Frontiers in Big Data最新文献

{"title":"GICPIdb: an archival repository of multimodal data focusing on pathological images for gastrointestinal cancers.","authors":"Huang Chen, Ling Tong, Jinyang Liu, Kai Liu, Xintao Li, Shufang Shi, Shuxue Xi, Geng Tian, Meijun Zhang, Dingrong Zhong, Shijun Li, Jialiang Yang","doi":"10.3389/fdata.2026.1924721","DOIUrl":"10.3389/fdata.2026.1924721","url":null,"abstract":"<p><strong>Introduction: </strong>Deep learning (DL) shows great potential for predicting biomarkers from routine histopathological slides of gastrointestinal (GI) cancers. Yet most existing models are validated on limited patient cohorts, while pathological image annotation and molecular marker standardization demand substantial professional expertise. To address these gaps, we constructed the Gastrointestinal Cancer Pathological Image Archive (GICPIdb, gicpidb.shubuzuo.top), a dedicated database and web platform covering seven major GI cancer types.</p><p><strong>Methods: </strong>High-quality hematoxylin and eosin (H&E)-stained whole-slide images were collected from multiple sources and uniformly processed. Image annotations were performed by board-certified pathologists following standardized protocols. GICPIdb offers five interactive web modules for data uploading, quality control, feature extraction, online annotation and AI-based prediction. Its intuitive interface supports data browsing, retrieval, visualization and downloading.</p><p><strong>Results: </strong>The database houses 2,863 pathologist-annotated, uniformly processed, high-quality H&E stained images collected from 2,655 patients. Of these, 1,699 patients were sourced from The Cancer Genome Atlas (TCGA), 182 from the Clinical Proteomic Tumor Analysis Consortium (CPTAC), and 424 from China-Japan Friendship Hospital and 350 from Chifeng Municipal Hospital in Inner Mongolia, China. It also integrates data on over 50 key molecular markers (e.g., MSI, TMB) and prognostic labels related to survival, recurrence and metastasis.</p><p><strong>Discussion: </strong>GICPIdb aims to promote the development of DL-driven AI tools for cancer research and clinical translation. The multi-institutional data collection and standardized annotation pipeline are expected to enhance the generalizability and reproducibility of AI-based prediction models across diverse patient populations.</p>","PeriodicalId":52859,"journal":{"name":"Frontiers in Big Data","volume":"9 ","pages":"1924721"},"PeriodicalIF":3.8,"publicationDate":"2026-08-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13572243/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148972387","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Study of deep learning cues for cross linguistic part of speech tagging in English- Malayalam code-mixed data.","authors":"Parvathy Padmakumar, Shreya S Nair, A K Prajisha, S Thara","doi":"10.3389/fdata.2026.1888885","DOIUrl":"https://doi.org/10.3389/fdata.2026.1888885","url":null,"abstract":"<p><strong>Introduction: </strong>Part Of Speech (POS) tagging is a fundamental task in Natural Language Processing (NLP) that assigns grammatical labels to words in a sentence. Code mixed text, which entails switching between two or more languages within a single conversation or a sentence, presents challenges for POS tagging. This investigation entailed a comprehensive study of deep learning approaches for cross linguistic POS tagging, focused on English Malayalam code mixed data prevalent on social media platforms. The study was carried out on linguistically complex and varied English Malayalam code mixed text from social media platforms with informal spellings, language switching, transliteration, slang, and unclear grammatical boundaries, reflecting the characteristics of informal online communication. We provide the first structured analysis of micro macro divergence and rare class behavior in English Malayalam code mixed POS tagging.</p><p><strong>Methods: </strong>We evaluated 14 state of the art model configurations that span traditional sequence labeling approaches and multilingual transformer architectures. Models were compared using standard performance metrics prevalent in the domain of data science, supplemented by normalized confusion matrices, error prone tag identification and micro-macro F1 gap analysis.</p><p><strong>Results: </strong>Our results showed that CRF (No Lang) emerged as the most balanced model overall on macro F1 (all classes) of 0.8170, while (BiLSTM + CRF) achieved the highest macro F1 (seen classes) of 0.8831, precision of 0.9167, and recall of 0.875, though this reflects strong performance concentrated on frequent tag classes rather than balanced coverage across the full tag set. Notably, the pretrained multilingual transformers (mBERT, MuRIL), despite prior exposure to Malayalam during pretraining, were outperformed on several key metrics by CRF and BiLSTM models trained directly on the code mixed dataset.</p><p><strong>Discussion: </strong>This finding was contrary to our expectation that existing multilingual knowledge would translate into a clear advantage on this task and merits further investigation.