Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

80 results about "Sequence learning" patented technology

In cognitive psychology, sequence learning is inherent to human ability because it is an integrated part of conscious and nonconscious learning as well as activities. Sequences of information or sequences of actions are used in various everyday tasks: "from sequencing sounds in speech, to sequencing movements in typing or playing instruments, to sequencing actions in driving an automobile." Sequence learning can be used to study skill acquisition and in studies of various groups ranging from neuropsychological patients to infants. According to Ritter and Nerb, “The order in which material is presented can strongly influence what is learned, how fast performance increases, and sometimes even whether the material is learned at all.” Sequence learning, more known and understood as a form of explicit learning, is now also being studied as a form of implicit learning as well as other forms of learning. Sequence learning can also be referred to as sequential behavior, behavior sequencing, and serial order in behavior.

Skeleton sequence recognition method based on masked image autoencoders and system

Disclosed in the present invention are a skeleton sequence recognition method based on masked image autoencoders and a system. The method comprises the following steps: building a skeleton action recognition model, and using the skeleton action recognition model to recognize a skeleton sequence so as to predict the class of an action, the skeleton action recognition model comprising an M-layer spatial-temporal representation learning model and a one-layer classifier, the spatial-temporal representation learning model comprising two masked image autoencoders connected in parallel, and, by means of 1×1 convolution, output ends of the masked image autoencoders being subjected to residual connection with input ends thereof. The present invention uses the M-layer spatial-temporal representation learning model and the one-layer classifier to build the skeleton action recognition model, which uses a fine-grained dependency relationship between different skeleton joints for training and learning, is a highly-efficient skeleton sequence learning model, and is well generalized on different data sets.
Owner:SUN YAT SEN UNIV

Terminal operation and maintenance management method and platform for medical big data platform

The invention provides a terminal operation and maintenance management method and platform for a medical big data platform, and the method comprises the steps: firstly collecting multi-mode historical operation and maintenance data of a platform terminal in a normal working state, and constructing a time sequence feature vector sequence after preprocessing and fusion; a deep sequence learning model training process is then utilized to learn the potential representation to capture the context state of the normal workflow mode and establish a reconstructed baseline model. Acquiring real-time operation and maintenance data of the terminal, constructing a feature vector, extracting potential context representation through the trained model, and calculating a reconstruction error; a current workflow state is identified based on the potential representation, and a context-aware anomaly metric value is calculated in conjunction with state information and reconstruction errors. And analyzing the time evolution characteristic of the abnormal metric value and comparing the time evolution characteristic with a preset abnormal mode criterion to judge whether the terminal has workflow abnormality, and if so, generating an early warning signal containing abnormal evolution characteristic description. The method has the effect of improving the operation and maintenance detection accuracy of the terminal.
Owner:WUHAN SHENGBOHUI INFORMATION TECH CO LTD

Dynamic and static function brain network spatio-temporal topology fusion method and device based on EEG

The invention discloses an EEG-based dynamic and static functional brain network spatio-temporal topology fusion method and device, and belongs to the technical field of functional brain network spatio-temporal signal classification, and the method comprises the steps: obtaining a multiplexing division EEG resting signal segment sequence and a multiplexing division continuous EEG resting signal segment sequence; inputting the multiplexing division EEG resting signal fragment sequence into a static function connected spatial topology learning module to obtain high-discrimination local and global spatial topology features; inputting the multiplexing division continuous EEG resting signal fragment sequence into a dynamic function connection time sequence learning module to obtain high-discrimination time sequence characteristics; and splicing the high-discrimination local and global spatial topological features and the high-discrimination time sequence features, and inputting a splicing result into a multi-layer perceptron classification layer to obtain a brain cognitive resting task classification result. When the functional brain network is explored, spatial and temporal changes of brain activities are fully considered from two scales of dynamic function connection and static function connection.
Owner:CHENGDU UNIV OF INFORMATION TECH

Multi-scale time-frequency network sleep stage classification method based on single-channel electroencephalogram

