A performing device of a gesture recognition system for reducing a false alarm rate executes a performing procedure of a gesture recognition method for reducing the false alarm rate. The gesture recognition system includes two neural networks. A first recognition neural network is used to classify a gesture event, and a first noise neural network is used to determine whether the sensing signal is the noise. Since the first noise neural network can determine whether the sensing signal is the noise, the gesture event may not be executed when the sensing signal is the noise. Therefore, the false alarm rate may be reduced.

A gesture recognition system using siamese neural network executes a gesture recognition method. The gesture recognition method includes steps of: receiving a first training signal to calculate a first feature; receiving a second training signal to calculate a second feature; determining a distance between the first feature and the second feature in a feature space; adjusting the distance between the first feature and the second feature in feature space according to a predetermined parameter. Two neural networks are used to generate the first feature and the second feature, and determine the distance between the first feature and the second feature in the feature space for training the neural networks. Therefore, the gesture recognition system does not need a big amount of data to train one neural network for classifying a sensing signal. A user may easily define a new personalized gesture.

A gesture recognition system using siamese neural network executes a gesture recognition method. The gesture recognition method includes steps of: receiving a first training signal to calculate a first feature; receiving a second training signal to calculate a second feature; determining a distance between the first feature and the second feature in a feature space; adjusting the distance between the first feature and the second feature in feature space according to a predetermined parameter. Two neural networks are used to generate the first feature and the second feature, and determine the distance between the first feature and the second feature in the feature space for training the neural networks. Therefore, the gesture recognition system does not need a big amount of data to train one neural network for classifying a sensing signal. A user may easily define a new personalized gesture.

An oscillator system includes a laser source; a high-Q electro-optical oscillator to generate a high-Q electro-optical oscillator signals having oscillator frequencies; and an environment-insensitive resonator including ENZ metamaterials. The resonator receives a laser from the laser source and generate a feedback signal to lock the oscillator to reduce a phase/frequency noise in the oscillator. An optical system also includes a high-Q electro-optical oscillator to generate a high-Q electro-optical oscillator signal having oscillator frequencies; an environment insensitive signal delay waveguide having an EMNZ metamaterial such that the signal delay waveguide delays the high-Q electro-optical oscillator signal and generates a delayed signal; and a phase-lock circuit to receive the delayed signal from the signal delay waveguide and provide an electrical feedback signal to the oscillator.

An oscillator system includes a laser source; a high-Q electro-optical oscillator to generate a high-Q electro-optical oscillator signals having oscillator frequencies; and an environment-insensitive resonator including ENZ metamaterials. The resonator receives a laser from the laser source and generate a feedback signal to lock the oscillator to reduce a phase/frequency noise in the oscillator. An optical system also includes a high-Q electro-optical oscillator to generate a high-Q electro-optical oscillator signal having oscillator frequencies; an environment insensitive signal delay waveguide having an EMNZ metamaterial such that the signal delay waveguide delays the high-Q electro-optical oscillator signal and generates a delayed signal; and a phase-lock circuit to receive the delayed signal from the signal delay waveguide and provide an electrical feedback signal to the oscillator.

A phase coherent NCO circuit includes a base frequency NCO, a phase seeding circuit, a scaled frequency NCO, a sine/cosine generator. The base frequency NCO is configured to generate base phase values based on a base frequency control word. The phase seeding circuit is coupled to the base frequency NCO. The phase seeding circuit is configured to generate a seed phase value based on the base phase values and a scale factor value. The scaled frequency NCO is coupled to the phase seeding circuit. The scaled frequency NCO is configured to generate oscillator phase values based on the phase seed value and an oscillator frequency control word. The sine/cosine generator is coupled to the scaled frequency NCO. The sine/cosine generator is configured to generate oscillator output samples based on the oscillator phase values.

A phase coherent NCO circuit includes a base frequency NCO, a phase seeding circuit, a scaled frequency NCO, a sine/cosine generator. The base frequency NCO is configured to generate base phase values based on a base frequency control word. The phase seeding circuit is coupled to the base frequency NCO. The phase seeding circuit is configured to generate a seed phase value based on the base phase values and a scale factor value. The scaled frequency NCO is coupled to the phase seeding circuit. The scaled frequency NCO is configured to generate oscillator phase values based on the phase seed value and an oscillator frequency control word. The sine/cosine generator is coupled to the scaled frequency NCO. The sine/cosine generator is configured to generate oscillator output samples based on the oscillator phase values.

Systems and methods for digital synthesis of an output signal using a frequency generated from a resonator and computing amplitude values that take into account temperature variations and resonant frequency variations resulting from manufacturing variability are described. A direct frequency synthesizer architecture is leveraged on a high Q resonator, such as a film bulk acoustic resonator (FBAR), a spectral multiband resonator (SMR), and a contour mode resonator (CMR) and is used to generate pristine signals.

Systems and methods for digital synthesis of an output signal using a frequency generated from a resonator and computing amplitude values that take into account temperature variations and resonant frequency variations resulting from manufacturing variability are described. A direct frequency synthesizer architecture is leveraged on a high Q resonator, such as a film bulk acoustic resonator (FBAR), a spectral multiband resonator (SMR), and a contour mode resonator (CMR) and is used to generate pristine signals.

Systems and methods for digital synthesis of an output signal using a frequency generated from a resonator and computing amplitude values that take into account temperature variations and resonant frequency variations resulting from manufacturing variability are described. A direct frequency synthesizer architecture is leveraged on a high Q resonator, such as a film bulk acoustic resonator (FBAR), a spectral multiband resonator (SMR), and a contour mode resonator (CMR) and is used to generate pristine signals.