45 results about "Longitudinal data" patented technology

A computer-implemented method is provided for generating a trained TTS-GAN which may be used to generate synthetic longitudinal data for use in survival analysis, a clinical trial or clinical research. The TTS-GAN is configured to generate synthetic time-series data based on synthetic context data generated using a machine-learning model by virtue of being trained using training data comprising real context data and added noise data. A technique for executing survival analysis is also provided, which relies on the synthetic longitudinal data.

Systems and methods are disclosed for identifying relationships between complex datasets and / or high-dimensional datasets for predictive modeling. The method includes clustering data associated with one or more entities in a first dataset based on distance data; clustering the data associated with the one or more entities in a second dataset based on longitudinal data; consolidating the first dataset and the second dataset into a third dataset based on weights assigned to one or more edges between one or more nodes in the first dataset and the second dataset; generating a diagnosis space indicating a condition of the one or more entities based on the third dataset; and determining, via input of the diagnosis space into a machine learning model, an optimization of a weighting scheme for assigning weights to one or more features within the longitudinal data.

Predicting cardiovascular diseases (CVD) may be preceded by subtle changes in various health indicators that may make early predictions useful for timely intervention. The present disclosure relates to prediction of one or more diseases, particularly CVD, for a given subject by leveraging one or more machine-learning models based on longitudinal multimodal data. The techniques, as disclosed herein, may utilize the one or more machine-learning models including one or more feature generators, a temporal aggregator and a prediction model to process the longitudinal multimodal data, generating relevant features, a temporal feature vector and one or more metrics corresponding to one or more diseases associated with the subject. The generated metrics based on the current time and previous time points may be analyzed to assess whether the subject currently has or is at risk of developing one or more diseases.

A disease prognosis model to may be trained to determine the clinical outcome of a disease based on longitudinal data including a health record for each timepoint in a sequence of timepoints. The disease prognosis model may include a recurrent neural network trained to extract, from each health record, a feature set representative of local dependencies present within the health record. The disease prognosis model may include a spacetime attention trained to determine an importance of each feature in the feature set at each timepoint in the sequence of timepoints. The disease prognosis model may include a feedforward neural network trained to determine, based on the importance of each feature in the feature set at each time point in the sequence of timepoints, the clinical outcome of the disease. The trained disease prognosis model may be applied to determine the clinical outcome of the disease for one or more patients.

The invention discloses a sepsis typing division method and a typing prediction model construction and application method and device, and relates to the field of machine learning, and the method comprises the steps: obtaining central venous oxygen saturation and peripheral perfusion indexes of a plurality of patients in a preset time period; calculating and acquiring a dynamic blood flow oxygen flow index track of each patient in the preset time period according to the central venous oxygen saturation and the peripheral perfusion index of the patient in the preset time period; evaluating trajectory similarity by using a dynamic time warping algorithm, and grouping trajectories by using a hierarchical clustering algorithm to obtain a plurality of sepsis types; and training the machine learning model by using each sepsis type and the corresponding clinical features of the patient to obtain a sepsis type prediction model. According to the application, sepsis typing division is carried out based on the longitudinal data of the central venous oxygen saturation and the peripheral perfusion index, a prediction model is established for each typing based on clinical features, and finally division and accurate prediction of sepsis crowds are realized.

The invention relates to the field of electric power engineering, and particularly discloses a port shore power load double-flow LSTM prediction method, which comprises the following steps: S1, selecting and collecting factors influencing power load data by using longitudinal data to obtain a multivariable time sequence data set D1, and preprocessing the data set D1 to obtain a data set D2; s2, correlation analysis is carried out, and dominant features and auxiliary features are divided based on the correlation degree of each variable and the load in the MIC quantitative data set D2; respectively inputting the dominant features and the auxiliary features into heterogeneous LSTM branch modeling, and splicing output results to generate a fusion feature map; and S3, constructing a BO-LSTM neural network, inputting the fusion feature map into a double-flow time sequence learning module, extracting dominant features and auxiliary features, performing deep representation, performing splicing, introducing a channel attention mechanism to perform weighting processing on fusion feature vectors, and outputting a power load prediction value through a residual error correction module. According to the method, the prediction precision and robustness are remarkably improved, and the real-time scheduling of the port shore power system is supported.

