• szuwqh201
    了解作者
  • PDF
    开发工具
  • 244KB
    文件大小
  • rar
    文件格式
  • 0
    收藏次数
  • 1 积分
    下载积分
  • 1
    下载次数
  • 2016-01-31 23:29
    上传日期
Adaptive neuro-fuzzy inference system for classification of EEG signals using wavelet coefficients
paper4.rar
  • Adaptive neuro-fuzzy inference system for classification of EEG signals using wavelet coefficients.pdf
    318.1KB
内容介绍
<html xmlns="http://www.w3.org/1999/xhtml"> <head> <meta charset="utf-8"> <meta name="generator" content="pdf2htmlEX"> <meta http-equiv="X-UA-Compatible" content="IE=edge,chrome=1"> <link rel="stylesheet" href="https://static.pudn.com/base/css/base.min.css"> <link rel="stylesheet" href="https://static.pudn.com/base/css/fancy.min.css"> <link rel="stylesheet" href="https://static.pudn.com/prod/directory_preview_static/622b58833d2fbb00076eed4c/raw.css"> <script src="https://static.pudn.com/base/js/compatibility.min.js"></script> <script src="https://static.pudn.com/base/js/pdf2htmlEX.min.js"></script> <script> try{ pdf2htmlEX.defaultViewer = new pdf2htmlEX.Viewer({}); }catch(e){} </script> <title></title> </head> <body> <div id="sidebar" style="display: none"> <div id="outline"> </div> </div> <div id="pf1" class="pf w0 h0" data-page-no="1"><div class="pc pc1 w0 h0"><img class="bi x0 y0 w1 h1" alt="" src="https://static.pudn.com/prod/directory_preview_static/622b58833d2fbb00076eed4c/bg1.jpg"><div class="t m0 x1 h2 y1 ff1 fs0 fc0 sc0 ls0 ws0">Journal<span class="_"> </span>of<span class="_"> </span>Neuroscience<span class="_"> </span>Methods<span class="_"> </span>xxx<span class="_"> </span>(2005)<span class="_"> </span>xxx&#8211;xxx</div><div class="t m0 x2 h3 y2 ff1 fs1 fc0 sc0 ls0 ws0">Adapti<span class="_ _0"></span>v<span class="_ _0"></span>e<span class="_"> </span>neuro-fuzzy<span class="_"> </span>inference<span class="_"> </span>system<span class="_"> </span>for<span class="_"> </span>classi&#64257;cation</div><div class="t m0 x3 h3 y3 ff1 fs1 fc0 sc0 ls0 ws0">of<span class="_"> </span>EEG<span class="_"> </span>signals<span class="_"> </span>using<span class="_"> </span>wa<span class="_ _0"></span>v<span class="_ _0"></span>elet<span class="_"> </span>coef<span class="_ _0"></span>&#64257;cients</div><div class="t m0 x4 h4 y4 ff1 fs2 fc0 sc0 ls0 ws0">&#729;</div><div class="t m0 x4 h4 y5 ff1 fs2 fc0 sc0 ls0 ws0">Inan<span class="_"> </span>G</div><div class="t m0 x5 h4 y6 ff1 fs2 fc0 sc0 ls0 ws0">&#168;</div><div class="t m0 x6 h4 y5 ff1 fs2 fc0 sc0 ls0 ws0">uler</div><div class="t m0 x7 h5 y7 ff1 fs3 fc1 sc0 ls0 ws0">a<span class="ff2 fc0">,</span><span class="ff3">&#8727;</span></div><div class="t m0 x8 h4 y8 ff1 fs2 fc0 sc0 ls0 ws0">,<span class="_"> </span>Elif<span class="_"> </span>Derya</div><div class="t m0 x9 h4 y9 ff1 fs2 fc0 sc0 ls0 ws0">&#168;</div><div class="t m0 xa h4 y8 ff1 fs2 fc0 sc0 ls0 ws0">Ubeyli</div><div class="t m0 xb h5 ya ff1 fs3 fc1 sc0 ls0 ws0">b</div><div class="t m0 xc h6 yb ff1 fs4 fc0 sc0 ls0 ws0">a</div><div class="t m0 xd h7 yc ff4 fs0 fc0 sc0 ls0 ws0">Department<span class="_ _1"> </span>of<span class="_ _1"> </span>Electr<span class="_ _0"></span>onics<span class="_ _1"> </span>and<span class="_ _1"> </span>Computer<span class="_ _1"> </span>Education,<span class="_ _1"> </span>F<span class="_ _0"></span>aculty<span class="_ _1"> </span>of<span class="_ _1"> </span>T<span class="_ _2"></span>echnical<span class="_ _1"> </span>Education,<span class="_ _1"> </span>Gazi<span class="_ _1"> </span>University<span class="_ _2"></span>,<span class="_ _1"> </span>06500<span class="_ _1"> </span>T<span class="_ _0"></span>eknikokullar<span class="_ _2"></span>,<span class="_ _1"> </span>Ankar<span class="_ _0"></span>a,<span class="_ _1"> </span>T<span class="_ _0"></span>urke<span class="_ _0"></span>y</div><div class="t m0 xe h6 yd ff1 fs4 fc0 sc0 ls0 ws0">b</div><div class="t m0 x2 h7 ye ff4 fs0 fc0 sc0 ls0 ws0">Department<span class="_ _1"> </span>of<span class="_ _1"> </span>Electrical<span class="_ _1"> </span>and<span class="_ _1"> </span>Electr<span class="_ _0"></span>onics<span class="_ _1"> </span>Engineering,<span class="_ _1"> </span>F<span class="_ _2"></span>aculty<span class="_ _1"> </span>of<span class="_ _1"> </span>Engineering,<span class="_ _1"> </span>TOBB<span class="_ _1"> </span>Ekonomi<span class="_ _1"> </span>ve<span class="_ _1"> </span>T<span class="_ _2"></span>eknoloji</div><div class="t m0 xf h7 yf ff4 fs0 fc0 sc0 ls0 ws0">&#168;</div><div class="t m0 x10 h7 ye ff4 fs0 fc0 sc0 ls0 ws0">Universitesi,</div><div class="t m0 x11 h7 y10 ff4 fs0 fc0 sc0 ls0 ws0">06530<span class="_ _1"> </span>S<span class="_ _3"></span>&#168;<span class="_ _4"></span><span class="ls1">o&#728;<span class="_ _5"></span>g&#168;<span class="_ _5"></span><span class="ls0">ut<span class="_ _3"></span>&#168;<span class="_ _4"></span>oz<span class="_ _3"></span>&#168;<span class="_ _4"></span>u,<span class="_ _1"> </span>Ankara,<span class="_ _1"> </span>T<span class="_ _0"></span>urke<span class="_ _0"></span>y</span></span></div><div class="t m0 x12 h2 y11 ff1 fs0 fc0 sc0 ls0 ws0">Receiv<span class="_ _0"></span>ed<span class="_"> </span>12<span class="_"> </span>January<span class="_"> </span>2005;<span class="_"> </span>received<span class="_"> </span>in<span class="_"> </span>re<span class="_ _0"></span>vised<span class="_"> </span>form<span class="_"> </span>12<span class="_"> </span>April<span class="_"> </span>2005;<span class="_"> </span>accepted<span class="_"> </span>15<span class="_"> </span>April<span class="_"> </span>2005</div><div class="t m0 x13 h8 y12 ff5 fs5 fc0 sc0 ls0 ws0">Abstract</div><div class="t m0 x14 h9 y13 ff1 fs5 fc0 sc0 ls0 ws0">This<span class="_"> </span>paper<span class="_ _6"> </span>describes<span class="_"> </span>the<span class="_ _6"> </span>application<span class="_"> </span>of<span class="_ _6"> </span>adaptiv<span class="_ _0"></span>e<span class="_"> </span>neuro-fuzzy<span class="_ _6"> </span>inference<span class="_"> </span>system<span class="_ _6"> </span>(ANFIS)<span class="_"> </span>model<span class="_ _6"> </span>for<span class="_"> </span>classi&#64257;cation<span class="_ _6"> </span>of<span class="_"> </span>electroencephalogram</div><div class="t m0 x13 h9 y14 ff1 fs5 fc0 sc0 ls0 ws0">(EEG)<span class="_ _6"> </span>signals.<span class="_ _6"> </span>Decision<span class="_ _6"> </span>making<span class="_ _6"> </span>was<span class="_ _6"> </span>performed<span class="_ _6"> </span>in<span class="_ _6"> </span>two<span class="_ _6"> </span>stages:<span class="_ _6"> </span>feature<span class="_ _6"> </span>extraction<span class="_ _6"> </span>using<span class="_ _6"> </span>the<span class="_ _6"> </span>wav<span class="_ _0"></span>elet<span class="_ _6"> </span>transform<span class="_ _6"> </span>(WT)<span class="_ _7"> </span>and<span class="_ _6"> </span>the<span class="_ _6"> </span>ANFIS<span class="_ _6"> </span>trained</div><div class="t m0 x13 h9 y15 ff1 fs5 fc0 sc0 ls0 ws0">with<span class="_ _6"> </span>the<span class="_ _7"> </span>backpropagation<span class="_ _7"> </span>gradient<span class="_ _7"> </span>descent<span class="_ _7"> </span>method<span class="_ _7"> </span>in<span class="_ _7"> </span>combination<span class="_ _6"> </span>with<span class="_ _7"> </span>the<span class="_ _7"> </span>least<span class="_ _7"> </span>squares<span class="_ _7"> </span>method.