Labeling Data Research Articles

Semi-supervised skin cancer diagnosis based on self-feedback threshold focal learning

Worldwide, skin cancer prevalence necessitates accurate diagnosis to alleviate public health burdens. Although the application of artificial intelligence in image analysis and pattern recognition has improved the accuracy and efficiency of early skin cancer diagnosis, existing supervised learning methods are limited due to their reliance on a large amount of labeled data. To overcome the limitations of data labeling and enhance the performance of diagnostic models, this study proposes a semi-supervised skin cancer diagnostic model based on Self-feedback Threshold Focal Learning (STFL), capable of utilizing partial labeled and a large scale of unlabeled medical images for training models in unseen scenarios. The proposed model dynamically adjusts the selection threshold of unlabeled samples during training, effectively filtering reliable unlabeled samples and using focal learning to mitigate the impact of class imbalance in further training. The study is experimentally validated on the HAM10000 dataset, which includes images of various types of skin lesions, with experiments conducted across different scales of labeled samples. With just 500 annotated samples, the model demonstrates robust performance (0.77 accuracy, 0.6408 Kappa, 0.77 recall, 0.7426 precision, and 0.7462 F1-score), showcasing its efficiency with limited labeled data. Further, comprehensive testing validates the semi-supervised model’s significant advancements in diagnostic accuracy and efficiency, underscoring the value of integrating unlabeled data. This model offers a new perspective on medical image processing and contributes robust scientific support for the early diagnosis and treatment of skin cancer.

Distantly Supervised Relation Extraction Based on Residual Attention and Self Learning

Relation extraction is an important task in information extraction, which aims to identify the relation between two given entities. The algorithm based on distant supervision can automatically generate a large amount of annotated data, which becomes the main method to deal with the task of relation extraction. However, previous studies rely too much on the precision of supervision information and ignore the effective supervision information hidden in the case of mislabeling, which leads to the loss of supervision information. To solve this problem, we propose the distantly supervised relation extraction model based on residual attention and self-learning. The model uses residual attention to extract features, and then uses self-learning idea to generate corrected labels for training data, which are added into the training process as supervisory signals to prevent parameter error updates caused by noisy labels. The model can not only reduce the problem of mislabeling caused by distant supervision, but also makes full use of the available supervisory information in the data to improve data utilization. Experiments show that compared with the existing mainstream baseline methods, the proposed model has higher precision and recall.

Multi-centre benchmarking of deep learning models for COVID-19 detection in chest x-rays.

This study is a retrospective evaluation of the performance of deep learning models that were developed for the detection of COVID-19 from chest x-rays, undertaken with the goal of assessing the suitability of such systems as clinical decision support tools. Models were trained on the National COVID-19 Chest Imaging Database (NCCID), a UK-wide multi-centre dataset from 26 different NHS hospitals and evaluated on independent multi-national clinical datasets. The evaluation considers clinical and technical contributors to model error and potential model bias. Model predictions are examined for spurious feature correlations using techniques for explainable prediction. Models performed adequately on NHS populations, with performance comparable to radiologists, but generalised poorly to international populations. Models performed better in males than females, and performance varied across age groups. Alarmingly, models routinely failed when applied to complex clinical cases with confounding pathologies and when applied to radiologist defined "mild" cases. This comprehensive benchmarking study examines the pitfalls in current practices that have led to impractical model development. Key findings highlight the need for clinician involvement at all stages of model development, from data curation and label definition, to model evaluation, to ensure that all clinical factors and disease features are appropriately considered during model design. This is imperative to ensure automated approaches developed for disease detection are fit-for-purpose in a clinical setting.

Using image segmentation models to analyse high-resolution earth observation data: new tools to monitor disease risks in changing environments.

