927 results about "Synthetic data" patented technology

The system described herein enables clinicians and researchers to use aggregated genetic and phenotypic data from clinical trials and medical records to make the safest, most effective treatment decisions for each patient. This involves (i) the creation of a standardized ontology for genetic, phenotypic, clinical, pharmacokinetic, pharmacodynamic and other data sets, (ii) the creation of a translation engine to integrate heterogeneous data sets into a database using the standardized ontology, and (iii) the development of statistical methods to perform data validation and outcome prediction with the integrated data. The system is designed to interface with patient electronic medical records (EMRs) in hospitals and laboratories to extract a particular patient's relevant data. The system may also be used in the context of generating phenotypic predictions and enhanced medical laboratory reports for treating clinicians. The system may also be used in the context of leveraging the huge amount of data created in medical and pharmaceutical clinical trials. The ontology and validation rules are designed to be flexible so as to accommodate a disparate set of clients. The system is also designed to be flexible so that it can change to accommodate scientific progress and remain optimally configured.

A database of personal information is built and controlled by the individual users creating it. This database can then be used to enhance the functionality and user experience associated with multi-participant online communities. By collecting information from users themselves, and by allowing users to maintain such data, the data can have significant added value both to the users and to any commercial services that wish to use it. Appropriate precautions are taken to ensure that users maintain control over the data they choose to share. Data is owned by the user that provided it, and any application or release of such data is only performed at user direction and under user control. The users are also given incentives to provide such data, in the form of promised rewards. These mechanisms improve the amount and quality of collected data, so that comprehensive databases describing users can be built more easily and effectively.

An illustrative mobile computing device executing weight, nutrition, health, behavior and exercise application software serves as a simulated combination personal trainer and dietician / nutritionist for the user using comprehensive databases storing personalized health, nutrition and exercise information. A mobile computing device, such as a smartphone, executing such software monitors, tracks and / or adjusts caloric intake, energy expenditure taking into account nutritional information and behavioral factors. The mobile computing device receives food consumption, exercise-related, behavior and other input using speech input and the device's GPS subsystem to ease data entry burden on users and to promote continued long-term usage. The system rewards user goal achievement in an automatic, seamless manner, through, for example, downloading music, books, or other media. In illustrative implementations, the system assists users to make healthy food and exercise choices by using a comprehensive color code system to identify good choices, bad choices and those in between.

An apparatus for consolidated data services comprising a plurality of devices, a plurality of data services and a content application programming interface (API). A user API provides user identification for each of the plurality of devices using one or more of a plurality of user API methods. A feedback API configured to receive data from each of the plurality of devices that identifies media content that was delivered to the plurality of devices using one or more of a plurality of feedback API methods. A device API configured to provide a client system to one or more of the plurality of devices using one or more of a plurality of device API methods. A web service consolidator coupled to the content API, the user API, the feedback API, the device API, the update API, a plurality of data services and the plurality of devices through the communications media.

The invention discloses an Internet of things intelligent home system and a method. The system comprises intelligent home equipment, an access and transmission network and an intelligent home service system, wherein the intelligent home equipment comprises sensing equipment, control equipment, an alarm device, a router and an intelligent home comprehensive gateway; the access and transmission network is a remote transmission broadband network for finishing interaction between the intelligent home service system and a background service system; and the intelligent home service system comprises a user terminal and the background service system. According to the method, the Internet of things intelligent home system is divided into an intelligent home basic service and a cell public service; the intelligent home basic service comprises abnormal situation alarming, environment monitoring and home energy metering; and the cell public service comprises public resource metering, comprehensive data acquisition and analysis, management and optimization and other services supplied by a third party. The Internet of things intelligent home system can alarm abnormal situations, monitor environments, meter home energy and comprehensively manage and control home information, so that the security of the system is guaranteed.

The technology includes the steps of: associating material-object identification code identifying each individual material object with material-object information representing information about material object identified by identification code and storing identification code and material-object information in material-object information database in each of business categories; sending code and information stored in database in each business category; integrating items of information having same code with each other among codes and items of information received from database in each business category to generate integrated material-object information, associating identification code with integrated material-object information identified by code and storing identification code and integrated material-object information in integrated database; requesting to send integrated material-object information associated with given identification code; reading requested integrated material-object information from integrated database and sending integrated information to requester of integrated material-object information; and receiving and outputting sent integrated material-object information.