The invention relates to a longitudinal data high-dimensional parameter estimation method based on Bayesian empirical likelihood and variational inference. The method comprises the following steps: acquiring longitudinal data, and standardizing the longitudinal data to obtain standardized data; based on the standardized data, obtaining theoretical posteriori distribution of the longitudinal data through Bayesian empirical likelihood function estimation; on the basis of the theoretical posteriori distribution, approximate posteriori distribution similar to the theoretical posteriori distribution is constructed through a variational inference method; estimating high-dimensional parameters of the longitudinal data based on the approximate posteriori distribution to obtain a high-dimensional parameter estimation table corresponding to the longitudinal data; the high-dimensional parameter estimation table is used for assisting in diagnosing the disease risk of the patient corresponding to the longitudinal data. By adopting the method, the posterior distribution of the Bayesian likelihood estimation can be quickly calculated, and the effect of quickly and accurately diagnosing the disease risk of the patient is realized.

The invention discloses a power load probability prediction method and system based on a neural network quantile regression model and multiple linear regression, and belongs to the technical field of power system load prediction. The method comprises the following steps: obtaining standardized data by using a longitudinal data analysis method; identifying key influence factors of the power load in the standardized data based on a Pearson correlation analysis method, and constructing a factor analysis model to quantify influence weights of the key influence factors on the power load; constructing a neural network quantile regression model based on seasonal trend decomposition to fit the key influence factors with different influence weights to obtain a quantile prediction result; based on the quantile prediction result, estimating a continuous probability distribution curve of a load common factor by adopting a non-parametric kernel density technology to obtain an interval prediction result; and constructing a multiple linear regression model to predict the load scale change, and adjusting the interval prediction result. According to the invention, the precision and calculation efficiency of load prediction are effectively improved.

Systems, methods, and devices for data ingestion, database management, and data security. A method includes aggregating data from a plurality of different data sources, wherein the data comprises equipment data and personnel data pertaining to a project. The method includes generating a longitudinal data bucket comprising information associated with the project for tracking the equipment data and the personnel data over time and storing the longitudinal data bucket on a database. The method includes assigning permissions to different types of data stored in the longitudinal data bucket such that a plurality of users of the database have personalized read and / or write permissions to the equipment data and the personnel data.

The embodiment of the invention discloses a Crohn disease longitudinal queue course prediction system based on time perception Transform, and relates to the technical field of medical data processing, the system comprises a data preprocessing module, an input embedding layer, a Transform encoder and a multi-task multi-time window prediction header, the system breaks through the limitation that only baseline data is used for prediction of a traditional model, and the prediction efficiency is improved. According to the method, the full-cycle longitudinal data (such as inflammation indexes and medication records of each treatment) of the patient from the morbidity to the prediction can be integrated, and the disease progress, operation and medication risks of 1 year / 3 years / 5 years can be dynamically output. And reference is provided for clinicians.

The present application belongs to the technical field of data management, and particularly relates to a data management system for a twisted wire automatic detection platform, to solve the technical problem that the prior art cannot identify periodic defects and the traceability analysis process cannot correlate defects. The management system comprises: a data acquisition and synchronization unit for forming a longitudinal data profile; a main data modeling unit for constructing a pedigree main data model containing twisted wire product, single wire raw material and production process data; a data warehouse hierarchical processing unit for establishing a hierarchical data warehouse; an identification unit for constructing a data theme layer above the data detail layer; and an application service unit for constructing a data application layer above the data theme layer. The present application realizes traceability from quality problems to production, and provides data decision basis for process improvement and quality control.

Creating a medical report, indicative of a longitudinal examination includes receiving an input longitudinal report data structure having longitudinal data elements, which are associated with annotation elements of a medical annotation database that is indicative of relationships between medical concepts. A set of reference report data structures is received, which has reference data elements associated with annotation elements of the medical annotation database. For each longitudinal data elements, it is determined whether the longitudinal data element can be linked with a reference data element of at least one reference report data structure from the set of reference report data structures. The determining is made based on the associated annotation elements and based on the medical annotation database. An interface element indicative of a pointer from the input longitudinal report data structure to the reference report data structure having the linked reference data element, is outputted responsive to the determining.

The invention relates to a cancer patient mental health prediction model based on multi-source data and application. The model comprises the following steps: utilizing electronic health record (EHR) data and longitudinal data of cancer patients in prospective queue research; constructing and verifying a prediction model in combination with multiple factors; carrying out model training and verification by utilizing a machine learning algorithm so as to realize early prediction of anxiety, depression and psychotic disorders; and quantifying the contribution of each factor to the psychological health risk through model interpretive analysis. Through multi-source data fusion and an advanced algorithm, the early recognition rate of the psychological health problem of the cancer patient can be effectively improved, resource waste and diagnosis delay are reduced, and the treatment effect and life quality of the patient are improved.