In the near future, the incidence of mosquito-borne diseases may expand to new sites due to changes in temperature and rainfall patterns caused by climate change. Therefore, there is a need to use recent technological advances to improve vector surveillance methodologies. Unoccupied Aerial Vehicles (UAVs), often called drones, have been used to collect high-resolution imagery to map detailed information on mosquito habitats and direct control measures to specific areas. Supervised classification approaches have been largely used to automatically detect vector habitats. However, manual data labelling for model training limits their use for rapid responses. Open-source foundation models such as the Meta AI Segment Anything Model (SAM) can facilitate the manual digitalization of high-resolution images. This pre-trained model can assist in extracting features of interest in a diverse range of images. Here, we evaluated the performance of SAM through the Samgeo package, a Python-based wrapper for geospatial data, as it has not been applied to analyse remote sensing images for epidemiological studies. We tested the identification of two land cover classes of interest: water bodies and human settlements, using different UAV acquired imagery across five malaria-endemic areas in Africa, South America, and Southeast Asia. We employed manually placed point prompts and text prompts associated with specific classes of interest to guide the image segmentation and assessed the performance in the different geographic contexts. An average Dice coefficient value of 0.67 was obtained for buildings segmentation and 0.73 for water bodies using point prompts. Regarding the use of text prompts, the highest Dice coefficient value reached 0.72 for buildings and 0.70 for water bodies. Nevertheless, the performance was closely dependent on each object, landscape characteristics and selected words, resulting in varying performance. Recent models such as SAM can potentially assist manual digitalization of imagery by vector control programs, quickly identifying key features when surveying an area of interest. However, accurate segmentation still requires user-provided manual prompts and corrections to obtain precise segmentation. Further evaluations are necessary, especially for applications in rural areas.

Crowdsourcing with the drift diffusion model of decision making.

Crowdsourcing involves the use of annotated labels with unknown reliability to estimate ground truth labels in datasets. A common task in crowdsourcing involves estimating reliabilities of annotators (such as through the sensitivities and specificities of annotators in the binary label setting). In the literature, beta or dirichlet distributions are typically imposed as priors on annotator reliability. In this study, we investigated the use of a neuroscientifically validated model of decision making, known as the drift-diffusion model, as a prior on the annotator labeling process. Two experiments were conducted on synthetically generated data with non-linear (sinusoidal) decision boundaries. Variational inference was used to predict ground truth labels and annotator related parameters. Our method performed similarly to a state-of-the-art technique (SVGPCR) in prediction of crowdsourced data labels and prediction through a crowdsourced-generated Gaussian process classifier. By relying on a neuroscientifically validated model of decision making to model annotator behavior, our technique opens the avenue of predicting neuroscientific biomarkers of annotators, expanding the scope of what may be learnt about annotators in crowdsourcing tasks.

An enhanced semi-supervised learning method with self-supervised and adaptive threshold for fault detection and classification in urban power grids

With the rapid development of urban power grids and the large-scale integration of renewable energy, traditional power grid fault diagnosis techniques struggle to address the complexities of diagnosing faults in intricate power grid systems. Although artificial intelligence technologies offer new solutions for power grid fault diagnosis, the difficulty in acquiring labeled grid data limits the development of AI technologies in this area. In response to these challenges, this study proposes a semi-supervised learning framework with self-supervised and adaptive threshold (SAT-SSL) for fault detection and classification in power grids. Compared to other methods, our method reduces the dependence on labeling data while maintaining high recognition accuracy. First, we utilize frequency domain analysis on power grid data to filter abnormal events, then classify and label these events based on visual features, to creating a power grid dataset. Subsequently, we employ the Yule–Walker algorithm extract features from the power grid data. Then we construct a semi-supervised learning framework, incorporating self-supervised loss and dynamic threshold to enhance information extraction capabilities and adaptability across different scenarios of the model. Finally, the power grid dataset along with two benchmark datasets are used to validate the model’s functionality. The results indicate that our model achieves a low error rate across various scenarios and different amounts of labels. In power grid dataset, When retaining just 5% of the labels, the error rate is only 6.15%, which proves that this method can achieve accurate grid fault detection and classification with a limited amount of labeled data.

DSFworld: A flexible and precise tool to analyze differential scanning fluorimetry data.

Differential scanning fluorimetry (DSF) is a method to determine the apparent melting temperature (Tma) of a purified protein. In DSF, the raw unfolding curves from which Tma is calculated vary widely in shape and complexity. However, the tools available for calculating Tma are only compatible with the simplest of DSF curves, hindering many otherwise straightforward applications of the technology. To overcome this limitation, we designed new mathematical models for Tma calculation that accommodate common forms of variation in DSF curves, including the number of transitions, the presence of high initial signal, and temperature-dependent signal decay. When tested these models against DSFbase, an open-source database of 6235 raw, real-life DSF curves, these models outperformed the existing standard approaches of sigmoid fitting and maximum of the first derivative. To make these models accessible, we created an open-source software and website, DSFworld (https://gestwickilab.shinyapps.io/dsfworld/). In addition to these improved fitting capabilities, DSFworld also includes features that overcome the practical limitations of many analysis workflows, including automatic reformatting of raw data exported from common qPCR instruments, labeling of data based on experimental variables, and flexible interactive plotting. We hope that DSFworld will enable more streamlined and accurate calculation of Tma values for DSF experiments.

