Search

To explore the application of a traditional machine learning model in the intelligent management of pigs, in this paper, the influence of PCA pre-treatment on pig face identification with RF is studied. By this testing method, the parameters of two testing schemes, one adopting RF alone and the other adopting RF + PCA, were determined to be 65 and 70, respectively. With individual identification tests carried out on 10 pigs, accuracy, recall, and f1-score were increased by 2.66, 2.76, and 2.81 percentage points, respectively. Except for the slight increase in training time, the test time was reduced to 75% of the old scheme, and the efficiency of the optimized scheme was greatly improved. It indicates that PCA pre-treatment positively improved the efficiency of individual pig identification with RF. Furthermore, it provides experimental support for the mobile terminals and the embedded application of RF classifiers.

BackgroundPrevious observational studies have shown conflicting results of vitamins supplementation for thyroid diseases. The causal relationships between vitamins and thyroid diseases are unclear. Therefore, we conducted a two-sample bidirectional Mendelian randomization (MR) study to explore association of circulating vitamin levels with thyroid diseases.MethodsWe performed a bidirectional MR analysis using genome-wide association study (GWAS) data. Genetic tool variables for circulating vitamin levels include vitamins A, B9, B12, C, D, and E, Genetic tool variables of thyroid diseases include autoimmune hyperthyroidism, autoimmune hypothyroidism, thyroid nodules (TNs), and Thyroid cancer (TC). Inverse-variance weighted multiplicative random effects (IVW-RE) was mainly used for MR Analysis, weighted median (WM) and MR Egger were used as supplementary methods to evaluate the relationships between circulating vitamin levels and thyroid diseases. Sensitivity and pluripotency were evaluated by Cochran’s Q test, MR-PRESSO, Radial MR, MR-Egger regression and leave-one-out analysis.ResultsPositive MR evidence suggested that circulating vitamin C level is a protective factor in autoimmune hypothyroidism (ORIVW-RE=0.69, 95%CI: 0.58-0.83, p = 1.05E-04). Reverse MR Evidence showed that genetic susceptibility to autoimmune hyperthyroidism is associated with reduced level of circulating vitamin A(ORIVW-RE = 0.97, 95% CI: 0.95–1.00, p = 4.38E-02), genetic susceptibility of TNs was associated with an increased level of circulating vitamin D (ORIVW-RE = 1.02, 95% CI: 1.00–1.03, p = 6.86E-03). No causal and reverse causal relationship was detected between other circulating vitamin levels and thyroid diseases.ConclusionOur findings provide genetic evidence supporting a bi-directional causal relationship between circulating vitamin levels and thyroid diseases. These findings provide information for the clinical application of vitamins prevention and treatment of thyroid diseases.

ObjectiveResearch data suggests that ultrasound-assisted wound debridement (UAWD) can effectively promote the healing of diabetic foot ulcers (DFU). However, existing research is not consistent with this viewpoint. Therefore, we conducted this study to investigate the effect of UAWD on the healing of diabetic foot ulcers.MethodsFrom the establishment of the database to January 2024, we searched 8 databases to study the effectiveness and safety of UAWD in the treatment of DFU. Two authors independently screened the qualifications of the articles, while two authors extracted relevant data. Statistical analysis was conducted using Review Manager 5.4 and STATA 18.0 software.ResultsA total of 11 randomized controlled studies were included, with 6 countries and 696 participants participating. Our findings showed that UAWD was associated with a significant benefit in healing rate (OR = 2.60, 95% CI: [1.67, 4.03], P < 0.0001, I2 = 25%), wound healing time (MD = -11.94, 95% CI: [-23.65, -0.23], P = 0.05, I2 = 99%), percentage reduction in wound size (MD = 14.2, 95% CI: [10.8, 17.6], P = 0.47, I2 = 32%), effectiveness of treatment (OR = 10.3, 95% CI: [4.68, 22.66], P < 0.00001, I2 = 0%). Moreover, UAWD did not cause any significant adverse reactions. However, there was no obvious difference in wound blood perfusion (MD = 0.25, 95% CI: [-0.01, 0.52], P = 0.06, I2 = 90%), transcutaneous oxygen partial pressure (MD = 14.34, 95% CI: [-10.03, 38.71], P = 0.25, I2 = 98%).ConclusionUAWD can significantly improve wound healing rate, shorten wound healing time, accelerate wound area reduction, and improve clinical treatment effectiveness without significant adverse reactions. Although there is no significant difference in transcutaneous oxygen pressure and wound blood flow perfusion between UAWD and SWC. So we look forward to more scientifically blinded, placebo-controlled, high-quality studies in the future, to enable researchers to obtain more complete and accurate analytical data, in order to improve the scientific and credibility of the evidence.Systematic review registrationhttps://www.crd.york.ac.uk/prospero/, identifier CRD42024501198.

With the rise of live streaming commerce, the relationship between consumers and content creators on the short-video platforms has become closer, forming a peculiar culture and language in each consumer community, which promotes the short-video platforms to become a natural breeding ground for forming consumer communities. While such communities give birth to its own language and culture from the interaction between content creators and consumers, this kind of co-creation can not only enhance the consumers’ trust to improve commodity premium space, but also strengthen the ties within the community and spread the information outside the communities, and consequently, expand community scale. Based on the view of the value co-creation from the language and culture among content creators and consumers in the communities, this study starts from the point of product type, employs consumers’ Willingness to pay premium (WoPP) as a proxy variable of brand advocacy in the co-creation of cultural and language values in consumer communities, and conducts three single-factor experiments between two groups. By analyzing the experimental results, this study identified the influence under the potential relationship mechanism, social comparison, and found another variable that can moderate the relationship, consumer trust, portrays the relationship between the product types of the live streaming commerce and the consumers’ WoPP, and explores the mediating effect of social comparison and the moderate effect of consumer trust effect. This paper also analyzes and discusses the WoPP caused by the co-creation of cultural and language values co-created by creators and consumer communities.

Accurately and continuously monitoring the hot metal temperature status of the blast furnace (BF) is a challenging job. To solve this problem, we propose a hot metal temperature prediction model based on the AdaBoost integrated algorithm using the real production data of the BF. We cleaned the raw data using the data analysis technology combined with metallurgical process theory, which mainly included data integration, outliers elimination, and missing value supplement. The redundant features were removed based on Pearson’s thermodynamic diagram analysis, and the input parameters of the model were preliminarily determined by using recursive feature elimination method. We built the hot metal temperature prediction model using the AdaBoost ensemble algorithm on a dataset with selected features as well as derived features by using K-mean clustering tags. The results show that the performance of the hot metal temperature prediction model with K-means clustering tags has been further improved, and the accurate monitoring and forecast of molten iron temperature has been achieved. The model can achieve an accuracy of more than 90% with an error of ±5°C.