19 results about "Time series" patented technology

An apparatus is provided for detecting Macro Sleep Architecture states of a subject such as WAKE, NREM and REM sleep from a subject's EEG. The apparatus includes an EEG digital signal assembly of modules arranged to convert analogue EEG signals into digital EEG signals. A bispectrum assembly is responsive to the EEG digital signal assembly and converts the digital EEG signals into signals representing corresponding bispectrum values. A bispectrum time series assembly, in electrical communication with an output side of the bispectrum assembly, generates at least one bispectrum time series for a predetermined frequency. A macro-sleep architecture (MSA) assembly is responsive to the bispectrum time series assembly and is arranged to produce classification signals indicating classification of segments of the EEG signals into macro-sleep states of the subject.

The present invention utilizes a cross-prediction scheme to predict values of discrete and continuous time observation data, wherein conditional variance of each continuous time tube variable is fixed to a small positive value. By allowing cross-predictions in an ARMA based model, values of continuous and discrete observations in a time series are accurately predicted. The present invention accomplishes this by extending an ARMA model such that a first time series “tube” is utilized to facilitate or “cross-predict” values in a second time series tube to form an “ARMAxp” model. In general, in the ARMAxp model, the distribution of each continuous variable is a decision graph having splits only on discrete variables and having linear regressions with continuous regressors at all leaves, and the distribution of each discrete variable is a decision graph having splits only on discrete variables and having additional distributions at all leaves.

The invention relates to a fraud detection method and device for video data, computer equipment and a storage medium. The method comprises the following steps: acquiring to-be-detected video data; extracting image data of each video frame from the to-be-detected video data, and dividing the image data into a plurality of image data sets according to the time sequence of each video frame, the imagedata sets which comprises image data corresponding to continuous video frames; inputting each image data set into a pre-trained image feature extraction model to obtain an image feature vector; extracting voice data from the to-be-detected video data, and obtaining a voice feature vector of the voice data; performing cascade splicing on the image feature vector and the voice feature vector to obtain a multi-modal feature vector; and inputting the multi-modal feature vector into a pre-trained fraud detection model to obtain a fraud detection result corresponding to the to-be-detected video data output by the fraud detection model. By adopting the method, the characteristic information amount can be increased, the comprehensiveness and diversity of the characteristic information are improved, and the accuracy of video data fraud detection is effectively improved.

The invention provides a time series based topic development clustering analysis system and method. The method comprises: collecting topics to form a cumulative reading quantity time series; performing differential processing on the time series to obtain a topic hot degree time series; determining whether the topic is in a recession period, continuing to collect topics if not; calculating S-Euc and S-DTW between the topics if so, and clustering all topics. The system comprises: a data collection unit; a data processing unit that performs forward differential processing on the cumulative reading quantity time series to determine whether the topic is in the recession period, stores the topics that are not in the recession period in a first topic storage library, and stores the topics that are in the recession period in a second topic repository; a time series distance calculation unit that calculates the S-Euc and the S-DTW between the topics; and a topic clustering unit that clusters all the topics. The above system and method have high precision and a good clustering effect.

The invention discloses an odor identification method based on gas sensors and deep learning, which is characterized in that a response curve cluster of odor to be detected is obtained through a gas sensor array, original data is directly used as an input sample of an odor identification deep neural network, data preprocessing and data amplification are performed on the input sample, time sequenceresponse data hierarchical features are automatically extracted by adoption of deep learning, global feature extraction and long-range dynamic feature extraction are performed at the same time, and an odor label is output through a classifier, so that high-sensitivity and specific odor identification is realized. The odor identification method of the invention has high sensitivity and high reliability, and can be widely applied to the fields of industrial production, medical treatment, environment, safety and the like.

A method for operating a real-time time series prediction model includes obtaining a first sequence corresponding to a target time series; obtaining a second sequence corresponding to a peer time series of the target time series; determining whether a predetermined number of time steps have elapsed since a last retraining of the real-time time series prediction model; and if the predetermined number of time steps have elapsed since the last retraining of the time series prediction model, retraining the real-time time series prediction model using a first portion of the first and second sequences; and applying a remaining portion of the first and second sequences to the real-time time series prediction model to predict a next value of the target time series.

A computer-implemented method for prescriptive time-series forecasting, which combines both what-if analysis and goal-seeking analysis. The method comprises building a model for a target metric with a set of predictors, based on historical time-series data, and computing, using the model, a set of forecast values. Using the set of forecast values with respect to a forecasting period, both a set of goals for the target metric and a set of constraints for the predictors are analyzed. A set of updated forecasts based on the analyses with respect to the forecasting period is determined to meet the goals within the set of constraints. The updated set of forecasts is presented with respect to the forecasting period, e.g., using a table, a visualization, and/or an interactive user interface.

The invention discloses a STM32 IAP based online program updating method. The method comprises the steps that I, an application program hex file of a lower computer circuit board in the need of being updated is loaded into an upper computer, the application program hex file structure is analyzed, the hexadecimal data in the need of being written into the lower computer flash are transferred through the Ethernet communications to a micro-controller; II, after the instructions transferred from the upper computer is received by the micro-controller, the program update time series are opened; III, the bootloader program is firstly run by the lower computer circuit board MCU, then the update related instructions of a micro-controller program are received through the bootloader program, application program erasing, application program data downloading, application program data validation and application program data jumping are applied on the lower computer, the hex data is written into an application program storage zone. The invention overcomes the deficiencies existing in the updating of the present circuit board program of the lower computer through an emulator.

