62 results about "Statistical pattern" patented technology

A method, system, and computer program product for enabling dynamic detection of anomalies occurring within an input graph representing a social network. More specifically, the invention provides an automated computer simulation technique that implements the combination of Social Network Analysis (SNA) and statistical pattern classification for detecting abnormal social patterns or events through the expanded use of SNA Metrics. The simulation technique further updates the result sets generated, based on observed occurrences, to dynamically determine what constitutes abnormal behavior, within the overall context of observed patterns of behavior.

A technique is provided for analyzing a dataset. The technique includes generating multivariate parameters to capture statistical patterns over time and/or across dimensions in the dataset, and developing a dynamic model based on the multivariate parameters for analyzing the dataset.

Systems, methods, and computer-coded software instructions are provided for automated data analysis using graph topology techniques in a connections-mapping process to automatically identify interrelationships between various data fields in a system or body of data followed by statistical pattern analysis and machine learning techniques applied on the graphs (e.g., hidden networks) identified to improve analyses (e.g., automated analysis of medical bills and health insurance documents). Automated conversion of paper-based medical and insurance billing records to electronic data is provided, along with automatic correlation of medical services data to insurance plan policies and tax regulations for health benefits to detect errors or fraud, and to project health insurance plans for various subscribers.

The invention relates to a mattress fitting human body curves and a height adjusting method of the mattress, and belongs to the technical field of home life articles. According to the height adjusting method, the headrest area height of the mattress can be adjusted, that is, the height adjusting method comprises the following steps: firstly, a sleeping posture recognition model is established based on statistical pattern recognition; secondly, obtained human body pressure data are input in the sleeping posture recognition model, and sleeping postures with the highest similarity are taken as an output result; finally, a controller controls the working state of a height adjusting device according to the output result of the sleeping posture recognition model, so as to ensure that the headrest area of the mattress can be adjusted up and down. The mattress provided by the invention has the advantages that not only can the pillow height requirements of different people be met, but also the different pillow height requirements of people lying on the side and on the back can be met; through appropriate height adjustment for a spondylopathy patient, recovery of the vertebral curve of the spondylopathy patient can be facilitated; for people always lowering or raising heads to work, spondylopathy can be prevented.

The invention discloses a flutter online monitoring method for machining equipment. The method comprises the steps that a proper sampling window is selected; empirical mode decomposition is carried out on sampled vibration signals; decomposed eigen modalities are screened to obtain a characteristic eigen modality; Hilbert transformation is carried out on the characteristic eigen modality to obtain a time-frequency spectrum; statistical pattern analysis is carried out on the time-frequency spectrum to obtain characteristic parameters; the statistical characteristic parameters are compared with a set characteristic threshold value and the statistical characteristic parameter of a historical adjacent signal, and the vibration state of a system is judged. The flutter online monitoring method aims to solve the problems that a flutter detecting method is strong in sample dependency and poor in generalization ability, threshold value measurement is difficult, and judgment is not carried out in time, the method combining Hilbert-Huang transformation and statistical pattern recognition is provided, statistical modeling and clustering analysis are carried out on the time-frequency spectrum of the vibration signal based on the aggregation character of energy on frequency in the fluttering process, the characteristic parameters are utilized, the physical characteristic of cutting flutter is represented essentially, the cutting vibration state is effectively monitored in real time, and the judgment result is accurate and visual.

Correlations between patterns of events generated by various separate components within a cloud deployment are statistically determined. The determinations of the correlations can be based on dependencies between the components as indicated by a system topology graph including the components. The patterns correlated can be patterns of events from event streams generated by monitoring systems that monitor the components. The events in the event streams can represent changes over time in component state, behavior, or problem occurrence. Because the quantity of components within such a cloud deployment can be enormous, the quantity of events generated by the monitoring systems over a significant period of time can be voluminous.

The invention belongs to the technical fields of statistical pattern recognition and image processing, in particular to a super-resolution method based on an artificial neural network. In the invention, the artificial neural network is used for expressing the function mapping relation among low-resolution images and high-resolution images. The method of the invention comprises the following concrete steps: creating a training set; establishing a BP neural network for training; bonding high-resolution images which are obtained by training according to the corresponding relation; and then, obtaining super-resolution images. The invention overcomes the disadvantage of time consumption of the original super-resolution algorithm based on manifold learning, and obtains better effect.

The invention belongs to the technical field of statistical pattern recognition and image processing and particularly relates to an optimization algorithm of unmarked flat object recognition. The optimization algorithm comprises the steps of taking local feature key points as features of an unmarked object, and extracting features in initial stages of an off-line training stage and a real-time recognition stage by means of a dichotomy decision algorithm; performing off-line training on the key points through a random Ferns classifier; adopting a random sampling consistency algorithm in the recognition stage to obtain the position and the posture of the object in a real-time frame; adding position and posture information of the target object obtained by calculation to a virtual object, and overlaying position and posture information in an actual scene to complete an augmented reality system. According to the optimization algorithm, two optimizations are performed, namely, weighting screen is performed on the key points in a feature detection stage, and an improved ARANSAC fitting algorithm is adopted to enable interior points in an initial random set to be scaled-up and improve fitting performance in the recognition stage. Compared with a basic line algorithm, performance in all aspects can be improved greatly, and requirements for real-time performance and reliability of the augmented reality system can be met.

Systems and methods of determining the content of frames transmitted on a wireless network through comparison of captured frames to predetermined statistical patterns.