The invention discloses a multi-scale time-frequency network sleep stage classification method based on single-channel electroencephalogram, and belongs to the technical field of medical signal processing. Aiming at the problems of capturing multi-scale time-frequency characteristics, processing variability among subjects and modeling long-range time dependence of a sleep staging method, the method comprises the following steps: firstly, acquiring electroencephalogram signal data, and performing time sequence segmentation, sleep stage category label determination and standardized preprocessing by taking a single-channel electroencephalogram signal as an analysis object; performing data set division by adopting nested cross validation, and constructing a multi-scale time-frequency network model; the model comprises a feature extraction module and a sequence learning module, wherein the feature extraction module comprises a time domain branch and a frequency domain branch; a subject adaptive feature calibration module is proposed to dynamically compensate the influence brought by individual difference and signal quality fluctuation; respectively training a feature extraction module and a sequence learning module by adopting a component type training strategy; and inputting to-be-classified electroencephalogram signal data into the trained model, and outputting a corresponding sleep stage classification result.
Owner:SHANXI UNIV

Electroencephalogram recognition method and system based on nonlinear cross frequency modulation network

ActiveCN118948277AStrong independenceeffective divisionBiological modelsSensorsAlgorithmFrequency modulation
The invention discloses an electroencephalogram recognition method and system based on a nonlinear cross frequency modulation network, relates to the technical field of electroencephalogram signal processing, and realizes nonlinear division of a target frequency band and self-adaptive extraction of cross frequency coupling characteristics. The electroencephalogram signal preprocessing module is used for receiving and preprocessing collected original electroencephalogram signals. And the frequency band decomposition and feature representation module is used for carrying out frequency band division on the preprocessed electroencephalogram signals based on eMEMD and nonlinearly extracting signal components of a target frequency band. And the cross frequency coupling layer is used for capturing coupling information among different frequency bands and outputting cross frequency coupling characteristics. The CNN1D-ALSTM model is combined with the time sequence feature extraction capability of the one-dimensional convolutional neural network and the long sequence learning capability of the Bi-LSTM to capture the time sequence features in the cross frequency coupling features. And the space decoding module is used for carrying out space decoding on the time sequence characteristics to obtain space-time characteristics. And the emotion classification module is used for projecting the spatial-temporal features into an emotion space to be classified.
Owner:BEIJING INST OF TECH

Multi-physiological signal fusion sleep staging method and system

The invention relates to the technical field of physiological signal processing and sleep monitoring, in particular to a sleep staging method and a sleep staging system for collecting multiple physiological signals, and the sleep staging method and the sleep staging system for collecting the multiple physiological signals synchronously collect auditory meatus photoelectric volume pulse waves, temperature and head micro-motion signals through an in-ear sensor array. According to the method, the signal quality index is calculated, time domain, frequency domain and nonlinear features are extracted, a dynamic weighted fusion mechanism is adopted, feature weights are adjusted according to the signal quality index, a hierarchical depth time sequence learning model is input for sleep staging, and the sleep staging accuracy is improved to 89% or above and is improved by 15-20% compared with a single brain wave method. A sleep state evaluation report and a personalized feedback intervention strategy generated by the system are beneficial for improving sleep quality, a dynamic weighted fusion mechanism enhances system robustness, adapts to different signal qualities and ensures stable performance, and the invention provides an efficient and accurate new method for the field of sleep monitoring.
Owner:COSONIC INTELLIGENT TECH CO LTD

Behavior guidance-based emergency lane changing dangerous scene generation method and system, and medium

The invention discloses an emergency lane changing dangerous scene generation method and system based on behavior guidance and a medium. The method comprises the following steps: constructing a track data set of vehicle emergency lane changing behaviors; training a behavior learning module with short sequence learning ability according to the trajectory data set; training an active attack strategy model through guidance of a behavior learning module; outputting a reference track point of the active attack vehicle through the active attack strategy model, and obtaining an optimal control input in a future time domain according to the reference track point and a preset prediction control model; and controlling the active attack vehicle to interact with the simulation platform according to the optimal control input, and generating an emergency lane changing dangerous scene. The method improves the generation efficiency of the emergency lane changing dangerous scene, thereby improving the efficiency of the automatic driving test, and can be applied to the technical field of automatic driving.
Owner:SUN YAT SEN UNIVERSITY SHENZHEN +1