<span class="_ _7"> </span>Fiv<span class="_ _0"></span>e<span class="_ _7"> </span>types<span class="_ _7"> </span>of<span class="_ _7"> </span>EEG<span class="_ _6"> </span>signals<span class="_ _7"> </span>were<span class="_ _7"> </span>used<span class="_ _7"> </span>as</div><div class="t m0 x13 h9 y16 ff1 fs5 fc0 sc0 ls0 ws0">input<span class="_ _1"> </span>patterns<span class="_ _1"> </span>of<span class="_ _1"> </span>the<span class="_ _8"> </span>&#64257;ve<span class="_ _8"> </span>ANFIS<span class="_"> </span>classi&#64257;ers.<span class="_ _8"> </span>T<span class="_ _2"></span>o<span class="_"> </span>impro<span class="_ _0"></span>ve<span class="_ _8"> </span>diagnostic<span class="_"> </span>accurac<span class="_ _0"></span>y<span class="_ _0"></span>,<span class="_ _8"> </span>the<span class="_"> </span>sixth<span class="_ _8"> </span>ANFIS<span class="_"> </span>classi&#64257;er<span class="_ _8"> </span>(combining<span class="_ _1"> </span>ANFIS)<span class="_ _8"> </span>was<span class="_"> </span>trained<span class="_ _8"> </span>using</div><div class="t m0 x13 h9 y17 ff1 fs5 fc0 sc0 ls0 ws0">the<span class="_ _6"> </span>outputs<span class="_ _6"> </span>of<span class="_ _6"> </span>the<span class="_ _6"> </span>&#64257;ve<span class="_ _6"> </span>ANFIS<span class="_ _6"> </span>classi&#64257;ers<span class="_ _6"> </span>as<span class="_ _6"> </span>input<span class="_ _7"> </span>data.<span class="_ _6"> </span>The<span class="_ _6"> </span>proposed<span class="_ _6"> </span>ANFIS<span class="_ _6"> </span>model<span class="_ _7"> </span>combined<span class="_ _6"> </span>the<span class="_ _6"> </span>neural<span class="_ _6"> </span>network<span class="_ _6"> </span>adaptiv<span class="_ _0"></span>e<span class="_ _6"> </span>capabilities<span class="_ _6"> </span>and</div><div class="t m0 x13 h9 y18 ff1 fs5 fc0 sc0 ls0 ws0">the<span class="_ _1"> </span>fuzzy<span class="_ _8"> </span>logic<span class="_"> </span>qualitati<span class="_ _0"></span>ve<span class="_ _1"> </span>approach.<span class="_ _1"> </span>Some<span class="_ _8"> </span>conclusions<span class="_"> </span>concerning<span class="_ _8"> </span>the<span class="_"> </span>saliency<span class="_ _8"> </span>of<span class="_"> </span>features<span class="_ _8"> </span>on<span class="_"> </span>classi&#64257;cation<span class="_ _8"> </span>of<span class="_"> </span>the<span class="_ _8"> </span>EEG<span class="_"> </span>signals<span class="_ _8"> </span>were<span class="_"> </span>obtained</div><div class="t m0 x13 h9 y19 ff1 fs5 fc0 sc0 ls0 ws0">through<span class="_ _7"> </span>analysis<span class="_ _9"> </span>of<span class="_ _7"> </span>the<span class="_ _9"> </span>ANFIS.