6results about How to "Improve information utilization" patented technology

The invention provides a non-stationary industrial process monitoring method and system. The method comprises an offline training stage: calculating a time Laplacian matrix and a space Laplacian matrix based on a historical data matrix; constructing an objective function of the stationary subspace analysis method, and adding a time constraint term of a time Laplacian matrix and a space constraint term of a space Laplacian matrix into the objective function; solving the objective function to obtain a stable projection matrix; calculating a stationary component and a monitoring index of each sample in the data matrix X in sequence; determining a control limit by using a kernel density estimation method; an online monitoring stage: based on the real-time operation data x, calculating a stationary component of the real-time operation data x and a corresponding real-time monitoring index according to the stationary projection matrix, and if the real-time monitoring index is greater than a control limit, judging that the operation of the non-stationary process has a fault; the monitoring accuracy can be improved.

The application provides a DNA storage method and a data information storage entity capable of realizing random lossless reading of data, and the DNA storage method comprises the following steps: S1, preparation of a DNA double-stranded structure; S2, preparation of a data information storage entity; S3, random lossless reading of DNA data; and S4, recycling of the data information storage entity. According to the DNA storage method provided by the application, the random access function is realized by using the DNA double-stranded structure, and the long-term storage function is realized by using the outer wrapping hydrogel material, random reading in a file system with a large number of files is realized, and the original data is ensured not to be lost, so that the application has a wide application prospect in the field of DNA storage.

The invention discloses an information fusion method and system based on the Internet of Things technology, and relates to the technical field of information fusion, and the method comprises the following steps: S1, preprocessing sensor measurement information; s2, multi-channel sensing information fusion is carried out; s3, acquiring a sensor measurement value under the historical track of the vehicle; s4, associating the sensor with the track of the vehicle; and S5, all-around perception of the vehicle is carried out. According to the method, the radar sensor is associated with the vehicle track, the tracking precision can be ensured while the automatic sensing requirement of the vehicle is met, the problem that the radar sensor is difficult to estimate a target in all directions in a complex environment is solved, all-direction 360-degree target tracking is carried out through the target-level fusion center, and the method is efficient, intelligent and high in practicability. And the track management module is used for managing and maintaining the moving tracks of all vehicles, so that all-directional and full-period target tracking is realized, the stability of the tracks is kept, the all-directional sensing requirement of vehicle automation function upgrading is met, and the development of social productivity is promoted.

The invention discloses a scalar pair function regression-based organism Raman spectrum cross-tissue migration processing method, which comprises the following steps: constructing a cross-tissue spectrum database which comprises Raman spectrum data and target component concentration data; carrying out pretreatment on the Raman spectrum data; carrying out B-spline primary function fitting on the preprocessed Raman spectrum data, and establishing a function relationship between the Raman spectrum wave number and the light intensity; constructing and training a scalar pair function regression model; and inputting the preprocessed Raman spectrum data of the to-be-detected organism source tissue into the trained scalar pair function regression model to obtain a predicted target component concentration. According to the method disclosed by the invention, the mapping model from the easily-measured source tissue spectrum to the difficultly-measured target tissue component concentration is established, so that nondestructive detection for predicting the internal tissue components of the organism without dissection is realized; an effective solution is provided for solving the long-standing technical problem of noninvasive and dynamic monitoring of internal tissue components of living organisms.

The invention discloses a method and device for identifying fish sound signals based on a single-channel hydrophone, belonging to the field of water sound signal and pattern recognition. A double-threshold activity segment detection algorithm is designed to extract the sound fish signals of the water sound activity segment, and the water sound activity segment signal is decomposed into three-scale wavelet packets to extract the energy characteristics and singular value characteristics of 8 wavelet packet coefficients. Then, a separability judgment method of cluster separation degree is used to find feature quantities with large separability to form a feature vector. Finally, a machine learning method based on a BP neural network is designed to learn sample data, and a category judgment is made using the principle of minimum root mean square error of the output vector, thereby realizing the identification of the sound fish and obtaining a higher recognition rate.

The invention provides a model quantification method and device, a model reasoning method and device, equipment, a medium and a product. Constructing an input base of a sample input space based on the sample set, and defining an energy distribution condition of a base direction of the sample input space; the method comprises the following steps of: mapping an original weight matrix to a sample input space through the original weight matrix based on an input base and an expert module to obtain a mapping weight matrix, so that a quantization process of a weight parameter is explicitly aligned with a model input space; then, carrying out generality extraction on the mapping weight matrix of each expert module to obtain a specific weight matrix and a generality weight matrix of each expert module; and the specific weight matrix is quantized to obtain a quantization matrix, so that only the specific part of each expert module is taken as a to-be-quantized object, the limited quantization matrix can focus on the difference between experts and contains more information amount, the information utilization rate of the quantization matrix is remarkably improved, and the accuracy of model quantization is improved.