BEGIN:VCALENDAR
METHOD:REQUEST
PRODID:Microsoft Exchange Server 2010
VERSION:2.0
BEGIN:VTIMEZONE
TZID:Eastern Standard Time
BEGIN:STANDARD
DTSTART:16010101T020000
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
RRULE:FREQ=YEARLY;INTERVAL=1;BYDAY=1SU;BYMONTH=11
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:16010101T020000
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
RRULE:FREQ=YEARLY;INTERVAL=1;BYDAY=2SU;BYMONTH=3
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
ORGANIZER;CN=Nida Shams:MAILTO:[log in to unmask]
ATTENDEE;ROLE=REQ-PARTICIPANT;PARTSTAT=NEEDS-ACTION;RSVP=TRUE;CN="SOCAAR-l:
Southern Ontario Centre for Atmospheric Aerosol Research":MAILTO:SOCA
[log in to unmask]
ATTACH:CID:[log in to unmask]
DESCRIPTION;LANGUAGE=en-US:SOCAAR is pleased to announce the next seminar f
or Dec 2018:\n\nWednesday\, December 5\, 2018\n3:00 – 4:00 PM\n200 Colle
ge Street\, WB 407\n\nParticulate Matter Air Pollution in Charlotte NC: A
Land Use Regression Model based on Citizen Science Monitoring\nMatthew Ada
ms\, PhD\nAssistant Professor\nDepartment of Geography\nUniversity of Toro
nto Mississauga\n\nAbstract: This study assessed the use of air pollution
data collected through Citizen Science activities for developing a land us
e regression (LUR) air pollution model. The model was applied to estimate
an air pollution surface for Charlotte\, NC. Particulate matter air pollut
ion was monitored for this study with air pollution sensors mounted to bic
ycles. The lower cost sensors are known to demonstrate bias. The observed
values were adjusted with a neural network model derived from a collocatio
n study of the low-cost sensor with a research grade instrument. For each
air pollution observation location\, land use information was calculated w
ithin buffers of varying sizes. A linear regression model was developed\,
to explain the variation in air pollution observations by the surrounding
land use conditions\, using a manual step-wise approach. The performance o
f the multivariate linear regression model was evaluated by cross-validati
on with data excluded during model fitting. The linear model performance w
as poor with an R^2 of 0.24. An artificial neural network model was develo
ped in an attempt to improve model performance and obtain a higher predict
ive performance during cross-validation. The neural network based LUR mode
l achieved a prediction R^2 of 0.71\, a significant improvement from the l
inear regression model. The application of neural networks in a land use r
egression framework has proven useful as it allows for complex non-linear
relationships that may be present in dataset.\n\n\nIf you are unable to jo
in the meeting in person\, please join this meeting from your computer\, t
ablet or smartphone.\n\nPlease join my meeting from your computer\, tablet
or smartphone.\nhttps://global.gotomeeting.com/join/725709717\n\nYou can
also dial in using your phone.\nCanada: +1 (647) 497-9391\nAccess Code: 72
5-709-717\n\nFor supported devices\, tap a one-touch number below to join
instantly.\nOne-touch: +16474979391\, 725709717\nAccess Code: 725-709-717\
n\nFirst GoToMeeting? Let's do a quick system check: https://link.gotomeet
ing.com/system-check\n
UID:040000008200E00074C5B7101A82E00800000000503B42E63644D401000000000000000
010000000D5D50D671C3AE04D94AEBE86E9E56064
RECURRENCE-ID;TZID=Eastern Standard Time:20181205T150000
SUMMARY;LANGUAGE=en-US:SOCAAR Seminar - Matthew Adams
DTSTART;TZID=Eastern Standard Time:20181205T150000
DTEND;TZID=Eastern Standard Time:20181205T170000
CLASS:PUBLIC
PRIORITY:5
DTSTAMP:20181115T222248Z
TRANSP:OPAQUE
STATUS:CONFIRMED
SEQUENCE:6
LOCATION;LANGUAGE=en-US:WB 407
X-MICROSOFT-CDO-APPT-SEQUENCE:6
X-MICROSOFT-CDO-OWNERAPPTID:-1998280734
X-MICROSOFT-CDO-BUSYSTATUS:TENTATIVE
X-MICROSOFT-CDO-INTENDEDSTATUS:BUSY
X-MICROSOFT-CDO-ALLDAYEVENT:FALSE
X-MICROSOFT-CDO-IMPORTANCE:1
X-MICROSOFT-CDO-INSTTYPE:3
X-MICROSOFT-ONLINEMEETINGEXTERNALLINK:https://meet.lync.com/utoronto.ca/nid
a.shams/7PMVS1SV
X-MICROSOFT-ONLINEMEETINGCONFLINK:conf:sip:[log in to unmask]\;gruu\;op
aque=app:conf:focus:id:7PMVS1SV?conversation-id=fEZLb2l65Z76
X-MICROSOFT-DONOTFORWARDMEETING:FALSE
X-MICROSOFT-DISALLOW-COUNTER:FALSE
X-MICROSOFT-LOCATIONS:[{"DisplayName":"WB 407"\,"LocationAnnotation":""\,"L
ocationUri":""\,"LocationStreet":""\,"LocationCity":""\,"LocationState":""
\,"LocationCountry":""\,"LocationPostalCode":""\,"LocationFullAddress":""}
]
BEGIN:VALARM
DESCRIPTION:REMINDER
TRIGGER;RELATED=START:-PT15M
ACTION:DISPLAY
END:VALARM
END:VEVENT
END:VCALENDAR
