20results about How to "High identification accuracy" patented technology

The invention discloses a traditional Chinese medicinal material authenticity identification platform, and relates to the technical field of traditional Chinese medicinal material authenticity identification, the traditional Chinese medicinal material authenticity identification platform comprises a data acquisition module, the data acquisition module is connected with a data analysis module, and the data analysis module is connected with a result display module; and the data acquisition module is used for acquiring appearance images, spectral data and background information of the traditional Chinese medicinal materials. According to the traditional Chinese medicine authenticity identification platform, traditional Chinese medicines are comprehensively analyzed from multiple angles, limitation of a single method is avoided, and identification accuracy is improved; the characteristics of the traditional Chinese medicinal materials are deeply analyzed to accurately judge authenticity and quality; the quality of the traditional Chinese medicinal materials is accurately evaluated by establishing a quantitative analysis model; the model is verified by adopting a cross validation method, so that the accuracy and stability are ensured, the identification accuracy is improved, and the problem that the traditional identification method is difficult to meet the requirement of quickly and accurately identifying the authenticity of the traditional Chinese medicinal materials is solved.

The invention discloses a deep learning-based deep forged compressed face image identification method, which belongs to the field of artificial intelligence image identification, and comprises the following steps of: 1, carrying out frequency domain modal extraction on a deep forged compressed face image by adopting dynamic adaptive discrete cosine transform; 2, a multi-head self-attention mechanism and a multi-dimensional entropy state load mutual feedback mechanism are adopted to extract frequency domain high-dimensional load features; step 3, extracting spatial domain features based on the pre-trained deep residual network; 4, performing feature fusion on the frequency domain high-dimensional load features and the spatial domain features based on an attention mechanism; and 5, discriminating and classifying the fusion features by using a classifier comprising a full connection layer. According to the method, high-accuracy identification can be carried out on the compressed face image manufactured by adopting a deep counterfeiting means.

The invention discloses a fulvic acid fertilizer identification method, device, equipment, medium and product, and relates to the field of fulvic acid fertilizer identification, the method comprises: obtaining a to-be-detected solution, the to-be-detected solution comprising fulvic acid fertilizer solutions with different base sources and fulvic acid fertilizer solutions with different doping ratios; and performing three-dimensional fluorescence spectrum scanning on the extracting solution of the solution to be detected to obtain three-dimensional fluorescence spectrum matrix data. Preprocessing the three-dimensional fluorescence spectrum matrix data to obtain a data set, and dividing the data set into a training set and a verification set; and training a preset model based on the training set to obtain a trained prediction model. Acquiring a detection data set based on a to-be-identified fulvic acid fertilizer sample, inputting the detection data set into the prediction model, outputting a prediction result, and judging the base source and the doping proportion of the to-be-identified fulvic acid fertilizer sample according to the prediction result. The detection accuracy is improved.

The present invention belongs to the field of molecular biology technology, and specifically relates to a microsatellite primer set for identifying yellow sand softshell turtle varieties, comprising a first primer set and a second primer set, wherein the sequence of the first primer set comprises: an upper primer: CTGAAGTCTGGCACTAAGCTTTCC, a lower primer: GTCTAAATTCCGAAGCGGGTAAAA; the sequence of the second primer set comprises: an upper primer: TAGCCCCGAGATTATCAGAGACAG, a lower primer: TGTGGCTGGTTGGTGTAGTAAGAA, and application of the microsatellite primer set in identifying yellow sand softshell turtle varieties. The microsatellite primer set proposed by the present invention has high conservatism and high versatility, and can accurately and quickly identify yellow sand softshell turtle varieties, thereby effectively improving the accuracy of identifying yellow sand softshell turtle varieties.

The present invention provides a three-dimensional Raman enhanced membrane for rapid identification of bacteria and a method and system thereof, wherein the three-dimensional Raman enhanced membrane for rapid identification of bacteria comprises a polymer material layer; the polymer material layer is provided with a plurality of funnel-shaped through holes, and the polymer material layer and the surfaces of the plurality of funnel-shaped through holes are both provided with Raman enhanced material layers. The three-dimensional Raman enhanced membrane for rapid identification of bacteria described in the present invention has a plurality of funnel-shaped through holes added to the polymer material layer, and during the detection process, the contact area between the pathogenic bacteria and the through holes (i.e., the polymer material layer) is large, which can indirectly improve the sensitivity of the detection.