The invention provides an abnormal data processing method, system and device for a wind turbine generator, and relates to the technical field of data processing, and the method comprises the steps: carrying out the window time sequence monitoring of Q wind turbine generators of a target wind power plant at a first monitoring window according to a preset monitoring index; performing longitudinal data expansion trend time sequence iteration on Q window time sequence monitoring data sequences; in combination with a density propagation mechanism, performing transverse consistency analysis on the Q longitudinal data expansion trend characteristics; and performing memory independent verification on the M abnormal longitudinal data expansion trend characteristics, and performing identification early warning on a corresponding window time sequence monitoring data sequence in the Q window time sequence monitoring data sequences according to the identified N verified abnormal longitudinal data expansion trend characteristics. Through the method and the device, the technical problem of relatively low abnormal data processing accuracy of the wind turbine generator in the prior art can be solved, and the technical effect of improving the abnormal data processing accuracy is achieved.

An electronic watch may be provided having functionality for space exploration and / or surface exploration on a terrestrial planet. The watch may comprise a time displaying means and a processor subsystem. The processor subsystem may be configured to maintain a coordinated planetary time of a terrestrial planet, obtain longitudinal data representing a longitude of interest on the terrestrial planet which is different from the planet's prime meridian, determine a local true solar time, LTST, at the longitude of interest as a function of the coordinated planetary time and using an equation of time which accounts for orbital eccentricity and rotational axis tilt of the terrestrial planet, and to control the time displaying means of the electronic watch to display the LTST.

The utility model belongs to the field of highway construction, specifically relates to a highway engineering original road flat, longitudinal data quick extraction auxiliary device, and the device includes: base, track, measuring device, supporting device, quick -detachable connecting portion and automatic correction device, the side portion mounting of base track, supporting device swing joint is in base, automatic correction device installs in the lower part of base, the bottom of measuring device is provided with the mounting rod, the hole is seted up on base, the lower extreme of mounting rod passes through the hole on base and is connected with automatic correction device, one end of quick -detachable connecting portion is connected with mounting rod, and the other end is connected with supporting device, and the electronic level gauge is installed on measuring device. The device can avoid the influence of inertia or uneven road to equipment when running, can be automatic, keep the accuracy of measurement data.

The invention discloses a power equipment state evaluation method based on a normal cloud model and gray fixed weight clustering, and belongs to the field of data processing. Comprising the steps of determining a basic parameter system suitable for state evaluation of the whole and basic units of the power equipment, and constructing a state evaluation key parameter system; checking data quality in the key parameter system, and performing data cleaning work if necessary; establishing a data analysis model, judging the abnormal change of the equipment state and the association relationship thereof by utilizing the correlation between the longitudinal data and the transverse data, and performing equipment anomaly detection by analyzing the association relationship and the change rule of the multi-dimensional state data; characteristic parameters related to the key performance and the coupling relation between the characteristic parameters and the key performance state of the equipment are determined, the abnormal key performance is screened out, and the evaluation value of each key performance is obtained. According to the method, a normal cloud model is used for effectively fusing and cleaning state monitoring data of the power equipment, and a grey weighting clustering method is used for deeply analyzing the fused data, so that the state of the power equipment is accurately evaluated.

The invention provides an SPECT imaging device and a swing-type acquisition tomography method. The device comprises an SPECT scanning frame, and the SPECT scanning frame comprises a main rotating motor, a first large probe, a second large probe, a first small probe and a second small probe; the main rotating motor is used for synchronously driving the first large probe, the second large probe, the first small probe and the second small probe to swing back and forth around the bed according to a preset angle; wherein the first large probe and the second large probe are used for covering and scanning to obtain longitudinal data of a human body, and the first small probe and the second small probe are used for assisting in scanning to obtain transverse data of the human body; in the reciprocating swing process, all the probes can advance and retreat in the radial direction of the SPECT scanning frame in the same plane and translate left and right in the second direction perpendicular to the radial direction, so that a parallelogram imaging area which is always close to the outline formed by a bed and a human body is defined, and plane and cross-sectional image data can be obtained through single-time small-angle scanning.

The invention relates to a method (200, 300) for characterizing a structure (104) etched in a first surface (140) of a substrate (102), such as a wafer, the structure (104) extending into the substrate (102) in a longitudinal direction z, the method (200, 300) being implemented by a characterization system (100) comprising a light source (130, 131) configured to emit an illumination beam having a wavelength suitable for transmission through the substrate (102), the invention relates to a method (200, 300) for imaging a substrate (102), comprising a first surface (140) of the substrate (102), and an imaging device positioned facing a second surface (147) of the substrate (102) opposite the first surface (140), the method (200, 300) comprising the steps of:-illuminating (202) at least one structure (104) with an illumination beam,-subsequently positioning (204) an object plane of the imaging device at at least two different longitudinal positions; -acquiring (206) at each of said longitudinal positions at least one image of the structure (104), said image being acquired through the substrate (102); -measuring (210) at least one transverse data relating to a transverse dimension of the structure (104) from at least one image acquired at each of the longitudinal positions; and determining (212) at least one piece of longitudinal data relating to the longitudinal shape of the structure from the transverse data of the at least two longitudinal positions. The invention also relates to a system for implementing such a method.