<span class="_ _7"> </span>The<span class="_ _9"> </span>performance<span class="_ _7"> </span>of<span class="_ _9"> </span>the<span class="_ _7"> </span>ANFIS<span class="_ _9"> </span>model<span class="_ _7"> </span>was<span class="_ _9"> </span>e<span class="_ _0"></span>valuated<span class="_ _7"> </span>in<span class="_ _9"> </span>terms<span class="_ _7"> </span>of<span class="_ _9"> </span>training<span class="_ _7"> </span>performance<span class="_ _9"> </span>and<span class="_ _7"> </span>classi&#64257;cation</div><div class="t m0 x13 h9 y1a ff1 fs5 fc0 sc0 ls0 ws0">accuracies<span class="_"> </span>and<span class="_"> </span>the<span class="_"> </span>results<span class="_"> </span>con&#64257;rmed<span class="_"> </span>that<span class="_"> </span>the<span class="_"> </span>proposed<span class="_"> </span>ANFIS<span class="_"> </span>model<span class="_"> </span>has<span class="_"> </span>potential<span class="_"> </span>in<span class="_"> </span>classifying<span class="_"> </span>the<span class="_"> </span>EEG<span class="_"> </span>signals.</div><div class="t m0 x13 h9 y1b ff1 fs5 fc0 sc0 ls0 ws0">&#169;<span class="_"> </span>2005<span class="_"> </span>Elsevier<span class="_"> </span>B.V<span class="_ _a"></span>.<span class="_"> </span>All<span class="_"> </span>rights<span class="_"> </span>reserved.</div><div class="t m0 x13 h2 y1c ff4 fs0 fc0 sc0 ls0 ws0">K<span class="_ _0"></span>eywor<span class="_ _0"></span>ds:<span class="_ _b"> </span><span class="ff1">Adaptiv<span class="_ _0"></span>e<span class="_"> </span>neuro-fuzzy<span class="_"> </span>inference<span class="_"> </span>system<span class="_"> </span>(ANFIS);<span class="_"> </span>Fuzzy<span class="_"> </span>logic;<span class="_"> </span>W<span class="_ _0"></span>a<span class="_ _0"></span>velet<span class="_"> </span>transform;<span class="_"> </span>Electroencephalogram<span class="_"> </span>(EEG)<span class="_"> </span>signals</span></div><div class="t m0 x13 ha y1d ff5 fs3 fc0 sc0 ls0 ws0">1.<span class="_ _c"> </span>Introduction</div><div class="t m0 x15 h5 y1e ff1 fs3 fc0 sc0 ls0 ws0">The<span class="_ _d"> </span>electroencephalogram<span class="_ _d"> </span>(EEG)<span class="_ _d"> </span>signal<span class="_ _d"> </span>is<span class="_ _d"> </span>widely<span class="_ _d"> </span>used</div><div class="t m0 x13 h5 y1f ff1 fs3 fc0 sc0 ls2 ws0">clinically<span class="_ _e"> </span>to<span class="_ _e"> </span>in<span class="_ _0"></span>vestigate<span class="_ _b"> </span>brain<span class="_ _e"> </span>disorders.<span class="_ _e"> </span>The<span class="_ _e"> </span>study<span class="_ _e"> </span>of<span class="_ _e"> </span>the</div><div class="t m0 x13 h5 y20 ff1 fs3 fc0 sc0 ls0 ws0">brain<span class="_ _1"> </span>electrical<span class="_ _1"> </span>activity<span class="_ _2"></span>,<span class="_ _1"> </span>through<span class="_ _1"> </span>the<span class="_ _1"> </span>electroencephalographic</div><div class="t m0 x13 h5 y21 ff1 fs3 fc0 sc0 ls0 ws0">records,<span class="_ _9"> </span>is<span class="_ _d"> </span>one<span class="_ _9"> </span>of<span class="_ _9"> </span>the<span class="_ _d"> </span>most<span class="_ _9"> </span>important<span class="_ _d"> </span>tools<span class="_ _9"> </span>for<span class="_ _9"> </span>the<span class="_ _d"> </span>diagno-</div><div class="t m0 x13 h5 y22 ff1 fs3 fc0 sc0 ls0 ws0">sis<span class="_ _7"> </span>of<span class="_ _9"> </span>neurological<span class="_ _7"> </span>diseases<span class="_ _9"> </span>(<span class="fc1">Adeli<span class="_ _7"> </span>et<span class="_ _9"> </span>al.,<span class="_ _7"> </span>2003;<span class="_ _9"> </span>Hazarika<span class="_ _7"> </span>et</span></div><div class="t m0 x13 h5 y23 ff1 fs3 fc1 sc0 ls0 ws0">al.,<span class="_ _b"> </span>1997;<span class="_ _b"> </span>Rosso<span class="_ _b"> </span>et<span class="_ _e"> </span>al.,<span class="_ _b"> </span>2004<span class="fc0">).