<![CDATA[The high prevalence of mental health disorders resulting from trauma caused by violence and sexual abuse has not been matched by adequate access to recovery services due to psychological barriers in the form of social stigma. This situation motivated the design of the “Pulih” interface, a smartwatch-based mental health support application developed using Research and Development (R&D) methods with a Design Thinking approach. This application integrates a Bidirectional Long Short-Term Memory (Bi-LSTM) deep learning architecture to analyze users’ Heart Rate Variability (HRV) and Resting Heart Rate (RHR) biometric data in real-time. AI testing results on the WESAD physiological dataset showed stable learning curve convergence without overfitting, achieving a training accuracy of 92.0%, validation accuracy of 90.5%, precision of 90.0%, recall of 91.0%, and an F1-Score of 90.5%. Meanwhile, an evaluation of the interface’s usability via the System Usability Scale (SUS) test with 27 respondents yielded an average score of 86.79 (falling into the ‘Excellent’ and ‘Acceptable’ categories with an A+ grade). The encrypted anonymous community feature further strengthens privacy aspects. In conclusion, Pulih has proven to possess trauma-sensitive technical reliability as well as high usability as an inclusive digital solution for the mental recovery of PTSD survivors.]]>
Copyrights © 2026