The invention belongs to the technical field of biology, and discloses VTN protein serving as an aging marker and application of the VTN protein to improvement of aging phenotypes. By collecting plasma protein data of healthy physical examination people and combining macroscopic phenotypic characteristic analysis and deep transverse and longitudinal data mining technologies, the VTN protein which is remarkably and negatively related to age is successfully screened out. Further researches find that expression of overexpressed or knocked-down VTN genes is closely related to changes of series senescence phenotypes, and action mechanisms of the VTN genes include protection of mitochondrial functions, improvement of metabolic activity and resistance to damage so as to relieve cell senescence. The results show that the VTN protein expression quantity detection can be used for evaluating or assisting in diagnosing aging and related diseases, the improvement of the VTN protein expression quantity possibly has the anti-aging potential, and the application of the VTN protein related detection technology and the research and development of related products have certain prospects.

Changes in ctDNA levels may significantly fluctuate across patients over time, and the results may be difficult to interpret. Methods and techniques are described herein that are capable of capturing these complexities while taking into account a distinct set of patient traits. Furthermore, an observation dataset consisting of a patient suffering from cancer undergoing treatment is analyzed, the analysis results being graphically rendered. These results demonstrate utility of the described methods and techniques in obtaining a comprehensive understanding of how response patterns evolve and how different patient characteristics affect these evolutions.

The invention relates to the technical field of fatty liver risk prediction, and discloses a fatty liver disease risk prediction method which comprises the following steps: step 1, collecting health physical examination data which comprises basic information of an individual, blood biochemical index data, body measurement index data and time information of multiple physical examinations, forming a non-independent longitudinal data set; 2, performing data preprocessing, including data cleaning and data standardization, on the collected non-independent longitudinal data set, and converting different types of data into formats suitable for analysis; by collecting and analyzing the longitudinal health examination data of the individual, preprocessing the data, screening the characteristic variables and constructing the fatty liver disease risk prediction model, the accuracy and reliability of fatty liver disease risk prediction are improved, the model complexity is simplified, and the diagnosis efficiency and accuracy are improved.

The application relates to the field of laser marking, and discloses a laser tab cutting control method, a device, a control terminal and a storage medium, the method comprising the following steps: segmenting tab cutting data to obtain longitudinal data segments and transverse data segments; determining the type of the data segment to be cut at the current moment, if the longitudinal data segment, the coordinate data of the longitudinal data segment is sent to a first processor, if the transverse data segment, the coordinate data of the transverse data segment is sent to a second processor; after the first processor receives the longitudinal data segment, the offset coordinates of the longitudinal line segment are calculated according to the conveying speed of a conveying belt, and the offset coordinates are sent to the second processor, and the second processor controls the movement of a galvanometer according to the offset coordinates; after the second processor receives the transverse data segment, the marking distance of the galvanometer is calculated according to the conveying speed of the conveying belt, and the movement of the galvanometer is controlled according to the marking distance. The calculation of the tab cutting is separated, the calculation pressure is reduced, and the reaction speed is accelerated.

Systems and methods for managing progression of a clinical trial. Input data for a machine learning model is formed, based on longitudinal data for clinical trial cohort. The input data corresponds to input features and the cohort includes a plurality of subjects. A clinical outcome output is generated for each subject, using the machine learning model and a portion of the input data corresponding to each subject. Feature importance values are generated, based on the machine learning model generating the clinical outcome output for each subject. The feature importance values include, for each subject, a set of feature importance values for a set of input features. A ratio of interest is computed using the plurality of feature importance values. An output is generated using the ratio of interest in which the output indicates whether the cohort should proceed to a next phase of the clinical trial.

The invention relates to an interpolation method for missing data in Alzheimer's disease progress prediction, which comprises an integrated feature selection module and a missing value interpolation module, and is characterized in that the integrated feature selection module adopts an isomorphic and heterogeneous integrated feature selection method for time heterogeneity and phenotypic heterogeneity respectively to screen out features closely related to disease progress; the missing value interpolation module obtains irregular missing time sequence information by calculating a real interval between follow-up visit data of each patient, takes specific individual features of the patient as intervention condition input of a variational auto-encoder, and learns conditional distribution of the features by using a conditional variational auto-encoder; according to the method, more refined conditional distribution modeling is carried out, and finally, missing data is generated by the model, so that the problems that the distribution characteristics of data are not fully considered and conditional dependence information behind a missing mechanism is difficult to capture in the current traditional interpolation method based on AD patient multi-source longitudinal data are solved, and the accuracy and reliability of Alzheimer's disease progress prediction are remarkably improved.