Federated variational generative learning for heterogeneous data in distributed environments

Distributedly training models across diverse clients with heterogeneous data samples can significantly impact the convergence of federated learning. Various novel federated learning methods address these challenges but often require significant communication resources and local computational capacity, leading to reduced global inference accuracy in scenarios with imbalanced label data distribution and quantity skew. To tackle these challenges, we propose FedVGL, a Federated Variational Generative Learning method that directly trains a local generative model to learn the distribution of local features and improve global target model inference accuracy during aggregation, particularly under conditions of severe data heterogeneity. FedVGL facilitates distributed learning by sharing generators and latent vectors with the global server, aiding in global target model training from mapping local data distribution to the variational latent space for feature reconstruction. Additionally, FedVGL implements anonymization and encryption techniques to bolster privacy during generative model transmission and aggregation. In comparison to vanilla federated learning, FedVGL minimizes communication overhead, demonstrating superior accuracy even with minimal communication rounds. It effectively mitigates model drift in scenarios with heterogeneous data, delivering improved target model training outcomes. Empirical results establish FedVGL's superiority over baseline federated learning methods under severe label imbalance and data skew condition. In a Label-based Dirichlet Distribution setting with α=0.01 and 10 clients using the MNIST dataset, FedVGL achieved an exceptional accuracy over 97% with the VGG-9 target model.

Perioperative Management of Traditional and Direct Oral Anticoagulants in Hip Fracture Patients.

Hip fractures are an increasingly common injury in the senior population and almost always require surgical fixation or prosthetic replacement. These surgeries, according to the American Academy of Orthopaedic Surgeons, are considered high-risk for bleeding, especially in a population fraught with comorbidities and often presenting on anticoagulation medications. Direct oral anticoagulants represent a class of drugs that have been becoming more popular in use in this population, with many benefits over the historically used Warfarin. There are recommendations for preoperative discontinuation and postoperative resumption of these medications, which can be more readily managed for elective surgeries. However, there is a paucity of literature detailing best practice guidelines for the perioperative management of direct oral anticoagulants when a patient presents with a hip fracture. This review article summary of the periprocedural management of DOACs for hip surgery was developed by examining the American College of Chest Physicians evidence-based clinical practice guidelines, Perioperative Guidelines on Antiplatelet and Anticoagulant Agents written by anesthesiologists, various retrospective studies, and drug labels for pharmacokinetic data. These recommendations should be used as a guideline, along with the collaboration of multidisciplinary hospital teams during inpatient admission, to manage these complex patients.

A novel self-supervised sentiment classification approach using semantic labeling based on contextual embeddings

AbstractSentiment Analysis (SA) is a domain or context-oriented task since the sentiment words convey different sentiments in various domains. As a result, the domain-independent lexicons cannot correctly recognize the sentiment of domain-dependent words. To address this problem, this paper proposes a novel self-supervised SA method based on semantic similarity, contextual embedding, and Deep Learning Techniques. It introduces a new Pseudo-label generator that estimates the pseudo-labels of samples using semantic similarity between the samples and their sentiment words. It proposes two new concepts to calculate semantic similarity: The Soft-Cosine Similarity of a sample with its Positive words (SCSP) and the Soft-Cosine Similarity of a document with its Negative words (SCSN). Then, the Pseudo-label generator uses these concepts and the number of sentiment words to estimate the label of each sample. Later on, a novel method is proposed to find the samples with highly accurate pseudo-labels. Finally, a hybrid classifier, composed of a Convolutional Neural Network (CNN) and a Gated Recurrent Unit (GRU), is trained using these highly accurate pseudo-labeled data to predict the label of unseen data. The comparison of the proposed method with the lexicons and other similar existing methods demonstrates that the proposed method outperforms them in terms of accuracy, precision, recall, and F1 score.

