An improved deep echo state network inspired by tissue-like P system forecasting for non-stationary time series

Abstract

As a recurrent neural network, ESN has attracted wide attention because of its simple training process and unique reservoir structure, and has been applied to time series prediction and other fields. However, ESN also has some shortcomings, such as the optimization of reservoir and collinearity. Many researchers try to optimize the structure and performance of deep ESN by constructing deep ESN. However, with the increase of the number of network layers, the problem of low computing efficiency also follows. In this paper, we combined membrane computing and neural network to build an improved deep echo state network inspired by tissue-like P system. Through analysis and comparison with other classical models, we found that the model proposed in this paper has achieved great success both in predicting accuracy and operation efficiency.

Recent Progress in Microfiltration/Ultrafiltration Membranes for Separation of Oil and Water Emulsions

“…Interestingly, the reaction between the coagulation medium and the additive can control the PAN permeation. It is concluded that the reaction rate is the controlling factor in the permeance performance of the membrane [173] . Incorporating PF127 and CaCO 3 into the PAN membranes fabricated through the NIPS process can help substantially improve the PAN membranes′ hydrophilicity and the flux recovery ratio (90 %) [174,175] .…”

Breaking RSA Encryption Protocol with Kernel P Systems

“…Membrane computing has been intensively studied. Some of the most recent papers refer to theoretical developments [6][7][8][9][10][11] and applications [12][13][14][15][16]. The possibility of generating exponential space in polynomial (more often linear) time, is a key feature of these models and represents the main element in solving NP-complete problems [17][18][19].…”