A method for coding and decoding seismic data acquired, based on the concept of multishooting, is disclosed. In this concept, waves generated simultaneously from several locations at the surface of the earth, near the sea surface, at the sea floor, or inside a borehole propagate in the subsurface before being recorded at sensor locations as mixtures of various signals. The coding and decoding method for seismic data described here works with both instantaneous mixtures and convolutive mixtures. Furthermore, the mixtures can be underdetemined [i.e., the number of mixtures (K) is smaller than the number of seismic sources (I) associated with a multishot] or determined [i.e., the number of mixtures is equal to or greater than the number of sources). When mixtures are determined, we can reorganize our seismic data as zero-mean random variables and use the independent component analysis (ICA) or, alternatively, the principal component analysis (PCA) to decode. We can also alternatively take advantage of the sparsity of seismic data in our decoding process. When mixtures are underdetermined and the number of mixtures is at least two, we utilize higher-order statistics to overcome the underdeterminacy. Alternatively, we can use the constraint that seismic data are sparse to overcome the underdeterminacy. When mixtures are underdetermined and limited to single mixtures, we use a priori knowledge about seismic acquisition to computationally generate additional mixtures from the actual recorded mixtures. Then we organize our data as zero-mean random variables and use ICA or PCA to decode the data. The a priori knowledge includes source encoding, seismic acquisition geometries, and reference data collected for the purpose of aiding the decoding processing.The coding and decoding processes described can be used to acquire and process real seismic data in the field or in laboratories, and to model and process synthetic data.

The invention discloses a substation secondary system operation and maintenance cloud platform, comprising in-place layers and a centralized control layer, which are configured to read data from a production management system directly to realize equipment management, operation management, fault handling, duty management and maintenance management. The in-place layers and the centralized control layer exchange power grid operation data by means of a dispatching data network, and exchange operation and maintenance management data by means of an integrated data network; each in-place layer comprises a substation control layer, a spacing layer and a process layer; each process layer comprises all primary equipment of a substation, and transmits information of the primary equipment of the present layer to the substation control layer by means of corresponding detection equipment; and each spacing layer comprises all secondary equipment of the substation, and transmits information of the primary equipment of the present layer to the substation control layer by means of corresponding detection equipment. The substation secondary system operation and maintenance cloud platform integrates the cloud computing technology, the big data technology, the Internet of things technology and the mobile internet technology, unifies data interfaces and dispatching among different secondary operation and maintenance systems in safety regions, and realizes good management of operation and maintenance information.

The invention relates to an information system integration method for power network manufacture control macrozone and management information macrozone which belongs to the technical field of power network control and management systems. The method includes coding for power network devices uniformly; a comprehensive data platform is established, consisting of a first data platform and a second data platform arranged in the power network manufacture control macrozone and the management information macrozone; the model, graphs and real time data as well as historical data of the power network manufacture control macrozone are transmitted into the first data platform and stored into a first data platform database; a mirror image of the first data platform database is set up on the second data platform; the management information data of the power network management information macrozone are transmitted into the second data platform; the first data platform database and the management information data are integrated and then displayed by the second data platform carries out conformity. The method practically realizes the integration on the information systems of the power network manufacture control macrozone and the management information macrozone, thereby improving the information using efficiency of each system of the power network and promoting the automatization of the power network dispatching and the information management level.

The invention provides a medical image synthesis method based on double generative adversarial networks. The method comprises the main content of performing data management, generating the generativeadversarial networks, training a U-NET, establishing assessment indexes and obtaining processed pictures, wherein first, a DRIVE database is used to manage a first-stage GAN, then the first-stage GANgenerates a partitioning mask representing variable geometry of a dataset, a second-stage GAN converts the mask produced at the first stage into an image with a sense of reality, an generator minimizes a loss function of the true data in classification through a descriminator, then the U-NET is trained to assess the reliability of synthetic data, and finally the assessment indexes are establishedto measure a generated model. According to the method, by use of a pair of generative adversarial networks to create a new image generation path, the problem that the synthetic image contains a fake shadow and noise is solved, the stability and the sense of reality of the image are improved, and meanwhile image details are clearer.

