<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8">
</head>
<body style="word-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;" class="">
Hey everyone,
<div class=""><br class="">
</div>
<div class="">I’m trying to work out why I am getting different decoding results using what I think to be rather equivalent pipelines.</div>
<div class=""><br class="">
</div>
<div class="">I am currently try to decode trials from my dataset after removing the first principal component. However, I’m getting drastically different results depending on how I do the component removal.</div>
<div class=""><br class="">
</div>
<div class="">If I follow what I imagine is the recommended method, I do this:</div>
<div class=""><br class="">
</div>
<div class="">
<div style="margin: 0px; font-stretch: normal; font-size: 11px; line-height: normal; font-family: Courier; min-height: 13px;" class="">
<br class="">
</div>
<div style="margin: 0px; font-stretch: normal; font-size: 11px; line-height: normal; font-family: Courier;" class="">
cfg = [];</div>
<div style="margin: 0px; font-stretch: normal; font-size: 11px; line-height: normal; font-family: Courier;" class="">
cfg.method = <span style="color: #aa04f9" class="">'pca'</span>;</div>
<div style="margin: 0px; font-stretch: normal; font-size: 11px; line-height: normal; font-family: Courier;" class="">
cfg.updatesens = <span style="color: rgb(170, 4, 249);" class="">'yes'</span>;</div>
<div style="margin: 0px; font-stretch: normal; font-size: 11px; line-height: normal; font-family: Courier;" class="">
comp = ft_componentanalysis(cfg, data);</div>
<div style="margin: 0px; font-stretch: normal; font-size: 11px; line-height: normal; font-family: Courier;" class="">
</div>
<div style="margin: 0px; font-stretch: normal; font-size: 11px; line-height: normal; font-family: Courier;" class="">
%remove component</div>
<div style="margin: 0px; font-stretch: normal; font-size: 11px; line-height: normal; font-family: Courier;" class="">
cfg = [];</div>
<div style="margin: 0px; font-stretch: normal; font-size: 11px; line-height: normal; font-family: Courier;" class="">
cfg.component = 1;</div>
<div style="margin: 0px; font-stretch: normal; font-size: 11px; line-height: normal; font-family: Courier;" class="">
data = ft_rejectcomponent(cfg,comp,data); %data to be decoded</div>
</div>
<div style="margin: 0px; font-stretch: normal; font-size: 11px; line-height: normal; font-family: Courier;" class="">
<br class="">
</div>
<div style="margin: 0px; font-stretch: normal; font-size: 11px; line-height: normal; font-family: Courier;" class="">
<br class="">
</div>
<div class="">However, I could instead just decode the components after removing the first, like this:</div>
<div class=""><br class="">
</div>
<div class="">
<div style="margin: 0px; font-stretch: normal; font-size: 11px; line-height: normal; font-family: Courier;" class="">
cfg = [];</div>
<div style="margin: 0px; font-stretch: normal; font-size: 11px; line-height: normal; font-family: Courier;" class="">
cfg.method = <span style="color: rgb(170, 4, 249);" class="">'pca'</span>;</div>
<div style="margin: 0px; font-stretch: normal; font-size: 11px; line-height: normal; font-family: Courier;" class="">
cfg.updatesens = <span style="color: rgb(170, 4, 249);" class="">'yes'</span>;</div>
<div style="margin: 0px; font-stretch: normal; font-size: 11px; line-height: normal; font-family: Courier;" class="">
comp = ft_componentanalysis(cfg, data);</div>
</div>
<div style="margin: 0px; font-stretch: normal; font-size: 11px; line-height: normal; font-family: Courier;" class="">
<br class="">
</div>
<div style="margin: 0px; font-stretch: normal; font-size: 11px; line-height: normal; font-family: Courier;" class="">
<div style="margin: 0px; font-stretch: normal; line-height: normal;" class=""> %remove component</div>
</div>
<div class="">
<div style="margin: 0px; font-stretch: normal; font-size: 11px; line-height: normal; font-family: Courier;" class="">
cfg = [];</div>
<div style="margin: 0px; font-stretch: normal; font-size: 11px; line-height: normal; font-family: Courier;" class="">
cfg.channel = comp.label(2:end);</div>
<div style="margin: 0px; font-stretch: normal; font-size: 11px; line-height: normal; font-family: Courier;" class="">
data = ft_selectdata(cfg,comp); %data to be decoded</div>
<div style="margin: 0px; font-stretch: normal; font-size: 11px; line-height: normal; font-family: Courier;" class="">
<br class="">
</div>
</div>
<div class=""><br class="">
</div>
<div class="">The first method (back projection) gives me results almost identical to that of the decoding of the full, original data - whereas the second method (decoding raw components) abolishes all successful decoding. </div>
<div class=""><br class="">
</div>
<div class="">I’m not sure what the technical difference is here, because in my mind the information contained in both datasets (components vs. back projected) is the same, so I’m not sure why one abolishes decoding but the other does not. As such, I’m not
sure which method is the correct one for my purposes of simply removing the first principal component prior to decoding.</div>
<div class=""><br class="">
</div>
<div class="">I appreciate any guidance or help,</div>
<div class="">Benjy</div>
</body>
</html>