Labeling Errors Research Articles

Dataset preparation for CROHME 2019 for training a neural network

Subject of research. This article examines the process of data preparation for training neural network models that address the task of recognizing complex handwritten mathematical expressions and converting them into typesetting systems like LaTeX or MathML. The dataset under study is CROHME 2019, which contains images of handwritten mathematical expressions and their corresponding LaTeX annotations. The objective of this research is to develop and describe a data preparation process that ensures correct model training and minimizes errors in numerical labels and transformations. The study focuses on the following key stages: loading and preprocessing images, parsing LaTeX annotations, linking images with their corresponding annotations, normalizing pixel values, creating and verifying the tokenizer vocabulary, and preparing the tokenizer itself. The methods include data analysis and processing using specialized tools for working with images and text annotations. The main outcome of this work is the creation of a dataset ready for use in training the neural network model. The prepared dataset ensures accurate alignment between images and annotations, as well as correct conversion of mathematical expressions into LaTeX code.

Learning and semiautomatic intention labeling for classification models: a COVID-19 dialog attendance study for chatbots

Abstract It is increasingly common to use chatbots as an interface to services. One of the main components of a chatbot is the Natural Language Understanding (NLU) model, which is responsible for interpreting the text and extracting the intent and entities present in that text. It’s possible to focus only on one of these tasks of NLU, such as intent classification. To train an NLU intent classification model, it’s generally necessary to use a considerable amount of annotated data, where each sentence of the dataset receives a label indicating an intent. Performing manually labeling data is arduous and impracticable, depending on the data volume. Thus, an unsupervised machine learning technique, such as data clustering, could be applied to find and label patterns in the data. For this task, it is essential to have an effective vector embedding representation of texts that depicts the semantic information and helps the machine understand the context, intent, and other nuances of the entire text. This paper extensively evaluates different text embedding models for clustering and labeling. We also apply some operations to improve the dataset’s quality, such as removing sentences and establishing various strategies for distance thresholds (cosine similarity) for the clusters’ centroids. Then, we trained some intent classification Models with two different architectures, one built with the Rasa framework and the other with a neural network (NN) using the attendance text from the Coronavirus Platform Service of Ceará, Brazil. We also manually annotated a dataset to be used as validation data. We conducted a study on semiautomatic labeling, implemented through clustering and visual inspection, which introduced some labeling errors to the intent classification models. However, it would be unfeasible to annotate the entire dataset manually. Nevertheless, results of competitive accuracy were still achieved with the trained models.

Genetic Diversity and Population Structure of Cacao (Theobroma cacao L.) Germplasm from Sierra Leone and Togo Based on KASP–SNP Genotyping

Cacao (Theobroma cacao L.) is a tropical tree species belonging to the Malvaceae, which originated in the lowland rainforests of the Amazon. It is a major agricultural commodity, which contributes towards the Gross Domestic Product of West African countries, where it accounts for about 70% of the world’s production. Understanding the genetic diversity of genetic resources in a country, especially for an introduced crop such as cacao, is crucial to their management and effective utilization. However, very little is known about the genetic structure of the cacao germplasm from Sierra Leone and Togo based on molecular information. We assembled cacao germplasm accessions (235 from Sierra Leone and 141 from Togo) from different seed gardens and farmers’ fields across the cacao-producing states/regions of these countries for genetic diversity and population structure studies based on single nucleotide polymorphism (SNP) markers using 20 highly informative and reproducible KASP–SNPs markers. Genetic diversity among these accessions was assessed with three complementary clustering methods, including model-based population structure, discriminant analysis of principal components (DAPC), and phylogenetic trees. STRUCTURE and DAPC exhibited some consistency in the allocation of accessions into subpopulations or groups, although some discrepancies in their groupings were noted. Hierarchical clustering analysis grouped all the individuals into two major groups, as well as several sub-clusters. We also conducted a network analysis to elucidate genetic relationships among cacao accessions from Sierra Leone and Togo. Analysis of molecular variance (AMOVA) revealed high genetic diversity (86%) within accessions. A high rate of mislabeling/duplicate genotype names was revealed in both countries, which may be attributed to errors from the sources of introduction, labeling errors, and lost labels. This preliminary study demonstrates the use of KASP–SNPs for fingerprinting that can help identify duplicate/mislabeled accessions and provide strong evidence for improving accuracy and efficiency in cacao germplasm management as well as the distribution of correct materials to farmers.

