This site has been permanently archived. This is a static copy provided by the University of Southampton.
--- abstract: "We study filter–based feature selection methods for classification of biomedical images. For feature selection, we use two filters — a relevance filter which measures usefulness of individual features for target prediction, and a redundancy filter, which measures similarity between features. As selection method that combines relevance and redundancy we try out a Hopfield network. We experimentally compare selection methods, running unitary redundancy and relevance filters, against a greedy algorithm with redundancy thresholds [9], the min-redundancy max-relevance integration [8,23,36], and our Hopfield network selection. We conclude that on the whole, Hopfield selection was one of the most successful methods, outperforming min-redundancy max-relevance when\r\nmore features are selected. " altloc: [] chapter: ~ commentary: ~ commref: ~ confdates: ~ conference: ~ confloc: ~ contact_email: ~ creators_id: [] creators_name: - family: Auffarth given: B. honourific: '' lineage: '' - family: Lopez given: M. honourific: '' lineage: '' - family: Cerquides given: J. honourific: '' lineage: '' date: 2008-07-17 date_type: published datestamp: 2010-10-18 11:03:10 department: ~ dir: disk0/00/00/70/61 edit_lock_since: ~ edit_lock_until: 0 edit_lock_user: ~ editors_id: [] editors_name: - family: Perner given: Petra honourific: '' lineage: '' eprint_status: archive eprintid: 7061 fileinfo: /style/images/fileicons/application_pdf.png;/7061/1/leipzip08.pdf full_text_status: public importid: ~ institution: ~ isbn: ~ ispublished: pub issn: ~ item_issues_comment: [] item_issues_count: 0 item_issues_description: [] item_issues_id: [] item_issues_reported_by: [] item_issues_resolved_by: [] item_issues_status: [] item_issues_timestamp: [] item_issues_type: [] keywords: 'feature selection, image features, pattern classification' lastmod: 2011-03-11 08:57:45 latitude: ~ longitude: ~ metadata_visibility: show note: ~ number: ~ pagerange: 16-31 pubdom: FALSE publication: 'Advances in data mining: medical applications, e-commerce, marketing, and theoretical aspects. LNAI 5077' publisher: Springer Heidelberg refereed: TRUE referencetext: ~ relation_type: [] relation_uri: [] reportno: ~ rev_number: 28 series: ~ source: ~ status_changed: 2010-10-18 11:03:10 subjects: - comp-sci-mach-learn - comp-sci-stat-model succeeds: ~ suggestions: ~ sword_depositor: ~ sword_slug: ~ thesistype: ~ title: Hopfield Networks in Relevance and Redundancy Feature Selection Applied to Classification of Biomedical High-Resolution Micro-CT Images type: bookchapter userid: 11278 volume: ~