Search

Ocean sensor data prediction has become a promising means for smart ocean monitoring. In alternative solutions, deep neural networks (DNNs) are considered as a good choice. The determination of activation functions in DNNs has a significant effect on training speed and nonlinear approximation. In this paper, the effect of activation functions on a deep computing model called deep belief echo-state network (DBEN) is studied in the scenario of ocean time series prediction. Here, different forms, including hyperbolic tangent, rectified linear unit, exponential linear unit, swish, softplus and their variants, are considered. The purpose is to investigate, from the perspectives of accuracy and training efficiency, whether certain activation function in DBEN is completely universal for the different tasks of ocean sensor data processing or not. On a great deal of real-world ocean time series of different characteristics, the results show that the selection of activation functions in DBEN is task-related. Specially, these newly introduced activation functions are more beneficial to the accurate predictions for conventional and chemical data sets compared with sigmoid benchmark. The statistical analysis further verifies this finding.

Rapid growth of global population should be demanded more high-quality food and this might be alleviated by improving protein nutrition levels in usual foodstuff. The expense associated with food additives used for animal production have led to the study of intracellular production of high-quality protein (HQP) by transgenic crops and other organisms, as a means of obtaining efficient and less costly sources of essential amino acids. One important approach is to extract high essential amino acids from bacteria or others. We designed a HQP gene encoding about 100 amino acids which had more than 80 % essential amino acids. GOR/Gibrat and Swiss-Pdb Viewer analysis were used to predict the secondary structure of HQP-1 in pI value, hydrophilic and hydrophobic properties. Then the HQP gene was transferred into E. coli BL21 (DE3), and the protein was extracted and identified by SDS-PAGE.