A natural language processing approach to detect inconsistencies in death investigation notes attributing suicide circumstances

BackgroundData accuracy is essential for scientific research and policy development. The National Violent Death Reporting System (NVDRS) data is widely used for discovering the patterns and causing factors of death. Recent studies suggested the annotation inconsistencies within the NVDRS and the potential impact on erroneous suicide-circumstance attributions.MethodsWe present an empirical Natural Language Processing (NLP) approach to detect annotation inconsistencies and adopt a cross-validation-like paradigm to identify possible label errors. We analyzed 267,804 suicide death incidents between 2003 and 2020 from the NVDRS. We measured annotation inconsistency by the degree of changes in the F-1 score.ResultsOur results show that incorporating the target state’s data into training the suicide-circumstance classifier brings an increase of 5.4% to the F-1 score on the target state’s test set and a decrease of 1.1% on other states’ test set.ConclusionsTo conclude, we present an NLP framework to detect the annotation inconsistencies, show the effectiveness of identifying and rectifying possible label errors, and eventually propose an improvement solution to improve the coding consistency of human annotators.

EEG-based emotional valence and emotion regulation classification: a data-centric and explainable approach

Emotion classification using electroencephalographic (EEG) data is a challenging task in the field of Artificial Intelligence. While many researchers have focused on finding the best model or feature extraction technique to achieve optimal results, few have attempted to select the best methodological steps for working with the dataset. In this study, we applied two different theoretical approaches based on the noise of the dataset: curriculum learning and confident learning. Curriculum learning involves presenting training examples to the model in a specific order, starting with easier examples and gradually increasing in difficulty. This approach has been shown to improve model performance. Confident learning is a method for identifying and correcting label errors in datasets. By identifying and correcting these errors, confident learning can improve the performance of machine learning models trained on noisy datasets. We then applied the Integrated Gradient technique in order to assess the explainability of each model. Our aim was to explore the impact of different models and methods on emotion classification performance using EEG data. We collected and used an EEG dataset in which participants rated the emotional valence of positive and negative pictures while performing an emotion regulation (ER) task, comparing a control condition (Look) with two ER strategies: cognitive reappraisal and expressive suppression. We performed a multilabel classification to identify emotional neutrality or polarization of emotional valence (both positive and negative) rated by participants and the emotion regulation strategy adopted during the task. We compared the performance of models trained on three datasets selected based on label noise and evaluated their suitability for this task. Our results suggest different patterns based on the architecture used for feature importance, highlighting both advantages and criticisms.

A-179 Improving specimen labeling errors in the pediatric emergency department at a tertiary care hospital

Abstract Background Specimen labeling errors, such as unlabeled, mislabeled, or sample-requisition mismatches, pose risks to patient care. Correcting these errors, particularly for pediatric patients, is crucial to avoid unnecessary stress to the family and time spent on follow-up. In 2018, the BCCH Emergency Department (ED) reported the highest labeling error rates among all departments at our tertiary care hospital, accounting for approximately 30% of all errors. Methods To address this issue, a quality improvement project following the Model for Improvement framework was initiated in 2019 at the ED. An interdisciplinary team approach was adopted initially, and a positive patient identification system (PPID) was implemented later in February 2022. Patient Safety Learning System (PSLS) data from January 2019 to November 2023 were analyzed to evaluate the impact of these interventions. Results 1763 (22.6%) of the 7802 PSLS events recorded during this period were sample labeling errors. Ward collections accounted for the majority of labeling errors compared to laboratory collections (20.3% vs 2.4%). In the ED, most of the labeling errors occurred with unspecified samples (25%), swabs (24%), urine (23%), and blood culture (19%). The interdisciplinary team intervention initially reduced labeling errors, but its impact was inconsistent. However, the implementation of PPID in 2022 led to a significant and consistent decrease in labeling errors in the ED (4.51 errors/month vs 1.14 errors/month; p = 0.01) (Figure. 1). Conclusions While the implementation of PPID has notably improved labeling errors in the ED, complete elimination remains challenging. In addition, more specific PSLS filing categories are needed to capture sources of labeling error from unspecified samples. Continued efforts are necessary to achieve the goal of zero labeling errors.

