Wheat grains are susceptible to contamination with various natural mycotoxins including regulated and emerging mycotoxins. This study surveyed the natural presence of regulated mycotoxins, such as deoxynivalenol (DON) and zearalenone (ZEN), and emerging mycotoxins such as beauvericin (BEA), enniatins (ENNs such as ENA, ENA1, ENB, ENB1) and Alternaria mycotoxins (i.e., alternariol monomethyl ether (AME), alternariol (AOH), tenuazonic acid (TeA), tentoxin (TEN), and altenuene (ALT)) in wheat grains randomly collected from eight provinces across China in 2021. The results revealed that each wheat grain sample was detected with at least one type of mycotoxin. The detection rates of these mycotoxins ranged from 7.1% to 100%, with the average occurrence level ranging from 1.11 to 921.8 µg/kg. DON and TeA were the predominant mycotoxins with respect to both prevalence and concentration. Approximately 99.7% of samples were found to contain more than one toxin, and the co-occurrence of ten toxins (DON + ZEN + ENA + ENA1 + ENB + ENB1 + AME + AOH + TeA + TEN) was the most frequently detected combination. The dietary exposure to different mycotoxins among Chinese consumers aged 4–70 years was as follows: 0.592–0.992 µg/kg b.w./day for DON, 0.007–0.012 µg/kg b.w./day for ZEN, 0.0003–0.007 µg/kg b.w./day for BEA and ENNs, 0.223–0.373 µg/kg b.w./day for TeA, and 0.025–0.041 µg/kg b.w./day for TEN, which were lower than the health-based guidance values for each mycotoxin, with the corresponding hazard quotient (HQ) being far lower than 1, implying a tolerable health risk for Chinese consumers. However, the estimated dietary exposure to AME and AOH was in the range of 0.003–0.007 µg/kg b.w./day, exceeding the Threshold of Toxicological Concern (TTC) value of 0.0025 µg/kg b.w./day, demonstrating potential dietary risks for Chinese consumers. Therefore, developing practical control and management strategies is essential for controlling mycotoxins contamination in the agricultural systems, thereby ensuring public health.

Human trajectory prediction is an essential task for various applications such as travel recommendation, location-sensitive advertisement, and traffic planning. Most existing approaches are sequential-model based and produce a prediction by mining behavior patterns. However, the effectiveness of pattern-based methods is not as good as expected in real-life conditions, such as data sparse or data missing. Moreover, due to the technical limitations of sensors or the traffic situation at the given time, people going to the same place may produce different trajectories. Even for people traveling along the same route, the observed transit records are not exactly the same. Therefore trajectories are always diverse, and extracting user intention from trajectories is difficult. In this paper, we propose an augmented-intention recurrent neural network (AI-RNN) model to predict locations in diverse trajectories. We first propose three strategies to generate graph structures to demonstrate travel context and then leverage graph convolutional networks to augment user travel intentions under graph view. Finally, we use gated recurrent units with augmented node vectors to predict human trajectories. We experiment with two representative real-life datasets and evaluate the performance of the proposed model by comparing its results with those of other state-of-the-art models. The results demonstrate that the AI-RNN model outperforms other methods in terms of top-k accuracy, especially in scenarios with low similarity.