Semi-supervised method for visual detection of automotive paint defects

Automotive paint defect detection plays a crucial role in the automotive production process. Current research on visual defect detection methods is mainly based on supervised learning, which requires a large number of labeled image samples for model training. The labeling work is not only time consuming but also expensive, seriously hindering the testing and application of these models in practice. To address this issue, this study proposes a new method for automotive paint defect detection based on a semi-supervised training strategy. First, a semi-supervised automotive paint defect detection framework, which can use labeled and unlabeled samples to reduce the cost of data labeling effectively, is presented. Then, a spatial pyramid pooling fast external attention module that introduces an external attention mechanism is proposed to improve the traditional YOLOv7 network structure, called YOLOv7-EA, to obtain good detection performance. This network acts as a detector to generate high-quality pseudo labels for the unlabeled samples, providing additional data to train the model; meanwhile, it performs the final detection task. Lastly, a Wise-intersection over union loss function that considers the quality of the anchor box is introduced to reduce the interference of low-quality samples and improve the convergence speed and detection accuracy of the model. Using this method, we can accomplish the task of automotive paint defect detection with a small number of labeled image samples. Experimental results on the automotive paint defect dataset show that mean average precision (mAp)@.5, mAp@.75, and mAp@.5:.95 are superior to other methods under the condition of 10% and 15% labeled data, achieving good defect detection performance.

Electrical Sensor Calibration by Fuzzy Clustering with Mandatory Constraint.

Electrical tomography sensors have been widely used for pipeline parameter detection and estimation. Before they can be used in formal applications, the sensors must be calibrated using enough labeled data. However, due to the high complexity of actual measuring environments, the calibrated sensors are inaccurate since the labeling data may be uncertain, inconsistent, incomplete, or even invalid. Alternatively, it is always possible to obtain partial data with accurate labels, which can form mandatory constraints to correct errors in other labeling data. In this paper, a semi-supervised fuzzy clustering algorithm is proposed, and the fuzzy membership degree in the algorithm leads to a set of mandatory constraints to correct these inaccurate labels. Experiments in a dredger validate the proposed algorithm in terms of its accuracy and stability. This new fuzzy clustering algorithm can generally decrease the error of labeling data in any sensor calibration process.

A Domain-Adaptive Segmentation Method Based on Segment Anything Model for Mechanical Assembly

Semantic segmentation of assembly images can effectively identify and prevent non-standard behaviors such as wrong assembly and missing assembly in the assembly process. However, supervised methods require massive training samples and are time-consuming to label. Unsupervised domain adaptation methods can address this issue without labeling the target data. Recently, the large-scale Segment Anything Model (SAM) has achieved significant success in semantic segmentation owing to its powerful feature extraction and instant interaction capabilities. Based on this, this paper proposed a new framework called U-SAM for unsupervised domain-adaptive semantic segmentation. Compared to other frameworks, U-SAM can obtain more segmented features while maintaining shallower features. Meanwhile, this study proposed an iterative loop strategy for the prompt module in U-SAM. This strategy gradually improves the accuracy of target prompt labels and solves the problem of no prompt labels in the target data. Additionally, a novel method of using oblique boxes instead of regular boxes was developed to achieve higher box prompt quality. Finally, a line discriminator module and a trainable line-guided filtering module were designed to improve the quality of edge segmentation. The experimental results indicate that the U-SAM network framework achieves a Dice accuracy of 84.4% for semantic segmentation on the mechanical assembly image dataset. This confirmed that our proposed method can be applied to the assembly monitoring process of target data.

A Human-In-One-Loop Active Domain Adaptation Framework for Digit Recognition

ABSTRACT Domain adaptation can effectively enhance a model’s performance on target domain data with limited data. However, when some target domain labels are obtainable, training the model with both source and target domain data simultaneously can lead to worse performance due to the lower density of target domain data. If a large amount of target domain data is labeled without discrimination, it will necessitate a considerable expenditure of human resources. To address this issue, this paper proposes a human-in-one-loop active domain adaptation framework based on Target Domain Feature Generation to solve the problems. The oracle participates in only one iteration of data labeling, and a target domain classifier will take over the subsequent rest iterations. An image generator based on multiple CycleGANs forms an iterative co-training mechanism, which can continuously generate more high-quality labeled fake target domain data in iterations to improve the performance of the target domain classifier. The Top-N labeled data selection method with high confidence is devised to select the most accurately predicted data for labeling, reducing manual labeling workload. This framework can achieve an average accuracy of 0.8869 on six domain pairs, doubling the classical domain adaptation method DSN, requiring only a small amount of manual labeling.

