298 results about "Data human" patented technology

The invention relates to the analysis of ECG data by exploiting computerized three-dimensional spatial presentation of the measured data using the vector concept. A three-dimensional presentation of the human heart may be correlated with waveforms specific for standard ECG or derived ECG signals based on the dipole approximation of the heart electrical activity. The three-dimensional heart model may be rotated, and the ECG signals are interactively linked to the model. In the visualization process, different types of signal presentation may be used, including graphical presentation of the heart vector hodograph, graphical presentation of the signal waveform in an arbitrary chosen point on the heart, and graphical presentation of the map of equipotential lines on the heart in a chosen moment. Additional tools for analyzing ECG data are also provided which may be interactively used with the display tools.

The invention discloses a monitoring system and device based on human face large data. The system is composed of a front-end real-time acquisition system and a human face monitoring center management system. The front-end real-time acquisition system distributively collects a human face video or a high-definition human face image and individual basic information, and carries out uploading to a human face comparison server. The human face comparison server establishes a local human face data management system for uploaded human face data, and periodically carries out data synchronization with the human face monitoring center management system to synchronize added human face data to a central database. The central database uses a simple and efficient human face matching algorithm, or merges and classifies human face data based on a unique identification code. Based on the classified human face large data, data analysis, blacklist large-scale early warning and other functions are carried out. The system provided by the invention effectively solves the problem that current urban human face monitoring systems are independent of each other, have separated data, and are not conducive to the construction of an accurate criminal suspect tracking system.

The embodiment of the invention discloses a medical diagnosis and treatment system. The system comprises a diagnosis and treatment data integration module used for obtaining diagnosis and treatment data related to a patient from one or more medical information sources and integrating the diagnosis and treatment data, wherein the diagnosis and treatment data at least comprises medical image data and medical text data; an artificial intelligence image analysis module used for analyzing the medical image data based on an artificial intelligence image analysis technology to generate an image analysis report; and an artificial intelligence text analysis module used for performing information extraction on the medical text data and/or the image analysis report based on an artificial intelligenceinformation extraction technology to obtain structured diagnosis and treatment data related to diseases.

The invention discloses an electrocardiosignal detection device and analysis method based on a joint neural network. The method comprises the following steps: firstly, building a joint neural networkalgorithm on a machine learning server, and training a model; aiming at preprocessed ECG data, enabling the model to extract data spatial features and acquire a spatial classification probability through a residual neural network module; extracting time sequence features of the data on a dimensionality-reduced spatial feature map through a bidirectional long-short-term memory neural network and anattention module, and acquiring a time sequence classification probability; finally, fusing the two classification probabilities to obtain a detection result; acquiring a small amount of ECG data ofa patient from a wearable device, performing manual marking, inputting the ECG data into the machine learning server, performing fine-tuning on the model, and deploying the final model to an intelligent mobile device; and finally, realizing real-time anomaly detection through wireless transmission of the wearable device and the intelligent mobile device. The invention develops the wearable devicefor electrocardiosignal acquisition and the real-time detection, and provides an effective technical means for auxiliary diagnosis of heart diseases.

The invention provides a building control system based on face identification. The building control system based on face identification comprises a video acquisition module used for obtaining video stream, a face detection module used for decoding, frame extraction, and face detection treatment of the video stream so as to obtain face data, a face identification module used for characteristic analysis on face data and obtaining identification results through face identification using a face database, a comprehensive management module used for determining the position of people based on identification results and camera number, an elevator linkage control module used for sending the commands of the comprehensive management module to an elevator, an elevator control module used for controlling calling, elevating, and door opening and closing logic operation of the elevator, an access control linkage control module used for sending the command information of the comprehensive management module to an access control module, and an access control module used for controlling building door opening and closing, building gate machine opening and closing, and visitor call operation. The building control system is used for realizing entrance automatic control through face identification of visitors.

