BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Women@CL Talkets - Kayla-Jade Butkow and Ting Dang and Ceren Kocao
 gullar
DTSTART:20220526T120000Z
DTEND:20220526T130000Z
UID:TALK174959@talks.cam.ac.uk
CONTACT:Kayla-Jade Butkow
DESCRIPTION:-----------------------------------------------\n\n*Speaker*: 
 Kayla-Jade Butkow\n\n*Title*: Earables for sensing of cardiovascular healt
 h\n\n*Abstract*: Heart rate is a key physiological marker of cardiovascula
 r health and physical fitness. Continuous and reliable HR monitoring with 
 wearable devices has therefore gained increasing attention in recent years
 . Existing HR detection systems in wearables mainly rely on photoplethysmo
 graphy (PPG) sensors\, however\, these are notorious for poor performance 
 in the presence of human motion. In this work\, leveraging the occlusion e
 ffect that can enhance low-frequency bone-conducted sounds in the ear cana
 l\,  we investigate in-ear audio-based motion-resilient HR monitoring. We 
 first collected the HR-induced sound in the ear canal leveraging an in-ear
  microphone under stationary and three different activities (i.e.\, walkin
 g\, running\, and speaking). Then\, we devise a novel deep learning based 
 motion artefact (MA) mitigation framework to denoise the in-ear audio sign
 als\, followed by an HR estimation algorithm to extract HR.\n\n-----------
 ------------------------------------\n\n*Speaker*: Ting Dang\n\n*Title*: C
 OVID-19 Disease Progression Prediction and Forecasting via Audio: A Longit
 udinal Study\n\n*Abstract*: While most existing studies focus on automatic
  one-off COVID-19 detection\, little attention has been paid to continuous
  and remote monitoring of COVID-19 disease progression which provides more
  valuable information of disease development to support clinical decision 
 making. In this talk\, I will present our work on exploring the potential 
 of using longitudinal audio biomarkers to aid the disease progression pred
 iction and forecasting using deep learning techniques. By modelling indivi
 dual’s historical audio dynamics over time\, the models can capture the 
 underlying process of disease development and achieve reliable progression
  prediction and forecasting ahead of time.\n\n----------------------------
 -------------------\n\n*Speaker*: Ceren Kocaogullar\n\n*Title*: Private us
 er discovery in anonymity networks\n\n*Abstract*: Private mobile communica
 tions have recently become an integral part of our everyday lives with enc
 rypted messaging apps such as Signal\, Telegram\, and WhatsApp. Although t
 hese popular messaging apps hide the conversation contents\, they do not p
 rotect metadata\, which is information about a message other than what is 
 said in it\, such as when\, with whom\, and how frequently parties communi
 cate. Metadata can expose critical information about conversations. For in
 stance\, a whistleblower's identity might be revealed if their messaging o
 r call history indicates that they have contacted the press. Similarly\, f
 requent communication between company executives might leak information ab
 out confidential mergers and acquisitions. Therefore\, not protecting meta
 data\, encrypted messaging apps potentially jeopardise user privacy. Anony
 mity networks can solve this problem. Nevertheless\, the current finding o
 ther users in these networks is currently very difficult. \n\nMy research 
 identifies the need for a new privacy-preserving and practical user discov
 ery mechanism in anonymity networks. To satisfy this need\, I have establi
 shed a security protocol named Pudding with two different user modes\, eac
 h representing a different point in the usability-privacy tradeoff space: 
 Verified user mode allows user discovery through validated email addresses
 \, but it cannot hide usernames from the user discovery mechanism. Unverif
 ied user mode solves this issue at the cost of sacrificing the ability to 
 link Pudding usernames to well-known external names. In this presentation\
 , I will describe the core mechanisms through which Pudding protocol provi
 des private and practical user discovery for anonymity networks. 
LOCATION:Computer Laboratory\, William Gates Building\, FW11
END:VEVENT
END:VCALENDAR