Your search

In authors or contributors
Resource type
  • With the cross development of neuroscience and artificial intelligence, the bio signal-based environmental adaptive technology has become a research frontier in the field of smart home. In this paper, we propose a smart aromatherapy machine system that can combine brainwave (EEG) monitoring and AI-driven, aiming to achieve dynamic optimisation of the home environment through real-time EEG signal analysis. The study first builds a multimodal data acquisition module to extract the characteristic frequency bands such as α-wave and β-wave to identify the user's relaxation, concentration or fatigue state. Secondly, a lightweight deep learning model is designed to classify EEG signals in real-time and ensure low-latency interaction through edge computing architecture. The system dynamically regulates the aromatherapy machine based on the classification results. Users can self-select a theme in the system according to their preferences or emotions, and then the aromatherapy device releases the corresponding aroma according to the selected theme to help the user fall asleep more easily. During sleep, the system continuously tracks the user's sleep dynamics through an integrated sleep monitoring application, which transmits the data to the device. At the same time, the system collects and analyses detailed data on sleep quality, dream activity and scent adjustment to generate a comprehensive report that is sent to the user's smartphone. This innovative design not only enhances the user experience, but also provides a scientific basis for assessing individual sleep conditions. Current research shows that aromatherapy has a positive effect on improving sleep quality and relieving anxiety symptoms. However, there is still a lack of research on the dynamic adjustment of fragrance based on real-time sleep data. This study aims to fill this gap by developing a system that enables personalised fragrance release based on user preferences and real-time sleep monitoring data, providing users with an unprecedented sleep experience.

Last update from database: 11/9/25, 7:01 PM (UTC)

Explore

USJ Theses and Dissertations

Resource type