Publications

Our objective is to investigate temporal changes in glycemic trends by analyzing intensively sampled blood glucose data from 137 patients (ages 2 to 76, primarily type 1 diabetes) over the course of 9 months to 4.5 years.

This paper reviews the current advancements in noninvasive glucose sensing technology in vivo, delves into the common challenges faced by these systems, and offers an insightful outlook on existing and future solutions.

This publication provides a detailed description of the DiaTrend dataset, which our team is making open access to the broader community, to accelerate development of novel data-driven solutions and robust computational tools for diabetes and beyond.

In this work, we propose a scalable computational framework for discovering digital biomarkers of glycemic control.

This paper aims to investigate patterns of glycemic control around the holidays. In this study, we found that majority of people with diabetes in our dataset had worse glycemic control during holiday weeks compared to non-holiday weeks.

Non-invasive monitoring of lung and lung airways health enables the early detection and tracking of respiratory diseases like asthma and COPD. This paper introduces an algorithm to extract respiratory information from electrocardiogram (ECG) signal.

This paper investigates potential under-utilization of wearable device data in diabetes management.

This paper presents a review on healthcare cognitive assistants, which are intelligent systems that interact with users by augmenting their cognitive abilities.

In this paper, we present the feasibility of adapting the Auracle, an existing research-grade earpiece designed to automatically and unobtrusively recognize eating behavior in adults, for measuring children’s eating behavior

We propose a compact noninvasive glucose monitoring system using polarized light, where a user simply needs to place his/her palm on the device for measuring his/her current glucose concentration level.

In this paper, we employ a data-driven approach to study the relationship between key behavioral factors (sleep, meal size, insulin dose) and proximal diabetic management indicators.

In this paper, we present Neural Physiological Encoder (NPE), a simple module that leverages decomposed convolutional filters to automatically generate effective features that can be used with a downstream neural network for blood glucose prediction.

In this work, we conducted a two-phase user-study involving patients, caregivers, and clinicians to understand gaps in current approaches that support reflection and user needs for new solutions.

Use cheap, nonclinical sensors to capture physiological signals and make inferences about the wearer’s stress level based on that data.

To evaluate the effects of incentives, weekly planning, and daily self-monitoring prompts that were used as intervention components as part of the Ally app.

We study the brain resting-state functional connectivity (RSFC) between the ventromedial prefrontal cortex (vmPFC) and the amygdala, which has been shown by neuroscientists to be associated with mental illness such as anxiety and depression

This paper takes a data mining approach to study adherence to continuous glucose monitors in diabetes management.

In this work, we explore the factors affecting users’ receptivity towards Just-In-Time Adaptive Interventions (JITAI).

Machine Learning algorithms trained on electrical-impedance tomography data are presented for portable cardiac monitoring. The approach was validated on a simulated thorax and a measured tank experiment.

Our work introduces a new recurrent unit architecture that is specifically adapted for on-device low power acoustic event detection.

The primary objective of this study is to quantify main effects, interactions, and moderators of 3 intervention components of a smartphone-based intervention for physical activity.

In this paper, we explore the viability of commercially available off-the-shelf sensors for stress monitoring.

In this paper, we propose Auracle, a wearable earpiece that can automatically recognize eating behavior. More specifically, in free-living conditions, we can recognize when and for how long a person is eating.

In this paper an end-to-end CMOS application specific integrated circuit (ASIC) for readout channel in a cardiac electrical impedance tomography (EIT) system is presented.

In this work, we attempt to determine whether the contextual information of a participant can be used to predict whether the participant will respond to a particular EMA trigger.

In this paper, we evaluate sensors and algorithms designed to detect eating activities, more specifically, when people eat.

The Auracle aims to be a wearable earpiece that detects eating behavior.

In this paper, we consider two different approaches of using deep neural networks for cough detection. The cough detection task is cast as a visual recognition problem and as a sequence-to-sequence labeling problem.