Toward a Brain-Computer Interface- and Internet of Things-Based Smart Ward Collaborative System Using Hybrid Signals

Area of Science:

• Biomedical Engineering
• Human-Computer Interaction
• Ubiquitous Computing

Background:

• Traditional smart ward systems lack integrated BCI control.
• Existing BCIs often struggle with accuracy and false operations.
• Need for seamless integration of patient monitoring and control systems.

Purpose of the Study:

• To develop a hybrid BCI and IoT system for smart ward collaboration.
• To enhance BCI control accuracy using electroencephalography (EEG), electrooculography (EOG), and gyroscope (gyro) signals.
• To establish an IoT architecture for efficient smart ward communication.

Main Methods:

• A hybrid asynchronous BCI control system with a GUI paradigm for cursor movement.
• User control via gyro for area selection and blink-related EOG for cursor clicks.
• EEG signal classification using Support Vector Machine (SVM) for attention state judgment.
• Development of an IoT monitoring and management system using Narrowband IoT (NB-IoT) technology.

Main Results:

• The hybrid BCI control system achieved 96.65% ± 1.44% accuracy.
• Low false operation rate (0.89 ± 0.42 events/min) and command response time (2.65 ± 0.48 s).
• The NB-IoT based architecture demonstrated superior communication transmission quality.

Conclusions:

• The proposed hybrid BCI system shows significant potential for application in daily tasks within smart wards.
• The integrated BCI-IoT system offers a robust solution for collaborative smart ward environments.
• This technology can improve patient interaction and monitoring efficiency in healthcare settings.