221 results about "Signal prediction" patented technology

An image encoding apparatus for application to images expressed as respective frames of a digital video signal, whereby an image is converted into an array of blocks with specific blocks predetermined as being independent internally encoded blocks and the remainder as predictively encoded blocks, with predicted pixel signal values for a predictively encoded block being derived by interpolation from pixel signal values of at least one pair of blocks which have been already encoded and enclose that predictively encoded block along the row or column directions or both the row and column directions. Encoding efficiency is enhanced by applying Discrete Sine Transform processing along the interpolation direction, when encoding an array of prediction error signal values derived for a block, and by executing adaptive prediction by determining an optimum interpolation direction, when there are two possible directions for deriving predicted pixel signal values for a block.

An encoder/decoder is based on a combination of two audio or video channels to obtain a first combination signal as a mid-signal and a residual signal derivable using a predicted side signal derived from the mid-signal. A decoder uses the prediction residual signal, the first combination signal, a prediction direction indicator and prediction information to derive decoded first channel and second channel signals. A real-to-imaginary transform can be applied for estimating the imaginary part of the spectrum of the first combination signal. The prediction signal used in the derivation of the prediction residual signal, the real-valued first combination signal is multiplied by a real portion of the complex prediction information and the estimated imaginary part of the first combination signal is multiplied by an imaginary portion of the complex prediction information.

Decision Feedback Equalization techniques are difficult to apply in high speed communications systems, as the decoding process for a received symbol may not be completed in time to allow adaptive detection of the following symbol. Advantage may be taken of certain novel aspects of vector signaling codes to provide decision feedback to an adaptive data receiver concurrent with symbol decoding, rather than being delayed to symbol decode completion. Methods and systems are described that error correct an initial non-adaptive decoding, based on differences between the actual received signals and simulated received signals derived from the initial decoding and historical received data. Additional methods and systems are described using bounding functions to estimate an error rate with reduced computation.

A prediction based engine control system is disclosed. The engine control system may have sensor configured to sense a current engine operation and generate a corresponding signal and a controller in communication with the sensor. The controller may be configured to receive the signal, compare the current engine operation to an allowable range of engine operation, predict a future engine operation based on the signal, and limit current engine operation based on the prediction, even when the current engine operation is within the allowable range of operation.

Devices and systems with methods for detecting a sealing condition between a patient interface and a patient, and adjusting the patient interface to maintain the patient interface in sealing contact with the patient. The patient interface may include a sealing structure to form a seal on the patient, and a positioning structure to secure the sealing structure to the patient. The patient interface may include a sensor coupled to the sealing structure. A processor determines the sealing condition between the sealing structure and the patient based on a signal from the sensor, and adjusts at least one of the sealing structure and the positioning structure to maintain the sealing structure in sealing contact with the patient. A prediction system predicts a leak between the sealing structure and the patient based on the sensor signal. A learning system learns how to fit the sealing structure to the patient to form a seal.

The invention discloses a fatigue factor recessive anomaly detection and fault diagnosis method based on LSTM, and the method comprises the following steps: S1, collecting the time sequence data of target equipment of a related diagnosis object, and carrying out the empirical mode decomposition of the data; S2, constructing an equipment vibration signal prediction model based on LSTM by using thenormal data; S3, classifying the collected abnormal data, and constructing a fault time series data classification model based on LSTM; S4, taking the obtained mean square error MSE of the LSTM-basedvibration signal prediction model as an initial fatigue factor threshold; S5, predicting the equipment production data by using an LSTM-based vibration signal prediction model, calculating a mean square error between a predicted value and an actual value, and comparing the mean square error with an initial fatigue factor threshold to detect an abnormal signal; S6, classifying the abnormal signalsthrough a fault time series data classification model to obtain a fault diagnosis result.