Automatic Road Crack Detection Using Convolutional Neural Network Based on Semi-Supervised Learning

Crack detection in pavements is a critical task for infrastructure maintenance, but it often requires extensive manual labeling of training samples, which is both time-consuming and labor-intensive. To address this challenge, this paper proposes a semi-supervised learning approach based on a DenseNet classification model to detect pavement cracks more efficiently. The primary objective is to leverage a small set of labeled samples to improve the model's performance by incorporating a large number of unlabeled samples through semi-supervised learning. This method enhances the DenseNet model's ability to generalize by iteratively learning from new unlabeled datasets. As a result, the proposed approach not only reduces the need for extensive manual labeling but also mitigates issues related to label inconsistency and errors in the original labels. The experimental results demonstrate that the semi-supervised DenseNet model achieves a prediction precision of 96.77% and a recall of 94.17%, with an F1 score of 95.45% and an Intersectidn over Union (IoU) of 91.30%. These metrics highlight the model's high accuracy and effectiveness in crack detection. The proposed method not only improves label quality and model performance but also offers practical value for engineering applications in the field of pavement maintenance, making it a valuable tool for infrastructure management.

Performance of the ChatGPT large language model for decision support in community pharmacy.

The aim of this study was to assess the ChatGPT-4 (ChatGPT) large language model (LLM) on tasks relevant to community pharmacy. ChatGPT was assessed with community pharmacy-relevant test cases involving drug information retrieval, identifying labelling errors, prescription interpretation, decision-making under uncertainty and multidisciplinary consults. Drug information on rituximab, warfarin, and St. John's wort was queried. The decision-support scenarios consisted of a subject with swollen eyelids and a maculopapular rash in a subject on lisinopril and ferrous sulfate. The multidisciplinary scenarios required the integration of medication management with recommendations for healthy eating and physical activity/exercise. The responses from ChatGPT for rituximab, warfarin, and St. John's wort were satisfactory and cited drug databases and drug-specific monographs. ChatGPT identified labeling errors related to incorrect medication strength, form, route of administration, unit conversion, and directions. For the patient with inflamed eyelids, the course of action developed by ChatGPT was comparable to the pharmacist's approach. For the patient with the maculopapular rash, both the pharmacist and ChatGPT placed a drug reaction to either lisinopril or ferrous sulfate at the top of the differential. ChatGPT provided customized vaccination requirements for travel to Brazil, guidance on management of drug allergies and recovery from a knee injury. ChatGPT provided satisfactory medication management and wellness information for a diabetic on metformin and semaglutide. LLMs have the potential to become a powerful tool in community pharmacy. However, rigorous validation studies across diverse pharmacist queries, drug classes and populations, and engineering to secure patient privacy will be needed to enhance LLM utility.

Transfusion sample mislabelling and wrong blood in tube in the UK: Insights from the national comparative audits of blood transfusion in 2012 and 2022.

Samples for transfusion rejected due to mislabelling can lead to harm when a patient has to be re-bled or has a transfusion or procedure delayed. Electronic labelling systems which scan the patient's identification band and generate a label at their side aim to reduce mislabelling and misidentification leading to wrong blood in tube (WBIT) errors. The 2022 National Comparative audit of sample collection aimed to compare national rates of sample mislabelling and WBIT to the 2012 audit and to examine the impact of electronic systems. All UK hospitals were invited to provide data on rejected transfusion samples and WBIT incidents in 1 month (October 2022) and were asked if they had electronic labelling. Twenty-three thousand five hundred and eighty-four rejected samples were reported by 179 sites in 1 month. The rejection rate of 4.4% represents a 47% increase compared to 2012 (2.99%). There were 92 WBIT incidents, an incidence of 1 in 5882 samples-a 45% increase compared to 1 in 8547 in 2012. Twenty-three percent of sites can print a sample label at the patient's side, up by 224%. The six sites using only electronic sample labelling had a 46.9% lower rejection rate than sites using only hand-labelling but still reported WBIT. The increase in sample rejection and WBIT may reflect pressures facing clinical staff, zero tolerance policies and the two-sample rule. A human factors approach to understanding and tackling underlying reasons locally is recommended. Electronic systems are associated with fewer labelling errors, but careful implementation and training is needed to maximise their safety benefits.

Phenotyping Alfalfa (Medicago sativa L.) Root Structure Architecture via Integrating Confident Machine Learning with ResNet-18.