A user interface for monitoring the status of medical machines includes a display which shows data coming from a processing unit relating to parameters of the machines. The processing unit comprises means for establishing to which operating status of the medical machines the data belongs to. The processing unit determines if a medical machine is in correct functioning status; if a medical machine is in a warning status; or if a machine is in critical status. Means generate synthetic data characterised using colours according to whether the medical machine is in the correct functioning, the warning or the critical status.

A data collection system includes remote, implantable sensors for monitoring one or more patient parameters, collecting and processing data from those sensors and utilizing that data in the performance of a clinical study of a drug or other pharmacological agent. The system assists with preparation of a protocol for a clinical trial; presentation of that protocol; assuring compliance with the protocol; and generating useful results from data collected via the system and externally for presentation to an approval forum.

A music information retrieval system and method that involve a query-by-humming (QbH) database system for processing queries in the form of analog audio sequences which encompass recorded parts of sung, hummed or whistled tunes, recorded parts of a melody played on a musical instrument or a speaker's recorded voice articulating at least one part of a song's lyrics to retrieve textual background information about a musical piece whose score is stored in an integrated database of said system after having analyzed and recognized said melody.

A method and system for detecting the presence of subterranean termites, involving use of a thermal imaging camera to scan the structure before installation of an acoustic sensor in order to quickly locate potential areas of subterranean termite infestation, and an acoustic sensor in the form of an accelerometer or the disclosed innovative acoustic sensors having a bandwidth of at least 100 Hz to 15 kHz to detect noises made by the subterranean termites. Information collected by the acoustic sensor may be transmitted to a portable mini-computer (pocket PC) for confirmation and to a central operations center for inclusion in a comprehensive database of termite data and information. A method and system for detecting the presence of dry-wood termites concealed in a structure, involving use of a heat source to warm up the wooden structure of interest and then using a thermal imaging camera to scan the structure for suspicious dry-wood infestation, followed by the use of an acoustic sensor and pattern recognition software to more precisely and accurately locate potential area of dry-wood termite infestation. Additionally, structural damage can be evaluated by the methods discussed herein, including live trees. Additionally, the method can be used to manipulate termite infestation behavior.

A data collection system includes remote, implantable sensors for monitoring one or more patient parameters, collecting and processing data from those sensors and utilizing that data in the performance of a clinical study of a drug or other pharmacological agent. The system assists with preparation of a protocol for a clinical trial; presentation of that protocol; assuring compliance with the protocol; and generating useful results from data collected via the system and externally for presentation to an approval forum.

An adaptive CT data acquisition system and technique is presented whereby radiation emitted for CT data acquisition is dynamically controlled to limit exposure to those detectors of a CT detector assembly that may be particularly susceptible to saturation during a given data acquisition. The data acquisition technique recognizes that for a given subject size and position that pre-subject filtering and collimating of a radiation beam may be insufficient to completely prevent detector saturation. Therefore, the present invention includes implementation of a number of CT data correction techniques for correcting otherwise unusable data of a saturated CT detector. These data correction techniques include a nearest neighbor correction, off-centered phantom correction, off-centered synthetic data correction, scout data correction, planar radiogram correction, and a number of others. The invention is applicable with energy discriminating CT systems as well as with conventional CT systems and other multi-energy CT systems, such as dual kVp-based systems.

A system and method for allowing an Internet user to create a web page which may simultaneously display public and private data as integrated data on one digital screen or other network interface device. Integrated data may derive from at least one internal content provider, but may also include data from one or more external content providers. The invention also allows an internal content provider to create a personal profile of a user, based on proprietary data stores of the internal content provider and / or on the user's choices of data for viewing on a web page. Finally, the invention allows an internal content provider to use the personal profile to personalize the user's experience on the provider's web site.

A data collection system includes remote, implantable sensors for monitoring one or more patient parameters, collecting and processing data from those sensors and utilizing that data in the performance of a clinical study of a drug or other pharmacological agent. The system assists with preparation of a protocol for a clinical trial; presentation of that protocol; assuring compliance with the protocol; and generating useful results from data collected via the system and externally for presentation to an approval forum.

