11results about How to "Fast decoding" patented technology

The invention provides a method for converting a multi-stage non-iodine contrast CT image into a coronary artery CTA image, and the method comprises the steps: obtaining an NCCT volume and a CTA volume which are matched, carrying out the data preprocessing, and constructing a training data set; respectively constructing an NCCT encoder-decoder network and a CTA encoder-decoder network, and carrying out pre-training based on the training data set; a mark reconstruction network is constructed and trained, a masked low-resolution CTA mark is reconstructed under the condition of an NCCT token obtained by a trained encoder, and then a low-resolution CTA volume is reconstructed by a trained decoder; a super-resolution network is constructed and trained, and a high-resolution CTA image is generated from the low-resolution CTA image; a high resolution CTA volume is generated from the low resolution NCCT volume using the trained multi-stage model. The method has the beneficial effects that the problem of posterior crash is avoided, the decoding speed during reasoning is higher, and the training process is more stable; in the low-resolution stage, the model can learn multi-scale context information, and in the high-resolution stage, the model focuses on recovering details, more fine structures are reserved in final output, and clinical requirements can be met.

The invention provides a data transmission method, system and device and a computer program product. The method comprises the following steps: a sending end device encodes target data based on a first neural network, and sends first encoding result data obtained by encoding to a receiving end device; and the receiving end device decodes the received moral first coding result data based on the second neural network, and determines target data based on first decoding result data obtained by decoding. Wherein the first neural network and the second neural network are obtained by training based on first loss between the sample data and the second decoding result data, the second decoding result data are obtained by decoding the second encoding result data by the second neural network, and the second encoding result data are obtained by encoding the sample data by the first neural network. Based on the characteristics of the neural network, the computing resources of the sending / receiving end are fully utilized to complete data compression transmission, and the neural network supports fine tuning training and can follow up the demand for dynamic upgrading.

The invention relates to the technical field of image processing, and particularly provides a bar code image recognition method, device and equipment and a storage medium, and the method comprises the steps: obtaining a to-be-recognized bar code image which comprises a plurality of parallel line segments; identifying the position of a first end point of each line segment; determining a target classification line of the first endpoint according to a set rule; determining the state of each first end point based on the position relationship between the position of each first end point and the target classification line of the first end point; determining the state of each line segment according to the state of the first end point of each line segment; and decoding based on the state of each line segment to obtain an identification result of the to-be-identified barcode image. By utilizing the characteristic that the end points on the single side of the bar code are simultaneously positioned on the same straight line, the state of each line segment in the bar code is efficiently determined, so that rapid decoding of the bar code is realized, and the identification precision is relatively good.

This application discloses an encoding method, a decoding method, an electronic device, and a readable storage medium, relating to the field of programmable logic controller (PLC) technology. The method includes: identifying instruction characteristics of an instruction; determining the instruction code type based on the instruction characteristics, wherein the instruction code type includes basic fixed-length instruction code, fixed extended instruction code, extended long instruction code, and variable-length instruction code; and filling the instruction code field of the instruction according to the instruction code type to obtain the target instruction code. This application solves the problem of low encoding efficiency in PLC instruction encoding methods and effectively improves decoding speed.

The invention discloses a decoding method of a periodic variable interval laser code. The decoding method comprises the following steps: S1, determining a required maximum decoding bit N; s2, the minimum array length S of the collected pulses is judged according to the maximum decoding bit N, and if N is an even number, S = N + 2; if N is an odd number, S = N + 1; s3, judging whether the front S / 2 pulse sequence and the rear S / 2 pulse sequence in the array are the same or not, if yes, resolving a code pattern and recording the sequence, and if not, performing the next step; s4, calculating whether S is equal to 2N or not so as to judge whether the maximum decoding length upper limit is reached or not, and if S is equal to 2N, indicating that the decoding capability is exceeded if the maximum decoding length upper limit is reached; and if S is not equal to 2N, adding two pulse intervals to the array, and repeating the steps S3 to S4 until decoding is completed. According to the method, the decoding speed is high, decoding can be carried out in two maximum decoding periods, and decoding is accurate.