Background: Root system architecture (RSA) is of growing interest in implementing plant improvements with belowground root traits. Modern computing technology applied to images offers new pathways forward to plant trait improvements and selection through RSA analysis (using images to discern/classify root types and traits). However, a major stumbling block to image-based RSA phenotyping is image label noise, which reduces the accuracies of models that take images as direct inputs. To address the label noise problem, this study utilized an artificial intelligence model capable of classifying the RSA of alfalfa (Medicago sativa L.) directly from images and coupled it with downstream label improvement methods. Images were compared with different model outputs with manual root classifications, and confident machine learning (CL) and reactive machine learning (RL) methods were tested to minimize the effects of subjective labeling to improve labeling and prediction accuracies. Results: The CL algorithm modestly improved the Random Forest model's overall prediction accuracy of the Minnesota dataset (1%) while larger gains in accuracy were observed with the ResNet-18 model results. The ResNet-18 cross-population prediction accuracy was improved (~8% to 13%) with CL compared to the original/preprocessed datasets. Training and testing data combinations with the highest accuracies (86%) resulted from the CL- and/or RL-corrected datasets for predicting taproot RSAs. Similarly, the highest accuracies achieved for the intermediate RSA class resulted from corrected data combinations. The highest overall accuracy (~75%) using the ResNet-18 model involved CL on a pooled dataset containing images from both sample locations. Conclusions: ResNet-18 DNN prediction accuracies of alfalfa RSA image labels are increased when CL and RL are employed. By increasing the dataset to reduce overfitting while concurrently finding and correcting image label errors, it is demonstrated here that accuracy increases by as much as ~11% to 13% can be achieved with semi-automated, computer-assisted preprocessing and data cleaning (CL/RL).

Better performance of deep learning pulmonary nodule detection using chest radiography with pixel level labels in reference to computed tomography: data quality matters

Labeling errors can significantly impact the performance of deep learning models used for screening chest radiographs. The deep learning model for detecting pulmonary nodules is particularly vulnerable to such errors, mainly because normal chest radiographs and those with nodules obscured by ribs appear similar. Thus, high-quality datasets referred to chest computed tomography (CT) are required to prevent the misclassification of nodular chest radiographs as normal. From this perspective, a deep learning strategy employing chest radiography data with pixel-level annotations referencing chest CT scans may improve nodule detection and localization compared to image-level labels. We trained models using a National Institute of Health chest radiograph-based labeling dataset and an AI-HUB CT-based labeling dataset, employing DenseNet architecture with squeeze-and-excitation blocks. We developed four models to assess whether CT versus chest radiography and pixel-level versus image-level labeling would improve the deep learning model’s performance to detect nodules. The models' performance was evaluated using two external validation datasets. The AI-HUB dataset with image-level labeling outperformed the NIH dataset (AUC 0.88 vs 0.71 and 0.78 vs.0.73 in two external datasets, respectively; both p < 0.001). However, the AI-HUB data annotated at the pixel level produced the best model (AUC 0.91 and 0.86 in external datasets), and in terms of nodule localization, it significantly outperformed models trained with image-level annotation data, with a Dice coefficient ranging from 0.36 to 0.58. Our findings underscore the importance of accurately labeled data in developing reliable deep learning algorithms for nodule detection in chest radiography.

Addressing label noise for electronic health records: insights from computer vision for tabular data

The analysis of extensive electronic health records (EHR) datasets often calls for automated solutions, with machine learning (ML) techniques, including deep learning (DL), taking a lead role. One common task involves categorizing EHR data into predefined groups. However, the vulnerability of EHRs to noise and errors stemming from data collection processes, as well as potential human labeling errors, poses a significant risk. This risk is particularly prominent during the training of DL models, where the possibility of overfitting to noisy labels can have serious repercussions in healthcare. Despite the well-documented existence of label noise in EHR data, few studies have tackled this challenge within the EHR domain. Our work addresses this gap by adapting computer vision (CV) algorithms to mitigate the impact of label noise in DL models trained on EHR data. Notably, it remains uncertain whether CV methods, when applied to the EHR domain, will prove effective, given the substantial divergence between the two domains. We present empirical evidence demonstrating that these methods, whether used individually or in combination, can substantially enhance model performance when applied to EHR data, especially in the presence of noisy/incorrect labels. We validate our methods and underscore their practical utility in real-world EHR data, specifically in the context of COVID-19 diagnosis. Our study highlights the effectiveness of CV methods in the EHR domain, making a valuable contribution to the advancement of healthcare analytics and research.