The invention provides an electronic police system detection reliability control method and system. The method comprises front-end equipment operation situation detection, data quality preliminary inspection, electronic police data quality inspection, risk data checking and risk assessment and data processing. A targeted data quality inspection method is adopted to automatically detect equipment offline, failure, network abnormity and other equipment operation abnormal situations and data null, timestamp error, data duplication and wrong data. Meanwhile, the risk of electronic police system detection and checking data is assessed according to equipment detection recognition rate, effective rate, illegal rate and other system data quality indicator detection situations and the illegal data artificial checking reliability detection result so that automatic inspection of the risk, the abnormal data and the equipment can be realized, the control requirements of traffic management personnel for the offsite law enforcement system data quality can be met, and law enforcement data reliability and effectiveness can be guaranteed.

A method for predicting a cancer staging score from medical image data includes receiving patient data for a plurality of patients, where patient data for each of the plurality of patients includes one or more of an image volume of a suspected tumor in an organ, blood test data, demographic data, and ground truth tumor staging scores for the suspected tumor in the organ, extracting features from the patient data, and using the features extracted from the patient data to train a classifier to predict a cancer staging score for a new patient from one or more of an image volume of a suspected tumor in the organ, patient blood test data and patient demographic data of that new patient.

The invention discloses an intelligent early warning care system based on community gridding and, belongs to the technical field of community gridding management, and aims to form a whole-process informatization management system for pre-event notification, intra-event attention and post-event evaluation through associated application and analysis of early warning prediction information of a concerned object main body on the basis of collection of element information of people, places, events, objects, situations and organizations in grids based on management requirements of social governancegridding. Advanced information technologies such as the Internet of Things, cloud computing, big data, artificial intelligence and spatial geographic information integration are applied; by integrating grassroots service management resources to the maximum extent, socialization, intellectualization and specialization levels of social governance are improved, and the system is an important carrierfor realizing modernization of social comprehensive governance and is also an important basic support for smart city construction.

The embodiment of the invention discloses a human body characteristic measuring method, a human body security detecting method and an FMCW radar-millimeter wave security detecting device. The human body characteristic measurement method using an FMCW radar comprises the steps that a plurality of mannequins and classifications are provided; the FMCW radar is used for emitting electromagnetic wavestoward the mannequins separately and collecting echo data to obtain an echo data-human body shape classification corresponding relation; the FMCW radar is used for emitting electromagnetic waves toward a to-be-tested human body and collecting echo data, and the to-be-tested human body is determined to be one of the various human body shape classifications based on the collected echo data-human body shape classification corresponding relation.

The invention discloses a human body action recognition method and device based on a circular attention network. The method comprises the following steps: S1, collecting various action data of a humanbody by utilizing a multi-axis sensor; S2, segmenting the data into long-time sequence segments containing a plurality of action categories, and attaching sequence tags to the sequence segments; andS3, inputting the processed data into a pre-constructed multi-layer recurrent attention neural network model to realize recognition of specific types of actions. According to the invention, the cyclicattention algorithm is utilized, automatic positioning recognition and cutting of the sensor data can be achieved, and manpower and material resources consumed by manual labeling of the sensor data can be greatly reduced.

A device is configured to classify data. Its operation involves providing (210) data samples including one or more of: image data, radar data, acoustic data, and/or lidar data to a processing unit. The data samples include at least one test sample, including positive samples and negative samples. Each positive sample has been determined to contain data relating to at least one object to be detected including at least one pedestrian, car, vehicle, truck or bicycle. Each negative sample has been determined not to contain data relating to the at least one object to be detected. These determinations regarding the positive samples and the negative samples are provided as input data, validated by a human operator, and/or provided by the device itself through a learning algorithm. A first plurality of groups is generated (220) by the processing unit implementing an artificial neural network, wherein at least some of the first plurality of groups are assigned a weighting factor. Each group of the first plurality of groups is populated (230) by the processing unit implementing the artificial neural network with a different at least one of the plurality of negative samples based on a different feature of sample data similarity for each group, which involves processing the negative samples to determine a number of different features of sample data similarity in order to populate different groups with negative samples that share or substantially share that or a similar feature, wherein at least one of the groups of the first plurality of groups contains at least two negative samples. It is determined (240) by the processing unit implementing the artificial neural network whether the at least one test sample contains data relating to the at least one object based on the plurality of the positive samples and the first plurality of groups. The artificial neural network implements the learning algorithm.

