Design Digital Twins (2024-2025)

This study focuses on a core design question: how can data from smart home environments and user sleep monitoring be utilised to help users proactively develop healthy sleep habits and regular sleep-wake patterns through personalised dynamic environmental adjustments and behavioural guidance, thereby enhancing home comfort and quality of life? The research background highlights that sleep quality is closely linked to the living environment; however, in modern life, many people’s sleep rhythms are disrupted by work-related stress, the use of electronic devices and irregular schedules. The development of smart home technology has made it technically possible to coordinate environmental and health adjustments; however, existing systems predominantly respond passively to user commands and lack the ability to actively learn from and provide long-term guidance on users’ sleep patterns. To address this, this study has designed a smart sleep comfort system named ‘The Self-Sculptor’. By deploying environmental sensors and contactless sleep monitoring devices throughout the home, the system collects objective physiological data and environmental parameters from users to construct personalised sleep models. The system’s core functions include: dynamically adjusting the environment based on real-time sleep stage recognition (such as dimming lights and adjusting temperature and humidity to create optimal conditions for falling asleep); establishing a model of the user’s sleep rhythm through long-term data accumulation to predict suitable bedtimes and wake-up times; selecting the optimal moment within a preset wake-up window to gently rouse the user (e.g. by simulating sunrise lighting effects), thereby avoiding the discomfort caused by sudden awakening during deep sleep; generating regular sleep quality analysis reports and personalised recommendations for optimising daily routines; and introducing social sharing and leaderboard mechanisms to encourage users to maintain healthy routines through gamified incentives. The system is also accompanied by a physical room model and a digital twin prototype, used to visualise environmental parameters and system feedback. The core contribution of this design lies in upgrading passive environmental regulation to active sleep health management. Through a closed-loop mechanism of ‘data-driven modelling – real-time environmental response – long-term behavioural guidance’, it enables users to naturally develop healthier sleep habits without the need for active intervention, thereby providing a practical design paradigm and prototype validation for the functional transition of smart homes from ‘comfort and convenience’ to ‘health promotion’.