Search

Predicting the popularity of a single tweet is useful for both users and enterprises. However, adopting existing topic or event prediction models cannot obtain satisfactory results. The reason is that one topic or event that consists of multiple tweets, has more features and characteristics than a single tweet. In this article, we propose two variations of Heterogeneous Bass models (HBass), originally developed in the field of marketing science, namely Spatial-Temporal Heterogeneous Bass Model (ST-HBass) and Feature-Driven Heterogeneous Bass Model (FD-HBass), to predict the popularity of a single tweet at the early stage and the stable stage. We further design an Interaction Enhancement to improve the performance, which considers the competition and cooperation from different tweets with the common topic. In addition, it is often difficult to depict popularity quantitatively. We design an experiment to get the weight of favorite, retweet and reply, and apply the linear regression to calculate the popularity. Furthermore, we design a clustering method to bound the popular threshold. Once the weight and popular threshold are determined, the status whether a tweet will be popular or not can be justified. Our model is validated by conducting experiments on real-world Twitter data, and the results show the efficiency and accuracy of our model, with less absolute percent error and the best Precision and F-score. In all, we introduce Bass model into social network single-tweet prediction to show it can achieve excellent performance. [ABSTRACT FROM AUTHOR]

In the authors’ prior works, the microstructure, turning cutting performance and wear mechanisms of PVD-CrAlN and TiAlN coated silicon nitride cutting inserts on turning of gray iron were studied. In the present work, based on the authors’ former study, the effects of the cutting speed on tool life, wear mechanism and surface quality of the workpieces were studied through high speed face milling tests. The uncoated, CrAlN and TiAlN coated cutting inserts were conducted by high speed face milling of gray iron at various cutting speeds of 600 m/min~1500 m/min. The results displayed that during high speed face milling, the tool life of the PVD coated Si 3 N 4 cutting inserts decreased as the cutting speed increased. When the cutting speed reached a certain value, the tool life increased with the cutting speed increasing. During high speed face milling, no spallation failure happened to both CrAlN and TiAlN coatings, and the coatings could protect the insert substrates effectively under various cutting speeds, improving the tool life of the uncoated cutting inserts by 138–150% and 32–65%, respectively. The wear mechanisms of all three kinds of the cutting inserts by face milling of gray iron under various cutting speed were the same. The only difference was that as the cutting speed increased, the adhesive wear of the inserts increased significantly. During high speed face milling of gray iron with three kinds of inserts, the alteration relationship of machining quality with the cutting speed was similar to the tool life with the cutting speed relationship. Furthermore, when high speed face milling of gray iron was conducted, CrAlN coated Si 3 N 4 cutting inserts displayed the best machining quality, followed by TiAlN coated and the uncoated inserts, respectively. [ABSTRACT FROM AUTHOR]

In this work, CrAlN and TiAlN coatings were produced on silicon nitride cutting inserts via physical vapor deposition. The microstructure and hardness of the coatings, as well as the adhesive strength between the coating and the substrate were studied using a scanning electronic microscope, a micro hardness tester and a scratch tester, respectively. Continuous turning tests of the obtained CrAlN and TiAlN-coated silicon nitride cutting inserts were performed on gray cast iron to evaluate the cutting performances and the machining quality. The results show that the surface hardness of the Si 3 N 4 cutting inserts could be improved by 87% and 50%, respectively, when applying the CrAlN and TiAlN coatings, thereby enhancing the abrasion resistance of the cutting inserts. At different tested cutting speeds, abrasive wear under compressional deformation and adhesive wear were identified as the main failure mechanisms for the two cutting inserts during continuous turning of gray cast iron. The machining quality of the gray cast iron workpieces machined using the uncoated, the CrAlN- or the TiAlN-coated inserts increased with the increment of the cutting speed. [ABSTRACT FROM AUTHOR]