TransConv-DDPM: Enhanced Diffusion Model for Generating Time-Series Data in Healthcare

2025-07-08

Annual International Computer Software and Applications Conference

AI Summary

This study addresses the challenge of training AI models on scarce physiological time-series data in healthcare by proposing a novel denoising diffusion probabilistic model (DDPM). The method uniquely integrates Transformers with multi-scale convolutions within a U-Net architecture to simultaneously capture local signal details and global temporal dependencies, thereby effectively modeling the progressive dynamics of physiological signals. Evaluated on datasets such as SmartFallMM and EEG, the approach significantly outperforms existing generative models including TimeGAN and Diffusion-TS. Downstream predictive models trained on the synthesized data achieve a 13.64% improvement in F1-score and a 14.93% increase in accuracy, demonstrating the high fidelity and practical utility of the generated physiological time series.

Technology Category

• Machine Learning: Deep Generative Models & Autoencoders
• Computer Vision: Diffusion Models for Vision
• Natural Language Processing: Generation

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

The lack of real-world data in clinical fields poses a major obstacle in training effective AI models for diagnostic and preventive tools in medicine. Generative AI has shown promise in increasing data volume and enhancing model training, particularly in computer vision and natural language processing (NLP) domains. However, generating physiological time-series data, a common type in medical AI applications, presents unique challenges due to its inherent complexity and variability. This paper introduces TransConv-DDPM, an enhanced generative AI method for biomechanical and physiological time-series data generation. The model employs a denoising diffusion probabilistic model (DDPM) with U-Net, multi-scale convolution modules, and a transformer layer to capture both global and local temporal dependencies. We evaluated TransConv-DDPM on three diverse datasets, generating both long and short-sequence time-series data. Quantitative comparisons against state-of-the-art methods, TimeGAN and Diffusion-TS, using four performance metrics, demonstrated promising results, particularly on the SmartFallMM and EEG datasets, where it effectively captured the more gradual temporal change patterns between data points. Additionally, a utility test on the SmartFallMM dataset revealed that adding synthetic fall data generated by TransConv-DDPM improved predictive model performance, showing a 13.64% improvement in F1-score and a 14.93% increase in overall accuracy compared to the baseline model trained solely on fall data from the SmartFallMM dataset. These findings highlight the potential of TransConv-DDPM to generate high-quality synthetic data for real-world applications.

Problem

• time-series data
• data scarcity
• healthcare
• generative AI
• physiological signals

Innovation

• TransConv-DDPM
• diffusion model
• time-series generation
• multi-scale convolution
• transformer