According to the latest data from ESI (Essential Science Indicators), the paper "Multivariate adaptive regression splines and neural network models for prediction of pile drivability" written by Prof. Wengang ZHANG of our faculty was selected as the top 1% of papers by field and publication year. The paper has been published in the journal of Geoscience Frontiers with CiteScore of 4.24, Impact Factor of 4.16, and 5-Year Impact Factor of 4.516 since January 2016. It has been cited 72 times in the core collection of Web of Science, and Google Scholar has shown 128 times. It has a significantly positive impact in the engineering field.
This highly cited paper adopted multivariate adaptive regression splines (MARS) and back propagation neural network (BPNN) to establish a predictive model for pile drivability and comprehensively compared the two algorithms from the aspects of modeling accuracy and computational efficiency. MARS is superior to BPNN in terms of computational efficiency and model interpretability. The research have been widely concerned by domestic and foreign counterparts, and it has practical reference to further explore the optimization and application of different data-driven algorithms for researchers in this field.
ESI (Essential Science Indicators) is a basic analytical evaluation tool for measuring the performance of scientific research and tracking the development trend of science in the international academic community. ESI includes 22 subject areas, and the highly cited papers are the top 1% of the papers ranked in the corresponding subject area according to the ESI statistics. It reflects the influence of the paper from the perspective of literature, and it is a direct manifestation of its research results approved by the academic community, which is conducive to the promotion of discipline construction. At present, ESI highly cited papers have become one of the important indicators to weigh the academic influence of schools.
The full text of paper as follows: https://www.sciencedirect.com/science/article/pii/S1674987114001364