Long-term continuous learning method based on task core memory management and consolidation

A long-term continuous learning method based on task core memory management and consolidation aims to enable a model to sequentially learn from a large number of task sequences, new knowledge is obtained, information of previous learning is reserved, and the method is similar to a human learning mode. The method comprises the following steps: 1) task input and instruction fine tuning; 2) performing difference analysis on the model parameters of the current task and the previous task, identifying a task core memory unit, calculating an adaptive weight based on task prototype similarity, and dynamically updating the memory unit; 3) constructing an experience playback buffer area through a difficult sample selection strategy and a difference sample selection strategy; and 4) utilizing the joint loss function training model to keep the memory of the historical tasks while learning the new tasks. According to the method, the problem of disastrous forgetting in long-term continuous learning is mainly solved, and the performance of the model in a long-term sequence task is remarkably improved.
Owner:EAST CHINA NORMAL UNIV +1

Sodium-ion battery energy storage system health state dynamic prediction method based on simulation digital twinning

The invention is suitable for the technical field of battery safety monitoring, and provides a sodium ion battery energy storage system health state dynamic prediction method based on simulation digital twinning, and the method comprises the steps: constructing a digital twinning body comprising a physical layer, a virtual layer and a data interaction layer; performing health state estimation based on the physical layer and the virtual layer, and outputting a health state estimation value; comparing the health state estimated value with the measured value, calculating a residual error, and updating key aging parameters in the simulation model; inputting the updated key aging parameters into a pre-trained time sequence neural network model, carrying out sequence learning, and outputting a capacity attenuation trend and a residual life prediction result of the battery; generating a full life cycle optimization strategy based on the prediction result, and generating an optimal charge-discharge power table by simulating the influence of different charge-discharge strategies on the life; the problems of life attenuation and high operation and maintenance cost caused by insufficient prediction precision in the prior art are effectively solved.
Owner:ELECTRIC POWER RES INST OF GUANGXI POWER GRID CO LTD

Full Transform video abstraction method based on local-global attention

The invention relates to a full Transform video abstraction method based on local-global attention, and the method employs a full Transform, employs an encoder-decoder structure, employs a supervised mode to carry out video abstraction, regards the video abstraction as a sequence-to-sequence learning problem, directly applies the full Transform to a video abstraction task, and improves the video abstraction efficiency. A full attention mechanism in an original Transform is replaced by a combination of local and global sparse attention, so that the model can capture a long-distance dependency relationship while reducing the calculation cost. The stacking mode of the encoder and the decoder is the same as that of an original Transform, and local-global sparse attention is only used in the encoder end. Experiments on two public multimedia reference data sets TVSum and SumMe show that the method can greatly exceed other video abstraction methods.
Owner:CHONGQING UNIV OF TECH

Feature reconstruction and consistency CTC-based semantic enhancement text recognition method

The invention discloses a semantic enhancement text recognition method based on feature reconstruction and consistency CTC. The method comprises the following steps that a CTC model is established in advance; obtaining a text image, and preprocessing the text image based on the height and the aspect ratio of the text image and a preset maximum aspect ratio; generating two different enhanced views from the preprocessed text image; inputting the two different enhanced views into a pre-trained CTC model for processing; and outputting a processing result as a text recognition result. In order to better fuse image information with voice and texts, sequence learning is carried out on the image information, a time sequence model is established to extract semantic information, through feature reconstruction and semantic enhancement technologies, the accuracy and robustness of text recognition can be improved, and the alignment problem existing in the prior art is effectively solved.
Owner:HARBIN INSTITUTE OF TECHNOLOGY (SHENZHEN) (INSTITUTE OF SCIENCE AND TECHNOLOGY INNOVATION HARBIN INSTITUTE OF TECHNOLOGY SHENZHEN)

Multi-vehicle cooperative three-dimensional target detection method for heterogeneous intelligent network connection vehicle group

