Flexible triboelectric nanogenerators of Au-g-C3N4/ZnO hierarchical nanostructures for machine learning enabled body movement detection

Here we report the development of triboelectric nanogenerator (TENG) based self-powered human motion detector with chemically developed Au-g-C3N4/ZnO based nanocomposite on common cellulose paper platform. Compared to bare g-C3N4, the nanocomposite in the form of hierarchical morphology is found to exhibit higher output voltage owing to the contribution of Au and ZnO in increasing the dielectric constant and surface roughness. While generating power & SIM;3.5 & mu;W cm(-2) and sensitivity & SIM;3.3 V N-1, the flexible TENG, is also functional under common biomechanical stimuli to operate as human body movement sensor. When attached to human body, the flexible TENG is found to be sensitive towards body movement as well as the frequency of movement. Finally upon attaching multiple TENG devices to human body, the nature of body movement has been traced precisely using machine learning (ML) techniques. The execution of the learning algorithms like artificial neural network and random forest classifier on the data generated from these multiple sensors can yield an accuracy of 99% and 100% respectively to predict body movement with great deal of precision. The exhibition of superior sensitivity and ML based biomechanical motion recognition accuracy by the hierarchical structure based flexible TENG sensor are the prime novelties of the work.

Automated summary

In this study, a self-powered human motion detector based on triboelectric nanogenerator (TENG) with chemically developed Au-g-C3N4/ZnO based nanocomposite on cellulose paper platform was developed. The hierarchical morphology of the nanocomposite showed higher output voltage, which was attributed to the contribution of Au and ZnO in increasing dielectric constant and surface roughness. The flexible TENG exhibited power generation of approximately 3.5 μW cm(-2) and sensitivity of approximately 3.3 V N-1, and could detect human body movement and its frequency. Machine learning techniques were used to accurately predict body movement based on data from multiple TENG sensors, with accuracy of 99% and 100% achieved using artificial neural network and random forest classifier, respectively. The hierarchical structure-based flexible TENG sensor demonstrated superior sensitivity and accuracy in biomechanical motion recognition using machine learning.