</p>","PeriodicalId":52859,"journal":{"name":"Frontiers in Big Data","volume":"9 ","pages":"1888885"},"PeriodicalIF":3.8,"publicationDate":"2026-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13561951/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148957145","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"BRI DataLab: an AI-assisted research platform for Chinese infrastructure finance.","authors":"Sanoop Sajan Koshy","doi":"10.3389/fdata.2026.1863692","DOIUrl":"https://doi.org/10.3389/fdata.2026.1863692","url":null,"abstract":"<p><p>BRI DataLab is an open-source web platform that integrates a harmonized infrastructure financing dataset, a curated policy and academic document corpus, and a retrieval-augmented generation (RAG) interface into a single queryable research environment for Chinese overseas development finance. Analysts working on the Belt and Road Initiative (BRI) must move between datasets, government documents, and academic literature without an integrated interface for querying across all three at once. This paper documents BRI DataLab, a research platform that combines a harmonized project-level dataset derived from AidData's China's Global Loans and Grants Dataset v1.0 with a curated corpus of 42 policy documents, institutional reports, and academic sources, accessed through an AI-assisted retrieval and synthesis layer built on RAG. Three methodological contributions are described: the decisions involved in converting more than 33,000 tranche-level financing records into 4,861 infrastructure projects; the four-category selection framework governing the document collection; and the system design of the AI interface, including the epistemic constraints built into its system prompt. The central argument is that AI-assisted research interfaces are methodologically defensible when they are transparent about what they can and cannot establish.</p>","PeriodicalId":52859,"journal":{"name":"Frontiers in Big Data","volume":"9 ","pages":"1863692"},"PeriodicalIF":3.8,"publicationDate":"2026-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13557982/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148931813","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A novel three-parameter Gompertz-Lomax Distribution with a physics-informed survival network: statistical theory, hazard shape characterization, and real-world applications.","authors":"Furqan Ahmed P, Sujatha V","doi":"10.3389/fdata.2026.1897881","DOIUrl":"10.3389/fdata.2026.1897881","url":null,"abstract":"<p><p>This article introduces the Gompertz-Lomax Distribution (GLD), a novel three-parameter continuous lifetime model whose composite hazard rate additively combines an increasing Gompertz component with a decreasing Lomax component. The resulting closed-form survival function nests the Gompertz and Lomax distributions as exact special cases and accommodates increasing, decreasing, and bathtub-shaped hazard profiles within a single parametric framework. Complete closed-form expressions are derived for the raw and central moments, incomplete moments, quantile function, mean residual life, stress-strength reliability, stochastic ordering, Rényi entropy, and Bonferroni-Lorenz inequality curves. Four estimation procedures, namely maximum likelihood, method of moments, least squares, and weighted least squares, are developed and validated through a Monte Carlo simulation study comprising <i>N</i> = 10, 000 replications, with finite-sample performance compared across all four estimators. As the primary machine-learning contribution, a Physics-Informed Survival Network (PISN) is introduced: a deep neural network that maps subject-level covariates to individual GLD shape and scale parameters while encoding the theoretically derived hazard shape condition as a smooth, differentiable penalty in the training loss. Empirical evaluation on three benchmark datasets, namely, leukemia patient survival, COVID-19 hospital survival, and electronic component failure times, demonstrates that the GLD achieves among the lowest Kolmogorov-Smirnov statistics and the most favorable Akaike Information Criterion (AIC), corrected AIC (AICC), and Bayesian Information Criterion (BIC) on all three datasets, with ΔAIC exceeding five units over the nearest competitor on the leukemia dataset and ΔAIC = 30.6 on the electronic component dataset, which exhibits a bathtub-shaped hazard rate.</p>","PeriodicalId":52859,"journal":{"name":"Frontiers in Big Data","volume":"9 ","pages":"1897881"},"PeriodicalIF":3.8,"publicationDate":"2026-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13557953/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148931801","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A cognitively inspired feature-level fusion framework for interpretable retail sales forecasting using integration of extreme gradient boost machine, artificial neural network and attention mechanism model.","authors":"Munienge Mbodila, Omobayo Ayokunle Esan","doi":"10.3389/fdata.2026.1889044","DOIUrl":"10.3389/fdata.2026.1889044","url":null,"abstract":"<p><strong>Introduction: </strong>Accurate retail sales forecasting in modern data-intensive environments requires models that not only achieve high predictive accuracy but also scale efficiently as data volume and feature complexity increase. This study proposes a novel cognitively inspired hybrid framework, XGB-ANN-Attn, for interpretable and scalable retail analytics.