Skip to main content
. Author manuscript; available in PMC: 2019 Jun 4.
Published in final edited form as: Phys Med Biol. 2019 Apr 10;64(8):085010. doi: 10.1088/1361-6560/ab13fa

Figure 1.

Figure 1.

(a) The LSTM many-to-many architecture for respiratory sequence prediction. The input vector is denoted by xt, the hidden layer vector is denoted by ht, and the output vector is denoted by yt. (b) A schematic diagram of a basic LSTM block as delineated in (a) by the red dash lines. The LSTM block consists of four parts: a memory cell st, an input gate it, a forget gate ft and an output gate ot. The updates of each part and the output of the LSTM block are illustrated in equations (1)–(6).