Zilu Liang 교수

Our analysis shows that Fitbit Charge 2 underestimated sleep stage transition dynamics compared with the medical device. Device accuracy may be significantly affected by perceived sleep quality (PSQI), WASO, and SE.

Wearable devices like Fitbit and Apple Watch provide convenient access to personal information about sleep habits. However, it is unclear if awareness of one's sleep habits also translates into improved sleep. Hence, we conducted an interview study with 12 people who track their sleep with Fitbit devices to investigate if they have managed to improve their sleep and to examine potential barriers for improving sleep. The participants reported increased awareness of sleep habits, but none of the p

The route guidance system (RGS) has been considered an important technology to mitigate urban traffic congestion. However, existing RGSs provide only route guidance after congestion happens. This reactive strategy imposes a strong limitation on the potential contribution of current RGS to the performance improvement of a traffic network. Thus, a proactive RGS based on congestion prediction is considered essential to improve the effectiveness of RGS. The problem of congestion prediction is transl

Consumer wearable activity trackers, such as Fitbit are widely used in ubiquitous and longitudinal sleep monitoring in free-living environments. However, these devices are known to be inaccurate for measuring sleep stages. In this study, we develop and validate a novel approach that leverages the processed data readily available from consumer activity trackers (i.e., steps, heart rate, and sleep metrics) to predict sleep stages. The proposed approach adopts a selective correction strategy and co

Intelligent Transportation Systems (ITS) have been considered important technologies to mitigate urban traffic congestion. Accurate traffic prediction is one of the critical steps in the operation of an ITS. While techniques for traffic prediction have existed for many years, the research effort has mainly been focused on highway networks. Due to the fundamental difference between the traffic flow pattern on highways and that on city roads, much of the existing models cannot be effectively appli

Consumer sleep-tracking devices provide an unobtrusive and affordable way to learn about personal sleep habits. Recent research focused primarily on the information provided by such devices, i.e., whether the information is accurate and meaningful to people. However, little is known about how people judge the credibility of such information, and how the functionality and the design may influence such judgements. Hence, the aim of this research was to examine how consumers assess the credibility

Nowadays emerging sleep-tracking technologies such as Fibit make it possible for individuals to collect personal sleep data. However, people find it difficult to gain insights from these data without proper analysis. The objective of this study was to investigate the possibility of establishing a sleep analysis approach that helps people detect their unusual sleep pattern by considering their own sleep baselines instead of the population average. The proposed approach was consisted of two steps.

It is now easy to track one's sleep through consumer wearable devices like Fitbit from the comfort of one's home. However, compared to clinical measures, the data generated by such consumer devices is limited in its accuracy. The aim of this paper is to explore how users perceive accuracy issues, possible measurement errors and what can be done to address these issues. Through an interview study with 14 Fitbit users we identified three main sources of errors: (1) lack of definition of sleep metr

Preventive health care is considered a promising solution to the prevalence of chronic diseases. Nevertheless, preventive health care at the population-level adopts an one-fit-all approach. We intend to solve the problem through promoting preventive health care at the individual level based on self-quantification. Nowadays millions of people are tracking their health conditions and collecting huge quantity of data. We propose a Preventive Health care on Individual Level (PHIL) framew

Consumer sleep tracking wristbands such as Fitbit have been increasingly used in scientific studies to measure sleep outcomes. Nevertheless, many validation studies indicate that Fitbit wristbands often misclassify wake as sleep (i.e. low specificity). This study aims to develop classification models that leverage Fitbit data to generate accurate sleep/wake classifications. The problem of interest was formulated into an imbalanced binomial classification problem, as a normal night of human sleep

The COVID-19 pandemic triggered unprecedented adoption of online education in universities and digital technologies are increasingly becoming an essential part of the learning and teaching experience. From within an ongoing pandemic ‘lockdown’, this study investigates the current landscape of online education with a focus on the learning and teaching experience in virtual classrooms compared to physical classrooms. We found that instructors typically combine multiple technologies to create a hol

Many university students experience stress that lead to negative effect on health and academic performance. In this paper we present the development of a mobile health application named NokoriMe, which consists of the design of an original academic stress questionnaire and the implementation of the application. NokoriMe application enables students to measure and track stress over time and to visualize trends and correlations in stress and physiological responses to stress (i.e. sleep quality an

It has been widely recognized that discovering potential contributing factors to personal sleep is as important as understanding sleep pattern per se. However, in large quantified-self datasets, contributing factors may only show correlations to sleep when their values are within certain ranges. Existing correlation analysis using Pearson Correlation Coefficient cannot identify such hidden dependencies. We propose a new method based on association rules mining. Our method not only can discover h