The invention provides a 20K liquid phase chip for simultaneously and accurately identifying various goose varieties and application, the 20K liquid phase chip covers 22005 SNP molecular markers, and the SNP molecular markers are specifically composed of a genetic differentiation index FSTgt, a genetic differentiation index FSTgt, a genetic differentiation index FSTgt, a genetic differentiation index FSTgt, a genetic differentiation index FSTgt, a genetic differentiation index FSTgt, a genetic differentiation index FSTgt The SNP molecular marker is composed of 4991 genetic differentiation specific sites, 12 important character associated sites and 17002 whole genome background sites of 22005 goose varieties, and the specific positions of the 22005 SNP molecular marker sites are shown in a table 1 in the specification. According to the method, 16 goose varieties can be accurately distinguished, the identification efficiency is high, the detection process can be completed within 24 hours, 48-96 samples can be detected at a time, and the technical repetition rate is gt; the cost of the chip is far lower than that of a high-density chip, and the chip is suitable for carrying out multi-variety and large-scale germplasm monitoring and identification work in a breed conservation field, a research and development unit and the like, and is high in practicability.

This invention discloses a combined SSR and SNP marker system for grass carp parentage identification and its application, belonging to the field of aquatic animal breeding technology. The marker system includes 11 pairs of highly polymorphic SSR primers and 2 pairs of specific SNP primers; the base sequences of the 11 pairs of highly polymorphic SSR primers are shown in SEQ ID NO:1-22; the base sequences of the 2 pairs of specific SNP primers are shown in SEQ ID NO:23-26; and a grass carp parentage identification kit and method are also provided. This invention combines the high polymorphism of SSR markers with the stability and ease of genotyping of SNP markers to form a grass carp parentage identification system that can be used for grass carp parentage identification and breeding, with high accuracy, economic efficiency, controllable cost, support for co-culture in the same pond, and improved accuracy of genetic assessment.

The present invention discloses a reagent composition for screening and / or diagnosing plasma cell tumors and its application. The reagent composition of the present invention comprises anti-CD19 antibody, anti-CD56 antibody, anti-CD138 antibody, anti-CD81 antibody, anti-CD38 antibody, anti-CD27 antibody, anti-CD45 antibody, KAPPA antibody and LAMBDA antibody. The reagent composition of the present invention can improve the ability to distinguish tumor plasma cells from normal plasma cells. In addition, the present invention also provides a gate setting method for flow cytometry analysis. Through the gate setting method of the present invention, the abnormal plasma cell ratio in CD56 or CD19 or CD117 or CD81 or CD27 of gate B and the expression ratio of KAPPA and LAMBDA can be combined to achieve accurate and rapid analysis of samples, and to achieve the determination and typing of plasma cell tumors, and effectively avoid false negative judgment results.

The invention discloses a substance identification device, a database calling method, equipment, a medium and a product, the substance identification device is provided with a detection module, a storage module and a data processing module, and the data processing module is configured to perform first similarity comparison on a protein fingerprint spectrum of a to-be-detected object and a standard protein fingerprint spectrum; obtaining a first matching set; verifying a second interference feature in the protein fingerprint spectrum of the to-be-detected object based on the first matching set; if the verification is passed, performing second similarity comparison on the protein fingerprint spectrum of the to-be-detected object and the standard protein fingerprint spectrum to obtain a second matching set; and determining an identification result of the to-be-detected object based on the first matching set and the second matching set. Similarity comparison is directly performed on the protein fingerprints of the to-be-detected object based on the predetermined related characteristics of the protein fingerprints, so that identification complexity is reduced while identification time consumption is shortened, and substance identification efficiency is improved.

