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:20241009T100348
DTSTART;TZID=America/Detroit:20241031T143000
DTEND;TZID=America/Detroit:20241031T153000
SUMMARY:Lecture / Discussion:ECE Distinguished Seminar Series - Self-Powered Connected Sensor Systems for Health and Environment
DESCRIPTION:Abstract\n\nSelf-powered wearable sensor systems can not only increase adoption and compliance but also enable long-term and continuous monitoring of key health and environmental parameters. To achieve this\, wearable devices must integrate a multimodal array of sensors that enable non-invasive\, continuous\, real-time monitoring\, have a long operational lifetime to gather meaningful long-term data\, and remain comfortable and flexible to ensure user adoption. The National Science Foundation-funded Center for Advanced Self-Powered Systems of Integrated Sensors and Technologies (ASSIST) is developing precisely such devices\, capable of continuous monitoring of personal environments and health. These capabilities are made possible by breakthroughs in power management\, low-power electronics\, and innovative health and environmental sensors\, all seamlessly integrated into wearable\, comfortable form factors. In this talk\, I will specifically focus on how advances in energy harvesting and sensor systems are making continuous monitoring a reality. Innovations in thermoelectric and piezoelectric harvesters\, catalyzed by optimized system design and flexible materials\, have enabled long-term operation of sensors for vigilant monitoring. Sensor advances in electronic-nose\, optical imaging and human health are providing a complete multi-modal picture into human health and its relationship environment. I will also present the applications that these sensor systems are enabling such as long-term sensing and effective management of chronic conditions\, sensing of personal exposure to air pollutants and toxins and longitudinal studies that provide new insight into correlation of various health and environmental parameters. I will also provide examples of translation of sensor systems and innovative education of the engineering pipeline enabled by the ecosystem associated with an NSF engineering research center.\n\nBio\n\nVeena Misra is the Department Head of Electrical and Computer Engineering and the M.C. Dean Distinguished University Professor at North Carolina State University. She is also the co-director of the National Science Foundation Engineering Research Center on Advanced Self-Powered of Integrated Sensors and Technologies (ASSIST). She is a 2012 IEEE Fellow and served as a distinguished lecturer for IEEE Sensors. She received the B.S.\, M.S.\, and Ph.D. degrees in electrical engineering from North Carolina State University\, Raleigh. After working at the Advanced Products Research and Development Laboratories\, Motorola Inc.\, Austin\, TX she joined the faculty of North Carolina State University in 1998. She has authored or coauthored over 250 papers. Dr. Misra was the recipient of the 2001 National Science Foundation Presidential Early CAREER Award\, the 2011 Alcoa Distinguished Engineering Research Award\, the 2007 Outstanding Alumni Research Award and the 2016 R.J. Reynolds Award. She also served as the general chair of the 2012 IEEE International Electron Device Meeting. In 2022\, she received the Alexander Holladay Medal\, the highest honor given to a faculty member at NC State. She has served as a member of the DARPA Microsystems Exploratory Council and is currently serving on the advisory committee of the NSF Directorate for Engineering.\n\nSPONSORED BY\nElectrical and Computer Engineering
UID:127561-21859331@events.umich.edu
URL:https://events.umich.edu/event/127561
CLASS:PUBLIC
STATUS:CONFIRMED
CATEGORIES:Lecture,engineering,Electrical Engineering and Computer Science,Electrical And Computer Engineering,Computer Engineering
LOCATION:Lurie Robert H. Engin. Ctr - Johnson Rooms (3rd Floor)
CONTACT:
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20240816T145625
DTSTART;TZID=America/Detroit:20241031T150000
DTEND;TZID=America/Detroit:20241031T170000
SUMMARY:Social / Informal Gathering:Hopwood Halloween Tea
DESCRIPTION:Join us for cider\, donut holes\, and candy galore! Enjoy Halloween music\, games\, and a book raffle in the spookily decorated Hopwood Room. Costumes optional but welcome!
UID:124355-21852952@events.umich.edu
URL:https://events.umich.edu/event/124355
CLASS:PUBLIC
STATUS:CONFIRMED
CATEGORIES:Food,Literary Arts,Department Of English Language And Literature,Creative Writing,Contemporary Literature,celebration,Books,Writing,Undergraduate Students,The Helen Zell Writers' Program,Music,Literature,Free,Games,Graduate Students,Halloween,Hopwood Program,In Person
LOCATION:Angell Hall - Hopwood Room, 1176 Angell Hall
CONTACT:
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20241016T135845
DTSTART;TZID=America/Detroit:20241031T150000
DTEND;TZID=America/Detroit:20241031T160000
SUMMARY:Workshop / Seminar:IOE 899: Interpreting Black-Box Supervised Learning Models Via Accumulated Local Effects
DESCRIPTION:About the speaker: Dan Apley is a Professor of Industrial Engineering &amp\; Management Sciences at\nNorthwestern University. His research and teaching interests are at the interface of engineering\nmodeling\, statistical analysis\, and predictive analytics\, with particular emphasis on improving\noperations of complex manufacturing and other enterprise systems. He received the NSF\nCAREER award\, the IIE Transactions Best Paper Award\, the Technometrics Wilcoxon Prize\,\nand the Journal of Quality Technology Lloyd S. Nelson award. He has served as Editor-in-Chief\nof Technometrics and of the Journal of Quality Technology. He is a Fellow of the American\nStatistical Association and served as Chair of the Quality\, Statistics &amp\; Reliability Section of\nINFORMS and Director of the Manufacturing and Design Engineering Program at Northwestern.\n\n\nAbstract: For many supervised learning applications\, understanding and visualizing the effects\nof the predictor variables on the predicted response is of paramount importance. A shortcoming\nof black-box supervised learning models (e.g.\, complex trees\, neural networks\, boosted trees\,\nrandom forests\, nearest neighbors\, local kernel-weighted methods\, support vector regression\,\netc.) in this regard is their lack of interpretability or transparency. Partial dependence (PD) plots\,\nwhich are the most popular general approach for visualizing the effects of the predictors with\nblack box supervised learning models\, can produce erroneous results if the predictors are\nstrongly correlated\, because they require extrapolation of the response at predictor values that are\nfar outside the multivariate envelope of the training data. Functional ANOVA for correlated\ninputs can avoid this extrapolation but involves prohibitive computational expense and\nsubjective choice of additive surrogate model to fit to the supervised learning model. We present\na new visualization approach that we term accumulated local effects (ALE) plots\, which have a\nnumber of advantages over existing methods. First\, ALE plots do not require unreliable\nextrapolation with correlated predictors. Second\, they are orders of magnitude less\ncomputationally expensive than PD plots\, and many orders of magnitude less expensive than\nfunctional ANOVA. Third\, they yield convenient variable importance/sensitivity measures that\npossess a number of desirable properties for quantifying the impact of each predictor.
UID:127928-21859940@events.umich.edu
URL:https://events.umich.edu/event/127928
CLASS:PUBLIC
STATUS:CONFIRMED
CATEGORIES:899 Seminar Series,Industrial And Operations Engineering,Michigan Engineering
LOCATION:Industrial and Operations Engineering Building - 1680
CONTACT:
END:VEVENT
END:VCALENDAR