Effects of In-Situ Reaction, Extrusion Ratio and CeO on the Performance of Al-Ti-C-(Ce) Grain Refiners for Refining Pure Aluminum Grains.

Al-Ti-C-(Ce) grain refiners were prepared by combining in-situ reaction, hot extrusion, and adding CeO. The effects of second phase TiC particle size and distribution, extrusion ratio, and Ce addition on the grain-refining performance of grain refiners were investigated. The results show that about 10 nm TiC particles are dispersed on the surface and inside of 100-200 nm Ti particles by in-situ reaction.

Research on the Prediction of A-Share "High Stock Dividend" Phenomenon-A Feature Adaptive Improved Multi-Layers Ensemble Model.

Since the "high stock dividend" of A-share companies in China often leads to the short-term stock price increase, this phenomenon's prediction has been widely concerned by academia and industry. In this study, a new multi-layer stacking ensemble algorithm is proposed. Unlike the classic stacking ensemble algorithm that focused on the differentiation of base models, this paper used the equal weight comprehensive feature evaluation method to select features before predicting the base model and used a genetic algorithm to match the optimal feature subset for each base model.