The invention discloses a substation equipment fault locating system based on a GPS. An air-conditioner/dehumidifier remote controller, a fan remote controller, an environment parameter collector, a fire smoke alarm, a human body infrared inductor and a video collecting and compressing module are in data transmission with a front end controller through a bus or a wireless sensor network. The front end controller communicates with a dispatching center server through a power SCADA communicating net or the Ethernet. The dispatching center server stores and processes received data. A central monitoring computer gets access to the data in the dispatching center server. Personnel locating terminals locate personnel wearing the personnel locating terminals through the GPS and electronic tags. According to the system, the environment of a substation can be monitored in real time, substation environment adjusting equipment is controlled in a classified and centralized mode, and the safe and high-quality environment is provided for normal operation of the substation equipment to the maximum.

The embodiment of the invention discloses a clustering analysis method and system for multi-omics data, and the method comprises the steps: segmenting MR image information through employing a neural network, and extracting a high-throughput image hyper-parameter according to the segmentation information of each part; processing the clinical data, the demographic data and the laboratory inspection data to generate vector representations of different dimensions; performing multi-source data fusion on the high-throughput image data and the vector representations of different dimensions to obtain fused multi-source heterogeneous data; constructing a multi-source heterogeneous data set, and training and testing a multi-source graph clustering model to obtain an optimal model; inputting MR image information into the optimal model, and analyzing differences of different categories and similarities of the same category. A graph structure mode is adopted, the correlation condition between data is visually expressed, different features are captured, the model is more robust, the efficient clustering algorithm based on the graph neural network model is achieved, and the practical value is very high.

The invention provides a Haar characteristic multi-processing framework human face detection system and method based on an FPGA (Field Programmable Gate Array) and belongs to the technical field of data human face characteristic detection, aiming at solving the problems that an existing human face characteristic detection algorithm is complicated and the computing speed of a processor is low. An image storage module is used for extracting Haar characteristics in an n*n range detection window of images acquired by a camera; human face characteristics are extracted by utilizing the Haar characteristics and a coordinate of each pixel point of the human face characteristics is calculated by utilizing the human face characteristics; the obtained coordinate of each pixel point of the human face characteristics is sent to an integral image generator; the integral image generator is used for calculating human face characteristic values according to the coordinate of each pixel point of the human face characteristics by utilizing an integral image method; the calculated human face characteristic values P are sent to a classifier; and the classifier is used for comparing the received human face characteristic values P with a characteristic threshold value A*m, and the human face characteristic values P greater than the characteristic threshold value A*m are kept. The Haar characteristic multi-processing framework human face detection system and method provided by the invention are suitable for human face detection.

The invention relates to the technical field of rare earth mining area environment pressure evaluation, in particular to a method for quantitatively evaluating rare earth mining area environment pressure on basis of a PSR model. The method comprises the following steps of: S101, data acquisition: obtaining an original remote sensing image, rainfall capacity data, topographic data, soil data and population density data of a to-be-evaluated area through a data acquisition unit; S102, data pre-processing: correcting the remote sensing image obtained in the step S101 through a geometric correction module, and carrying out atmospheric correction and mask clipping to obtain a research area remote sensing image; S103, remote sensing image information extraction: analyzing surface feature classification information of an evaluation area through a remote sensing information extraction unit, and carrying out statistic on the area of the evaluation area; and S104, PSR model analysis. By adoption of the method and system, the environmental safety conditions of rare earth mining areas are quantitatively evaluated, so that technical support is provided for the environment governance of the rear earth mining areas; and compared with the field investigation manner, the method and system have the characteristics of being time-saving, labor-saving and high in efficiency.

The invention provides a power grid planning data security printing method and system. Power grid planning data, access data personnel authority, an access client and a printer are classified according to security levels. For different data access personnel, the data can only be accessed through the client with the corresponding authority. The power grid planning data of the corresponding securitylevel is printed through the printer with the corresponding authority, so that access to the power grid planning data and the printing process are managed, especially for core data, the whole processis further tracked through the RFID tag technology, and data leakage in the printing process is avoided.