The embodiment of the invention discloses a task completion measurement method, electronic equipment, a storage medium and a program product. The method comprises the steps of obtaining a to-be-measured task completion file, and determining a measurement index corresponding to an achievement type according to the achievement type of the to-be-measured task completion file; performing information statistics on the to-be-measured task completion file according to the measurement index to obtain a first measurement index value; obtaining a historical measurement task completion file corresponding to the to-be-measured task completion file, and performing document deduplication on the to-be-measured task completion file according to the historical measurement task completion file to obtain a deduplicated task completion file; performing information statistics on the de-duplicated task completion file according to the measurement index to obtain a second measurement index value; and according to the first measurement index value and the second measurement index value, performing task completion measurement on the to-be-measured task completion file to obtain a task completion measurement value, and realizing reliability evaluation of the task completion degree under different measurement indexes based on the longitudinal data.

The present invention provides a method and system for data fusion and prediction of drug-induced liver injury in children based on time series, which relates to the technical field of information processing of drug-induced liver injury in children. The method mainly includes: collecting the historical medical data of inpatients as a longitudinal data set, arranging it horizontally in chronological order, and constructing a clinical database; based on the related event phenotypes of drug-induced liver injury in children, performing entity relationship annotation on the unstructured information in the research data set; constructing and training a MUIRFTI model for structured mapping reconstruction of unstructured text based on time series information; training a machine learning prediction model to predict whether drug-induced liver injury occurs; inputting the medical data of the measured child into the machine learning prediction model to predict whether the child will suffer from drug-induced liver injury. This solution can greatly improve the information content and logic of the research data set, so as to train a better-performing machine learning prediction model for predicting drug-induced liver injury in children.

The utility model provides a hand-held SLAM device which comprises a handle, a main frame, a laser radar, a motor and a synchronizing wheel, a laser radar support is arranged on the inner side of a main body of the laser radar, and the laser radar support is fixedly connected with a rotating shaft of the synchronizing wheel driven by the motor. Therefore, when the laser radar performs circumferential scanning in the circumferential direction and the pitch angle range of the preset range, the synchronous wheel is driven by the motor to drive the laser radar to perform transverse overturning around the horizontal axis of the laser radar, so that the radar can collect longitudinal data through transverse overturning while performing circumferential scanning. The vertical field of view is expanded for the laser radar, more environmental data can be acquired, and the sensing accuracy of the laser radar to a complex environment is improved.

The present invention relates to a core-holding positioning control system, which includes a positioning unit, a control unit, and a driving unit; the positioning unit and the driving unit are respectively connected to the control unit. The positioning unit measures the traveling data of the core-holding mechanism and the longitudinal data between it and the core. The control unit converts the measured data into the positioning information of the core and controls the driving unit to drive the core-holding mechanism to accurately grasp the core, transport it to the target location, and place it at the target position. The present invention also discloses a core-holding machine including the above-mentioned core-holding positioning control system, and the core-holding positioning control system can be set on the core-holding machine during the manufacture or transformation of the core-holding machine. The core-holding positioning control system disclosed by the present invention has accurate positioning, is not affected by the placement position of the core on the tray or workbench, effectively prevents core-holding deviation caused by changes in the size and position of the core, and adopts a fully automatic measurement and identification operation mode, without the need for manual intervention, greatly reducing the labor intensity.

The power transmission channel data processing method based on artificial intelligence provided by the application comprises the following steps: acquiring a standard image of a patrol area of a power transmission channel and setting an identification anchor point; receiving original images transmitted by different patrol devices, embedding a detection anchor point, identifying and matching the original images with an image set of the same scene; performing data alignment processing on the original images in the image set according to the position of the identification anchor point in the standard image by using a feature alignment algorithm to obtain aligned images; extracting feature fingerprints of the detection anchor points in the aligned images of the same scene of different patrol devices, comparing the feature fingerprints two by two to obtain comparison results; eliminating the aligned images that do not meet the requirements based on the comparison results to form a cross-device patrol image set of the same patrol area; and performing longitudinal data processing and horizontal data comparison based on the identification anchor point and the detection anchor point to obtain the cross-device patrol image set, which can improve the accuracy of subsequent defect identification and ensure the stable operation of the power system.