AutoDLAR: A Semi-supervised Cross-modal Contact-free Human Activity Recognition System

WiFi-based human activity recognition (HAR) plays an essential role in various applications such as security surveillance, health monitoring, and smart home. Existing HAR methods, though yielding promising performance in indoor scenarios, highly depend on a massive labeled dataset for training which is extremely difficult to acquire in practical applications. In this paper, we present an automatic data labeling and HAR system, termed AutoDLAR. Taking a semi-supervised cross-modal learning framework with a hybrid loss function as the core, AutoDLAR transfers rich visual information to automatically label WiFi signals for WiFi-based HAR. Specifically, we devise a lightweight and multi-view WiFi sensing model with a parallel feature embedding method to accurately identify activities and accelerate recognition speed. Then, we exploit the video data to fine-tune a well-established visual HAR model, generating effective pseudo-labels for guiding the WiFi model’s training. We also build a synchronized Video-WiFi dataset with seven types of human activities under different scenarios to enable training and validating the semi-supervised HAR system. Extensive experiments on our collected activity dataset and the emotion recognition benchmark demonstrate that AutoDLAR attains an average accuracy of over 95.89% without manual labeling and only spends the inference time of 3.35 ms, outperforming the state-of-the-art (SOTA) methods.

Catalyzing Precision Medicine: Artificial Intelligence Advancements in Prostate Cancer Diagnosis and Management.

The aim was to analyze the current state of deep learning (DL)-based prostate cancer (PCa) diagnosis with a focus on magnetic resonance (MR) prostate reconstruction; PCa detection/stratification/reconstruction; positron emission tomography/computed tomography (PET/CT); androgen deprivation therapy (ADT); prostate biopsy; associated challenges and their clinical implications. A search of the PubMed database was conducted based on the inclusion and exclusion criteria for the use of DL methods within the abovementioned areas. A total of 784 articles were found, of which, 64 were included. Reconstruction of the prostate, the detection and stratification of prostate cancer, the reconstruction of prostate cancer, and diagnosis on PET/CT, ADT, and biopsy were analyzed in 21, 22, 6, 7, 2, and 6 studies, respectively. Among studies describing DL use for MR-based purposes, datasets with magnetic field power of 3 T, 1.5 T, and 3/1.5 T were used in 18/19/5, 0/1/0, and 3/2/1 studies, respectively, of 6/7 studies analyzing DL for PET/CT diagnosis which used data from a single institution. Among the radiotracers, [68Ga]Ga-PSMA-11, [18F]DCFPyl, and [18F]PSMA-1007 were used in 5, 1, and 1 study, respectively. Only two studies that analyzed DL in the context of DT met the inclusion criteria. Both were performed with a single-institution dataset with only manual labeling of training data. Three studies, each analyzing DL for prostate biopsy, were performed with single- and multi-institutional datasets. TeUS, TRUS, and MRI were used as input modalities in two, three, and one study, respectively. DL models in prostate cancer diagnosis show promise but are not yet ready for clinical use due to variability in methods, labels, and evaluation criteria. Conducting additional research while acknowledging all the limitations outlined is crucial for reinforcing the utility and effectiveness of DL-based models in clinical settings.

Towards optimal model evaluation: enhancing active testing with actively improved estimators

With rapid advancements in machine learning and statistical models, ensuring the reliability of these models through accurate evaluation has become imperative. Traditional evaluation methods often rely on fully labeled test data, a requirement that is becoming increasingly impractical due to the growing size of datasets. In this work, we address this issue by extending existing work on active testing (AT) methods which are designed to sequentially sample and label data for evaluating pre-trained models. We propose two novel estimators: the Actively Improved Levelled Unbiased Risk (AILUR) and the Actively Improved Inverse Probability Weighting (AIIPW) estimators which are derived from nonparametric smoothing estimation. In addition, a model recalibration process is designed for the AIIPW estimator to optimize the sampling probability within the AT framework. We evaluate the proposed estimators on four real-world datasets and demonstrate that they consistently outperform existing AT methods. Our study also shows that the proposed methods are robust to changes in subsample sizes, and effective at reducing labeling costs.

Artificial Intelligence for safety and reliability: A descriptive, bibliometric and interpretative review on machine learning