The invention relates to an intelligent design method of concrete production matching ratio, and belongs to the field of big data artificial intelligence. The method comprises the following steps thatS1, a concrete production matching ratio database is established, and the historical production matching ratio data of the concrete is input; S2, according to the part production matching ratio of the concrete input by users, expert system analysis is carried out, and the concrete production matching ratio with the highest score is primarily screened out; S3, a concrete production cost optimization model with constraint conditions is established; and S4, through the concrete production cost optimization model with the constraint conditions, fine adjustment on the concrete production cost optimization model with the highest initial screening score is carried out, the optimal concrete production matching ratio is output. According to the intelligent design method, the constraint conditionsare improved by combining historical production data, the production matching ratio reference is screened, the number of iterations of calculation can be effectively reduced, the intelligent design concrete production ratio can be efficient and real-time to carry out for the users, and the production cost is saved.

The invention provides a target tracking method and system based on unmarked video training, and the method comprises the steps: carrying out the unsupervised optical flow prediction of an original video, extracting a candidate frame of each frame in the original video, and obtaining a candidate frame sequence; constructing a pseudo calibration frame sequence of a moving object in the original video based on the candidate frame sequence; constructing a training sample based on the pseudo calibration frame sequence, inputting the training sample into a naive twinning network to train the naive twinning network, and generating a preliminary tracking model; performing storage loop training on the preliminary tracking model to obtain a target tracking model; and tracking a target in a to-be-tracked video by using the target tracking model. Meanwhile, the invention provides a corresponding terminal and a medium. The cost of manual annotation of the video data is greatly reduced, and available video data is enriched and trained; and under the condition of no annotation, a target tracking model based on calibration frame regression is trained from an unannotated video.

The invention discloses a falling-into-water detection and alarm system. The system comprises high-performance embedded GPU computing equipment integrated with a video acquisition module, a personnelfalling-into-water detection module and an alarm module. All the modules are operated on the embedded GPU computing equipment; the video acquisition module carries out decoding and image conversion ona real-time video stream shot by the front-end camera, thus video image data which can be calculated is obtained; during detection, firstly, video frame data of a camera at the front end of a monitored water area is collected in real time through a video collection module; the personnel falling-into-water detection module defines a detection area for the video frame data, then performs personneldetection on the video frame data in the defined detection area by utilizing the personnel falling-into-water detection module, sends an alarm signal in time once finding out a personnel falling-into-water situation, and sends personnel falling-into-water information to the background server. The method is used for realizing all-weather 24-hour automatic real-time early warning of personnel falling into water, manpower and material resources are effectively saved, the accuracy is improved, and the method can be deployed at the front end and is convenient and fast.

The invention discloses an interest point recommendation method and device, an interest point recommendation model training method and device, equipment, a storage medium and a computer program product, and relates to the fields of big data, artificial intelligence, deep learning and the like. The specific implementation scheme includes: determining the mhistorical interest points accessed by a current user according to historical behaviors of the current user; determining a plurality of candidate interest points according to the historical interest points; sorting the plurality of candidate interest points by utilizing the label of each candidate interest point; recommending a plurality of candidate interest points according to the sequence; constructing interests of the current user by utilizing historical behaviors of the current user, and expanding the interests of the current user to obtain candidate interest points; and obtaining the recommendation sequence according to the labels of the candidate interest points, so that various requirements can achieved in the map application program in combination with the interest of the user, the personalized requirements of the user are met, and the use experience of the user is improved.

The invention discloses a building energy-saving control system based on artificial intelligence. The building energy-saving control system comprises a building management system, Internet data, an artificial intelligence module and an energy station control system. The method is characterized in that artificial intelligence acquires historical and real-time data such as setting and operation states of a building management system, an external internet and energy station equipment, and learns optimal setting and control instructions of the energy station equipment under past building use and external weather conditions through an artificial intelligence module. Meanwhile, the artificial intelligence predicts the future use condition of the building based on the data. The trained artificialintelligence is combined with building future use condition prediction and weather prediction data, optimized equipment setting and operation commands are sent to an energy station control system, and the operation state of energy station equipment is adjusted, so that the purpose of saving energy is achieved.