The invention discloses a multi-vehicle cooperative three-dimensional target detection method for a heterogeneous intelligent network connection vehicle group, and the method comprises the following steps: carrying out the preprocessing of obtained multi-source heterogeneous vehicle-mounted sensor data, and extracting the features of multi-mode heterogeneous data; constructing a dynamic pose compensation network, learning and predicting a pose compensation amount by using a time sequence, correcting a pose error in multi-vehicle cooperative perception, and ensuring a space reference of multi-vehicle features; performing cross-modal feature fusion on the multi-vehicle multi-modal heterogeneous data features through a global-local cross-modal attention mechanism; designing a multi-scale feature distillation strategy, and reducing the semantic fusion gap of the cross-modal features; an end-to-end combined training framework is constructed to integrate dynamic pose compensation, cross-modal feature fusion and multi-scale feature distillation strategies, and a multi-vehicle collaborative three-dimensional target detection model is optimized through an adaptive weighted loss function. The technical problems of multi-vehicle heterogeneous sensor fusion, pose drift correction and cross-modal semantic alignment are solved.
Owner:ANHUI UNIV OF SCI & TECH

APT attack tracing method fusing sequence learning and causal analysis

The invention discloses an APT attack tracing method fusing sequence learning and causal analysis, comprising: acquiring system kernel logs and POI events, the system kernel logs including attacked and non-attacked system kernel logs; constructing a POI strong dependency influence module to obtain a POI strong dependency influence graph; a key sequence recognition model training module is adopted to obtain a trained key sequence recognition model; and performing APT attack tracing through a key component identification module, and executing the following operations: inputting an embedded vector obtained based on the POI strong dependency influence graph into a trained model for identification, identifying a key process and a key event, combining the key process and the key event into a key component graph, and realizing APT attack tracing according to the key component graph. According to the method, efficient, accurate and fine-grained APT attack traceability can be realized, the problem of lack of marked data sets is solved, and reliance of dependency explosion is facilitated.
Owner:ZHEJIANG UNIV OF TECH

Multi-modal sentiment analysis method based on graph-attention collaborative optimization cross-modal recombination

The invention provides a multi-modal sentiment analysis method based on graph-attention collaborative optimization cross-modal recombination, and relates to the technical field of multi-modal sentiment analysis. The method comprises the following steps: firstly, designing a modal self-adaptive multi-modal graph construction module, constructing a local sparse graph based on KNN-RBF for a language modal, and adopting a low-rank representation method combined with nuclear norm regularization for an audio and video modal; secondly, the processed modal features are transmitted into a graph attention network to realize high-order feature aggregation; then, a language-guided hierarchical cross-modal interaction mechanism is constructed, and multi-granularity semantics are accumulated in combination with an advanced multi-modal feature container module; and finally, designing an advanced feature recombination strategy based on dynamic matching, and realizing feature alignment by taking a language feature container as an anchor point. According to the method, graph learning and sequence learning are unified in a collaborative framework through a graph-attention collaborative optimization cross-modal recombination model, so that the problems of cross-modal attention noise interference, modal imbalance, insufficient cross-modal feature alignment efficiency and the like can be effectively solved.
Owner:ZHONGYUAN ENGINEERING COLLEGE

Method and apparatus for sequential learning of two-sided artificial intelligence / machine learning model for feedback of channel state information in communication system

A method of a first training node may comprise: performing training on a first two-sided AI / ML model using a raw training data set collected for CSI feedback; generating a sequential training data set for sequential training on the first two-sided AI / ML model; performing pruning on the sequential training data set to obtain a reduced sequential training data set; and transmitting, to a second training node, two-sided AI / ML training data information including at least one of the reduced sequential training data set or sequential training data configuration information.
Owner:ELECTRONICS & TELECOMM RES INST

ATE embedded wafer defect detection method and device based on dynamic electrical sequence RNN

