Search

Exploiting advanced and appropriate methods to construct high-quality features from different types of data becomes crucial in agricultural futures price forecasting. Thus, this study develops a comprehensive commodity price forecasting framework using text mining methods. First, the modal features of the price series are extracted using the proposed Integrated-EEMD-VMD-SE method, and dynamic topic sentiment features are constructed from Weibo texts using the proposed dynamic topic model joint sentiment analysis method. Second, combined with statistical variables, lag order selection and feature selection are performed on these comprehensive factors. Finally, 12 comparative prediction models are designed based on random forest (RF), long shortterm memory (LSTM), and multilayer perceptron (MLP), and empirical analysis is carried out on two cases of pork prices and soybean futures prices. The experimental results show that the proposed prediction framework has high prediction accuracy, and the mean absolute percentage error (MAPE) values are 1.00 and 0.92, respectively. The constructed time series modal features and dynamic topic sentiment features can significantly improve the performance of the prediction model. [ABSTRACT FROM AUTHOR]

To establish a model with a short modeling period and consistent with the pathogenesis of IBS, chronic stimulation and chemical stimulation were combined. In the present study, we aimed to establish a novel model of irritable bowel syndrome (IBS) and investigate its feasibility. Chronic unpredictable stimulation was used as a single factor model, and its addition with glacial acetic acid stimulation was used as a comprehensive factor model. The symptoms of the IBS model were analyzed from a collection of tests, including body weight, essential food consumption, sucrose consumption, fecal grain number, Bristol score, abdominal withdrawal reflex, open field tests, elevated cross-maze tests, intestinal transportation time, and H&E staining. The results showed that compared with the single-factor model and the control groups, the rats in the comprehensive model group exhibited less body weight, reduced food consumption, decreased sucrose consumption, increased fecal grain number, decreased Bristol score and pain threshold, and significantly reduced physical activity. The comprehensive factor group model conformed to the complex pathogenesis of IBS and thus had a significant effect on it, which could be used to establish an effective IBS model. Furthermore, the modeling effect was significantly evident in male rats compared with female ones. [ABSTRACT FROM AUTHOR]

Objective To analyze the comprehensive factors causing adverse reactions to apheresis platelet donation(ARAPD), so as to provide references for effective prevention of ARAPD. Methods The 272 cases of ARAPD from 2012 to 2019 in Lanzhou were statistically analyzed, and factors that induced ARAPD were studied. Statistical analysis were performed according to the gender, nationality, occupation, age, weight, donation units, and number of donations. Results As to the factors inducing ARAPD, anticoagulant reactions accounted for the first(32.4%, 88/272). Women and students were prone to develop ARAPD. Among all age groups, 18~25 years old were most likely to develop ARAPD(53.68%, 10 572/35 265). The incidence of ARAPD were significantly different by ages and weights(P