Deep-Learning-Based Deconvolution of Mechanical Stimuli with Ti3C2Tx MXene Electromagnetic Shield Architecture via Dual-Mode Wireless Signal Variation Mechanism.

Passive component-based soft resonators have been spotlighted in the field of wearable and implantable devices due to their remote operation capability and tunable properties. As the output signal of the resonator-based wireless communication device is given in the form of a vector (i.e., a spectrum of reflection coefficient), multiple information can, in principle, be stored and interpreted. Herein, we introduce a device that can deconvolute mechanical stimuli from a single wireless signal using dual-mode operation, specifically enabled by the use of Ti3C2Tx MXene. MXene's strong electromagnetic shielding effect enables the resonator to simultaneously measure pressure and strain without overlapping its output signal, unlike other conductive counterparts that are deficient in shielding ability. Furthermore, convolutional neural-network-based deep learning was implemented to predict the pressure and strain values from unforeseen output wireless signals. Our MXene-integrated wireless device can also be utilized as an on-skin mechanical stimuli sensor for rehabilitation monitoring after orthopedic surgery. The dual-mode signal variation mechanism enabled by integration of MXene allows wireless communication systems to efficiently handle various information simultaneously, through which multistimuli sensing capability can be imparted into passive component-based wearable and implantable electrical devices.

Parallel Signal Processing of a Wireless Pressure-Sensing Platform Combined with Machine-Learning-Based Cognition, Inspired by the Human Somatosensory System.

Inspired by the human somatosensory system, pressure applied to multiple pressure sensors is received in parallel and combined into a representative signal pattern, which is subsequently processed using machine learning. The pressure signals are combined using a wireless system, where each sensor is assigned a specific resonant frequency on the reflection coefficient (S11 ) spectrum, and the applied pressure changes the magnitude of the S11 pole with minimal frequency shift. This allows the differentiation and identification of the pressure applied to each sensor. The pressure sensor consists of polypyrrole-coated microstructured poly(dimethylsiloxane) placed on top of electrodes, operating as a capacitive sensor. The high dielectric constant of polypyrrole enables relatively high pressure-sensing performance. The coils are vertically stacked to enable the reader to receive the signals from all of the sensors simultaneously at a single location, analogous to the junction between neighboring primary neurons to a secondary neuron. Here, the stacking order is important to minimize the interference between the coils. Furthermore, convolutional neural network (CNN)-based machine learning is utilized to predict the applied pressure of each sensor from unforeseen S11 spectra. With increasing training, the prediction accuracy improves (with mean squared error of 0.12), analogous to humans' cognitive learning ability.