The embodiment of the invention provides an ATE embedded wafer defect detection method and device based on a dynamic electrical sequence RNN, and the method comprises the steps: obtaining original electrical parameter data from an ATE test process, and carrying out the preprocessing of the original electrical parameter data, and determining quality parameter data; constructing sequence data based on the quality parameter data; constructing an initial depth sequence learning model, training the initial depth sequence learning model based on the sequence data, and determining a target depth sequence learning model; wherein the deep sequence learning model is an RNN architecture; and acquiring current wafer test data, and determining defect information based on the current wafer test data and the target depth sequence learning model. Through the deep dynamic analysis of the electrical parameter sequence, the potential failure risk and process abnormality can be identified earlier and more sensitively before the defect feature of the Die is not completely shown or is judged to be qualified in the traditional test, and the capture rate of early defects is improved.
Owner:NORTHEASTERN UNIV CHINA

RRU multi-band passive intermodulation elimination method based on sequence-to-sequence learning model

The invention discloses an RRU multi-band passive intermodulation elimination method based on a sequence-to-sequence learning model, and the method comprises the steps: obtaining a transmitting signal and a receiving signal of a multi-band RRU, carrying out the feature extraction of the signals through adaptive transformation, and obtaining the multi-band intermodulation interference feature data; generating a nonlinear intermodulation feature vector based on the multi-band intermodulation interference feature data; training a PIM signal prediction model by using a sequence-to-sequence learning model, and performing residual compensation on a prediction result based on an error optimization mechanism; performing adaptive filtering processing on the predicted PIM interference signal to generate an optimized interference compensation signal; and dynamically updating the PIM signal prediction model by using an online learning mechanism based on the signal data after interference suppression. According to the method, the multi-band nonlinear intermodulation characteristics can be modeled in a self-adaptive manner, the PIM prediction precision is improved, and the calculation complexity is reduced.
Owner:SYNTRONIC (BEIJING) TECH R&D CENT CO LTD

Double-flow LSTM (Long Short Term Memory) prediction method for port shore power load

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.
Owner:CHINA THREE GORGES UNIV

Deep learning-based pollutant into-sea flux monitoring and predicting method

The invention relates to the technical field of sea flux monitoring, in particular to a pollutant sea flux monitoring and predicting method based on deep learning. The method comprises the following steps: collecting historical flow and pollutant concentration data of a target area according to different time intervals, and locking an area to be analyzed according to the historical flow and pollutant concentration data; then obtaining a regional water sample, extracting concentration and flow data of nitrite, ammonia nitrogen and nitrate, and constructing a training set; after the training set and the real-time flow test set are standardized, deep time sequence learning is carried out through a TCN model, and the future flow and the concentration of each pollutant are predicted; and finally, calculating the into-sea flux based on a prediction result, and realizing high-precision pollutant into-sea flux monitoring and forecasting. According to the method, deep causal convolution and residual feature extraction are performed on long-time sequence data by using the time sequence convolution network, so that the prediction precision and efficiency of the pollutant into-sea flux under complex terrains, extreme climates and human activity dense areas are improved.
Owner:GUANGDONG OCEAN UNIVERSITY

Micro-expression recognition method and device based on local-global time relation and medium

The invention discloses a micro-expression recognition method and device based on a local-global time relationship, and a medium, and relates to the technical field of video processing. The method comprises the following steps: decomposing a micro-expression video into a micro-expression image sequence; preprocessing the micro-expression image sequence; constructing a multi-scale spatio-temporal feature extraction module for extracting local spatial features and local time features; constructing an improved double-flow global time sequence learning module which is used for extracting global spatial-temporal features of the micro-expressions; a cross-modal global time relation learning module is constructed and used for fusing global spatial and temporal features, and a multi-head self-attention mechanism is adopted to perform modeling on the relation between the time features and the spatial features; constructing and training a local-global time relation network; and preprocessing a to-be-recognized micro-expression video, inputting the trained local-global time relation network, and recognizing a micro-expression category. The method is high in automation degree and robustness, and can fully learn the local and global time relation.
Owner:BEIJING FORESTRY UNIVERSITY