<span class="_ _b"> </span>Large<span class="_ _b"> </span>amounts<span class="_ _b"> </span>of<span class="_ _b"> </span>data<span class="_ _b"> </span>are</span></div><div class="t m0 x13 h5 y24 ff1 fs3 fc0 sc0 ls0 ws0">generated<span class="_ _1"> </span>by<span class="_"> </span>EEG<span class="_ _8"> </span>monitoring<span class="_"> </span>systems<span class="_ _1"> </span>for<span class="_ _1"> </span>electroencephalo-</div><div class="t m0 x13 h5 y25 ff1 fs3 fc0 sc0 ls0 ws0">graphic<span class="_ _d"> </span>changes,<span class="_ _b"> </span>and<span class="_ _d"> </span>their<span class="_ _d"> </span>complete<span class="_ _b"> </span>visual<span class="_ _d"> </span>analysis<span class="_ _d"> </span>is<span class="_ _b"> </span>not</div><div class="t m0 x13 h5 y26 ff1 fs3 fc0 sc0 ls0 ws0">routinely<span class="_ _d"> </span>possible.<span class="_ _9"> </span>Computers<span class="_ _d"> </span>have<span class="_ _9"> </span>long<span class="_ _d"> </span>been<span class="_ _d"> </span>proposed<span class="_ _d"> </span>to</div><div class="t m0 x13 h5 y27 ff1 fs3 fc0 sc0 ls0 ws0">solve<span class="_ _1"> </span>this<span class="_"> </span>problem<span class="_ _1"> </span>and<span class="_ _1"> </span>thus,<span class="_"> </span>automated<span class="_ _1"> </span>systems<span class="_"> </span>to<span class="_ _1"> </span>recognize</div><div class="t m0 x13 h5 y28 ff1 fs3 fc0 sc0 ls0 ws0">electroencephalographic<span class="_ _6"> </span>changes<span class="_ _7"> </span>have<span class="_"> </span>been<span class="_ _7"> </span>under<span class="_"> </span>study<span class="_ _7"> </span>for</div><div class="t m0 x13 h5 y29 ff1 fs3 fc0 sc0 ls0 ws0">sev<span class="_ _0"></span>eral<span class="_ _9"> </span>years<span class="_ _d"> </span>(<span class="fc1">Glov<span class="_ _0"></span>er<span class="_ _d"> </span>et<span class="_ _9"> </span>al.,<span class="_ _d"> </span>1989;<span class="_ _9"> </span>Gabor<span class="_ _d"> </span>and<span class="_ _9"> </span>Seyal,<span class="_ _9"> </span>1992;</span></div><div class="t m0 x13 h5 y2a ff1 fs3 fc1 sc0 ls2 ws0">W<span class="_ _2"></span>ebber<span class="_ _b"> </span>et<span class="_ _e"> </span>al.,<span class="_ _b"> </span>1993;<span class="_ _e"> </span>Nigam<span class="_ _b"> </span>and<span class="_ _e"> </span>Graupe,<span class="_ _b"> </span>2004<span class="fc0 ls0">).<span class="_ _b"> </span>There<span class="_ _e"> </span>is</span></div><div class="t m0 x13 h5 y2b ff1 fs3 fc0 sc0 ls0 ws0">a<span class="_ _e"> </span>strong<span class="_ _e"> </span>demand<span class="_ _e"> </span>for<span class="_ _f"> </span>the<span class="_ _e"> </span>dev<span class="_ _0"></span>elopment<span class="_ _e"> </span>of<span class="_ _f"> </span>such<span class="_ _e"> </span>automated</div><div class="t m0 x13 h5 y2c ff1 fs3 fc0 sc0 ls0 ws0">devices,<span class="_ _8"> </span>due<span class="_"> </span>to<span class="_ _1"> </span>the<span class="_ _1"> </span>increased<span class="_"> </span>use<span class="_ _1"> </span>of<span class="_ _1"> </span>prolonged<span class="_"> </span>and<span class="_ _1"> </span>long-term</div><div class="t m0 x16 hb y2d ff3 fs4 fc0 sc0 ls0 ws0">&#8727;</div><div class="t m0 x15 h2 y2e ff1 fs0 fc0 sc0 ls0 ws0">Corresponding<span class="_"> </span>author<span class="_ _0"></span>.