A Novel Smart Belt for Anxiety Detection, Classification, and Reduction Using IIoMT on Students' Cardiac Signal and...

Area of Science:

• Medical Informatics
• Psychology
• Integrative and Complementary Medicine

Background:

• Rising anxiety levels in university students negatively impact academic and social development.
• Effective anxiety detection and management are crucial for cognitive function and competitive academic performance.
• The study addresses the need for integrated frameworks combining technology and interventions for student mental well-being.

Purpose of the Study:

• To investigate a framework for detecting and reducing anxiety in university students.
• To evaluate the efficacy of Mano Shakti Yoga (MSY) in mitigating anxiety.
• To utilize the Intelligent Internet of Medical Things (IIoMT) for real-time anxiety monitoring and intervention.

Main Methods:

• An integrated detection-estimation-reduction framework using IIoMT (wearable smart belt) and machine learning algorithms (Decision Tree, Random Forest, AdaBoost).
• Sixty-six university students with anxiety (identified via SAS and smart belt) were randomly assigned to an experimental (MSY intervention) or control group.
• The experimental group practiced MSY for 1 hour, twice weekly, over 6 weeks.

Main Results:

• The experimental group showed a significant reduction in anxiety compared to the control group (p < 0.05).
• Machine learning analysis of cardiac signals from the smart belt facilitated anxiety detection and assessment.
• The Random Forest algorithm achieved a maximum accuracy of 80% in intelligent anxiety detection techniques.

Conclusions:

• Mano Shakti Yoga (MSY) is an effective intervention for reducing anxiety in university students.
• The IIoMT framework, combined with MSY, offers a viable approach for managing student anxiety.
• Practicing MSY can enhance students' intelligence, attention, and memory, supporting academic success.