Larger aggregate formed by self-assembly process of the mixture surfactants enhance the dissolution and oxidative removal of non-aqueous phase liquid contaminants in aquifer.

Surfactants can transfer non-aqueous phase liquid (NAPL) contaminants to the aqueous phase, and enhance the removal of the latter in groundwater. However, the extensive use of surfactants causes secondary contamination and increases the non-target consumption of oxidants. It is pressing to develop a surfactant with high phase transfer efficiency and sound compatibility with oxidants to minimize the use of surfactants for groundwater remediation. The phase transfer capability of different surfactants and their binary mixtures, their enhanced KMnO4 oxidation performance for NAPL contaminants as well as influencing factors were investigated to solve the above-mentioned question. The results showed that Tween20, SDBS and BS-12 perform best in terms of phase transfer capability among nonionic, anionic and amphoteric surfactants respectively, and only SDBS and BS-12 produce a synergistic effect among the binary mixtures. The CMC of SDBS/BS-12 was lower than its ideal CMC value, and the self-assembly process of SDBS/BS-12 also formed larger aggregates, which improved the phase transfer performance. Compared to other single surfactants, the removal efficiency of petroleum hydrocarbons in the aquifer sediments was raised by 7.4-33.8 % using the mixed surfactant. The SDBS/BS-12 mixture was compatible with KMnO4 and boosted the reaction of NAPL contaminants with KMnO4 by transferring from the NAPL phase to the aqueous phase. As a result, the NAPL toluene and phenanthrene removal efficiency increased from 37 % and 29 % to 80 % and 86 % respectively. Natural organic matters inhibited the phase transfer efficiency of the SDBS/BS-12 mixture, whereas anions and monovalent cations enhanced the phase transfer capability of the mixture. High-valent cations led to precipitation in the SDBS/BS-12, which could be eliminated by adding Na2Si2O5. The SDBS/BS-12 mixture delivered the same phase transfer efficiency with the dosage of 1.73-23.07 % of other single surfactants, and its cost was equivalent to 0.25-41.7 % of the latter, thus embracing bright application prospects.

A New Approach for Mobile Advertising Click-Through Rate Estimation Based on Deep Belief Nets.

In recent years, with the rapid development of mobile Internet and its business applications, mobile advertising Click-Through Rate (CTR) estimation has become a hot research direction in the field of computational advertising, which is used to achieve accurate advertisement delivery for the best benefits in the three-side game between media, advertisers, and audiences. Current research on the estimation of CTR mainly uses the methods and models of machine learning, such as linear model or recommendation algorithms. However, most of these methods are insufficient to extract the data features and cannot reflect the nonlinear relationship between different features. In order to solve these problems, we propose a new model based on Deep Belief Nets to predict the CTR of mobile advertising, which combines together the powerful data representation and feature extraction capability of Deep Belief Nets, with the advantage of simplicity of traditional Logistic Regression models. Based on the training dataset with the information of over 40 million mobile advertisements during a period of 10 days, our experiments show that our new model has better estimation accuracy than the classic Logistic Regression (LR) model by 5.57% and Support Vector Regression (SVR) model by 5.80%.