The invention discloses a collecting method of driver's driving behavior data and a collecting device of driver's driving behavior data. The method includes steps of collecting image of a driver in a car or/and outside of the car, performing grey and binarization processing on the image and forming multiple gray pictures; performing Fourier transform, orthogonal transformation and picture segmentation operation on the gray picture, and extracting target information; identifying vehicles, road lines, passengers and traffic signboard information by a fuzzy mode identification method and a statistical pattern recognition method; according to the well set alarm level, judging the alarm, and finally sending the analysis result to a sever through the network, classifying and summarizing by the server; integrating the vehicle running state and the driver's driving behavior, and using the data as basis for the third party to analyze the driver's driving behavior, or sending to the driver or insurance company. The invention can provide comprehensive dynamic information, complete data for insurance company, related O2O of automobile, traffic management and other industries, and well use big data to optimize traffic and improve safety.

A method of using natural language processing (NLP) techniques to extract information from online news feeds and then using the information so extracted to predict changes in stock prices or volatilities. These predictions can be used to make profitable trading strategies. Company names can be recognized and simple templates describing company actions can be automatically filled using parsing or pattern matching on words in or near the sentence containing the company name. These templates can be clustered into groups which are statistically correlated with changes in the stock prices. The system is composed of two parts: message understanding component that automatically fills in simple templates and a statistical correlation component that tests the correlation of these patterns to increases or decreases in the stock price. The methods can be applied to a broad range of text, including articles in online newspapers such as the Wall Street Journal, financial newsletters, radio &TV transcripts and annual reports. In an enhanced embodiment of the system statistical patterns in Internet usage data and Internet data such as newly released textual information on Web pages are further leveraged.

The invention discloses a real-time driver's braking behavior and state distinguishing method. The method comprises the following steps that 1, original test data of an actual vehicle of a driver is obtained through an actual vehicle testing platform; 2, the test data is preprocessed, wherein the preprocessing includes noise reduction preprocessing and abnormal data processing; 3, a principal component analysis method is utilized to conduct feature extraction and data dimension reduction on preprocessed data; 4, a braking pedal force, a braking pedal stroke and braking pedal stroke change rate data are clustered; 5, offline learning of different braking behaviors and states is completed based on a statistic pattern recognition model, and a behavior training library and a state training library of corresponding quantization representation values are obtained; 6, braking behaviors and states of different drivers under different driving working conditions are distinguished in real time. The method can be used in the technical fields of a brake-by-wire system, a braking energy recovery strategy, vehicle running state monitoring and the like, and can also create conditions for automatic driving decision-making control based on driver's behaviors.

A method for performing packet loss concealment of lost packets in Voice over IP (Internet Protocol) speech transmission. Statistical n-gram models are initially created with use of a training speech corpus, and then, packets lost during transmission are advantageously replaced based on these models. In particular, the existence of statistical patterns in successive voice over IP (VoIP) packets is advantageously exploited by first using conventional vector quantization (VQ) techniques to quantize the parameter data for each packet with use of a corresponding VQ index, and then determining statistical correlations between consecutive sequences of such VQ indices representative of the corresponding sequences of n packets. The statistic n-gram predictive models so created are then used to predict parameter data for use in representing lost data packets.

A simple, inexpensive, and fast method of establishing if a defect does or does not exist within a thick-walled solid geometry, which is especially useful to detect if such a defect, a crack, exists within a gun barrel. With further analysis, the method allows not only the identification of the defect's presence; but, a means of establishing the size thereof—which, for example, is critical to understanding if a gun tube has a defect that would warrant its being taken out of service for the safety of its crew or removed from manufacturing. The method involves creating an acoustic vibration in the particular thick-walled, solid geometry, esp. a gun barrel, and observing the vibration pattern which results. The size of the particular defect can be ascertained by a) manually using a correlation between the magnitude of the defect and the relative changes in the decay coefficient or shifts in frequency data or (b) automatically using a Bayes maximum likelihood, statistical pattern classification algorithm and a library comprised of either the decay coefficients or the means and covariances of defect-free and cracked objects.

A method is provided for determining an adhesive condition of a surface of a vehicle road using a statistical pattern recognition technique. A plurality of probability distribution functions is provided representing respective adhesive effects between the vehicle tire of a driven vehicle and the vehicle road. An index is calculated which represents a vehicle understeer characteristic. Probability analysis is applied for each of the road surface adhesive conditions as a function of the index. Each probability analysis is recursively updated. A likelihood factor is determined for each road surface adhesive condition as a function of each respective recursively updated probability analysis. Each respective road surface adhesive condition has a respective likelihood factor that identifies the likelihood of the road surface having the respective adhesive condition as a function of the index. The identified adhesive condition of the road surface is input into a vehicle control process.

The invention discloses a monitoring index switching based multi-operating-mode process monitoring method and system. The method includes: acquiring normal data in different operating modes to serve as a training sample set; obtaining a hidden Markov model on the basis of the training sample set, and acquiring control limits corresponding to monitoring indexes of the hidden Markov model; respectively establishing statistical pattern analysis models of corresponding operating modes on the basis of training samples of each operating mode, and acquiring control limits corresponding to monitoring indexes of each statistical pattern analysis model; computing operating mode vectors on the basis of process data acquired in real time, and further computing differential operating mode vectors; computing corresponding real-time monitoring indexes according to norms of the differential operating mode vectors, and comparing the real-time monitoring indexes with the control limits corresponding to the monitoring indexes of the corresponding models so as to monitor running states of the operating modes. The method has the advantages that the process data are acquired in real time, reliability in monitoring is guaranteed, data in each operating mode need not to obey Gaussian distribution, and applicability is higher.