Advanced artificial intelligence (AI)-based technologies offer great opportunities for enhancing the driving experience. Proactive voice agents (PVAs) present benefits by being proactive rather than responding to requests. This study uses a driving simulator to investigate whether PVAs can create value for drivers. We designed three types of PVAs: a task agent, a social agent, and a companion agent, as well as a control agent for a 2 (small talk vs. non-small talk) × 2 (task-based talk vs. non-task-based talk) between-subjects experiment. We found that PVAs (i.e., social or companion agents) engaging in small talk increased perceived intimacy, but task agents increased perceived pressure. Moreover, experienced drivers preferred PVAs that engage in small talk to avoid sleepiness or boredom, while novice drivers favored control agents. As younger, experienced drivers have the highest technology acceptance, they will be potential adopters of PVAs.

MoodPupilar introduces a novel method for mood evaluation using pupillary response captured by a smartphone's front- facing camera during daily use. Over a four-week period, data was gathered from 25 participants to develop models capable of predicting daily mood averages. Utilizing the GLOBEM behavior modeling platform, we benchmarked the utility of pupillary response as a predictor for mood. Our proposed model demonstrated a Matthew's Correlation Coefficient (M CC) score of 0.15 for Valence and 0.12 for Arousal, which is on par with or exceeds those achieved by existing behavioral modeling algorithms supported by GLOBEM. This capability to accurately predict mood trends underscores the effectiveness of pupillary response data in providing crucial insights for timely mental health interventions and resource allocation. The outcomes are encouraging, demonstrating the potential of real-time and pre-dictive mood analysis to support mental health interventions.

In public health and safety, precise detection of blood alcohol concentration (BAC) plays a critical role in implementing responsive interventions that can save lives. While previous research has primarily focused on computer-based or neuropsychological tests for BAC identification, the potential use of daily smartphone activities for BAC detection in real-life scenarios remains largely unexplored. Drawing inspiration from Instrumental Activities of Daily Living (I-ADL), our hypothesis suggests that Smartphone-based Activities of Daily Living (S-ADL) can serve as a viable method for identifying BAC. In our proof-of-concept study, we propose, design, and assess the feasibility of using S-ADLs to detect BAC in a scenario-based controlled laboratory experiment involving 40 young adults. In this study, we identify key S-ADL metrics, such as delayed texting in SMS, site searching, and finance management, that significantly contribute to BAC detection (with an AUC-ROC and accuracy of 81%). We further discuss potential real-life applications of the proposed BAC model.

Depression, a prevalent and complex mental health issue affecting millions worldwide, presents significant challenges for detection and monitoring. While facial expressions have shown promise in laboratory settings for identifying depression, their potential in real-world applications remains largely unexplored due to the difficulties in developing efficient mobile systems. In this study, we aim to introduce FacePsy, an open-source mobile sensing system designed to capture affective inferences by analyzing sophisticated features and generating real-time data on facial behavior landmarks, eye movements, and head gestures - all within the naturalistic context of smartphone usage with 25 participants. Through rigorous development, testing, and optimization, we identified eye-open states, head gestures, smile expressions, and specific Action Units (2, 6, 7, 12, 15, and 17) as significant indicators of depressive episodes (AUROC=81%). Our regression model predicting PHQ-9 scores achieved moderate accuracy, with a Mean Absolute Error of 3.08. Our findings offer valuable insights and implications for enhancing deployable and usable mobile affective sensing systems, ultimately improving mental health monitoring, prediction, and just-in-time adaptive interventions for researchers and developers in healthcare.

Continuous passive sensing of daily behavior from mobile devices has the potential to identify behavioral patterns associated with different aspects of human characteristics. This paper presents novel analytic approaches to extract and understand these behavioral patterns and their impact on predicting adaptive and maladaptive personality traits. Our machine learning analysis extends previous research by showing that both adaptive and maladaptive traits are associated with passively sensed behavior providing initial evidence for the utility of this type of data to study personality and its pathology. The analysis also suggests directions for future confirmatory studies into the underlying behavior patterns that link adaptive and maladaptive variants consistent with contemporary models of personality pathology.

Hospital readmissions are a major problem facing health care systems today, costing Medicare alone US$26 billion each year. Being readmitted is associated with significantly shorter survival, and is often preventable. Predictors of readmission are still not well understood, particularly those under the patient's control: behavioral risk factors. Our work evaluates the ability of behavioral risk factors, specifically Fitbit-assessed behavior, to predict readmission for 25 postsurgical cancer inpatients. Our results show that sum of steps, maximum sedentary bouts, frequency, and low breaks in sedentary times during waking hours are strong predictors of readmission. We built two models for predicting readmissions: Steps-only and Behavioral model that adds information about sedentary behaviors. The Behavioral model (88.3%) outperforms the Steps-only model (67.1%), illustrating the value of passively collected information about sedentary behaviors. Indeed, passive monitoring of behavior data, i.e., mobility, after major surgery creates an opportunity for early risk assessment and timely interventions.

Recently, stereoscopic 3D technologies have come to be used widely in various applications including movies and computer games. Stereoscopic 3D is defined as that which provides visual depth and details by exploiting the stereoscopic vision of the eyes caused by binocular disparity. Prior studies proposed important system features of stereoscopic 3D that may increase the user’s sense of presence. However, few studies, either theoretical or empirical, have investigated how these perceived system features affect the user’s sense of presence. This study aims to construct a theoretical model that explains the perceived effects of stereoscopic 3D features on sense of presence, and to verify the validity of the model in the 3D computer game domain. The study focuses on spatial representation and perceived realism as important mediating factors between the perceived system features and sense of presence. According to the Dual Mode Model (DMM), two types of spatial representation are crucial for perceived realism and presence: egocentric representation and allocentric representation. Egocentric representation implies representing locations with respect to the particular perspective of the perceiver, while allocentric representation locates reference points outside of the perceiver, regardless of his or her position. Research questions in this study are: How strongly do perceived expression and manipulation features of stereoscopic 3D systems influence spatial representation? How does spatial representation influence perceived realism and presence in a stereoscopic 3D environment? In order to answer these research questions an empirical study was conducted in a controlled lab environment. A total number of 257 users participated in the study and collected data was analyzed by using structural equation modeling with SmartPLS2.0. The findings are as follows: First, both the perceived expression and manipulation features of the stereoscopic 3D system influenced spatial representation, but the perceived expression features had stronger effects than the perceived manipulation features. Second, both egocentric and allocentric representation were found to affect presence. In addition, egocentric representation was found to affect sense of presence both directly and indirectly through perceived realism, whereas allocentric representation contributed a sense of presence only indirectly through perceived realism. This paper concludes by discussing the study’s limitations and implications.