</p><p><strong>Methods: </strong>The model introduces feature-level fusion by integrating XGBoost-derived leaf embeddings with deep neural representations, enabling joint modeling of low-order statistical dependencies and high-order nonlinear feature interactions. A lightweight attention mechanism dynamically assigns instance-specific feature importance, enhancing both predictive performance and interpretability while maintaining linear computational complexity with respect to feature dimensionality. Unlike conventional ensemble approaches that operate at the decision level, the proposed framework integrates representations at the level of representations, reducing redundancy and improving computational efficiency. The model is designed for scalability, combining the log-linear complexity of gradient boosting with the linear scaling properties of neural networks and attention mechanisms.</p><p><strong>Results: </strong>Experimental evaluation on the BigMart and Walmart datasets demonstrates superior performance compared to state-of-the-art models, achieving RMSE = 0.1584 and <i>R</i> ² = 0.9946 on BigMart, and RMSE = 0.8652 and <i>R</i> ² = 0.9568 on Walmart. Furthermore, the framework supports parallelization and distributed deployment, making it suitable for large-scale retail systems.</p><p><strong>Discussion: </strong>The alignment between attention weights and SHAP explanations provides transparent and actionable insights. The results confirm that the proposed approach offers a scalable, interpretable, and high-performance solution for AI-driven decision support systems in big-data retail environments.</p>","PeriodicalId":52859,"journal":{"name":"Frontiers in Big Data","volume":"9 ","pages":"1889044"},"PeriodicalIF":3.8,"publicationDate":"2026-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13538013/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148888845","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Interviewer effects on underreporting of traditional contraceptive use: evidence from National Family Health Survey-5.","authors":"Rupalee Singh Chauhan, Laxmi Kant Dwivedi, Priyanka Dixit, Shiva S Halli","doi":"10.3389/fdata.2026.1812391","DOIUrl":"10.3389/fdata.2026.1812391","url":null,"abstract":"<p><strong>Background: </strong>Socioeconomic alignment between interviewers and respondents may play a critical role in shaping the accuracy of reported reproductive histories. This study investigates how interviewer characteristics contribute to the reporting of adoption of traditional contraceptive methods using reproductive event calendar data from the fifth round of the National Family Health Survey (2019-21) in India.</p><p><strong>Data and methods: </strong>Using contraceptive calendar data, a cross-classified multilevel model was employed to assess the interviewer's influence on the reporting of traditional contraceptive method use. The analysis included women aged 15-49 years who reported contraceptive use in the calendar month(s), and the interviewers interviewed them.</p><p><strong>Results: </strong>Multilevel cross-classified models show that interviewer characteristics significantly influence reporting of traditional contraceptive use following periods of non-use, childbirth, or pregnancy termination. Women interviewed by older interviewers (≥30 years; adjusted odds ratio (AOR) = 1.40, <i>p</i> < 0.01) and those who shared the same religion (AOR = 1.21, <i>p</i> ≤ 0.01) and marital status (AOR = 1.42, <i>p</i> < 0.01) as the interviewer were more likely to report traditional contraceptive method use. While women of the same age group (AOR = 0.89, <i>p</i> < 0.05), same-state residence (AOR = 0.82, <i>p</i> < 0.01), and same caste (AOR = 0.94, <i>p</i> < 0.01) as the interviewer were less likely to report traditional contraceptive method use. Older interviewers (AOR = 0.86, <i>p</i> < 0.01), those with secondary education (AOR = 0.54, <i>p</i> < 0.01), those belonging to the Muslim religion (AOR = 0.43, <i>p</i> < 0.01), and those with a lack of prior experience in conducting surveys (AOR = 0.90, <i>p</i> < 0.10) were associated with lower reporting. Moderate (AOR = 1.35, <i>p</i> < 0.01) and high (AOR = 1.22, <i>p</i> < 0.05) levels of prior experience with the same survey schedule in conducting the survey significantly improved reporting. Distribution of variance across different levels indicates substantial variation at the interviewer level (28.50%), followed by the district (18.50%) and PSU (13.46%) levels, suggesting that interviewer effects play a significant role in shaping the outcome.