An information processing method for generating an identification algorithm that identifies types of waste material includes a step of generating a first model that is an identification algorithm of types of waste material by machine learning first image data obtained by capturing images of inside of waste pits of a plurality of facilities in which waste material is accumulated and first training data in which respective pieces of the waste material in the images are labeled with types, and a step of generating a second model that is an identification algorithm that supports waste material of a second facility different from the plurality of facilities by additionally learning second image data obtained by capturing an image of inside of a waste pit of the second facility and second training data in which respective pieces of waste material in the image are labeled with types, with respect to the generated first model.

The invention belongs to the technical field of plant chemical component analysis, and discloses a multi-species polyphenol flavonoid compound high-throughput identification method which comprises the following steps: S1, constructing a cross-platform compatible MSP database; s2, sample pretreatment: carrying out ultrasonic extraction on a plant sample with 70% methanol, centrifuging, and filtering a supernatant with a filter membrane; wherein the plant sample comprises folium cortex eucommiae, rosemary, day lily, sea-buckthorn, herba houttuyniae or tea leaves; s3, carrying out liquid chromatography-mass spectrometry detection; s4, data matching and identification: using open source mass spectrum data processing software, setting the mass deviation to be less than or equal to 5ppm, the retention time deviation to be less than or equal to 0.3 min and the Dot product score to be more than or equal to 80%, and carrying out automatic identification; the technical problems that mass spectrum platform data is isolated, multi-species batch detection is difficult, the detection consistency is influenced by the matrix effect, and the compound identification efficiency is low are solved.

This invention provides a specific primer set for identifying the sex of Eucommia ulmoides and its identification method, relating to the field of plant molecular identification technology. The specific primer set includes primers INV53, INV54, INV55, and INV56. The upstream primer of primer INV53 is shown in SEQ ID NO.1, and the downstream primer is shown in SEQ ID NO.2; the upstream primer of primer INV54 is shown in SEQ ID NO.3, and the downstream primer is shown in SEQ ID NO.4; the upstream primer of primer INV55 is shown in SEQ ID NO.5, and the downstream primer is shown in SEQ ID NO.6; the upstream primer of primer INV56 is shown in SEQ ID NO.7, and the downstream primer is shown in SEQ ID NO.8. The specific primer set for identifying the sex of Eucommia ulmoides provided by this invention targets the Chr10a inverted region, achieving 100% identification accuracy. It features high specificity and accuracy, is adaptable to samples with different genetic backgrounds and cultivation environments, and solves the problems of low accuracy and poor stability in existing methods.

The present application relates to rubber tree seedling breeding field, specifically to a kind of in rubber tree seedling high-efficiency rapid selection high-yield single plant method, comprising the following steps: S1: 2 age rubber tree seedling is sawed, according to the amount of latex flowing out of horizontal sawing surface, preliminary selection is carried out, and preliminary selection seedling is selected;S2: preliminary selection seedling is continued to cultivate 24-48 hours, and on the basis of horizontal sawing surface, continue to cut off 0.2-0.4 cm, according to the amount of latex flowing out of horizontal sawing surface, reselecting is carried out, and reselected seedling is selected;S3: reselected seedling is continued to cultivate 24-48 hours, and on the basis of horizontal sawing surface, continue to cut off 0.2-0.4 cm, according to the amount of latex flowing out of horizontal sawing surface, approval selection is carried out, and approved seedling is obtained;S4: approved seedling is continued to cultivate 20-30 days, and latex is collected for detection, according to the sucrose content of obtained latex, final selection is carried out, and high-yield single plant is obtained.The present application method can be screened at 2-3 age in seedling stage, and the method steps are simple, low in cost, high in screening accuracy.

This invention discloses a molecular marker InDel05 related to soybean oil content, detection primers, and their applications. The molecular marker InDel05 is located at the physical location 41854660-41854682 on soybean chromosome 5, and its nucleotide sequence is shown in SEQ ID No. 1. Based on this, detection primers for the molecular marker InDel05 were designed. The length difference of the amplification products is detected by PCR amplification. Soybean materials without the inserted fragment in the PCR amplification product are high-oil-content soybeans, while those with the inserted fragment are low-oil-content soybeans, thus achieving the identification of soybean oil content phenotypes with an accuracy of up to 87.5%. The molecular marker InDel05 and detection primers provided by this invention can be used for rapid, accurate, and efficient screening of high-oil-content soybean germplasm, significantly improving the efficiency of marker-assisted selection breeding and accelerating the breeding process of high-oil-content soybean varieties.

