BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:US/Pacific BEGIN:DAYLIGHT DTSTART:20210314T030000 TZOFFSETFROM:-0800 TZOFFSETTO:-0700 RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3 TZNAME:PDT END:DAYLIGHT BEGIN:STANDARD DTSTART:20211107T010000 TZOFFSETFROM:-0700 TZOFFSETTO:-0800 RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11 TZNAME:PST END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20211023T224934Z UID:8465B121-4F7F-497C-9A22-34DA44E949C8 DTSTART;TZID=US/Pacific:20211021T180000 DTEND;TZID=US/Pacific:20211021T184500 DESCRIPTION:A classification fusion technique using feature extraction and fuzzy logic known as Feature Object Extraction is developed and applied to hypothesis-based decision problems such as cyber security and GPS attacks . The Feature Object Extraction approach is not a probabilistic approach t hat determines the odds of one hypothesis over another\, e.g.\, GPS Jammin g vs. Dropouts. Instead\, evidence to support or refute each hypothesis is accrued to create a degree of certainty. The feature-aided object extract ion technique was initially developed for the target classification proble m. Unlike probabilistic methods\, evidence that supports one hypothesis do es not necessarily refute the probability of another hypothesis. For examp le\, the U.S. Mint recently was overwhelmed during the opening of sales fo r limited edition coin sets. The evidence of the high volume on the site c ould indicate a denial-of-service attack or large numbers of customers. Th e relationship to the availability of limited-edition coins supports expec ted high traffic. It does not\, however\, refute a denial-of-service attac k\, as actually has occurred. Feature Object Extraction also allows for er roneous information and can recover where probabilistically a class can el iminated without the ability to recover. In one application\, cybersecurit y is interpreted as a sensor fusion problem that includes various alternat ive techniques into the solution space. GPS security\, where various jammi ng and spoofing techniques are possibilities\, the ability to discern the type of attacks that are possible has been shown to be well suited for thi s evidence accrual technique.\n\nPost event: A recording (that has not bee n nicely edited) of this presentation is available here: [Link to Zoom Rec ording](https://abet-org.zoom.us/rec/share/risgLpg423ukiI5CTW3GAVT2XI0Eh0Q TNB4jnyQiez33S5yu8iIC4q5MRVdNGU7s.IYCNqpaBYhtbeI2J?startTime=1634863951000 )\n\nCo-sponsored by: San Diego Chapter of the Aerospace Electronic System s Society\, Computer Chapter\, and Computational Intelligence Chapter\n\nS peaker(s): Prof. Kathleen A. Kramer\, \n\nAgenda: \n6:00pm pacific/9:00 pm eastern time - lecture begins\n\n(Virtual Meeting)\, Connection informati on will be supplied to all preregistered.\, San Diego\, California\, Unite d States\, Virtual: https://events.vtools.ieee.org/m/282204 LOCATION:(Virtual Meeting)\, Connection information will be supplied to all preregistered.\, San Diego\, California\, United States\, Virtual: https: //events.vtools.ieee.org/m/282204 ORGANIZER:scstubberud@ieee.org SEQUENCE:12 SUMMARY:Feature Object Extraction – Fusing Evidence\, Not Rolling the Die URL;VALUE=URI:https://events.vtools.ieee.org/m/282204 X-ALT-DESC:Description: <br /><p>A classification fusion technique using fe ature extraction and fuzzy logic known as Feature Object Extraction is dev eloped and applied to hypothesis-based decision problems such as cyber sec urity and GPS attacks.&nbsp\; The Feature Object Extraction approach is no t a probabilistic approach that determines the odds of one hypothesis over another\, e.g.\, GPS Jamming vs. Dropouts.&nbsp\; Instead\, evidence to s upport or refute each hypothesis is accrued to create a degree of certaint y. The feature-aided object extraction technique was initially developed f or the target classification problem.&nbsp\; Unlike probabilistic methods\ , evidence that supports one hypothesis does not necessarily refute the pr obability of another hypothesis.&nbsp\; For example\, the U.S. Mint recent ly was overwhelmed during the opening of sales for limited edition coin se ts.&nbsp\; The evidence of the high volume on the site could indicate a de nial-of-service attack or large numbers of customers.&nbsp\; The relations hip to the availability of limited-edition coins supports expected high tr affic.&nbsp\; It does not\, however\, refute a denial-of-service attack\, as actually has occurred.&nbsp\; &nbsp\;Feature Object Extraction also all ows for erroneous information and can recover where probabilistically a cl ass can eliminated without the ability to recover. In one application\, cy bersecurity is interpreted as a sensor fusion problem that includes variou s alternative techniques into the solution space. GPS security\, where var ious jamming and spoofing techniques are possibilities\, the ability to di scern the type of attacks that are possible has been shown to be well suit ed for this evidence accrual technique.</p>\n<p><em>Post event: &nbsp\;A r ecording (that has not been nicely edited) of this presentation is availab le here: <a href="https://abet-org.zoom.us/rec/share/risgLpg423ukiI5CTW3GA VT2XI0Eh0QTNB4jnyQiez33S5yu8iIC4q5MRVdNGU7s.IYCNqpaBYhtbeI2J?startTime=163 4863951000">Link to Zoom Recording</a></em></p><br /><br />Agenda: <br />< p>6:00pm pacific/9:00 pm eastern time - lecture begins</p>\n<p>&nbsp\;</p> \n<p>&nbsp\;</p> END:VEVENT END:VCALENDAR