Regarding the limitations of traditional web real-time communication solutions such as polling, long-polling, flash plug-in, propose that using new coming Web Socket technology in the web real-time communication field, introduce the features of Web Socket technology, analysis the difference between Web Socket protocol and HTTP protocol, offer an approach to implement the Web Socket both in client and server side, prove Web Socket can decrease network traffic and latency greatly by an experiment, made the prospect of future application of Web Socket in web real-time communication.
In this paper, we investigated the customer churn prediction problem in the Internet funds industry. We designed a novel feature embedded convolutional neural networks (FE-CNN) method that can automatically learn features from both the dynamic customer behavioral data and static customer demographic data and can utilize the advantage of convolutional neural networks to automatically learn features that capture the structured information. Our results show that our FE-CNN model outperforms the other traditional machine learning models with hand-crafted features, such as logistic regression (LR), support vector machines (SVM), random forests (RF) and neural networks (NN) in terms of accuracy, area under the receiver operating characteristics curve (AUC) and top-decile lift. Furthermore, we found that after adding the demographic data feature to the basic CNN model, the performance of the FE-CNN model improved. Overall, we found that the FE-CNN is the most powerful way to solve the problem of customer churn prediction in the Internet funds industry. Our FE-CNN method can also be applied to other fields that have both dynamic data and static data.
Non-isocyanate polyurethanes (NIPUs) from renewable resources have attracted wide attention because of their remarkable benefits to sustainable development and green production. In this work, a strong, self-healing, and catalyst-free NIPU (ECMP) was prepared based on the hyperbranched biobased cyclic carbonate (Ec-MTDA) synthesized through catalytic carbonization of 1,8-menthane diamine (MTDA) and CO 2 . The hyperbranched and rigid structures of ECMP enable improved mechanical properties that a high tensile strength of up to 34.9 MPa can be achieved. Benefiting from the dynamic transesterification reaction between the carbamate and hydroxyl groups, ECMP presents favorable self-healing, reprocessing properties, and shape memory. Notably, 91% of the original tensile strength can be recovered after self-healing behavior. In addition, abundant polar groups provide excellent adhesion properties for ECMP with a high shear strength of 7.09 MPa. This study provides a promising strategy for the design of bio-based NIPUs, which broadens their applications in printing, furniture, packaging, and other industries.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.