Adaptive Online Sequential ELM for Concept Drift Tackling

<table class="figure-group"><tr class="fig-image" id="a"><td><object data="https://static.hindawi.com/articles/cin/volume-2016/8091267/figures/8091267.fig.005a.svgz" name="8091267.fig.005a" type="image/svg+xml"></object></td></tr><tr class="fig-caption"><td><b>(a) </b>The SEA concept</td></tr><tr class="fig-image" id="b"><td><object data="https://static.hindawi.com/articles/cin/volume-2016/8091267/figures/8091267.fig.005b.svgz" name="8091267.fig.005b" type="image/svg+xml"></object></td></tr><tr class="fig-caption"><td><b>(b) </b>The STAGGER concept</td></tr></table>

<div>Predictive accuracy of AOS-ELM1 (black line △) and AOS-ELM2 (black dashes △) compared with OS-ELM (blue line <svg height="7.35473pt" id="M356" style="vertical-align:-0.3499303pt" version="1.1" viewbox="-0.0498162 -7.0048 7.75925 7.35473" width="7.75925pt" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink"><g transform="matrix(.013,0,0,-0.013,0,0)"><path d="M528 54L331 254L528 455L492 493L294 291L96 493L60 455L257 254L60 54L96 16L294 217L492 16L528 54Z" id="g117-42"></path><glyph.data ascent="3473" descent="-2876" horiz-adv-x="587" vert-adv-y="587"></glyph.data></g></svg>) and CEOS-ELM (blue dashes  <svg height="7.35473pt" id="M357" style="vertical-align:-0.3499303pt" version="1.1" viewbox="-0.0498162 -7.0048 7.75925 7.35473" width="7.75925pt" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink"><g transform="matrix(.013,0,0,-0.013,0,0)"><path d="M528 54L331 254L528 455L492 493L294 291L96 493L60 455L257 254L60 54L96 16L294 217L492 16L528 54Z" id="g117-42"></path><glyph.data ascent="3473" descent="-2876" horiz-adv-x="587" vert-adv-y="587"></glyph.data></g></svg>).</div>

Computational Intelligence and Neuroscience

Adaptive Online Sequential ELM for Concept Drift Tackling

Figure 5