Numerical Analysis of Modeling Based on Improved Elman Neural Network

<table class="table-group" width="800px"><tr class="fig-image" id="a"><td><img alt="271593.fig.004a" src="https://static.hindawi.com/articles/tswj/volume-2014/271593/figures/271593.fig.004a.jpg"/></td></tr><tr class="fig-caption"><td align="center"><table><tr><td><b>(a) </b>BENN model</td></tr></table></td></tr><tr class="fig-image" id="b"><td><img alt="271593.fig.004b" src="https://static.hindawi.com/articles/tswj/volume-2014/271593/figures/271593.fig.004b.jpg"/></td></tr><tr class="fig-caption"><td align="center"><table><tr><td><b>(b) </b>IENN model</td></tr></table></td></tr></table>

<table>SSE varying with iteration number <svg height="11.175" id="M93" style="vertical-align:-0.0pt" version="1.1" viewbox="0 0 13.3125 11.175" width="13.3125" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink">
<g transform="matrix(.017,-0,0,-.017,.062,11.113)"><path d="M764 650l-7 -26q-61 -10 -91.5 -22.5t-76.5 -48.5l-235 -184q104 -152 208 -276q31 -37 54.5 -48.5t68.5 -16.5l-7 -28h-156q-138 170 -213 284q-19 29 -33.5 35t-33.5 -7l-29 -173q-15 -75 -5.5 -90.5t74.5 -20.5l-5 -28h-260l7 28q58 5 74 21.5t30 89.5l70 378
q12 68 2 83t-72 22l6 28h257l-7 -28q-62 -7 -76 -21.5t-27 -83.5l-32 -172q29 11 78 46q112 84 217 179q18 16 23.5 25.5t-1 14.5t-26.5 8l-30 4l5 28h249z" id="x1D43E"></path></g>
</svg> and number of hidden neurons <svg height="11.3125" id="M94" style="vertical-align:-0.0pt" version="1.1" viewbox="0 0 14.9875 11.3125" width="14.9875" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink">
<g transform="matrix(.017,-0,0,-.017,.062,11.113)"><path d="M857 650l-6 -28q-44 -4 -61.5 -16.5t-29.5 -48.5q-11 -32 -37 -166l-78 -399h-29l-351 537h-4l-56 -276q-24 -120 -24 -164q0 -35 17.5 -46t75.5 -15l-6 -28h-245l7 28q41 2 62 14t31 44q10 30 41 171l53 245q8 44 6.5 60.5t-14.5 33.5q-10 15 -27 19.5t-64 6.5l6 28h153
l350 -516h5l48 257q25 131 25 171q0 34 -17.5 45t-77.5 15l7 28h240z" id="x1D441"></path></g>
</svg>.</table>

The Scientific World Journal

fig4

Figure 4

Figure 4: Numerical Analysis of Modeling Based on Improved Elman Neural Network 