Sensing real-time mood swings in reaction to noise by detecting focal change patterns in time series of individual noise exposure data
Topics: Human-Environment Geography
, Medical and Health Geography
, Geography and Urban Health
Keywords: emotional sensing, noise exposure, human mobility, focal change pattern detection, uncertain geographic context problem
Session Type: Virtual Paper
Day: Sunday
Session Start / End Time: 4/11/2021 09:35 AM (Pacific Time (US & Canada)) - 4/11/2021 10:50 AM (Pacific Time (US & Canada))
Room: Virtual 8
Authors:
Jiannan Cai, The Chinese University of Hong Kong
Mei-Po Kwan, The Chinese University of Hong Kong
,
,
,
,
,
,
,
,
Abstract
Exposure to noise can induce personal mood swings and threaten mental health. However, personal emotional information about noise is mainly collected by self-reports in past studies, making it difficult to track dynamic mood swings in real-time. In addition, previous studies on noise-health relationships mostly ignored people’s daily mobility and their exposures to non-residential contexts, which could lead to misleading findings. Thus, this study aims to analysis and map personal real-time mood swings about noise in various contexts experienced by people in their daily movements using individual GPS trajectories and noise exposure data collected from portable smart devices. To characterize noise-induced mood swings, we present a focal change pattern detection method to identify changes of measured sounds that are significantly different from their temporal neighborhoods in time series. Further, we examine the variations of individual noise exposure and mood swings across different travel models, activity types, places, and times. The results show that (1) the temporal change patterns of surrounding sounds identified at a focal scale are an important and effective indicator of personal mood swings; (2) the same level of sound may cause different perceptions of noise and moods in different acoustic environments; (3) personal noise exposure and mood swings vary significantly across space and time, as well as activity-related contexts.
Sensing real-time mood swings in reaction to noise by detecting focal change patterns in time series of individual noise exposure data
Category
Virtual Paper
Description
This abstract is part of a session. Click here to view the session.
Presentation File(s):
| File #2
| File #3
| File #4
| File #5
| Slides