An Improved Long Short-Term Memory Model for Dam Displacement Prediction

<figure class="figure-group responsive"><div class="sub-figure" id="a"><object data="https://static.hindawi.com/articles/mpe/volume-2019/6792189/figures/6792189.fig.009a.svgz" name="6792189.fig.009a" type="image/svg+xml"></object><div class="fig-label">(a) Training</div></div><div class="sub-figure" id="b"><object data="https://static.hindawi.com/articles/mpe/volume-2019/6792189/figures/6792189.fig.009b.svgz" name="6792189.fig.009b" type="image/svg+xml"></object><div class="fig-label">(b) Validation</div></div></figure>

<p>Effects of the input subsequence length of the LSTM models. Five runs have been conducted under each length condition. The region is enveloped by the maximum and minimum values. The curve in the region is connected by the mean value. MSE, mean square error.</p>

Mathematical Problems in Engineering

fig9

Figure 9

Figure 9: An Improved Long Short-Term Memory Model for Dam Displacement Prediction 