BEGIN:VCALENDAR VERSION:2.0 PRODID:IEEE vTools.Events//EN CALSCALE:GREGORIAN BEGIN:VTIMEZONE TZID:America/New_York BEGIN:DAYLIGHT DTSTART:20250309T030000 TZOFFSETFROM:-0500 TZOFFSETTO:-0400 RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3 TZNAME:EDT END:DAYLIGHT BEGIN:STANDARD DTSTART:20251102T010000 TZOFFSETFROM:-0400 TZOFFSETTO:-0500 RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11 TZNAME:EST END:STANDARD END:VTIMEZONE BEGIN:VEVENT DTSTAMP:20250612T162637Z UID:6A2689D8-3486-4CD1-BD38-2357481B3AAF DTSTART;TZID=America/New_York:20250611T170000 DTEND;TZID=America/New_York:20250611T190000 DESCRIPTION:Please join the Boston IEEE Reliability Chapter for the followi ng Technical Presentation on June 11\, 2025!\n\nIf attending in person\, y ou must show a valid photo ID at the MIT LL gate\, at 244 Wood St\, Lexing ton\, MA. State that you are attending the IEEE meeting in the Main Cafete ria.\n\nIf attending remotely\, see the Zoom link in the "Location" sectio n below.\n\nDetailed agenda is at the bottom of this web page.\n\nAbstract :\n\nSystem reliability and resilience are crucial for ensuring dependable performance\, especially in response to evolving demands and unexpected d isruptions. Traditional reliability models\, such as the Non-Homogeneous P oisson Process (NHPP)\, are widely used to predict defect occurrence based on testing time or effort. However\, these models often fail to capture t he complexities of real-world systems. Resilience engineering\, which focu ses on a system's ability to respond to and recover from shocks\, has gain ed significant attention as a complementary approach to traditional reliab ility methods. Although statistical models provide foundational insights\, their rigid assumptions can limit flexibility and fail to capture dynamic patterns in defect occurrence and recovery processes. Conversely\, machin e learning methods\, such as neural networks\, offer the potential to mode l intricate dependencies and non-linear trends. However\, these models oft en require extensive data\, which may not always be available in resilienc e engineering contexts\, and they can lack robustness in long-term predict ions. This limitation underscores the need for integrated approaches that effectively tackle the challenges of modeling resilience in systems experi encing various types and intensities of shocks.\n\nTo address these challe nges\, this talk explores hybrid approaches that enhance defect prediction in both regression and classification tasks and improve resilience assess ment. We introduce flexible time series techniques that account for multip le stressors and recovery patterns. By integrating machine learning and st atistical methods\, this presentation aims to advance the assessment of bo th reliability and resilience in systems\, providing robust\, adaptable mo dels capable of predicting defects and tracking recovery under complex con ditions.\n\nSpeaker(s): Fatemeh Salboukh\, \n\nAgenda: \n5:00 pm doors ope n\, for networking. Arriving earlier is welcome.\n\n5:30 pm: Pizza\, salad \, and refreshments are scheduled to arrive\, while networking continues.\ n\n6:00 pm: A plaque presentation\, followed by an introduction to the pre sentation\, followed by the formal presentation.\n\n.\n\nBldg: Main Cafete ria\, 244 Wood Street\, Lexington\, Massachusetts\, United States\, 02420\ , Virtual: https://events.vtools.ieee.org/m/486009 LOCATION:Bldg: Main Cafeteria\, 244 Wood Street\, Lexington\, Massachusetts \, United States\, 02420\, Virtual: https://events.vtools.ieee.org/m/48600 9 ORGANIZER:danweidman@ieee.org SEQUENCE:10 SUMMARY:“Statistical and Machine Learning Models for System Reliability a nd Resilience” URL;VALUE=URI:https://events.vtools.ieee.org/m/486009 X-ALT-DESC:Description: <br /><p class="MsoNormal"><span style="font-family : 'Arial'\,sans-serif\;">Please join the Boston IEEE Reliability Chapter f or the following Technical Presentation on June 11\, 2025!</span></p>\n<p class="MsoNormal"><span style="font-family: 'Arial'\,sans-serif\;">If atte nding in person\, you must show a valid photo ID at the MIT LL gate\, at 2 44 Wood St\, Lexington\, MA. State that you are attending the IEEE meeting in the Main Cafeteria.</span></p>\n<p class="MsoNormal"><span style="font -family: 'Arial'\,sans-serif\;">If attending remotely\, see the Zoom link in the "Location" section below.&nbsp\;</span></p>\n<p class="MsoNormal">< span style="font-family: 'Arial'\,sans-serif\;">Detailed agenda is at the bottom of this web page.&nbsp\;</span></p>\n<p class="MsoNormal">&nbsp\;</ p>\n<p class="MsoNormal"><span style="font-family: 'Arial'\,sans-serif\;"> Abstract:&nbsp\;</span></p>\n<p class="MsoNormal"><span style="font-family : 'Arial'\,sans-serif\;">System reliability and resilience are crucial for ensuring dependable performance\, especially in response to evolving dema nds and unexpected disruptions. Traditional reliability models\, such as t he Non-Homogeneous Poisson Process (NHPP)\, are widely used to predict def ect occurrence based on testing time or effort. However\, these models oft en fail to capture the complexities of real-world systems. Resilience engi neering\, which focuses on a system's ability to respond to and recover fr om shocks\, has gained significant attention as a complementary approach t o traditional reliability methods. Although statistical models provide fou ndational insights\, their rigid assumptions can limit flexibility and fai l to capture dynamic patterns in defect occurrence and recovery processes. Conversely\, machine learning methods\, such as neural networks\, offer t he potential to model intricate dependencies and non-linear trends. Howeve r\, these models often require extensive data\, which may not always be av ailable in resilience engineering contexts\, and they can lack robustness in long-term predictions. This limitation underscores the need for integra ted approaches that effectively tackle the challenges of modeling resilien ce in systems experiencing various types and intensities of shocks.</span> </p>\n<p class="MsoNormal"><span style="font-family: 'Arial'\,sans-serif\; ">To address these challenges\, this talk explores hybrid approaches that enhance defect prediction in both regression and classification tasks and improve resilience assessment. We introduce flexible time series technique s that account for multiple stressors and recovery patterns. By integratin g machine learning and statistical methods\, this presentation aims to adv ance the assessment of both reliability and resilience in systems\, provid ing robust\, adaptable models capable of predicting defects and tracking r ecovery under complex conditions.</span></p><br /><br />Agenda: <br /><p>< span style="font-family: 'Arial'\,sans-serif\;">5:00 pm doors open\, for n etworking. Arriving earlier is welcome.&nbsp\;</span></p>\n<p><span style= "font-family: 'Arial'\,sans-serif\;">5:30 pm: Pizza\, salad\, and refreshm ents are scheduled to arrive\, while networking continues.&nbsp\;</span></ p>\n<p><span style="font-family: 'Arial'\,sans-serif\;">6:00 pm: A plaque presentation\, followed by an introduction to the presentation\, followed by the formal presentation.</span></p>\n<p><span style="font-family: 'Aria l'\,sans-serif\;">.</span></p>\n<p>&nbsp\;</p> END:VEVENT END:VCALENDAR