Hydraulic loading system fault diagnosis method based on sequence learning

A hydraulic loading system fault diagnosis method based on sequence learning comprises the steps that firstly, sample data and corresponding labels are imported, and the imported sample data are flattened and then subjected to normalization processing; then, a three-layer one-dimensional CNN convolution structure is adopted, each layer comprises convolution, batch normalization, ReLU activation function and maximum pooling operation, and a feature matrix is obtained; then, inputting the feature matrix into a single-layer one-way GRU network to capture a dynamic time sequence dependency relationship, and taking a final hidden state of the dynamic time sequence dependency relationship as a global feature representation; and finally, the global features are mapped to a fault category space by a full connection layer, and a Softmax activation function is used to complete fault classification. Cross entropy is adopted as a loss function, the normalized data sample is used for training, and when the accuracy of the verification set reaches a design value or reaches the maximum training round number, the training is ended; according to the method, the automation degree and reliability of fault diagnosis of the hydraulic loading device are remarkably improved by fusing the advantages of the CNN in feature extraction and the GRU in time sequence modeling.
Owner:XI AN JIAOTONG UNIV

Annotation method and system for medical ultrasonic image

The invention discloses a medical ultrasonic image annotation method and system, and the method comprises the steps: obtaining a medical ultrasonic image data set, and carrying out the preprocessing of an image, including image denoising and enhancement operation; for the preprocessed medical ultrasonic image, automatically detecting and positioning a text region in the image by adopting a text detection algorithm based on deep learning, and obtaining the position and size space information of a text; according to the detected text area, the OCR technology is used for text recognition, a method based on character segmentation and a method based on sequence learning are used, text content in the image is accurately extracted, and a preliminary text recognition result is obtained.
Owner:曹葳

Key Phrase Generation Using Indefinite Sequence Learning

Key phrase generation using indefinite sequence learning is described. In accordance with the described techniques, a sequence generation model generates a sequence of key phrases based on an input document. During the generation task, the sequence generation model omits use of a self-generated sequence termination token. Key phrases in the sequence are then output as recommended key phrases for the input document.
Owner:EBAY INC

Permanent magnet synchronous motor phase sequence learning method of rotary transformer

The invention discloses a phase sequence learning method for a permanent magnet synchronous motor of a rotary transformer, which comprises a motor positive and negative phase sequence learning process: step A1, a preset direct-axis current and an electrical angle of the permanent magnet synchronous motor are given, and the electrical angle of the permanent magnet synchronous motor is positively increased; a2, sine and cosine signals of the rotary transformer in the rotating process are obtained, and the positive and negative phase sequences are judged according to the sine and cosine signals; the absolute position difference learning process of the rotary transformer and the permanent magnet synchronous motor comprises the steps that B1, preset direct-axis current of the permanent magnet synchronous motor is given, and the electrical angle of the permanent magnet synchronous motor is set to be zero degree; b2, the electrical angle of the permanent magnet synchronous motor is increased until the rotary transformer outputs zero position information; and step B3, acquiring a current rotated angle of the permanent magnet synchronous motor, and calculating an absolute position difference and a rotor position of the rotary transformer and the permanent magnet synchronous motor. According to the method, the problems of phase sequence learning and angle analysis under different pole pair number combinations of different rotary transformers and permanent magnet synchronous motors are solved.
Owner:JIANGSU UNIV OF SCI & TECH

A machine learning-based intelligent monitoring method for operating state of communication power supply

The application discloses a kind of communication power supply operating state intelligent monitoring methods based on machine learning, comprising the following steps: S1, obtains multiple-source monitoring data and pre-processes;S2, sequence segmentation is carried out using sliding time window and statistical feature vector is extracted, forms state variable set;S3, each state variable is encoded to construct state node and establish weighted directed connection, and construct operating state evolution diagram;S4, state transition matrix is constructed, main transition feature is extracted and low rank is approximately reconstructed, sequence learning is carried out to construct state update function;S5, to state node, multiple-step recursion is carried out, and the Euclidean distance between recursive state and risk boundary is calculated, to determine state monitoring result;S6, error is calculated and state update function parameter is iteratively updated.The application can realize the multiple-step recursion prediction and risk trend identification of communication power supply operating state, improve the accuracy and stability of communication power supply operating state monitoring.
Owner:WUHAN ZHIMA TECH CO LTD