Situational diversity in video person re-identification: introducing MSA-BUPT dataset

Thanks to the success of deep learning over the past few years, the video person re-identification (ReID) algorithms have achieved high accuracy on multiple public benchmark datasets. However, the available video person ReID datasets cover a limited range of real-world scenarios, and they have several obvious limitations: limited camera viewing angles, tiny variations of the shooting scene, and even errors in manual labels. These disadvantages prevent video person ReID from being widely used in real-life scenarios. In this work, a new high-quality multi-situation video person ReID dataset, named MSA-BUPT, is built to promote the video person ReID task in large-scale urban surveillance. Specifically, MSA-BUPT contains 684 identities, 2,665 trajectories, and nearly 250,000 frames from 200-h videos across various complex scenarios. Person attribute annotations and unannotated video data are also provided for other research perspectives, such as cross-modality ReID, cross-domain ReID, and so on. Furthermore, two plug-and-play components are used to improve retrieval capabilities: a new scenario-based data augmentation method is proposed to alleviate the person misalignment problem; a re-ranking strategy based on person attribute is applied to make secondary adjustments to the content to the results of the model. The extensive experimental results show that the above methods improve the performance of some representative state-of-the-art models on the new dataset.

Enhancing the automatic facies classification of Brazilian presalt acoustic image logs with SwinV2-Unet: Leveraging transfer learning and confident learning

Facies classification of image logs plays a vital role in reservoir characterization, especially in the heterogeneous and anisotropic carbonate formations of the Brazilian presalt region. Although manual classification remains the industry standard for handling the complexity and diversity of image logs, it has the notable disadvantages of being time consuming, labor intensive, subjective, and nonrepeatable. Recent advancements in machine learning offer promising solutions for automation and acceleration. However, previous attempts to train deep neural networks for facies identification have struggled to generalize to new data due to insufficient labeled data and the inherent intricacy of image logs. In addition, human errors in manual labels further hinder the performance of trained models. To overcome these challenges, we develop adopting the state-of-the-art SwinV2-Unet to provide depthwise facies classification for Brazilian presalt acoustic image logs. The training process incorporates transfer learning to mitigate overfitting and confident learning to address label errors. Through a k-fold cross-validation experiment, with each fold spanning more than 350 m, we achieve an impressive macro F1 score of 0.90 for out-of-sample predictions. This significantly surpasses the previous model modified from the widely recognized U-Net, which provides a macro F1 score of 0.68. These findings highlight the effectiveness of the used enhancements, including the adoption of an improved neural network and an enhanced training strategy. Moreover, our SwinV2-Unet enables a highly efficient and accurate facies analysis of the complex yet informative image logs, significantly advancing our understanding of hydrocarbon reservoirs, saving human effort, and improving productivity.

228: Hit the right vertebra on CBCT: A robust safeguard against labeling errors in a “one-stop-shop”

228: Hit the right vertebra on CBCT: A robust safeguard against labeling errors in a “one-stop-shop”

Learning From Alarms: A Robust Learning Approach for Accurate Photoplethysmography-Based Atrial Fibrillation Detection Using Eight Million Samples Labeled With Imprecise Arrhythmia Alarms.

Atrial fibrillation (AF) is a common cardiac arrhythmia with serious health consequences if not detected and treated early. Detecting AF using wearable devices with photoplethysmography (PPG) sensors and deep neural networks has demonstrated some success using proprietary algorithms in commercial solutions. However, to improve continuous AF detection in ambulatory settings towards a population-wide screening use case, we face several challenges, one of which is the lack of large-scale labeled training data. To address this challenge, we propose to leverage AF alarms from bedside patient monitors to label concurrent PPG signals, resulting in the largest PPG-AF dataset so far (8.5 M 30-second records from 24,100 patients) and demonstrating a practical approach to build large labeled PPG datasets. Furthermore, we recognize that the AF labels thus obtained contain errors because of false AF alarms generated from imperfect built-in algorithms from bedside monitors. Dealing with label noise with unknown distribution characteristics in this case requires advanced algorithms. We, therefore, introduce and open-source a novel loss design, the cluster membership consistency (CMC) loss, to mitigate label errors. By comparing CMC with state-of-the-art methods selected from a noisy label competition, we demonstrate its superiority in handling label noise in PPG data, resilience to poor-quality signals, and computational efficiency.