<span class="_"> </span>T<span class="_ _0"></span>el.:<span class="_"> </span>+90<span class="_"> </span>312<span class="_"> </span>212<span class="_"> </span>3976;<span class="_"> </span>fax:<span class="_"> </span>+90<span class="_"> </span>312<span class="_"> </span>212<span class="_"> </span>0059.</div><div class="t m0 x15 h2 y2f ff4 fs0 fc0 sc0 ls0 ws0">E-mail<span class="_ _1"> </span>addr<span class="_ _0"></span>ess:<span class="_ _1"> </span><span class="ff1 ls3">iguler@gazi.edu.tr<span class="_"> </span>(</span></div><div class="t m0 x17 h2 y30 ff1 fs0 fc0 sc0 ls0 ws0">&#729;</div><div class="t m0 x17 h2 y2f ff1 fs0 fc0 sc0 ls0 ws0">I.<span class="_"> </span>G</div><div class="t m0 x18 h2 y31 ff1 fs0 fc0 sc0 ls0 ws0">&#168;</div><div class="t m0 x19 h2 y2f ff1 fs0 fc0 sc0 ls0 ws0">uler).</div><div class="t m0 x1a h5 y32 ff1 fs3 fc0 sc0 ls0 ws0">video<span class="_ _1"> </span>EEG<span class="_ _1"> </span>recordings<span class="_"> </span>for<span class="_ _8"> </span>proper<span class="_ _1"> </span>ev<span class="_ _0"></span>aluation<span class="_ _1"> </span>and<span class="_"> </span>treatment<span class="_ _8"> </span>of</div><div class="t m0 x1a h5 y33 ff1 fs3 fc0 sc0 ls0 ws0">neurological<span class="_ _1"> </span>diseases<span class="_"> </span>and<span class="_ _1"> </span>prev<span class="_ _0"></span>ention<span class="_"> </span>of<span class="_ _1"> </span>the<span class="_"> </span>possibility<span class="_ _1"> </span>of<span class="_ _1"> </span>the</div><div class="t m0 x1a h5 y34 ff1 fs3 fc0 sc0 ls0 ws0">analyst<span class="_ _7"> </span>missing<span class="_ _7"> </span>(or<span class="_ _7"> </span>misreading)<span class="_ _9"> </span>information<span class="_"> </span>(<span class="fc1">W<span class="_ _0"></span>ebber<span class="_ _6"> </span>et<span class="_ _9"> </span>al.,</span></div><div class="t m0 x1a h5 y35 ff1 fs3 fc1 sc0 ls0 ws0">1993<span class="fc0">).</span></div><div class="t m0 x1b h5 y36 ff1 fs3 fc0 sc0 ls0 ws0">Abnormalities<span class="_ _b"> </span>in<span class="_ _b"> </span>the<span class="_ _b"> </span>EEG<span class="_ _b"> </span>in<span class="_ _b"> </span>serious<span class="_ _b"> </span>psychiatric<span class="_ _b"> </span>disor-</div><div class="t m0 x1a h5 y37 ff1 fs3 fc0 sc0 ls0 ws0">ders<span class="_ _b"> </span>are<span class="_ _e"> </span>at<span class="_ _b"> </span>times<span class="_ _b"> </span>too<span class="_ _e"> </span>subtle<span class="_ _b"> </span>to<span class="_ _e"> </span>be<span class="_ _b"> </span>detected<span class="_ _e"> </span>using<span class="_ _b"> </span>con<span class="_ _0"></span>ven-</div><div class="t m0 x1a h5 y38 ff1 fs3 fc0 sc0 ls0 ws0">tional<span class="_ _e"> </span>techniques.<span class="_ _f"> </span>Such<span class="_ _e"> </span>techniques<span class="_ _f"> </span>work<span class="_ _e"> </span>by<span class="_ _e"> </span>transforming</div><div class="t m0 x1a h5 y39 ff1 fs3 fc0 sc0 ls0 ws0">the<span class="_ _7"> </span>mostly<span class="_ _9"> </span>qualitati<span class="_ _0"></span>ve<span class="_ _7"> </span>diagnostic<span class="_ _7"> </span>criteria<span class="_ _9"> </span>into<span class="_ _7"> </span>a<span class="_ _7"> </span>more<span class="_ _9"> </span>objec-</div><div class="t m0 x1a h5 y3a ff1 fs3 fc0 sc0 ls0 ws0">tiv<span class="_ _0"></span>e<span class="_ _b"> </span>quantitati<span class="_ _0"></span>ve<span class="_ _d"> </span>signal<span class="_ _b"> </span>feature<span class="_ _d"> </span>classi&#64257;cation<span class="_ _b"> </span>problem.