</p><p><strong>Discussion and conclusion: </strong>Interviewer characteristics such as education, age, and prior survey experience influence the reporting of traditional contraceptive use. Similarities or differences between interviewers and respondents in characteristics such as age, marital status, religion, caste, and state of residence also affect the accuracy and completeness of reporting traditional contraceptive use in contraceptive calendar data.</p>","PeriodicalId":52859,"journal":{"name":"Frontiers in Big Data","volume":"9 ","pages":"1812391"},"PeriodicalIF":3.8,"publicationDate":"2026-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13538000/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148889048","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A novel two-parameter discrete exponentiated exponential distribution with its neutrosophic extension: mathematical characterization and real-world count data modeling.","authors":"Furqan Ahmed P, Sujatha V","doi":"10.3389/fdata.2026.1927115","DOIUrl":"10.3389/fdata.2026.1927115","url":null,"abstract":"<p><p>This paper proposes and studies the Discrete Exponentiated Exponential (DEE) distribution, a new two-parameter discrete lifetime model obtained by applying the survival discretization technique to the exponentiated exponential distribution. The DEE distribution possesses a key structural advantage: the single shape parameter α simultaneously controls both the hazard rate shape (increasing for 0 < α < 1, decreasing for α > 1) and the dispersion regime (over-dispersion for small α, under-dispersion for large α), a dual flexibility that most competing discrete models cannot replicate without structural modification. These properties are rigorously established in closed form via the Glaser technique and numerical investigation of the dispersion index. Closed-form expressions are derived for the probability mass function, cumulative distribution function, survival and hazard rate functions, moment generating and characteristic functions, raw and central moments up to the fourth order, and the mean residual life function. Parameter estimation is carried out via maximum likelihood, and a comprehensive Monte Carlo simulation study assesses the finite-sample performance of the estimators and benchmarks it against four competing discrete models under identical settings. The practical advantage of the DEE distribution is demonstrated through three real-world count datasets from oncology, education, and nephrology; the DEE model exhibits competitive and frequently superior performance relative to seven benchmark discrete distributions. Finally, a neutrosophic generalization (DNEE) extends the framework to count data characterized by vagueness, incompleteness, or indeterminacy, with accompanying estimation and illustrative numerical analysis.</p>","PeriodicalId":52859,"journal":{"name":"Frontiers in Big Data","volume":"9 ","pages":"1927115"},"PeriodicalIF":3.8,"publicationDate":"2026-08-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13529497/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148876512","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Benchmarking retrieval augmented generation LLMs for Arabic noise robustness.","authors":"Saleh Almohaimeed, Abdulrahman Alabduljabbar, Mousa Jari, Mohammed Alkhowaiter, Saad Almohaimeed, Mohamad Mahmoud Al Rahhal","doi":"10.3389/fdata.2026.1884673","DOIUrl":"https://doi.org/10.3389/fdata.2026.1884673","url":null,"abstract":"<p><p>Hallucination has become a serious concern in large language models (LLMs), as these models can generate useful yet incorrect or misleading information, which has led to growing research interest in retrieval-augmented generation (RAG) as a mitigation approach. RAG provides LLMs with access to external information, such as databases or documents, which can help them to answer users' questions. Currently, several benchmarks released measure RAG performance on various LLMs; however, evaluations of the noise robustness ability in Arabic are absent. In this paper, we systematically investigated the capabilities of state-of-the-art multilingual LLMs with regard to two essential RAG abilities, noise robustness and negative rejection. To accomplish this, we generated an Arabic benchmark consisting of 300 questions along with 6,196 documents. Then, we assessed the performance of six LLMs in relation to the two aforementioned RAG abilities. The results reveal that all six LLMs were negatively affected when the noise ratio in the external documents was increased. Under the highest noise settings at 80%, the best LLM performance was for Claude-4 sonnet, in which their performance decreased by only 4.67 percentage points. Furthermore, when it comes to the negative rejection task, there has been a significant impact on all six models. The best two models, Claude-4 sonnet and Llama-4, scored 90.67% and 85.67%, respectively, while smaller models, like GPT-3.5, scored 69.33%. Furthermore, our manual analysis reveals that many errors made by LLMs are attributed to over-caution behavior. LLMs often decline to respond probably due to training mechanisms designed to reduce hallucinations. Additionally, other errors occur when there is a high lexical similarity between the question and the words of noisy documents, which causes the model to rely on irrelevant content instead of the correct information.