BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//UM//UM*Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:America/Detroit
TZURL:http://tzurl.org/zoneinfo/America/Detroit
X-LIC-LOCATION:America/Detroit
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20070311T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20071104T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20250208T014658
DTSTART;TZID=America/Detroit:20250219T160000
DTEND;TZID=America/Detroit:20250219T180000
SUMMARY:Workshop / Seminar:Student AIM Seminar: From Signals to Signatures: Mathematical Approaches to Modeling the Human Stress Response + Casual Networking Mixer
DESCRIPTION:The increasing adoption of wearable devices in healthcare presents unique opportunities and analytical challenges for applied mathematics. This talk will explore two interconnected research directions in digital health monitoring: analyzing physiological adaptation in bone marrow transplant (BMT) patients and developing mathematical frameworks for stress detection.\n\nIn the first part\, we'll examine methods for quantifying physiological acclimatization in BMT patients using continuous heart rate\, activity\, and sleep data. We'll discuss the mathematical challenges in processing high-dimensional\, temporally-correlated physiological signals and approaches for detecting significant changes during vs post engraftment period.\n\nThe second part will introduce our novel MOXIE (MultimOdal eXploration of psychological challenges in Interactive Environments) study\, which aims to characterize individual stress signatures through multiple biophysiological signals. We'll explore planned approaches for integrating diverse data streams - from continuous physiological monitoring to ecological momentary assessments to video and blood samples. Special attention will be given to emerging computational frameworks\, including applications of Long Short-Term Memory networks for temporal pattern recognition\, self-attention mechanisms for capturing long-range dependencies in stress responses\, and state-space models for efficient sequence modeling. We'll discuss how these advanced architectures might help bridge the gap between traditional time series analysis and the inherent complexity of mind-body interactions.\n\nThe talk will conclude by exploring how these mathematical frameworks could advance our understanding of psychoneuroimmunology in cancer patients. We'll discuss the potential impact on developing targeted interventions to improve survival outcomes\, particularly in understanding how psychological stress influences immune function and disease progression in cancer patients. This work aims to bridge the gap between computational modeling and personalized clinical interventions in oncology.\n\nCasual Networking Mixer:\nGraduate students\, postdocs\, and faculty\, especially those working in Applied Math are invited to a casual networking mixer after the talk. Foods and drinks will be provided.
UID:131414-21868445@events.umich.edu
URL:https://events.umich.edu/event/131414
CLASS:PUBLIC
STATUS:CONFIRMED
CATEGORIES:Applied Mathematics,Mathematics
LOCATION:East Hall - 3088
CONTACT:
END:VEVENT
END:VCALENDAR