepFeature, respectively. The positive correlation coefficient between DeepFeature and improved robustness can achieve 0.858, and the p-value is 0.001.

RViT: Robust Fusion Vision Transformer with Variational Hierarchical Denoising Process for Image Classification

Transformers designed for natural language processing have originally been explored for computer vision in recent research. Various Vision Transformers (ViTs) play an increasingly important role in the field of image tasks such as computer vision, multimodal fusion and multimedia analysis. However, to obtain promising performance, most existing ViTs usually rely on artificially filtered high-quality images, which may suffer from inherent noise risk. Generally, such well-constructed images are not always available in every situation. To this end, we propose a Robust ViT (RViT) to focus on the relevant and robust representation learning for image classification tasks. Specifically, we first develop a novel Denoising VTUnet module, where we conceptualize the nonrobust noise as the uncertainty under the variational conditions. Furthermore, we design a fusion transformer backbone with a tailored fusion attention mechanism to perform image classification based on the extracted robust representations effectively. To demonstrate the superiority of our model, the compared experiments are conducted on several popular datasets. Benefiting from the sequence regularity of the Transformer and captured robust feature, the proposed method exceeds compared Transformer-based models with superior performance in visual tasks.

Comparative Analysis for Bag of Features (BoF) Performance

The accuracy of the Bag of Features (BoF) is greatly affected by the discriminatory power of feature extraction techniques. This paper presented a proposed method designed to find the best features technique for constructing a BoF model according to the image classification. It consists of four stages: feature extraction, where detectors and descriptor feature techniques have been exploited to generate different BoF models. Each BoF model is generated depending on what detector and descriptor are used. The BoF models are constructed to represent the images as feature vectors. The classification process is then performed on two image datasets. Finally, the efficiency of BoF models is analyzed and evaluated with respect to the accuracy of their classification performance. Experimental results indicated that the best level of accuracy was provided by the proposed BoF model with the KAZE features method. The results also showed that the BoF model with Speeded Up Robust Features (SURF) was superior to other feature methods in terms of execution time, which was 0.01218 seconds. Moreover, the BoF model generated by the SURF detector combined with the KAZE descriptor achieved a high level of accuracy of 0.99 and kept the time complexity low (0.01948 seconds).

Integrating Cloud Services with Mobile Applications for Seamless User Experience

In the modern digital era, the integration of cloud services with mobile applications has emerged as a pivotal strategy for delivering a seamless and dynamic user experience. This approach not only enhances the functionality of mobile applications but also ensures that users can access services and data in real-time, regardless of their location. As mobile devices continue to dominate the technology landscape, the demand for responsive, scalable, and user-centric applications has skyrocketed. Cloud services, with their inherent capabilities such as storage, computing power, and advanced analytics, provide the backbone for developing applications that meet these demands. The integration of cloud services with mobile applications offers numerous advantages. It allows for the offloading of heavy computational tasks to cloud servers, thereby preserving the limited processing power and battery life of mobile devices. This capability enables mobile applications to perform complex tasks such as real-time data processing, machine learning inference, and multimedia content rendering without compromising user experience. Additionally, cloud services facilitate the synchronization of data across multiple devices, ensuring that users have consistent access to their data and settings regardless of the device they are using. This is particularly important in scenarios where users switch between devices, such as moving from a smartphone to a tablet or laptop. Moreover, the use of cloud services in mobile applications enhances security and reliability. Cloud providers typically offer robust security features, including data encryption, identity and access management, and continuous monitoring, which are essential for protecting sensitive user data. By leveraging these features, mobile applications can offer a higher level of security than would be feasible with on-device storage and processing. Furthermore, the reliability of cloud services ensures that applications remain available and functional even during peak usage times or when the user is in a location with poor network connectivity. Through techniques such as caching and offline access, cloud-integrated mobile applications can continue to operate smoothly even when real-time access to cloud resources is temporarily unavailable.

A source free robust domain adaptation approach with pseudo-labels uncertainty estimation for rolling bearing fault diagnosis under limited sample conditions

As essential components of machinery equipment, rolling bearings directly affect the safety of the machinery equipment. The timely diagnosis of bearing faults can effectively prevent equipment lapses. However, bearings are often inconsistently distributed. This has resulted in a significant decrease in their availability. Moreover, the performances of traditional models are poor when fault samples are scarce. The unsupervised domain adaptation (UDA) model based on the transfer learning theory can solve the above problems in static scenarios. However, source domain data are often not directly accessible for privacy protection. Therefore, achieving the robustness of UDA models is significantly challenging. Source-free UDA can achieve a positive transfer from the source domain to the target domain based only on a pretrained source-domain model and unlabeled target-domain data. In this study, we built a source-free robust UDA approach with pseudo-label uncertainty estimation (SFRDA-PLUE) for diagnosing bearing faults using a limited number of samples. First, we designed a robust feature extractor (SANet) and proposed a novel binary soft-constrained information entropy. This was applied to solve the problem that standard information entropy cannot effectively estimate the uncertainty of pseudo-labels. In addition, we constructed a weighted comparison filter strategy to smoothen the fuzzy samples. Finally, we introduced an information-maximizing loss strategy to optimize the performance of the source domain classifier and the pseudo-label estimator. Thus, the robustness of the pseudo-label uncertainty estimation was significantly improved. The experimental results validated that the SFRDA-PLUE approach can achieve excellent diagnostic performance under a limited number of samples.

RA-XTNet: A Novel CNN Model to Predict Rheumatoid Arthritis from Hand Radiographs and Thermal Images: A Comparison with CNN Transformer and Quantum Computing.

The aim and objective of the research are to develop an automated diagnosis system for the prediction of rheumatoid arthritis (RA) based on artificial intelligence (AI) and quantum computing for hand radiographs and thermal images. The hand radiographs and thermal images were segmented using a UNet++ model and color-based k-means clustering technique, respectively. The attributes from the segmented regions were generated using the Speeded-Up Robust Features (SURF) feature extractor and classification was performed using k-star and Hoeffding classifiers. For the ground truth and the predicted test image, the study utilizing UNet++ segmentation achieved a pixel-wise accuracy of 98.75%, an intersection over union (IoU) of 0.87, and a dice coefficient of 0.86, indicating a high level of similarity. The custom RA-X-ray thermal imaging (XTNet) surpassed all the models for the detection of RA with a classification accuracy of 90% and 93% for X-ray and thermal imaging modalities, respectively. Furthermore, the study employed quantum support vector machine (QSVM) as a quantum computing approach which yielded an accuracy of 93.75% and 87.5% for the detection of RA from hand X-ray and thermal images. In addition, vision transformer (ViT) was employed to classify RA which obtained an accuracy of 80% for hand X-rays and 90% for thermal images. Thus, depending on the performance measures, the RA-XTNet model can be used as an effective automated diagnostic method to diagnose RA accurately and rapidly in hand radiographs and thermal images.