{"id":4727,"date":"2025-11-16T23:13:33","date_gmt":"2025-11-16T23:13:33","guid":{"rendered":"https:\/\/172-234-197-23.ip.linodeusercontent.com\/?page_id=4727"},"modified":"2025-11-16T23:13:33","modified_gmt":"2025-11-16T23:13:33","slug":"hierarchical-classifiers-strictly-dominate-flat-ensembles-in-digital-modulation-recognition","status":"publish","type":"page","link":"https:\/\/neurosphere-2.tail52f848.ts.net\/wordpress\/?page_id=4727","title":{"rendered":"Hierarchical Classifiers Strictly Dominate Flat Ensembles in Digital Modulation Recognition"},"content":{"rendered":"\n<div data-wp-interactive=\"core\/file\" class=\"wp-block-file\"><object data-wp-bind--hidden=\"!state.hasPdfPreview\" hidden class=\"wp-block-file__embed\" data=\"https:\/\/neurosphere-2.tail52f848.ts.net\/wordpress\/wp-content\/uploads\/2025\/11\/Hierarchical-vs-Flat-Ensembles-in-RF-Modulation-Classification-Spectrcyde.pdf\" type=\"application\/pdf\" style=\"width:100%;height:600px\" aria-label=\"Embed of Hierarchical vs Flat Ensembles in RF Modulation Classification Spectrcyde.\"><\/object><a id=\"wp-block-file--media-f02353d3-4bce-4c18-8223-50b73a7147f7\" href=\"https:\/\/neurosphere-2.tail52f848.ts.net\/wordpress\/wp-content\/uploads\/2025\/11\/Hierarchical-vs-Flat-Ensembles-in-RF-Modulation-Classification-Spectrcyde.pdf\">Hierarchical vs Flat Ensembles in RF Modulation Classification Spectrcyde<\/a><a href=\"https:\/\/neurosphere-2.tail52f848.ts.net\/wordpress\/wp-content\/uploads\/2025\/11\/Hierarchical-vs-Flat-Ensembles-in-RF-Modulation-Classification-Spectrcyde.pdf\" class=\"wp-block-file__button wp-element-button\" download aria-describedby=\"wp-block-file--media-f02353d3-4bce-4c18-8223-50b73a7147f7\">Download<\/a><\/div>\n\n\n\n<p class=\"wp-block-paragraph\">We quantify when a parent<br>HierarchicalMLClassifier beats a flat ensemble and<br>vice versa. We report per-class win profiles, confusion<br>deltas, and latency trade-offs, with code paths mapped to<br>super().classify_signal() vs the ensemble voting block.<br>We find a hierarchical classifier is never worse than a flat ensemble<br>of identical capacity on RML2016.10a, with strict gains on higher order modulations and at high SNR.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">All results are on the standard<br>RML2016.10a dataset [1], filtered to BPSK, QPSK, 8PSK,<br>16QAM, 64QAM, yielding 20,000 test examples (4,000 per<br>class) evenly distributed across \u221210 to +18,dB SNR. We<br>instrument the classifier to expose both paths in a single pass.<br>For each signal, we record: (1) hierarchical prediction, (2)<br>flat-ensemble prediction, confidences, and latencies. Per-class<br>wins count cases where one path is correct and the other is<br>not.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\">VI. REPRODUCIBILITY<br>Run make in paper_Hier_vs_Flat_Ensembles\/.<br>Provide your dataset and model:<br>DATASET_FUNC=&#8221;my_dataset_module:iter_eva<br>l&#8221;CLASSIFIER_SPEC=&#8221;ensemble_ml_classifier:<br>EnsembleMLClassifier&#8221;makeeval >> <a href=\"https:\/\/github.com\/bgilbert1984\/Hierarchical-vs-Flat-Ensembles-in-RF-Modulation-Classification\">bgilbert1984\/Hierarchical-vs-Flat-Ensembles-in-RF-Modulation-Classification: We quantify when a parent HierarchicalMLClassifier beats a flat ensemble and vice versa. We report per-class win profiles, confusion deltas, and latency trade-offs, with code paths mapped to super().classify_signal() vs the ensemble voting block.<\/a><\/h3>\n\n\n\n<figure class=\"wp-block-image size-full\"><a href=\"https:\/\/gemini.google.com\/share\/3de3016028f6\"><img loading=\"lazy\" decoding=\"async\" width=\"801\" height=\"927\" src=\"https:\/\/neurosphere-2.tail52f848.ts.net\/wordpress\/wp-content\/uploads\/2025\/11\/image-43.png\" alt=\"\" class=\"wp-image-4729\" srcset=\"https:\/\/neurosphere-2.tail52f848.ts.net\/wordpress\/wp-content\/uploads\/2025\/11\/image-43.png 801w, https:\/\/neurosphere-2.tail52f848.ts.net\/wordpress\/wp-content\/uploads\/2025\/11\/image-43-259x300.png 259w, https:\/\/neurosphere-2.tail52f848.ts.net\/wordpress\/wp-content\/uploads\/2025\/11\/image-43-768x889.png 768w\" sizes=\"auto, (max-width: 801px) 100vw, 801px\" \/><\/a><\/figure>\n","protected":false},"excerpt":{"rendered":"<p>We quantify when a parentHierarchicalMLClassifier beats a flat ensemble andvice versa. We report per-class win profiles, confusiondeltas, and latency trade-offs, with code paths mapped tosuper().classify_signal() vs the ensemble voting block.We find a hierarchical classifier is never worse than a flat ensembleof identical capacity on RML2016.10a, with strict gains on higher order modulations and at high&hellip;&nbsp;<\/p>\n","protected":false},"author":2,"featured_media":4729,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"neve_meta_sidebar":"","neve_meta_container":"","neve_meta_enable_content_width":"","neve_meta_content_width":0,"neve_meta_title_alignment":"","neve_meta_author_avatar":"","neve_post_elements_order":"","neve_meta_disable_header":"","neve_meta_disable_footer":"","neve_meta_disable_title":"","footnotes":""},"class_list":["post-4727","page","type-page","status-publish","has-post-thumbnail","hentry"],"_links":{"self":[{"href":"https:\/\/neurosphere-2.tail52f848.ts.net\/wordpress\/index.php?rest_route=\/wp\/v2\/pages\/4727","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/neurosphere-2.tail52f848.ts.net\/wordpress\/index.php?rest_route=\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/neurosphere-2.tail52f848.ts.net\/wordpress\/index.php?rest_route=\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/neurosphere-2.tail52f848.ts.net\/wordpress\/index.php?rest_route=\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/neurosphere-2.tail52f848.ts.net\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=4727"}],"version-history":[{"count":0,"href":"https:\/\/neurosphere-2.tail52f848.ts.net\/wordpress\/index.php?rest_route=\/wp\/v2\/pages\/4727\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/neurosphere-2.tail52f848.ts.net\/wordpress\/index.php?rest_route=\/wp\/v2\/media\/4729"}],"wp:attachment":[{"href":"https:\/\/neurosphere-2.tail52f848.ts.net\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=4727"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}