Search

In this communication, we propose the vector-graph-feature-extraction (VGFE) approach to accurately and concisely characterize details of electromagnetic metasurface (EM), and then train a progressive deep neural network (DNN), which can realize accurate prediction of complex electromagnetic spectrums from precise EM structures, or vice versa. Compared with the traditional neural-network-assisted design of metasurface structures, the VGFE-DNN method ensures comprehensive coverage of graphical features of metasurface and simplifies the number of feature extraction parameters at the same time, which can cover the complex and diverse surface structure designs with a smaller number of parameters. It offers strong adaptability and versatility by flexibly altering the electromagnetic spectrums and parameter combinations according to the needs of design objectives. The multifrequency point FSS design was realized as an example. A DNN was built up and trained by 6000 random combinations of parameters with an average error of 4%. After VGFE-DNN training, a variety combination of different spectral widths, different numbers, and location of frequency points can be easily customized, while maintaining angular stability and high light transmittance. The FSS structures with one to five frequency points were designed, respectively, and two of them were experimentally fabricated and tested, which successfully verified the accuracy of the VGFE-DNN method.

This work proposes a new type of portable piano based on a gridless flexible intelligent pressure-sensing system, deep neural networks (DNNs), and hardware circuits. First, a gridless flexible sensor with the same shape and size of a traditional piano key is fabricated using carbon black (CB)-doped polydimethylsiloxane (PDMS). Second, with the help of DNN, the gridless flexible sensor replaces the traditional piano key to collect the pressing pressure and location information in real time. Finally, the collected information is used to drive a speaker to make the corresponding piano sound, mimicking the accurate response of a traditional piano key when pressed with the same location and magnitude. In terms of material innovation, a multilayer packaging scheme for the sensor is developed so that the resistance change rate of the sample after 21 days was less than 2%, and the average coefficient of variation (CV) was close to 1%, which greatly improves the long-term stability. In terms of mechanism innovation, the DNN accurately predicts the magnitude and location of pressure, with an average localization error of less than 3% and an average pressure prediction error of less than 1%, so that the sound of the target frequency can be precisely stimulated.