University of Nebraska

Mohammad H Hasan

Fadi Mohammad Alsaleem

A micro-electro-mechanical-systems (MEMS) device is disclosed that is configured to operate as a reservoir computer including performing sensing and computing co-locally. The MEMS device includes circuitry for: generating a modulated input signal based on an input signal; generating a MEMS deflection signal based on the modulated input signal and a time-delayed MEMS deflection signal; sampling the MEMS deflection signal N times during a time internal T to generate a MEMS deflection matrix, wherein MEMS deflection matrix has a size M×N, wherein N corresponds to a number of virtual nodes of the reservoir computer and M is a number of time steps of time interval T; receiving a trained weight matrix, wherein the trained weight matrix is trained by linear regression; and multiplying the MEMS deflection matrix by the trained weight matrix to generate an output signal that classifies the input signal.

Artificial intelligence-based analog sensors and wearable devices incorporating the same

Systems and methods to amplify the response of a MEMS micro-oscillator by driving the MEMS device at its electrical and mechanical resonance frequencies, simultaneously. This enhances the MEMS mechanical sensitivity to electrical excitation and increases the voltage across the MEMS capacitor. Moreover, using a combination of two input signals at different frequencies (beat signal) may be used to achieve double resonance in any MEMS device, even if its natural frequency is far from its electrical resonance.

Growing community of inventors

Omaha, NE, United States of America

Mohammad H Hasan