EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Generative AI Data Augmentation and Missing Value Completion Method for Multi-Source Heterogeneous Big Data

Linfeng Yang

Modern Management Science & Engineering · 03.07.2026 · 8 (3) · p66

DOI: 10.22158/mmse.v8n3p66 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Modern Management Science & Engineering, online erschienen am 03.07.2026. Verfasst von Linfeng Yang. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The proliferation of multi-source heterogeneous big data across healthcare, industrial Internet of Things (IIoT), and smart city domains has introduced two pervasive bottlenecks in data analytics: widespread missing values and insufficient high-quality training samples. Traditional missing value imputation methods fail to capture complex nonlinear correlations across heterogeneous data modalities, while existing data augmentation techniques are mostly designed for single-modal data and neglect intrinsic cross-source associations. To address these gaps, this paper proposes Hetero-GenAI, a unified generative artificial intelligence framework for joint missing value completion and data augmentation in multi-source heterogeneous big data. First, a heterogeneous data embedding module with cross-modal attention maps numerical, categorical, temporal, and textual features into a shared latent space, explicitly modeling inter-source and intra-source feature dependencies. Second, a missing-aware conditional diffusion model performs adaptive imputation by integrating missing masks as soft constraints, eliminating the need for pre-assumptions about missing mechanisms (MCAR, MAR, MNAR). Third, a distribution-aligned augmentation strategy generates diverse, realistic samples via latent space interpolation and semantic perturbation while preserving cross-modal semantic coherence and distribution consistency. Extensive experiments on two real-world datasets—the MIMIC-IV clinical dataset and NASA C-MAPSS industrial sensor dataset—demonstrate that the proposed method reduces numerical imputation RMSE by 12.3%–21.7% and improves categorical imputation F1-score by 8.5%–15.2% under 30% missing rates compared to state-of-the-art baselines. Furthermore, the augmentation pipeline improves downstream classification and prediction task performance by 9.2%–14.6%, verifying its dual effectiveness in data completion and quality enhancement.

Zitieren

APA

Yang, L. (2026). Generative AI Data Augmentation and Missing Value Completion Method for Multi-Source Heterogeneous Big Data. Modern Management Science & Engineering, 8(3), p66. https://doi.org/10.22158/mmse.v8n3p66

Vancouver

Yang L. Generative AI Data Augmentation and Missing Value Completion Method for Multi-Source Heterogeneous Big Data. Modern Management Science & Engineering. 2026;8(3):p66. doi:10.22158/mmse.v8n3p66

BibTeX
@article{Yang2026,
  author = {Yang, Linfeng},
  title = {Generative AI Data Augmentation and Missing Value Completion Method for Multi-Source Heterogeneous Big Data},
  journal = {Modern Management Science & Engineering},
  year = {2026},
  volume = {8},
  number = {3},
  pages = {p66},
  doi = {10.22158/mmse.v8n3p66}
}
Kostenlos starten →