Field exercise and training medical service equipment management system based on block chain

The invention discloses a field exercise and training medical service equipment management system based on a block chain, and relates to the technical field of field emergency medical equipment management and power supply safeguard.The viability of field medical service equipment in an extreme environment is remarkably improved through deep coupling of a block chain architecture and an intelligent algorithm; the dynamic analysis unit adopts an online sequence learning model to compress and analyze the window size according to the real-time altitude and power supply quality index, so that the capture speed of a plateau voltage sag event is increased to millisecond level, and the downtime risk caused by instantaneous power failure of key equipment such as a cardio-pulmonary resuscitation machine is thoroughly avoided; on the premise of protecting data privacy, the federal aggregation mechanism fuses fluctuation characteristics of a plurality of generators, the generated prediction model can adapt to different altitude intervals, and the problem of cross-scene failure of a single model is solved.
Owner:CHENGDU MILITARY GENERAL HOSPITAL OF PLA

Chinese character stroke sequence learning system combining character and image processing

A Chinese character stroke sequence learning system combining character and image processing comprises hardware and software, and the hardware comprises a touch display screen and a handwriting board; the software comprises an image recognition and processing module, an animation display module, a database, a user interface, a knowledge explanation module and an interactive evaluation module; the touch display screen is used for displaying contents such as stroke sequence animations and images of Chinese characters on a main interface where a user interacts with the system; the handwriting board is used for Chinese character writing practice of a user and capturing writing actions of the user in real time; the image recognition and processing module is used for recognizing Chinese characters written on the writing board by a user and judging the correctness of a stroke sequence; the animation display module is used for displaying the correct writing sequence of the Chinese characters step by step and vividly demonstrating the writing mode of each stroke through animation; and the database is used for storing knowledge data such as stroke sequences, cultural backgrounds, pronunciation and meaning, exercises and the like of the Chinese characters.
Owner:SHANDONG PROVINCE HEZE HEALTH SCHOOL

An information mining method for heterogeneous time series data

ActiveCN116543917BMedical recordHidden data
The application belongs to the field of medical prediction, and discloses an information mining method for heterogeneous time series data, comprising: acquiring electronic medical record data and constructing a hypergraph, analyzing and calculating the hypergraph to obtain embedding representation data, weighting the embedding representation data based on an attention mechanism to obtain embedding sequence data, constructing a sequence learning model and performing hidden state access to obtain hidden representation data and weight data thereof, weighting the embedding sequence data to obtain embedding sequence hidden data; training the sequence learning model through time training parameter data, weighting the embedding sequence hidden data through the trained sequence learning model to obtain time dimension hidden data, constructing a full connection network to analyze the time dimension hidden data to obtain medical event prediction data. The technical scheme disclosed by the application can learn complex information in the time dimension by using time step information, and can obtain accurate medical event prediction results.
Owner:NORTHWESTERN POLYTECHNICAL UNIV

Image analysis method based on double-branch multi-modal sequence learning

The invention provides an image analysis method based on double-branch multi-modal sequence learning, and belongs to the technical field of medical image analysis, and the method comprises the steps: constructing a multi-modal embedding module, filling missing multi-modal disease data by using learnable parameters, fusing the filled multi-modal features, and obtaining the coding features of a subject; a dual-branch structure comprising a static information analysis module and a dynamic information analysis module is utilized to analyze the coding features, and dual-branch multi-modal image analysis features are obtained; fusing the dual-branch multi-modal image analysis features to obtain image features in the longitudinal queue data; and stacking the image features in all the longitudinal queue data, and analyzing the image features in all the stacked longitudinal queue data by using the multi-modal data except the filled multi-modal disease data to obtain an image analysis result. According to the method, the problem of insufficient utilization of multi-modal information and time sequence evolution information in a multi-modal longitudinal queue image analysis method is solved.
Owner:BEIHANG UNIV