<span class="_ _b"> </span>The</div><div class="t m0 x1a h5 y3b ff1 fs3 fc0 sc0 ls0 ws0">techniques<span class="_ _f"> </span>hav<span class="_ _0"></span>e<span class="_ _f"> </span>been<span class="_ _f"> </span>used<span class="_ _f"> </span>to<span class="_ _f"> </span>address<span class="_ _c"> </span>this<span class="_ _f"> </span>problem<span class="_ _f"> </span>such</div><div class="t m0 x1a h5 y3c ff1 fs3 fc0 sc0 ls0 ws0">as<span class="_ _d"> </span>the<span class="_ _b"> </span>analysis<span class="_ _b"> </span>of<span class="_ _d"> </span>EEG<span class="_ _b"> </span>signals<span class="_ _b"> </span>for<span class="_ _d"> </span>detection<span class="_ _b"> </span>of<span class="_ _d"> </span>electroen-</div><div class="t m0 x1a h5 y3d ff1 fs3 fc0 sc0 ls0 ws0">cephalographic<span class="_ _9"> </span>changes<span class="_ _9"> </span>using<span class="_ _9"> </span>the<span class="_ _9"> </span>autocorrelation<span class="_ _9"> </span>function,</div><div class="t m0 x1a h5 y3e ff1 fs3 fc0 sc0 ls0 ws0">frequency<span class="_ _f"> </span>domain<span class="_ _c"> </span>features,<span class="_ _f"> </span>time<span class="_ _c"> </span>frequency<span class="_ _f"> </span>analysis,<span class="_ _c"> </span>and</div><div class="t m0 x1a h5 y3f ff1 fs3 fc0 sc0 ls0 ws0">wa<span class="_ _0"></span>velet<span class="_"> </span>transform<span class="_ _7"> </span>(WT)<span class="_ _7"> </span>(<span class="fc1">Adeli<span class="_ _7"> </span>et<span class="_ _7"> </span>al.,<span class="_ _7"> </span>2003;<span class="_ _6"> </span>Hazarika<span class="_ _7"> </span>et<span class="_ _7"> </span>al.,</span></div><div class="t m0 x1a h5 y40 ff1 fs3 fc1 sc0 ls0 ws0">1997;<span class="_"> </span>Rosso<span class="_"> </span>et<span class="_"> </span>al.,<span class="_"> </span>2004;<span class="_"> </span>Glover<span class="_"> </span>et<span class="_"> </span>al.,<span class="_"> </span>1989<span class="fc0">).<span class="_"> </span>The<span class="_"> </span>results<span class="_"> </span>of</span></div><div class="t m0 x1a h5 y41 ff1 fs3 fc0 sc0 ls0 ws0">the<span class="_ _1"> </span>studies<span class="_"> </span>in<span class="_ _1"> </span>the<span class="_"> </span>literature<span class="_ _1"> </span>hav<span class="_ _0"></span>e<span class="_"> </span>demonstrated<span class="_ _1"> </span>that<span class="_ _1"> </span>the<span class="_"> </span>WT<span class="_ _1"> </span>is</div><div class="t m0 x1a h5 y42 ff1 fs3 fc0 sc0 ls0 ws0">the<span class="_ _1"> </span>most<span class="_"> </span>promising<span class="_ _1"> </span>method<span class="_"> </span>to<span class="_ _1"> </span>extract<span class="_"> </span>features<span class="_ _1"> </span>from<span class="_"> </span>the<span class="_ _1"> </span>EEG</div><div class="t m0 x1a h5 y43 ff1 fs3 fc0 sc0 ls0 ws0">signals<span class="_ _1"> </span>(<span class="fc1">Adeli<span class="_ _1"> </span>et<span class="_ _1"> </span>al.,<span class="_ _1"> </span>2003;<span class="_ _1"> </span>Hazarika<span class="_ _1"> </span>et<span class="_ _1"> </span>al.,<span class="_ _1"> </span>1997;<span class="_ _1"> </span>Rosso<span class="_ _1"> </span>et<span class="_"> </span>al.,</span></div><div class="t m0 x1a h5 y44 ff1 fs3 fc1 sc0 ls0 ws0">2004<span class="fc0">).