Experimental resultsIn our experiment, we adopted full cross-validation. Everytime we chose one protein as the test set, and the rest 37 proteinswere chose as the train set. Thus we carried out 38 times andevery protein was tested and predicted (see Figs. 2–5).Every time, the PSO and...
Full size table Conclusion This study used image processing technologies and machine learning algorithms to identify 15 kinds of plant leaves. A new BP-RBF hybrid neural network was proposed to further improve the recognition accuracy rate. The conclusions of this study are as follows. ...
Ji L, Zhou CB, Lu SW, Jiang N, Li HB (2021) Modeling study of cumulative damage effects and safety criterion of surrounding rock under multiple full-face blasting of a large cross-section tunnel. International Journal of Rock Mechanics and Mining Sciences 147: 104882, DOI: https://doi.org...
The position 𝒑p, velocity 𝒗v, attitude 𝒒q, gyro bias 𝒃𝒈bg, accelerometer bias 𝒃𝑎𝑐𝑐bacc, and acoustic fix bias 𝒃ℎbh in full state vector 𝒙x form are given as 𝒙=[𝒑𝒗𝒒𝒃𝑔𝒃𝑎𝑐𝑐𝒃ℎ𝑠𝑣]𝑇x=pvqbgbaccbhsvT (23) where ...
Moreover, it can simplify the calculation steps using a transformed functional form. Several studies on the Weibull distribution have shown that, if a localized failure results in the malfunctioning of the entire system, the life of such a system generally obeys the Weibull distribution. The ...
After optimization, the head and pump efficiency increased under the full flow condition. The maximum pump efficiency increased by 4.7%, and the best efficiency point shifts to large flow. At the same time, the optimization scheme alleviates the problem of the rapid drop of the head and ...
The input data will be expanded in the form of the polynomial kernel and mapped from low dimension to high dimension. In this paper, the traditional single-layer RBF network is improved to a multilayer RBF network, in which the full connection layer is inserted for connection. According to ...