The invention provides a time sequence signal efficient denoising and high-precision reconstruction modeling method and system. The method comprises: carrying out data preprocessing on original pulsewave signals; selecting a preset signal duration, and dividing the pulse wave signals after data preprocessing into a prediction set, a training set and a test set; selecting a convolutional neural network as a basic model of the deep convolutional noise reduction auto-encoder, and obtaining a deep convolutional noise reduction auto-encoder model according to a signal denoising requirement; inputting the training set into a deep convolution noise reduction auto-encoder model for training, and optimizing and selecting parameters of the deep convolution noise reduction auto-encoder model by using the regularization parameters and the test set to obtain an optimal deep learning model; and inputting the noisy pulse wave signal prediction set into the optimal deep learning model to obtain deepstructure features, performing signal reconstruction and denoising processing, and evaluating model performance. According to the method, denoising and reconstruction of the pulse wave signals are effectively carried out, and a new thought is provided for filtering same-frequency noise interference in the pulse wave signals.

A wide area measurement system adaptive time-delay compensation method relates to a time-delay compensation method. At present, for methods adopting prediction compensation, the duration of prediction time is directly set at a fixed value according to experience, the adaptation is poor, and the prediction compensation error is large. The method provided by the invention comprises the following steps of determining the time-delay duration of prediction compensation required by each PMU substation of a wire area measurement system; selecting a corresponding measurement signal according to needs, performing prediction compensation, performing pretreatment of the measurement signal, wherein the pretreatment comprises detection and processing of abnormal data in historical data, detecting whether abnormal data occur by calculating whether the measurement signal data change rate is suddenly changed or not, and replacing the abnormal data when the abnormal data are detected; and a step of performing prediction compensation of data of the selected measurement signal. The time-delay compensation method of the technical scheme is simple and reliable, the calculation data size is small, the prediction compensation error is small, and accurate prediction compensation is achieved.

A neural network learning process provides a trained network that has good generalization ability for even highly nonlinear dynamic systems, and is trained with approximations of a signal obtained, each at a different respective resolution, using wavelet transformation. Approximations are used in order from low to high. The trained neural network is used to predict values. In a preferred embodiment of the invention, the trained neural network is used in predicting network traffic patterns.

One embodiment of the present invention provides a system that optimizes a regression model which predicts a signal as a function of a set of available signals. During operation, the system receives training data for the set of available signals from a computer system during normal fault-free operation. The system also receives an objective function which can be used to evaluate how well a regression model predicts the signal. Next, the system initializes a pool of candidate regression models which includes at least two candidate regression models, wherein each candidate regression model in the pool includes a subset of the set of available signals. The system then optimizes the regression model by iteratively: (1) selecting two regression models U and V from the pool of candidate regression models, wherein regression models U and V best predict the signal based on the training data and the objective function; (2) using a genetic technique to create an offspring regression model W from U and V by combining parts of the two regression models U and V; and (3) adding W to the pool of candidate regression models.

The invention discloses an unmanned aerial vehicle anti-GPS spoofing system and a method based on multisource information fusion. The method comprises the following steps of: the sensor subsystem collecting the data in real time and sending the data to a Kalman filtering subsystem and a GPS spoofing attack detection subsystem; the Kalman filtering subsystem carries out the filtering processing onthe data received by the sensor by using an extended Kalman filtering method, calculating a prediction value of the state of the unmanned aerial vehicle at the kth moment of the unmanned aerial vehicle, and obtaining a prediction value of the GPS sensor signal, then sending the prediction value to a spoofing detection subsystem; the GPS spoofing attack detection subsystem comparing the received GPS signal prediction value with the actual value received by the GPS sensor, calculating the residual error between the two, and recognizing whether the residual error is abnormal or not by using a BHTalgorithm, realizing the real-time detection of the GPS spoofing attack of the unmanned aerial vehicle. The unmanned aerial vehicle has relative high anti-interference performance, and can effectively improve the safety of the unmanned aerial vehicle in performing tasks in the complex airspace when the unmanned aerial vehicle is in an interfering more complicated environment.

An analog-to-digital converter has a sampler to hold a sampled signal, an input signal predictor to generate a prediction signal at predetermined timing before a signal level of a ramp signal that monotonically increases or monotonically decreases with time crosses a signal level of the sampled signal, a comparator to compare signal levels of the ramp signal and the sampled signal to output a comparison signal showing whether the signal level of the ramp signal is larger than the signal lever of the sampled signal, a first counter to perform a count operation in synchronism with a first clock signal within a period from start of a comparison operation by the comparator to generation of the prediction signal, and a second counter to perform a count operation in synchronism with a second clock signal.