The invention relates to an encrypted traffic data detection method and system, an electronic device and a storage medium, and the method comprises the steps: obtaining encrypted traffic data, and dividing the encrypted traffic data into a plurality of data packets according to a time sequence; detecting preset feature information in the plurality of data packets by using a streaming computation module; taking each data packet and the time sequence feature corresponding to each data packet as first traffic data, inputting the first traffic data into a trained first traffic prediction model, obtaining first probability information corresponding to each data packet, and obtaining second probability information corresponding to each data packet; at least performing data processing on the first probability information and the second probability information to obtain final probability information, and determining a network intrusion behavior corresponding to the data packet according to the final probability information. Through application of the method and the device, the problem of low detection efficiency of the abnormal behavior in the traffic data in related technologies is solved, and the technical effect of improving the detection efficiency of the abnormal behavior in the traffic data is realized.

The invention discloses a denoising method for a human embryo heart ultrasonic image based on a deep convolutional neural network, and the method comprises the following steps: obtaining an ultrasonicimage data set with time sequence and space sequence features, selecting a central image, and determining an adjacent image of the central image; calculating the similarity between the central pixelof the central image and each pixel in the search domain corresponding to the adjacent image; calculating a central pixel gray value corresponding to the adjacent image according to the similarity information and averaging the central pixel gray value to obtain a final gray value of the central pixel; and constructing a deep convolutional neural network model, and inputting the ultrasonic image which is not denoised into the trained deep convolutional neural network model to carry out denoising processing to obtain a difference between the noise image and the clean image, namely a residual image.

The invention discloses a vehicle load dynamic real-time calculation method, which comprises the following steps of: firstly, acquiring vehicle power system data in real time through a sensor, and establishing a vehicle dynamic theoretical model; introducing a deep neural network model, reducing the influence of sensor noise and environmental noise by using big data, and filtering interference factors to obtain a neural network model; wherein the big data comprises full-life-cycle time series data of a plurality of automobiles; training a neural network model at the cloud through a GPU cluster, and realizing edge deployment after test optimization; and finally, acquiring sensor data in real time through a vehicle-mounted module, synchronously inputting the sensor data into the trained neural network model, and calculating dynamic vehicle load data. Real-time monitoring of commercial vehicle load data is achieved, the overload phenomenon can be effectively eradicated, good social benefits are achieved. A pure software scheme is adopted, and compared with a traditional fixed-point inspection station and a refitted vehicle scheme, the invention has overwhelming advantages.

The invention provides an oil tank liquid level ultrasonic measurement method and system based on LSTM, a terminal and a storage medium, and the method comprises the steps: employing an ultrasonic device to regularly collect the height of the oil tank liquid level, and generating a liquid level time sequence; processing the liquid level time sequence by using a pre-trained long-short-term memory artificial neural network model to obtain a predicted liquid level height; generating a liquid level fluctuation curve graph by using the liquid level time sequence, and outputting and displaying the liquid level fluctuation curve graph and the predicted liquid level height. According to the method, the actually detected oil tank liquid level height is imported into the trained long-short-term memory artificial neural network model, so that the predicted liquid level height is obtained, the predicted liquid level height is a numerical value obtained by learning the long-short-term memory artificial neural network model based on an actual liquid level height trend, the influence of liquid level fluctuation is small, and the prediction accuracy is high. Therefore, compared with a traditional liquid level measuring method, the accuracy of a result obtained by the method is better.

The invention discloses an engine parameter detection method which is characterized by comprising the following steps: acquiring a plurality of engine parameters of a plurality of sorts of an airplane; obtaining a time series data set formed by each engine parameter of a single sortie; performing anomaly detection on the engine parameters of each time series data set through an anomaly detection algorithm based on a probability statistics model, and calculating an average value, a standard deviation and probability statistics model parameters of each single sortie engine parameter; for each engine parameter, constructing a support vector machine classification model through the calculated multiple groups of average values, standard deviations and probability statistics model parameters; and calculating an average value and a standard deviation of the engine parameters of the new sortie, predicting corresponding probability statistics model parameters through a support vector machine model, and obtaining abnormal data in the probability statistics model parameters of the aircraft engine of the new sortie by the probability statistics model parameters through an anomaly detection algorithm based on a probability statistics model. The method can effectively predict the health condition of the aircraft engine.

The invention relates to a method for automatically extracting a coral reef based on a time sequence remote sensing image. The method comprises the following steps: 1, carrying out parallel preprocessing on the remote sensing image, namely carrying out atmospheric correction on the image; step 2, automatic screening of remote sensing images: automatic screening of the images is realized from four aspects of space overlapping, date uniqueness, cloud cover and image entropy; 3, time sequence construction: constructing a time sequence of the image MNDWI; and 4, automatically extracting the coral reef, namely constructing a characteristic curve of the coral reef time sequence, calculating a DTW value between the pixel-level time sequence and the characteristic curve, determining a DTW threshold value by using a dichotomy method, and extracting the coral reef. According to the invention, the problem that various noises exist in the coral reef image is solved, automatic screening of the remote sensing image is realized, a reliable method for automatically extracting the coral reef based on the time sequence remote sensing image is provided, and a process thought is provided for automatically extracting the coral reef range based on other satellite sensors.