Enhancing Basketball Game Outcome Prediction through Fused Graph Convolutional Networks and Random Forest Algorithm.

Basketball is a popular sport worldwide, and many researchers have utilized various machine learning models to predict the outcome of basketball games. However, prior research has primarily focused on traditional machine learning models. Furthermore, models that rely on vector inputs tend to ignore the intricate interactions between teams and the spatial structure of the league. Therefore, this study aimed to apply graph neural networks to basketball game outcome prediction, by transforming structured data into unstructured graphs, to represent the interactions between teams in the 2012-2018 NBA season dataset. Initially, the study used a homogeneous network and undirected graph to build a team representation graph. The constructed graph was fed into a graph convolutional network, which yielded an average success rate of 66.90% in predicting the outcome of games. To improve the prediction success rate, feature extraction based on the random forest algorithm was combined with the model. The fused model yielded the best results, and the prediction accuracy was improved to 71.54%. Additionally, the study compared the results of the developed model with previous studies and the baseline model. Our proposed method considers the spatial structure of teams and the interaction between teams, resulting in superior performance in basketball game outcome prediction. The results of this study provide valuable insights for basketball performance prediction research.

Excretory expression of IsPETase in E. coli by an enhancer of signal peptides and enhanced PET hydrolysis.

The PET hydrolase from Ideonella sakaiensis (IsPETase) is efficient for PET degradation, which provides a promising solution for environmental contamination by plastics. This study focuses on improving the excretion of IsPETase from E. coli by signal peptide (SP) engineering. A SP enhancer B1 (MERACVAV) was fused to the N-terminal of commonly-used SP (PelB, MalE, LamB, and OmpA) to mediate excretion of IsPETase. Strikingly, the modified SP B1OmpA, B1PelB, and B1MalE significantly increased the excretion of IsPETase, while IsPETase was basically expressed in periplasmic space without enhancer B1. The excretion efficiency of IsPETase mediated by B1PelB was improved by 62 folds compared to that of PelB. The hydrolysis of PET by crude IsPETase in culture solution was also enhanced. Furthermore, the amount of released MHET/TPA from PET by IsPETase was increased by 2.7 folds with pre-incubation of hydrophobin HFBII. Taken together, this work may provide a feasible strategy for the excretion and application of the IsPETase.

Meta-Analysis on Intervention Effects of Physical Activities on Children and Adolescents with Autism.

This paper aimed to discuss the intervention effects of physical activities on children and adolescents with autism with a meta-analysis so as to serve as a reference to further relevant research on the same topic. As for research methods, by searching in CNKI (China National Knowledge Infrastructure), WanFang data, VIP Database for Chinese Technical Periodicals, PubMed, Scopus, Web of Science, and other databases, this study collected randomized controlled trials (RCTs) on the intervention of physical activities on children and adolescents with autism and used Review Manager 5.3 software to process and analyze the outcome indicators of the literature. As for the result, a total of 12 papers and 492 research targets were selected. The results of the meta-analysis show that physical activity had a significant positive impact on social interaction ability, communication ability, motor skills, and autism degree of autistic children as well as the social skills and communication skills of autistic adolescents. On the other hand, physical activity had no significant effect on the stereotyped behavior of autistic children and adolescents. In conclusion, physical activity intervention is beneficial to children and adolescents with autism, and continuous physical activity intervention can produce greater intervention effect.

Magnetic separation of phosphate contaminants from starch wastewater using magnetic seeding.

Traditional chemical precipitation of phosphates from wastewater is somewhat inefficient because it produces some ultrafine hydroxyapatite particles that are difficult to settle. In this study, magnetic seeds with a core-shell structure were prepared by sulfation roasting for magnetic flocculation of those fine particles. Zeta potential measurements show that the hydroxyapatite particles are positively charged at pH 10, whereas the magnetic seeds are negatively charged. The Derjaguin-Landau-Verwey-Overbeek calculation indicates that the van der Waals force between the magnetic seeds and hydroxyapatite particles is always attractive. Moreover, the electrostatic attraction also contributes to aggregation of the magnetic seeds and hydroxyapatite particles. Orthogonal experiments show that the main factor affecting the magnetic flocculation is the dosage of magnetic seeds, and polymeric ferric sulfate also plays an important role. Under the optimal magnetic flocculation experimental conditions, the turbidity of wastewater after magnetic separation was only 16.388 NTU, contributing to the removal of phosphate contaminants. Therefore, magnetic flocculation and magnetic separation may provide an alternative solution for efficient purification of phosphate-containing wastewater.

Purification of starch and phosphorus wastewater using core-shell magnetic seeds prepared by sulfated roasting.

Core-shell magnetic seeds with certain adsorption capacity that were prepared by sulfated roasting, served as the core of a magnetic separation technology for purification of starch wastewater. XRD and SEM results indicate that magnetite's surface transformed to be porous α-Fe2O3 structure. Compared with magnetite particles, the specific surface area was significantly improved to be 8.361 from 2.591 m2/g, with little decrease in specific susceptibility. Zeta potential, FT-IR and XPS experiments indicate that both phosphate and starch adsorbed on the surface of the core-shell magnetic seeds by chemical adsorption, which fits well with the Langmuir adsorption model. The porous surface structure of magnetic seeds significantly contributes to the adsorption of phosphate and starch species, which can be efficiently removed to be 1.51 mg/L (phosphate) and 9.51 mg/L (starch) using magnetic separation.