This research provides a structured review of studies that utilize Artificial Intelligence for safety and reliability. In particular, it focuses on Machine Learning techniques to perform fault detection and diagnosis, anomaly detection, system prognosis, reliability analysis, and risk assessment of engineering-related systems across the industry. Relevant studies were identified through clear research questions, screened, and assessed for eligibility. Explicit inclusion and exclusion criteria were defined to verify the suitability of the records. The analysis encompasses a descriptive, bibliometric, and interpretative review. The descriptive analysis details how different ML approaches are adapted and implemented across various domains of safety and reliability. The bibliometric analysis provides in-depth and comprehensive statistics, covering aspects such as data types used, preprocessing steps undertaken, and categories of ML algorithms employed. The interpretative analysis offers a critical and forward-looking perspective on the current state of the field. A total of 308 papers were analyzed, mostly adopting supervised learning frameworks (81%) and addressing fault detection and diagnosis (57%) in more than 16 different industrial fields. The outcome of this study reflects the rapid development of this cross-cutting and interdisciplinary research field and highlights the potential for future improvement in the data-driven operational safety of industrial plants. Challenges and limitations have been highlighted and discussed, including data availability and label scarcity, data quality, trust and explainability, and interdisciplinary collaboration. Additionally, suggestions on potential solutions to overcome existing limitations and outline future directions are provided.

Advanced Computational Framework to Analyze the Stability of Non-Newtonian Fluid Flow through a Wedge with Non-Linear Thermal Radiation and Chemical Reactions

The main idea of this investigation is to introduce an integrated intelligence approach that investigates the chemically reacting flow of non-Newtonian fluid with a backpropagation neural network (LMS-BPNN). The AI-based LMS-BPNN approach is utilized to obtain the optimal solution of an MHD flow of Eyring–Powell over a porous shrinking wedge with a heat source and nonlinear thermal radiation (Rd). The partial differential equations (PDEs) that define flow problems are transformed into a system of ordinary differential equations (ODEs) through efficient similarity variables. The reference solution is obtained with the bvp4c function by changing parameters as displayed in Scenarios 1–7. The label data are divided into three portions, i.e., 80% for training, 10% for testing, and 10% for validation. The label data are used to obtain the approximate solution using the activation function in LMS-BPNN within the MATLAB built-in command ‘nftool’. The consistency and uniformity of LMS-BPNN are supported by fitness curves based on the MSE, correlation index (R), regression analysis, and function fit. The best validation performance of LMS-BPNN is obtained at 462, 369, 642, 542, 215, 209, and 286 epochs with MSE values of 8.67 × 10−10, 1.64 × 10−9, 1.03 × 10−9, 302 9.35 × 10−10, 8.56 × 10−10, 1.08 × 10−9, and 6.97 × 10−10, respectively. It is noted that f′(η), θ(η), and ϕ(η) satisfy the boundary conditions asymptotically for Scenarios 1–7 with LMS-BPNN. The dual solutions for flow performance outcomes (Cfx, Nux, and Shx) are investigated with LMS-BPNN. It is concluded that when the magnetohydrodynamics increase (M=0.01, 0.05, 0.1), then the solution bifurcates at different critical values, i.e., λc=−1.06329,−1.097,−1.17694. The stability analysis is conducted using an LMS-BPNN approximation, involving the computation of eigenvalues for the flow problem. The deduction drawn is that the upper (first) branch solution remains stable, while the lower branch solution causes a disturbance in the flow and leads to instability. It is observed that the boundary layer thickness for the lower branch (second) solution is greater than the first solution. A comparison of numerical results and predicted solutions with LMS-BPNN is provided and they are found to be in good agreement.

Orbital learning: a novel, actively orchestrated decentralised learning for healthcare

A novel collaborative and continual learning across a network of decentralised healthcare units, avoiding identifiable data-sharing capacity, is proposed. Currently available methodologies, such as federated learning and swarm learning, have demonstrated decentralised learning. However, the majority of them face shortcomings that affect their performance and accuracy. These shortcomings include a non-uniform rate of data accumulation, non-uniform patient demographics, biased human labelling, and erroneous or malicious training data. A novel method to reduce such shortcomings is proposed in the present work through selective grouping and displacing of actors in a network of many entities for intra-group sharing of learning with inter-group accessibility. The proposed system, known as Orbital Learning, incorporates various features from split learning and ensemble learning for a robust and secure performance of supervised models. A digital embodiment of the information quality and flow within a decentralised network, this platform also acts as a digital twin of healthcare network. An example of ECG classification for arrhythmia with 6 clients is used to analyse its performance and is compared against federated learning. In this example, four separate experiments are conducted with varied configurations, such as varied age demographics and clients with data tampering. The results obtained show an average area under receiver operating characteristic curve (AUROC) of 0.819 (95% CI 0.784–0.853) for orbital learning whereas 0.714 (95% CI 0.692–0.736) for federated learning. This result shows an increase in overall performance and establishes that the proposed system can address the majority of the issues faced by existing decentralised learning methodologies. Further, a scalability demo conducted establishes the versatility and scalability of this platform in handling state-of-the-art large language models.