BEGIN:VCALENDAR
CALSCALE:GREGORIAN
VERSION:2.0
METHOD:PUBLISH
PRODID:-//Drupal iCal API//EN
X-WR-TIMEZONE:America/New_York
BEGIN:VTIMEZONE
TZID:America/New_York
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
DTSTART:20070311T020000
TZNAME:EDT
TZOFFSETTO:-0400
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
DTSTART:20071104T020000
TZNAME:EST
TZOFFSETTO:-0500
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
SEQUENCE:1
X-APPLE-TRAVEL-ADVISORY-BEHAVIOR:AUTOMATIC
UID:193671
DTSTAMP:20241112T143235Z
DTSTART;TZID=America/New_York:20241120T110000
DTEND;TZID=America/New_York:20241120T120000
URL;TYPE=URI:https://www.wpi.edu/news/calendar/events/computer-science-depa
 rtment-ms-thesis-presentation-samuel-uche-dui-detection-gait-using-multich
 annel
SUMMARY:Computer Science Department, MS Thesis Presentation , Samuel Uche  
 " DUI Detection from Gait using a Multichannel 1DCNN-Attention-BiLSTM Fram
 ework "
DESCRIPTION:\n\nDUI Detection from Gait using a Multichannel1DCNN-Attention
 -BiLSTM Framework​\n\nSamuel Uche\nPhD Student\nWPI – Computer Science Dep
 artment\n\nWednesday, November 20, 2024\nTime: 11:00 a.m. - 12:00 p.m.\nLo
 cation: Fuller Labs 141\n\nAdvisor: Prof. Emmanuel Agu\nReader: Prof. Rodi
 ca Neamtu\n\nABSTRACT:\nAlcohol intoxication increases the drinker’s Blood
  Alcohol Content (BAC) and impairs Psychomotor function. Driving under the
  influence (DUI) of alcohol impairs the driver’s cognitive and motor funct
 ions, and caused over 30% of motor vehicle traffic fatalities in 2017. Uno
 btrusive methods of detection of driver intoxication can reduce cases of D
 UI . This master’s thesis proposes a novel hybrid Multi-channel 1DCNN-Atte
 ntion-BiLSTM Framework approach for automated, passive detection of alcoho
 l intoxication from gait data collected from smartphone (accelerometer) se
 nsors.\nChallenges addressed include class imbalance that arose due to ins
 ufficient amount of intoxicated gait samples. Such class imbalance can bia
 s machine learning models towards the sober samples and hinder the alcohol
  intoxication detection model’s performance. Raw time-series sensor data w
 as pre-processed using carefully thought out, task-relevant pre-processing
  steps before classification using a hybrid Multi-channel 1D-CNN-Attention
 -BiLSTM Framework to determine if a smartphone user is above the legal dri
 ving limit (BAC > 0.08). In rigorous evaluation, our proposed approach 
 achieved an accuracy of 93%, outperforming the current state of the art by
  9.5%.\n
END:VEVENT
END:VCALENDAR