Effective Subjective Reporting Project (2021 – present)

Subjective Report Reliability Prediction

While subjective reports can complement objective reporting based on sensor data collected from personal devices, the effective utilization of subjective reporting depends on its reliability. Unreliable responses may lead to wrong conclusions while analyzing. Therefore, it is crucial to determine whether a self-report has been made with care or not. Such a reliability prediction can help warn the participants to retake, help the researchers assess meaningful patterns from self-reported data, and develop a better recommender system to help people in various aspects, including managing health and well-being. The work has been published at the

Elsevier Smart Health Journal (SMHL 2023)

User-Centric Subjective Report and App Design

Due to recent advancements in smartphone sensing and computing capabilities, mobile health (mHealth) applications are getting popular to monitor a range of diseases, including coronavirus-caused COVID-19 disease, chronic obstructive pulmonary disease (COPD), asthma, bronchitis, emphysema, sleep apnea, among many others utilizing the audio recordings obtained from the smartphone microphones. To improve user compliance, app utility, and life cycle, it is important to understand various user concerns, including data privacy and battery drain rate, as well as user trust in different recommended groups to adapt a user-centric app design approach where users have options to configure the app, i.e., choose an architecture from a set of options based on their concerns and preferences. Findings from a detailed analysis of 60 subjects with varying backgrounds are published at

Effective Longitudinal Smartphone-Survey Design

Phone-based surveys are increasingly being used in healthcare settings to collect data from potentially large numbers of subjects, e.g., to evaluate their levels of satisfaction with medical providers, to study behaviors and trends of specific populations, and to track their health and wellness. Often subjects respond to such surveys once, but capturing their responses multiple times over an extended period has become increasingly important to accurately and quickly detect and track changes. With the help of smartphones, it is now possible to automate such longitudinal data collections, e.g., push notifications can be used to alert a subject whenever a new survey is available. I have investigated various human factors in designing a longitudinal smartphone-based survey data collection that contributes to user compliance and the quality of collected data. This work presents the design recommendations based on the analysis of objective (phone sensor data, spat-temporal information of survey responses) and subjective (survey responses) data collected from 17 subjects over a one-month period. The work has been published at the