University of Cambridge > Talks.cam > Women@CL Events > Women@CL Talkets

Women@CL Talkets

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Kayla-Jade Butkow.

———————————————————————-

Speaker: Kayla-Jade Butkow

Title: Earables for sensing of cardiovascular health

Abstract: Heart rate is a key physiological marker of cardiovascular 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 photoplethysmography (PPG) sensors, however, these are notorious for poor performance in the presence of human motion. In this work, leveraging the occlusion effect that can enhance low-frequency bone-conducted sounds in the ear canal, 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., walking, running, and speaking). Then, we devise a novel deep learning based motion artefact (MA) mitigation framework to denoise the in-ear audio signals, followed by an HR estimation algorithm to extract HR.

———————————————————————-

Speaker: Ting Dang

Title: COVID -19 Disease Progression Prediction and Forecasting via Audio: A Longitudinal Study

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 prediction and forecasting using deep learning techniques. By modelling individual’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.

———————————————————————-

Speaker: Ceren Kocaogullar

Title: Private user discovery in anonymity networks

Abstract: Private mobile communications have recently become an integral part of our everyday lives with encrypted messaging apps such as Signal, Telegram, and WhatsApp. Although these popular messaging apps hide the conversation contents, they do not protect metadata, which is information about a message other than what is said in it, such as when, with whom, and how frequently parties communicate. Metadata can expose critical information about conversations. For instance, a whistleblower’s identity might be revealed if their messaging or call history indicates that they have contacted the press. Similarly, frequent communication between company executives might leak information about confidential mergers and acquisitions. Therefore, not protecting metadata, encrypted messaging apps potentially jeopardise user privacy. Anonymity networks can solve this problem. Nevertheless, the current finding other users in these networks is currently very difficult.

My research identifies the need for a new privacy-preserving and practical user discovery mechanism in anonymity networks. To satisfy this need, I have established a security protocol named Pudding with two different user modes, each 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. Unverified 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 provides private and practical user discovery for anonymity networks.

This talk is part of the Women@CL Events series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2022 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity