An inlet debris monitoring includes processing circuitry configured to: obtain a data set of electrostatic charge data from an electrostatic sensor; utilize a dimensional reduction technique to obtain a first set of basis vectors that represent the data set in a reduced dimensional space that is reduced with respect to initial dimensions of the data set; utilize the first set of basis vectors or a second set of reference basis vectors which are based on historical electrostatic charge data for one or more reference gas turbine engines, to project the data set onto the reduced dimensional space and obtain a reduced dimensional representation of the data set; utilize machine learning to determine whether the reduced dimensional representation of the data set indicates foreign object debris in the particular gas turbine engine; and based on the determination indicating detection of foreign object debris, provide a foreign object debris notification.

An atomizer for adaptively generating pharmaceutical aerosols of different particle sizes is illustrated, which comprises a sensor module, a waveform pattern determination module, a high-frequency oscillation circuit, a signal modulation module, a piezoelectric device and a porous screen. The sensor module senses a body state of the patient, wherein the body state includes a breathing state. The waveform pattern determination module generates a modulation control signal according to the body state. The high-frequency oscillation circuit provides a high-frequency oscillation signal. The signal modulation module modulates the high-frequency oscillation signal by using the modulation control signal to generate a vibration signal. The piezoelectric device vibrates according to the vibration signal. According to vibration of the piezoelectric device, the porous screen presses the liquid medicine through a plurality of holes of the porous screen to generate a plurality of pharmaceutical aerosols.

A sensory evaluation method for spectral data of mainstream smoke includes: performing a data enhancement on spectral data of mainstream smoke of a plurality of cigarettes; extracting a shallow spectral characteristic from the spectral data of the mainstream smoke of each cigarette; obtaining a shallow sensory quality result of the spectral data of the mainstream smoke of each cigarette based on the spectral data of the mainstream smoke of each cigarette and the shallow spectral characteristic; extracting deep spatial characteristics from the spectral data of the mainstream smoke of each cigarette; obtaining a deep sensory quality result based on the spectral data of the mainstream smoke of each cigarette and the deep spatial characteristics; obtaining a comprehensive sensory quality result according to the shallow sensory quality result and the deep sensory quality result. The sensory evaluation method achieves accurate screening of unknowns in the mainstream smoke.

In some embodiments, a style transfer computing system receives, from a computing device, an input text and a request to transfer the input text to a target style combination including a set of target styles. The system applies a style transfer language model associated with the target style combination to the input text to generate a transferred text in the target style combination. The style transfer language model comprises a cascaded language model configured to generate the transferred text. The cascaded language model is trained using a set of discriminator models corresponding to the set of target styles. The system provides, to the computing device, the transferred text.

This disclosure relates generally to a system and method to identify a plurality of noises or their combination to suppress them and enhancing the deteriorated input signal in a dynamic manner. It identifies noises in the audio signal and categorizing them based on the trained database of noises. A combination of deep neural network (DNN) and artificial Intelligence (AI) helps the system for self-learning to understand and capture noises in the environment and retain the model to reduce noises from the next attempt. The system suppresses unwanted noise coming from the external environment with the help of AI based algorithms, by understanding, differentiating, and enhancing human voice in a live environment. The system will help in the reduction of unwanted noises and enhance the experience of business and public meetings, video conferences, musical events, speech broadcasts etc. that could cause distractions, disturbances and create barriers in the conversation.

A method for calibrating the position and orientation of a camera, in particular a vehicle-mounted camera, relative to a calibration pattern includes the steps of: A] acquiring an image of the calibration pattern by the camera; B] determining a parameter of the image or of the calibration pattern; C] transforming the image based on the parameter; D] identifying characteristic points or possible characteristic points of the calibration pattern within the transformed image; E] deriving the position or orientation of the camera relative to the calibration pattern from the identified characteristic points or possible characteristic points; F] in dependence of a confidence value of the derived position or orientation of the camera or in dependence of the number of iterations of steps B to F so far, repeating steps B to F; and G] outputting the position or orientation of the camera derived in the last iteration of step E.

A tactile perception system is provided. The tactile perception system includes a storage unit storing tactile data and feature information corresponding to the tactile data, a sensing unit sensing surface characteristics of an object to generate a sensing signal, an extraction unit extracting sensing information from the sensing signal generated by the sensing unit, and a matching unit extracting a piece of feature information, which is matched with the sensing information, from the feature information stored in the storage unit and extracting a piece of tactile data, which corresponds to the piece of feature information, from the tactile data stored in the storage unit.

Embodiments of the present invention are directed to a noise-model based sensor converter configured to map a sensor measurement output to discrete, nonlinear steps of constant uncertainty. In a non-limiting embodiment of the invention, the sensor converter receives an output signal from a sensor. The output signal can include a measurement. The sensor converter can also receive a noise model. The output signal is mapped to a discrete set of steps based on the noise model. The discrete set of steps are nonlinearly spaced to provide constant uncertainty between adjacent steps. The sensor converter generates an output based on the discrete set of steps.

An integrated circuit (IC) is provided for in-situ anomaly detection. Sensors in the IC generates sensor datasets including information indicating conditions in the IC. A processing unit in the IC uses a sensor dataset and a model to detect and classify the anomaly. The processing unit may filter the sensor dataset, extract features from the filtered sensor dataset, and input the features into the model. The model outputs one or more classifications of the anomaly. A feature may be a distance vector that represents a difference between a data value in the filtered sensor dataset from a reference data value. The model may be a network of bit-cells in the IC. The model may be continuously trained in-situ, i.e., on the IC. The processing unit may provide the classifications to another processing unit in the IC. The other processing unit may mitigate the anomaly based on the classifications.

Disclosed is a system for face recognition based on dynamic updating of facial features, comprising an image acquisition unit, a face image standardization unit, a facial feature comparison unit, and a facial feature update unit. The image acquisition unit acquires an original image which is processed by the face image standardization unit, and then the facial feature comparison unit completes extraction and comparison of a facial feature vector to determine whether the original image belongs to a user ID or a stranger, or to complete entry of the facial feature vector. Each user ID corresponds to one or more facial feature vectors. The facial feature update unit automatically updates the facial feature vector in a normal workflow to improve reliability and accuracy of face recognition. Also disclosed is a method for face recognition using the system. The disclosure has the advantages of simple deployment and simple to use, improving the accuracy of face recognition without increasing the size of a face recognition network, and may quickly and effectively adapt to changes in environment or user's appearance.