AUTHOR=Cao Wenjie , Shi Ya-Zhou , Qiu Huahai , Zhang Bengong 

TITLE=SS-RNN: A Strengthened Skip Algorithm for Data Classification Based on Recurrent Neural Networks

JOURNAL=Frontiers in Genetics

VOLUME=Volume 12 - 2021

YEAR=2021

URL=https://www.frontiersin.org/journals/genetics/articles/10.3389/fgene.2021.746181

DOI=10.3389/fgene.2021.746181

ISSN=1664-8021

ABSTRACT=Recurrent neural networks are widely used in time series prediction and classification. However, it has problems such as insufficient memory ability and difficulty in gradient back propagation. To solve these problems, this paper proposes a new algorithm called SS-RNN which directly uses multiple historical information to predict the current time information. It can enhance the long-term memory ability. At the same time, for the time direction, it can improve the correlation of states at different moments. To include the historical information, we design two different processing methods for the SS-RNN in continuous and discontinuous ways, respectively. And for each method, there are two ways for historical information addition: (1) directly addition, (2) adding weight weighting and function mapping to activation function. It provides six pathways so as to fully and deeply explore the effect and influence of historical information on the recurrent neural networks (RNN). By comparing the average accuracy of real datasets with LSTM, Bi-LSTM and GRU, MCNN and calculating the main indexes (Accuracy, Precision, Recall, F1-score), it can be observed that our method can improve the average accuracy, and optimize the structure of the RNN and effectively solve the problems of exploding and vanishing gradients.