A Multi-Step Prediction Method Based on Small Sample Data Augmentation to Assess Wheat Flour Safety Risk

Food safety significantly impacts the human health, establishing an effective prediction method to assess food safety risk is crucial for food safety control. At present, in the situation of insufficient detection data, it is necessary to employ data augmentation methods to generate large-scale detection data and accurately capture the long-term variation patterns through safety risk prediction models. However, existing data augmentation methods and safety prediction models face challenges such as gradient vanishing and difficulty in capturing long-term dependencies. Therefore, this paper proposes a Small sample Data Augmentation Multi-step Prediction Method (SDAMPM) to assess wheat flour safety risks. Firstly, we improved time-series generative adversarial networks based on external temporal convolution and Wasserstein distance to expand wheat flour hazard factor detection data. Secondly, we employed expanded data to establish dietary exposure evaluation system for wheat flour, serving as the desired output for multi-step prediction models. Finally, we constructed a stable Informer (Stainformer) multi-step prediction model by designing symmetric ProbSparse self-attention and distilling layer based on dilated causal convolution. Experiments on the wheat flour dietary exposure evaluation system demonstrate that compared to other methods, the expanded data is similar to the distribution of the original data. This approach effectively predicts long-term safety risks associated with wheat flour consumption and can provide assistance and technical support in decision-making for relevant departments, thereby reducing the occurrence of food safety incidents.