A Core Set Based Large Vector-Angular Region and Margin Approach for Novelty Detection

<table class="figure-group"><tr class="fig-image" id="a"><td><object data="https://static.hindawi.com/articles/mpe/volume-2016/1658758/figures/1658758.fig.005a.svgz" name="1658758.fig.005a" type="image/svg+xml"></object></td></tr><tr class="fig-caption"><td><b>(a) </b>Influence of <svg height="9.32509pt" id="M241" style="vertical-align:-3.1815pt" version="1.1" viewbox="-0.0498162 -6.14359 10.9702 9.32509" width="10.9702pt" 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="M213 67C239 136 257 225 255 300C253 353 242 447 164 447C112 447 54 389 41 319L67 309C90 362 117 377 134 377C184 377 189 277 190 239C193 153 164 43 146 -12H176C278 73 450 253 450 390C450 439 410 463 396 463C384 463 380 459 382 449C385 440 389 415 389 402C389 284 312 146 216 67H213Z" id="g185-47"></path><glyph.data ascent="989" descent="-303" horiz-adv-x="454" vert-adv-y="454"></glyph.data></g><g transform="matrix(.0091,0,0,-0.0091,5.902,3.132)"><path d="M414 144C384 79 371 75 317 75H135L276 221C367 316 408 376 408 465C408 570 327 635 237 635C179 635 131 609 100 575L42 494L67 471C94 510 138 565 205 565C277 565 321 517 321 435C321 348 258 270 195 195C146 137 88 81 33 26V0H411C423 44 433 88 446 135L414 144Z" id="g50-51"></path><glyph.data ascent="3443" descent="-2856" horiz-adv-x="487" vert-adv-y="487"></glyph.data></g></svg> on geometric mean accuracy</td></tr><tr class="fig-image" id="b"><td><object data="https://static.hindawi.com/articles/mpe/volume-2016/1658758/figures/1658758.fig.005b.svgz" name="1658758.fig.005b" type="image/svg+xml"></object></td></tr><tr class="fig-caption"><td><b>(b) </b>Influence of <svg height="9.32509pt" id="M242" style="vertical-align:-3.1815pt" version="1.1" viewbox="-0.0498162 -6.14359 10.9702 9.32509" width="10.9702pt" 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="M213 67C239 136 257 225 255 300C253 353 242 447 164 447C112 447 54 389 41 319L67 309C90 362 117 377 134 377C184 377 189 277 190 239C193 153 164 43 146 -12H176C278 73 450 253 450 390C450 439 410 463 396 463C384 463 380 459 382 449C385 440 389 415 389 402C389 284 312 146 216 67H213Z" id="g185-47"></path><glyph.data ascent="989" descent="-303" horiz-adv-x="454" vert-adv-y="454"></glyph.data></g><g transform="matrix(.0091,0,0,-0.0091,5.902,3.132)"><path d="M414 144C384 79 371 75 317 75H135L276 221C367 316 408 376 408 465C408 570 327 635 237 635C179 635 131 609 100 575L42 494L67 471C94 510 138 565 205 565C277 565 321 517 321 435C321 348 258 270 195 195C146 137 88 81 33 26V0H411C423 44 433 88 446 135L414 144Z" id="g50-51"></path><glyph.data ascent="3443" descent="-2856" horiz-adv-x="487" vert-adv-y="487"></glyph.data></g></svg> on the number of core sets</td></tr></table>

<div>Influence of parameter <svg height="9.32509pt" id="M240" style="vertical-align:-3.1815pt" version="1.1" viewbox="-0.0498162 -6.14359 10.9702 9.32509" width="10.9702pt" 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="M213 67C239 136 257 225 255 300C253 353 242 447 164 447C112 447 54 389 41 319L67 309C90 362 117 377 134 377C184 377 189 277 190 239C193 153 164 43 146 -12H176C278 73 450 253 450 390C450 439 410 463 396 463C384 463 380 459 382 449C385 440 389 415 389 402C389 284 312 146 216 67H213Z" id="g185-47"></path><glyph.data ascent="989" descent="-303" horiz-adv-x="454" vert-adv-y="454"></glyph.data></g><g transform="matrix(.0091,0,0,-0.0091,5.902,3.132)"><path d="M414 144C384 79 371 75 317 75H135L276 221C367 316 408 376 408 465C408 570 327 635 237 635C179 635 131 609 100 575L42 494L67 471C94 510 138 565 205 565C277 565 321 517 321 435C321 348 258 270 195 195C146 137 88 81 33 26V0H411C423 44 433 88 446 135L414 144Z" id="g50-51"></path><glyph.data ascent="3443" descent="-2856" horiz-adv-x="487" vert-adv-y="487"></glyph.data></g></svg> on geometric mean accuracy and the number of core sets.</div>

Mathematical Problems in Engineering

fig5

Figure 5

Figure 5: A Core Set Based Large Vector-Angular Region and Margin Approach for Novelty Detection 