A positioning method includes: determining a receiving environment of a satellite signal from a positioning satellite; predicting a state vector including a position of a positioning device and a velocity of the positioning device based on the satellite signal; predicting a first distance-equivalent value indicating a distance between the positioning satellite and the positioning device; measuring a second distance-equivalent value indicating a distance between the positioning satellite and the positioning device; calculating an observed value indicating a difference between the first distance-equivalent value and the second distance-equivalent value; setting a first measurement error for the positioning satellite based on a signal strength of the satellite signal; setting a suitability condition of the observed value based on the receiving environment; setting a second measurement error larger than the first measurement error when the observed value is not suitable by the suitability condition; and correcting the state vector using the observed value and the second measurement error.

Various methods and systems disclosed compand audio signals using signal prediction, followed by expansion and reconstruction. The methods and systems compress and expand an error signal that represents deviations between samples of the original signal and predicted samples. Each predicted sample is generated by an extrapolation based on a sub-sequence of prior samples of the original signal. A time series of correction samples based on the error signal as it is received from the analog channel after amplitude expansion. Output samples are then generated from the sums of the correction samples and respective predicted samples of a second time series, each of which is extrapolated based on a sub-sequence of prior correction samples. Numerous variations are also disclosed.

Methods and apparatuses are described for performing adaptive analog-to-digital conversion and time-to-delay conversion by using signal prediction to adjust reference voltages of adjustable comparators.

Methods and apparatuses are described for performing adaptive analog-to-digital conversion and time-to-delay conversion by using signal prediction to adjust reference voltages of adjustable comparators.

Provided is a display device (100) which predicts a predicted temperature difference between a peripheral display area and an outer peripheral area of a display section (200) based on an input image signal from an image-signal input section (10). When the predicted temperature difference is a set reference value or more, the display device (100) controls luminance of an image displayed on the peripheral display area so as to be lowered. Therefore, the predicted temperature difference is predicted by using only the input image signal, and the luminance of the image displayed on the peripheral display area can be appropriately controlled without performing a calculation using the predicted temperature difference. Hence, such a luminance control for preventing breakage of the display section (200) can be easily performed.

Disclosed herein are a system and method for trend prediction of signals in a time series using a Markov model. The method includes receiving a plurality of data series and input parameters, where the input parameters include a time step parameter, preprocessing the plurality of data series according to the input parameters, to form binned and classified data series, and processing the binned and classified data series. The processing includes initializing a Markov model for trend prediction, and training the Markov model for trend prediction of the binned and classified data series to form a trained Markov model. The method further includes deploying the trained Markov model for trend prediction, including outputting trend predictions. The method develops an architecture for the Markov model from the data series and the input parameters, and disposes the Markov model, having the architecture, for trend prediction.

A method (and system) for coding a signal includes comparing a first prediction which is based upon a previously reconstructed signal to an actual signal to determine a first prediction error, comparing a second prediction which is based upon temporal filtering to the actual signal to determine a second prediction error, and selecting one of the first prediction error and the second prediction error.

When the entire image is divided into regions, each of which is subjected to predictive encoding while predicting an image signal by using an independent method assigned to the region, the object number and a representative pixel value for each object are predicted utilizing spatial continuity for the presence of the object, and also using decoded pixel values of a previously-processed neighbor region adjacent to a processing region. Accordingly, it is possible to reduce the amount of code required for encoding the object number in the processing region or the pixel value as a representative of each object in the processing region, where these encoded items are required in highly accurate image signal prediction which can handle any object shape by utilizing the pixel value as a representative of each object in the processing target region and information for identifying the object assigned to each pixel in the processing region. Therefore, efficient image encoding can be implemented. Since the employed decoded pixel values of pixels in a previously-decoded neighbor region are common information between the encoding and decoding sides, appropriate prediction can be performed even in the case where one of multiple image signal prediction modes is selected for each region, like in H.264.