Search

[Image: see text] An attempt has been made to optimize the preparation of biodiesel from the transesterification of oleic acid with methanol over iron(III)-doped phosphomolybdic acid (H(3)PMo) catalysts. The prepared doped H(3)PMo salts were characterized using powder X-ray diffraction, Fourier transform infrared spectroscopy, thermogravimetric analysis, and scanning electron microscopy. The detailed characterization results demonstrated that the doped H(3)PMo salts have a strong interaction between the iron(III) ions and metal oxygen cluster, well preserving a typical Keggin structure of heteropolyacids and possessing good thermal stability. The effect of esterification reaction parameters was investigated and optimized using single-factor experiments method in combination with response surface methodology (RSM). The doped catalyst exhibited good catalytic activity, affording the oleic acid conversion of 89.2% with single factor optimization and 95.1% with RSM. More importantly, the catalyst was simply separated by decantation and exhibited good stability, with the oleic acid conversion of 70.2% after three consecutive cycles. Besides, this catalyst can also catalyze the esterification of other free fatty acids. Therefore, the doped H(3)PMo catalyst is a promising candidate for eco-friendly production of biodiesel in industry.

While massive open online courses (MOOCs) have gained increasing popularity in recent years, dropout prediction has been an important task to solve due to the high rates of dropout students found in MOOCs. Current methods normally apply supervised learning methods to dropout prediction, using general features extracted from behavior records without the concern of behavior types. However, student learning behavior is diverse and there are no sufficient labeled data to train a model because it is a time-costing task to label enormous data in practice. To solve these problems, in this work, we proposed a novel multi-view semi-supervised learning model based on behavior features for the dropout prediction task. Specifically, we derived features from each type of learning behavior to form multi-view behavior features. In addition, based on these features, we proposed a new multi-view semi-supervised learning method to make use of a large number of unlabeled data to assist insufficient labeled data for improving prediction performance. We conducted experiments on KDD Cup 2015 dataset, and the results show that our proposed method achieves better prediction of student dropouts as compared to state-of-the-art approaches.

With the recent explosive growth of the Web, recommendation systems have been widely accepted by users. Item-based Collaborative Filtering (CF) is one of the most popular approaches for determining recommendations. A common problem of current item-based CF approaches is that all users have the same weight when computing the item relationships. To improve the quality of recommendations, we incorporate the weight of a user, userrank, into the computation of item similarities and differentials. In this paper, a data model for userrank calculations, a PageRank-based user ranking approach, and a userrank-based item similarities/differentials computing approach are proposed. Finally, the userrank-based approaches improve the recommendation results of the typical Adjusted Cosine and Slope One item-based CF approaches.