<span class="_"> </span>In<span class="_"> </span>this<span class="_ _6"> </span>respect,<span class="_ _7"> </span>in<span class="_"> </span>the<span class="_"> </span>present<span class="_"> </span>study<span class="_ _7"> </span>the<span class="_"> </span>WT<span class="_"> </span>was<span class="_"> </span>used</span></div><div class="t m0 x1a h5 y45 ff1 fs3 fc0 sc0 ls0 ws0">for<span class="_"> </span>feature<span class="_"> </span>extraction<span class="_"> </span>from<span class="_"> </span>the<span class="_"> </span>EEG<span class="_"> </span>signals.</div><div class="t m0 x13 h2 y46 ff1 fs0 fc0 sc0 ls0 ws0">0165-0270/$<span class="_"> </span>&#8211;<span class="_"> </span>see<span class="_"> </span>front<span class="_"> </span>matter<span class="_"> </span>&#169;<span class="_"> </span>2005<span class="_"> </span>Elsevier<span class="_"> </span>B.V<span class="_ _a"></span>.<span class="_"> </span>All<span class="_"> </span>rights<span class="_"> </span>reserved.</div><div class="t m0 x13 h2 y47 ff1 fs0 fc0 sc0 ls0 ws0">doi:10.1016/j.jneumeth.2005.04.013</div><div class="t m0 xf h2 y48 ff1 fs0 fc0 sc0 ls0 ws0">NSM-3945;<span class="_ _10"> </span>No.<span class="_"> </span>of<span class="_"> </span>Pages<span class="_"> </span>9</div><a class="l" rel='nofollow' onclick='return false;'><div class="d m1"></div></a><a class="l" rel='nofollow' onclick='return false;'><div class="d m1"></div></a><a class="l" rel='nofollow' onclick='return false;'><div class="d m1"></div></a><a class="l" rel='nofollow' onclick='return false;'><div class="d m1"></div></a><a class="l" rel='nofollow' onclick='return false;'><div class="d m1"></div></a><a class="l" rel='nofollow' onclick='return false;'><div class="d m1"></div></a><a class="l" rel='nofollow' onclick='return false;'><div class="d m1"></div></a><a class="l" rel='nofollow' onclick='return false;'><div class="d m1"></div></a></div><div class="pi" data-data='{"ctm":[1.613445,0.000000,0.000000,1.613445,-67.764706,-72.605042]}'></div></div> </body> </html>
评论
    相关推荐
    • cv2rababw.tar.gz
      research paper on image processing
    • matlab精度检验代码-deep-multi-view-feature-learning:深入的多视图功能学习
      通过分析癫痫患者的脑电图(EEG)信号,可以监测他们的病情,以便及时发现并干预癫痫发作。 在癫痫研究中,使用适当的方法获得有效特征对检测准确性非常重要。 为了获得能够产生更好检测结果的特征,本文提出了一种...
    • getmswpfeat.rar
      wavelet transform features
    • VIHAROS_Neuro-fuzzy_IMEKO_TC10_Conference_2014_we
      Survey on Neuro-Fuzzy Systems and their Applications in Technical Diagnostics Neural Networks
    • Active-Segment-Selection-Method-in-EEG-Classifica
      Active Segment Selection Method in EEG Classification Using Fractal Features
    • Fuzzy and Neuro-Fuzzy Systems in Medicine
      Chapter 3—Brain State Identification and Forecasting of Acute Pathology Using Unsupervised Fuzzy Clustering of EEG Temporal Patterns 1. Introduction 2. Background 2.1 The Electroencephalogram ...
    • 基于CI_HMM的运动想象脑电信号分类_孟明.rar
      基于CI_HMM的运动想象脑电信号分类_孟明
    • codesforimageprocessing.rar
      实现简单图像处理,包括256色转灰度图、Hough变换、Walsh变换、中值滤波、二值化变换、亮度增减、傅立叶变换、反色、取对数、取指数、图像平移、图像旋转、图像细化、图像缩放、图像镜像、均值滤波、对比度拉伸、拉普拉斯锐化(边缘检测)、方块编码、梯度锐化、灰度均衡、直方图均衡、离散余弦变换、维纳滤波处理、逆滤波处理、阈值变换、高斯平滑。
    • matlab.rar
      基于MATLAB-GUI图形界面的数字图像处理软件 本系统设计基于GUI图形界面,用matlab语言编写代码,实现功能包括图象的读取、存储、显示、直方图均衡化、阈值化、小波分解、小波重构、加噪、去噪、平滑、锐化、边缘检测、图像分割等
    • OPENCV_SIFT_VC6.rar
      基于OPENCV的SIFT特征提取与匹配算法。包含完整的从图像高斯金字塔、DOG、空间极值点提取、关键点描述、KDtree匹配等关键步骤的全部函数实现,对全面深入理解Lowe的SIFT算法有莫大帮助。程序运行前须安装(1)OpenCV: http://opencvlibrary.sourceforge.net (2)SIFT: http://web.engr.oregonstate.edu/~hess/index.html,并配置其环境参数。