Enhancing User Experience for Real-Time Panic Attack Detection with Wearable Technology: A Human-Computer Interaction Approach with Machine Learning Integration

چکیده

Panic attacks are sudden and debilitating episodes of intense fear, often accompanied by physiological symptoms such as increased heart rate, irregular heart rhythms, and shortness of breath. Early detection and timely intervention can significantly improve the management of panic disorder. This paper presents a human-computer interaction (HCI) focused approach to real-time panic attack detection using wearable devices that monitor physiological signals. The system uses data such as heart rate (HR), heart rate variability (HRV), blood oxygen saturation (SpO2), and electrocardiogram (ECG) to predict panic attacks. A machine learning model, incorporating algorithms such as Support Vector Machines (SVM) and Convolutional Neural Networks (CNN), is employed to analyze these signals and detect abnormal patterns indicative of a panic episode. The study prioritizes the user interface design and interaction experience, ensuring the system is user-friendly, discreet, and provides timely alerts and coping strategies. A six-month clinical trial with participants diagnosed with panic disorder demonstrated the feasibility of real-time monitoring and detection. Results show promising accuracy in detecting panic attacks, while user feedback indicated high satisfaction with the device's usability and effectiveness in real-world scenarios. This research contributes to the growing field of wearable technology in mental health by integrating machine learning with a focus on improving user experience.