Identifying systems factors contributing to adverse events in maternal care using incident reports

The maternal mortality rate in the US increased significantly from 20.1 deaths per 100,000 live births in 2019 to 32.9 in 2021. Black women have a higher rate of mortality and also experience higher rates of severe maternal morbidity, which are life-threating maternal health complications. However, maternal mortality and SMM are preventable with timely and responsive care, suggesting opportunities to intervene at the point of care. To examine processes contributing to adverse maternal outcomes and racial/ethnic disparities in these outcomes, we analyzed 550 incident report (IRs) collected in the maternity units of a large academic hospital in 2019 and 2020. IRs were disaggregated by race/ethnicity and the IR narratives were coded using the systems factors from the SEIPS 2.0 model. Tasks (40%) and organization (30%) were most frequently reported SEIPS 2.0 categories. The majority of these incidents were the result of omissions (15%), staffing (9%), teamwork and coordination (7%), specimen labeling errors (7%), and hospital protocols (6%). These findings from this analysis can improve system safety and support the development of targeted efforts to improve health equity for women and birthing of people of color.

TorchQL: A Programming Framework for Integrity Constraints in Machine Learning

Finding errors in machine learning applications requires a thorough exploration of their behavior over data. Existing approaches used by practitioners are often ad-hoc and lack the abstractions needed to scale this process. We present TorchQL, a programming framework to evaluate and improve the correctness of machine learning applications. TorchQL allows users to write queries to specify and check integrity constraints over machine learning models and datasets. It seamlessly integrates relational algebra with functional programming to allow for highly expressive queries using only eight intuitive operators. We evaluate TorchQL on diverse use-cases including finding critical temporal inconsistencies in objects detected across video frames in autonomous driving, finding data imputation errors in time-series medical records, finding data labeling errors in real-world images, and evaluating biases and constraining outputs of language models. Our experiments show that TorchQL enables up to 13x faster query executions than baselines like Pandas and MongoDB, and up to 40% shorter queries than native Python. We also conduct a user study and find that TorchQL is natural enough for developers familiar with Python to specify complex integrity constraints.

Enhancing ground classification models for TBM tunneling: Detecting label errors in datasets

Tunnel Boring Machine (TBM) construction, particularly with closed-face TBMs, faces uncertainties due to the inability of the operator to directly observe the ground ahead. These uncertainties can lead to time delays, cost overruns, and accidents. While supervised machine learning techniques have been used to predict geology from TBM sensor data, their performance drops significantly when applied to other projects, indicating poor generalization. To ensure accurate results and improved generalization to future data, supervised learning models require high-quality, well-labeled data which is not usually the case for TBM datasets. This paper addresses the issue of “noisy” labels in TBM datasets, which human operators and engineers often label with varying interpretations. A data-centric framework was adapted and applied to an Earth Pressure Balance Machines (EPBM) tunnel dataset to detect and identify these mislabeled datapoints. The framework's outputs were validated using two techniques and apply several methods to clean the dataset. The best-performing method was selected for the test set. The paper concludes by discussing the limitations of the proposed method, the challenges encountered, and future research directions in this area.

Mitigating Label Bias in Machine Learning: Fairness through Confident Learning

Discrimination can occur when the underlying unbiased labels are overwritten by an agent with potential bias, resulting in biased datasets that unfairly harm specific groups and cause classifiers to inherit these biases. In this paper, we demonstrate that despite only having access to the biased labels, it is possible to eliminate bias by filtering the fairest instances within the framework of confident learning. In the context of confident learning, low self-confidence usually indicates potential label errors; however, this is not always the case. Instances, particularly those from underrepresented groups, might exhibit low confidence scores for reasons other than labeling errors. To address this limitation, our approach employs truncation of the confidence score and extends the confidence interval of the probabilistic threshold. Additionally, we incorporate with co-teaching paradigm for providing a more robust and reliable selection of fair instances and effectively mitigating the adverse effects of biased labels. Through extensive experimentation and evaluation of various datasets, we demonstrate the efficacy of our approach in promoting fairness and reducing the impact of label bias in machine learning models.