</p>","PeriodicalId":52859,"journal":{"name":"Frontiers in Big Data","volume":"9 ","pages":"1884673"},"PeriodicalIF":3.8,"publicationDate":"2026-08-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13526670/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148867698","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Real-time AI-driven trend analytics for smart city digital services using streaming data.","authors":"Zhuldyz Kalpeyeva, Abdul Razaque, Raissa Uskenbayeva, Aliya Beishenaly, Venera Elle, Aizhan Kassymova","doi":"10.3389/fdata.2026.1811835","DOIUrl":"10.3389/fdata.2026.1811835","url":null,"abstract":"<p><p>Real-time data analysis plays an important role in the operation of digital urban systems, where the behavior of residents and the load on services can change over short periods of time. At the same time, traditional analytical approaches based on batch data processing often do not allow timely detection of such changes, which leads to delayed and not always accurate management decisions. This paper introduces an artificial intelligence-driven smart city system (AISSC) for real-time data trend analysis. The proposed AISSC framework processes streaming data in a smart city digital environment. The proposed approach encompasses real-time feature generation and statistical techniques for identifying significant changes. The proposed AISSC solution is executed on the Python platform. The results demonstrate that the proposed AISSC solution achieves a directional accuracy of 98.6% for trend prediction, together with strong numerical forecasting performance with a MAPE of 6.3% and a WMAPE of 7.8%. The framework detects statistically significant deviations within 2.4 s at the sliding-window level while maintaining an end-to-end system update cycle of approximately 5 min. These results demonstrate the capability of the proposed framework to support reliable real-time trend analysis and short-term forecasting for smart city decision-making. This shows that the framework can reliably identify trends and accurately estimate demand for real-time smart city decision-making. The results demonstrate consistent performance improvements compared to representative baseline methods under identical streaming and computational constraints. The proposed AISSC facilitates real-time observation of urban dynamics and enhances short-term forecasting accuracy for informed decision-making in smart city management systems.</p>","PeriodicalId":52859,"journal":{"name":"Frontiers in Big Data","volume":"9 ","pages":"1811835"},"PeriodicalIF":3.8,"publicationDate":"2026-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13521872/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148851952","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"DKFraudNet: a knowledge-guided adversarial learning framework for fraud user detection.","authors":"Yingjun Shen, Renda Shi, Kaixi Song, Yunpeng Li","doi":"10.3389/fdata.2026.1887075","DOIUrl":"10.3389/fdata.2026.1887075","url":null,"abstract":"<p><strong>Introduction: </strong>Fraud user identification in telecommunications is hindered by scarce, noisy, and imbalanced labels, while expert rules may provide ambiguous or contradictory evidence.</p><p><strong>Methods: </strong>We propose DKFraudNet, a knowledge-guided framework that integrates domain knowledge regularization, an attention-adaptive conditional generative adversarial network, and virtual category learning. Expert rules are organized into a Deterministic-Ambiguous-Contradictory evidence taxonomy for controlled pseudo-labeling. Class-conditioned augmentation alleviates data imbalance, and kernel-based similarity refines ambiguous samples. The framework was evaluated using two real-world city-level telecommunications datasets containing 59,015 and 52,183 users, respectively.</p><p><strong>Results: </strong>DKFraudNet consistently improved downstream classification performance under weak supervision. On the independent City 2 validation set, the CatBoost instantiation achieved an accuracy of 0.911 and an F1-score of 0.909. For operational review prioritization, DKFraudNet-XGBoost required reviewing 40.2% of unverified users to capture 80% of fraud users, corresponding to a 49.71% workload reduction relative to random review, with an AUPRC of 0.954. In operator-side blind verification, genuine-member identification and false-member screening achieved accuracies of 98.9% and 93.3%, respectively.</p><p><strong>Discussion: </strong>The results show that combining structured domain evidence, adaptive generative augmentation, and uncertainty-aware refinement improves robustness, data efficiency, and operational usefulness for fraud detection under weak supervision.</p>","PeriodicalId":52859,"journal":{"name":"Frontiers in Big Data","volume":"9 ","pages":"1887075"},"PeriodicalIF":3.8,"publicationDate":"2026-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13506494/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148834573","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}