A cattle management system and method are provided for managing numerous routine and non-routine management activities. The system and method incorporate a data processing system wherein comprehensive data is gathered and maintained on each individual animal as well as on selected groups of animals. Preferably, a central database is used which allows enhanced functionality with respect to not only data entry and data transfer, but also with respect to providing system generated management recommendations. Some significant functionality of the present invention includes the ability to track the location of each individual animal by utilizing unique identification data for each animal, recording all monitored events that take place at each location during the animal's production cycle, managing feeding operations at a feed lot wherein ration changes can be automatically triggered by parameters and rules established for each feed lot, and reporting the events and locations as required to government entities, financial institutions, and other entities within the cattle industry.

A comprehensive database system employs common medical terms, vocabularies and identifiers in identifying organizational characteristics as well as location availability and suitability for delivering services by a particular physician to a patient with particular medical conditions via a user friendly display interface. A system for providing healthcare related information comprises a database incorporating information identifying an encompassing organization and multiple constituent organizations of the encompassing organization including a constituent organization type identifier. The database information also incorporates location information identifying multiple locations in a constituent organization available to accommodate a patient for different purposes and includes a location type identifier. An interface processor employs the database in supporting business applications of an organization and in providing a user with service and location information related to a particular constituent organization in response to user command.

Systems and methods are disclosed for providing benchmark services to customers. The services may be provided through a benchmark provider. The benchmark provider may build a benchmark database based on data collected from customers and / or third party sources. The submission of benchmark data can be made optional to the customer and, thus, not a requirement to receive service(s) from the benchmark provider. In addition, the benchmark database may be built as a comprehensive database, such that it is well-populated and provides benchmark data for many or all types of functional areas (e.g., FIN, CRM, SCM, SRM, HR, etc.), industries and / or sizes of companies. Offers for benchmark services may be presented to customers and specific service(s) may be provided in accordance with the service election(s) made by each customer.

Sales data and vehicle data may be collected by a vehicle data system embodying a special sales analyzer application. For each dealer affiliated or registered with the system and each vehicle transaction record received from the dealer, the system may run analytics to determine, compute, and / or impute supplemental data and internal vehicle pricing data such as trim-level vehicle configuration data, price ranges, exclusion reasons, dealer-specific recommendations, etc. that can later be used to generate a dealer-facing custom user interface. The results are collated into a comprehensive database and persisted in a data store. When requested by a dealer, the system may retrieve dealer-specific information, including sales prices, salespeople, average dealer margins, sales volumes, etc., and anonymized sales data from others in the same geographic region as the dealer and display a visual presentation of all transactions and also individual transactions for that dealer.

The invention relates to an intelligent online monitoring and pre-warning system for cable operation condition. The intelligent online monitoring and pre-warning system comprises a monitoring terminal and a monitoring center master station, wherein the monitoring terminal acquires monitoring parameters of the cable operation condition, such as the grounding current of the metal protective layer of the cable, cable joint temperature, combustible gas content, poisonous gas content, oxygen gas content, smoke, water level and manhole cover security, in real time and reports the acquisition data to the monitoring center master station in a timing manner through a wireless network; the monitoring center master station is used for timely carrying out storage, statistic, analysis, display and processing on the reported acquisition data and has functions of acquiring synthetic data of cable operation, monitoring the operation state in real time, displaying image data, pre-warning a fault and giving an alarm, carrying out statistic analysis of information data and the like. The intelligent online monitoring and pre-warning system can provide an effective monitoring method for ensuring the cable trench line security, ensure that the high-voltage cable line runs stably and reliably and greatly improve the power supplying reliability.

An illustrative mobile computing device executing weight, nutrition, health, behavior and exercise application software serves as a simulated combination personal trainer and dietician / nutritionist for the user using comprehensive databases storing personalized health, nutrition and exercise information. A mobile computing device, such as a smartphone, executing such software monitors, tracks and / or adjusts caloric intake, energy expenditure taking into account nutritional information and behavioral factors. The mobile computing device receives food consumption, exercise-related, behavior and other input using speech input and the device's GPS subsystem to ease data entry burden on users and to promote continued long-term usage. The system rewards user goal achievement in an automatic, seamless manner, through, for example, downloading music, books, or other media. In illustrative implementations, the system assists users to make healthy food and exercise choices by using a comprehensive color code system to identify good choices, bad choices and those in between.