The present application relates to the technical field of brain-computer interface and neural signal processing, and provides a cross-subject intracranial electroencephalogram decoding method and system based on transfer learning, comprising: acquiring heterogeneous channel intracranial electroencephalogram data and task labels of multiple source subjects; projecting the electrode channel dimension of each source subject to a unified shared channel dimension through a channel projection adapter, extracting cross-subject reusable time-space features through a shared core, and obtaining a prediction result through a multi-task decoding head; jointly training the adapter, the shared core and the decoding head of each source subject to obtain pre-training shared core parameters; constructing a target adapter for a target subject and reconfiguring a task head, performing fast fine-tuning on the target adapter, the task head and the shared core to obtain a target decoding model, and decoding the data of the target subject to obtain an intracranial electroencephalogram decoding result. The present application realizes explicit alignment of heterogeneous electrode channels, fast migration of new subjects with few samples, flexible reuse across tasks and robust decoding of ring visual attributes.

This invention provides an automatic billet information tracking and receiving / sending control method based on a steel rolling heating furnace, relating to the field of steel production technology. The method includes the following steps: Step 1: Receiving billet coding information from the steelmaking system via a gateway communication device between steelmaking and rolling; Step 2: Determining if the coding information is correct. If it does not conform to the rules, the system returns to receive the coding information again and returns an error instruction to the steelmaking system; Step 3: Upon receiving data that conforms to the rules, the system calls the information decoding module to perform protocol decoding on the received data; Step 4: Generating a tracking sequence from the decoded data according to the data definition. This invention quickly, accurately, and in real-time decodes the billet coding data sent from the steelmaking system, achieving fully automatic billet tracking from the hot conveyor roller to the furnace. It then matches the weighing, length measurement, and temperature data with the steelmaking flow data, re-matches and returns the data to the steelmaking system, facilitating collaborative work between the steel rolling and steelmaking systems.

The invention relates to the technical field of power systems, in particular to a low-delay communication conversion system and method for micro-grid communication, and the system comprises a data analysis unit which is used for obtaining communication load data for collected communication protocol data; the data packaging unit is used for combining and packaging the communication load data obtained by the data analysis unit according to a set protocol format to generate a data packet; the data transceiving unit is used for packaging the data packet obtained by the data packaging unit, outputting the packaged data packet to a PCIE interface, receiving data of the PCIE interface, and decoding to obtain communication data to be sent and a sending interface corresponding to the communication data; the communication management unit is used for loading and packaging the communication data obtained by the data analysis unit and then forwarding the communication data to an interface corresponding to the sub-equipment; and the data sending unit is used for packaging and outputting the communication data obtained in the data transceiving unit and the communication management unit. According to the method, multiple communication protocols can be quickly decoded and transferred, and the real-time performance and efficiency of the system are improved.

This invention provides a data storage device and a decoding method selection method. The data storage device includes a controller and non-volatile memory. The non-volatile memory stores multiple instructions, and the controller executes these instructions to implement the decoding method selection method, which includes: determining if a first read voltage from a previously correctly read data is stored; determining if hard decoding based on the first read voltage has failed; obtaining the symptom weight of the hard decoding; finding the number of reads required for soft decoding based on the first read voltage according to the symptom weight; and determining if soft decoding based on the first read voltage has succeeded. This allows for fast soft decoding, saving the time required to track the read voltage.

The invention provides a data decoding method and device, equipment and a storage medium, and the method comprises the steps: transmitting a radio frequency carrier wave to a target detection region, and receiving echo coding data of the target detection region; according to the echo coded data, generating to-be-processed data corresponding to the echo coded data; determining a decoding initial position in the to-be-processed data according to the to-be-processed data and a predefined synchronous data head; and decoding the to-be-processed data according to the decoding starting position and a pre-configured decoding data standard sequence to obtain decoded data corresponding to the echo coding data. According to the method, the decoding distance and the decoding accuracy during decoding are greatly improved, meanwhile, the decoding initial position is determined through the pre-defined synchronous data head, and then decoding is performed through the pre-configured decoding data standard sequence, so that the method also has the advantage of relatively high decoding speed, and the decoding efficiency is improved. And the storage space and the decoding time are saved.