BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:Europe/Berlin BEGIN:DAYLIGHT DTSTART:20260329T030000 TZOFFSETFROM:+0100 TZOFFSETTO:+0200 RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3 TZNAME:CEST END:DAYLIGHT BEGIN:STANDARD DTSTART:20251026T020000 TZOFFSETFROM:+0200 TZOFFSETTO:+0100 RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10 TZNAME:CET END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20251208T173207Z UID:F47238FA-D2A6-4380-8706-9277CD2CAD4C DTSTART;TZID=Europe/Berlin:20251208T170000 DTEND;TZID=Europe/Berlin:20251208T183000 DESCRIPTION:The challenge of learning from imbalanced data is well-recognis ed\, as standard classification algorithms are often found to struggle wit h minority instances\, which may represent rare but critical events. Impro vements have been developed in both data pre-processing and Radial Basis F unction Networks (RBFNs). Feature selection has been enhanced by storing a nd combining multiple candidate solutions\, reducing overfitting and more reliably identifying relevant features. Oversampling has been refined to d etermine neighbourhoods and the number of synthetic instances automaticall y\, simplifying its use. RBFN classifiers have been designed incrementally \, with knowledge from simpler networks guiding the construction of more c omplex ones. These approaches have been shown to improve minority class re cognition and overall performance\, providing practical methods for tackli ng imbalanced data in real-world problems.\n\nSpeaker(s): Dr. Mario Dudjak \n\nVirtual: https://events.vtools.ieee.org/m/516224 LOCATION:Virtual: https://events.vtools.ieee.org/m/516224 ORGANIZER:alexandros.tanzanakis@fau.de SEQUENCE:21 SUMMARY:Webinar: Learning from imbalanced data using improved data pre-proc essing procedures and machine learning techniques URL;VALUE=URI:https://events.vtools.ieee.org/m/516224 X-ALT-DESC:Description: <br /><p>The challenge of learning from imbalanced data is well-recognised\, as standard classification algorithms are often found to struggle with minority instances\, which may represent rare but c ritical events. Improvements have been developed in both data pre-processi ng and Radial Basis Function Networks (RBFNs). Feature selection has been enhanced by storing and combining multiple candidate solutions\, reducing overfitting and more reliably identifying relevant features. Oversampling has been refined to determine neighbourhoods and the number of synthetic i nstances automatically\, simplifying its use. RBFN classifiers have been d esigned incrementally\, with knowledge from simpler networks guiding the c onstruction of more complex ones. These approaches have been shown to impr ove minority class recognition and overall performance\, providing practic al methods for tackling imbalanced data in real-world problems.</p> END:VEVENT END:VCALENDAR