The invention is a method of estimating, from data obtained by exploration of a zone of a heterogeneous medium, a model representative of a distribution, in the zone, of at least one physical quantity, the model being free of a presence of correlated noises that may be contained in the data which has application to determining the distribution in an underground zone of acoustic impedance, propagation velocities and permeabilities, etc. The method includes acquiring measurements giving information about physical characteristics of the zone; specifying a noise modelling operator which associates, with a model of each physical quantity, synthetic data that constitute a response of the model; selecting a noise modelling operator which associates a correlated noise with a noise-generating function belonging to a predetermined space of the noise-generating functions; specifying a norm or of a semi-norm in the data space; specifying a semi-norm in the space of the noise-generating functions; defining a cost function; and adjusting the model and of the noise-generating functions.

An autonomous control system generates synthetic data that reflect simulated environments. Specifically, the synthetic data is a representation of sensor data of the simulated environment from the perspective of one or more sensors. The system generates synthetic data by introducing one or more simulated modifications to sensor data captured by the sensors or by simulating the sensor data for a virtual environment. The autonomous control system uses the synthetic data to train computer models for various detection and control algorithms. In general, this allows autonomous control systems to augment training data to improve performance of computer models, simulate scenarios that are not included in existing training data, and / or train computer models that remove unwanted effects or occlusions from sensor data of the environment.

Some embodiments of the invention provide an automated method for continuously monitoring at least one patient. The method continuously collects medical data about the patient from several different inputs. The method integrates the collected data, and continuously computes at least one severity score for the patient based on the integrated data. The method uses the severity scores to continuously monitor the patient. In some embodiments, integrating the data includes formatting the data so that that the data can be used to compute the severity score. Formatting the data in some embodiments includes using a set of database tables to convert the data. In some embodiments, the database tables are modifiable by a user. Some embodiments continuously compute multiple severity scores. The severity scores computed in some embodiments include the APACHE II score, the SAPS II score, the MEWS score, or user-defined severity scores.

The invention relates to a method for analyzing a traffic network, comprising the steps of: importing, organizing and managing geographic data, mobile phone base station positioning data, road network data and public transportation net data to obtain base data; comprehensively processing the base data and establishing a population travel time-space characteristic model to obtain the comprehensive data; and analyzing the traffic management according to the comprehensive data. In combination with the mobile phone base station positioning data, the public transportation network data, the road network data, and the like, the traffic network analysis method ensures that the population travel information dynamic change is obtained, the traffic information based on the population travel characteristic is found, and the service quality reliability is analyzed through a traffic topology network, traffic accessibility and relative analysis. The invention provides convincement and effective decision support for traffic management, traffic plan, land utilization planning, urban planning, and the like, can effectively improve the use ratio of public traffic and a road network, relieves the pressure of the urban traffic, and provides a method for solving the problems in traffic management and traffic planning.

The invention discloses a medical image synthesis and classification method based on a conditional multi-judgment generative adversarial network. The method comprises the following steps: 1, segmenting a lesion area in a computed tomography (CT) image, and extracting a lesion interested area (Region of Interest, ROIs for short); 2, performing data preprocessing on the lesion ROIs extracted in thestep 1; 3, designing a Conditional Multi-Discriminant Generative Adversarial Network (Conditional Multi-) based on multiple conditions The method comprises the following steps: firstly, establishing aCMDGAN model architecture for short, and training the CMDGAN model architecture by using an image in the second step to obtain a generation model; 4, performing synthetic data enhancement on the extracted lesion ROIs by using the generation model obtained in the step 3; and 5, designing a multi-scale residual network (Multiscale ResNet Network for short), and training the multi-scale residual network. According to the method provided by the invention, the synthetic medical image data set with high quality can be generated, and the classification accuracy of the classification network on the test image is relatively high, so that auxiliary diagnosis can be better provided for medical workers.

The present invention extends to methods, systems, and computer program products for refining synthetic data with a Generative Adversarial Network (GAN) using auxiliary inputs. Refined synthetic data can be rendered more realistically than the original synthetic data. Refined synthetic data also retains annotation metadata and labeling metadata used for training of machine learning models. GANs can be extended to use auxiliary channels as inputs to a refiner network to provide hints about increasing the realism of synthetic data. Refinement of synthetic data enhances the use of synthetic data for additional applications.