Machine Learning-Powered Ultrahigh Controllable and Wearable Magnetoelectric Piezotronic Touching Device

Recent advancements in nanomaterials have enabled the application of nanotechnology to the development of cutting-edge sensing and actuating devices. For instance, nanostructures' collective and predictable responses to various stimuli can be monitored to determine the physical environment of the nanomaterial, such as temperature or applied pressure. To achieve optimal sensing and actuation capabilities, the nanostructures should be controllable. However, current applications are limited by inherent challenges in controlling nanostructures that counteract many sensing mechanisms that are reliant on their area or spacing. This work presents a technique utilizing the piezo-magnetoelectric properties of nanoparticles to enable strain sensing and actuation in a flexible and wearable patch. The alignment of nanoparticles has been achieved using demagnetization fields with computational simulations confirming device characteristics under various types of deformation followed by experimental demonstrations. The device exhibits favorable piezoelectric performance, hydrophobicity, and body motion-sensing capabilities, as well as machine learning-powered touch-sensing/actuating features.