Disclosed is a quaternion multi-degree-of-freedom neuron-based multispectral welding image recognition method, comprising: using three cameras having different wavebands to obtain multispectral weld pool images, and respectively performing pre-processing and edge extraction on the weld pool images having the different wavebands obtained at a same moment by the three cameras; establishing a quaternion-based multispectral weld pool image edge model; extracting low-frequency features after a quaternion discrete cosine transform; using a quaternion-based multi-degree-of-freedom neuron network to perform classification, training and recognition on edge features of the multispectral weld pool images. Compared to traditional means, the present invention has multiple recognition information sources, strong anti-interference capabilities and high recognition accuracy.

The present application provides a prediction method and a prediction device for food safety risk level and an electronic apparatus. The method includes: classifying food safety risk level based on historical test data for food safety, to obtain historical data for food safety risk level; performing wavelet decomposition on the historical data for food safety risk level based on Daubechies wavelet basis, to obtain a plurality of historical data components for food safety risk level; and inputting the plurality of historical data components for food safety risk level into an LSTM model and predicting a food safety risk level, to obtain a predicted value of the food safety risk level. By the prediction method and the prediction device for food safety risk level and the electronic apparatus according to the present application, the food safety risk level may be effectively predicted.

A computer implemented method includes accessing a multivariate time series set of samples collected by multiple biological sensors sensing a first biological function over a first period of time, dividing the data set into windows, calculating statistical dependencies between the samples of the timeseries data collected by each sensor, generating a relationship matrix as a function of the statistical dependencies, and transforming the relationship matrix to generate a first feature vector for each window of time that captures the statistical dependencies amongst the sensors.

An information processing method, an apparatus, an electronic device, a computer readable storage medium and a computer program product are provided. The method includes performing a fast Fourier transform-based feature crossing process on at least two target vectors in an input sequence of target information to obtain an output sequence of target information, and performing a feature perception process on the output sequence of the target information to obtain a target sequence of the target information, wherein the target sequence represents semantic information of each target object in the target information correlated to other target objects in the target information.

A network of motion sensors employs sensitive accelerometers to issue time-domain measurements of building movement from multiple locations within and between buildings and other structures. The time-domain measurements from the various motion sensors are synchronized and converted into frequency-domain measurements of building movement. Individual motion sensors can be equipped with the requisite processor and memory to synchronize and covert the time-domain measurements. The motions sensors can classify detected events into various event types, such as earthquakes, wind events, or bipedal locomotion. The sensors can also communicate with one another or other resources to calculate event probabilities. A motion sensor may, for example, receive an earthquake-verification signal responsive to an earthquake-verification request. The network of motion sensors can calculate local soil stiffness and financial loss estimations responsive to their individual or collective frequency-domain measurements.

A network of motion sensors employs sensitive accelerometers to issue time-domain measurements of building movement from multiple locations within and between buildings and other structures. The time-domain measurements from the various motion sensors are synchronized and converted into frequency-domain measurements of building movement. Individual motion sensors can be equipped with the requisite processor and memory to synchronize and covert the time-domain measurements. The motions sensors can classify detected events into various event types, such as earthquakes, wind events, or bipedal locomotion. The sensors can also communicate with one another or other resources to calculate event probabilities. A motion sensor may, for example, receive an earthquake-verification signal responsive to an earthquake-verification request. The network of motion sensors can calculate local soil stiffness and financial loss estimations responsive to their individual or collective frequency-domain measurements.

A device identification method, apparatus, and system are provided. A management device or a collection device first determines a network traffic feature of a to-be-identified device based on a first dataset. The first dataset includes a plurality of pieces of first data, and each piece of first data includes a data amount of a data packet that is of the to-be-identified device and that is collected within one first periodicity. Then, the management device or the collection device determines a device type of the to-be-identified device based on a device identification model and the network traffic feature of the to-be-identified device.

Disclosed is a quaternion multi-degree-of-freedom neuron-based multispectral welding image recognition method, comprising: using three cameras having different wavebands to obtain multispectral weld pool images, and respectively performing pre-processing and edge extraction on the weld pool images having the different wavebands obtained at a same moment by the three cameras; establishing a quaternion-based multispectral weld pool image edge model; extracting low-frequency features after a quaternion discrete cosine transform; using a quaternion-based multi-degree-of-freedom neuron network to perform classification, training and recognition on edge features of the multispectral weld pool images. Compared to traditional means, the present invention has multiple recognition information sources, strong anti-interference capabilities and high recognition accuracy.

Methods and systems to correct low-resolution measurements corresponding to unobservable high-resolution measurements by introducing variation in the plurality of low-resolution measurements to obtain perturbed values for the low-resolution measurements. The perturbed values have a higher resolution than another resolution of the low-resolution measurements. A distribution test is performed on the perturbed values.

A method, a computer program product, and a computer system handle a data gap in sequential data. The method includes receiving the sequential data for a period of time. The method includes selecting the data gap in the sequential data at a timestamp. The method includes determining a sliding window associated with the data gap based on the timestamp for a duration of time. The sliding window includes dependent data from which the data gap depends. The method includes, as a result of the dependent data of the sliding window including at least one window data gap, generating extracted patterns based on the dependent data to mask the at least one window data gap. The method includes determining a prediction to fill the data gap using a prediction model that takes as input modified data based on the dependent data and the extracted patterns.