This invention relates to the field of microbial technology, and particularly to a culture medium for inhibiting the formation of secondary metabolites in Bacillus and its application. This invention provides a culture medium for inhibiting the formation of secondary metabolites in Bacillus and a method for identifying Bacillus. Experiments have shown that the culture medium provided by this invention can significantly reduce the production of secondary metabolites in Bacillus. The cultured colonies can be accurately identified directly using a formic acid treatment method, which is simple and rapid. It significantly improves the quality of the identification mass spectrum, lowers the baseline, increases peak intensity, and improves the accuracy of identification.

The application discloses a contaminated soil hazard characteristic identification point layout method, an identification method and related devices, and the layout method comprises the following steps: acquiring the positions of all contaminated over-standard points in a region to be identified, the number of contaminated over-standard points, and the quality of contaminated soil; determining the minimum number of samples of the region to be identified based on the quality of the contaminated soil; and laying identification points based on the size relationship between the number of contaminated over-standard points and the minimum number of samples and the positions of the contaminated over-standard points. According to the number of contaminated over-standard points in the region to be identified and the minimum number of samples that meet the identification requirements, the identification points are laid around the positions of the contaminated over-standard points, on the positions of the contaminated over-standard points, or in the radiation areas of the positions of the contaminated over-standard points. Compared with the prior art, the point layout method in the application is more in line with the diffusion trend of soil pollution, and the identification accuracy can be improved as much as possible under the premise of laying the minimum number of identification points.

The invention belongs to the technical field of plant grafting, and particularly relates to an early identification method for healing degree and affinity of fruit tree grafted rootstocks and scions. The early identification method comprises the following steps: grafting a scion to a stock, culturing for 10-20 days, inserting the base part of the stock into a fast green staining solution for staining, and judging the healing degree and affinity according to the staining condition. Different rootstock and scion combinations after grafting are dyed by using the dyeing agent fast green, the transportation difference of the fast green in the grafted rootstock and scion combinations is analyzed, the rootstock and scion healing degree and affinity can be rapidly judged, and technical and theoretical supports are provided for rapid rootstock breeding, rootstock and scion combination screening and rootstock application.

This application relates to the technical field of coin authentication, and in particular to an automated method and system for coin authenticity authentication based on multispectral image fusion. The method determines the type information of the coin to be authenticated, and moves the coin to be authenticated to either a banknote authentication position or a coin authentication position based on the type information. For the banknote authentication position, multispectral image detection and microscopic feature detection are performed to generate authenticity information. For the banknote authentication position, creases and moisture spots are identified to generate condition information. For the coin authentication position, alloy composition and patina elements are detected to determine authenticity information. For the coin authentication position, data acquisition and model construction of the three-dimensional morphology are performed to obtain condition information.

This invention discloses a DNA barcode for identifying *Pyrrosia lingua* and *Echinopsis pilosula* and its application, belonging to the field of plant gene molecular marker technology. The nucleotide sequence of the DNA barcode is shown in SEQ ID NO.1; polymorphisms are present at bases 77, 82-86, 95, 110, 456-458, 460, 480, 565, and 596 of the sequence shown in SEQ ID NO.1. The DNA barcode for identifying *Pyrrosia lingua* and *Echinopsis pilosula* provided by this invention contains a combination of specific variant sites located in the ITS1 region, forming a species-diagnostic site matrix. These sites possess stable species specificity, and by detecting the nucleotide sequence of the ITS1 region of the sample, *Pyrrosia lingua* and *Echinopsis pilosula* can be rapidly identified.

The application discloses a kind of access control management system, method and storage medium of transport vehicle, the system includes: first monitoring module, second monitoring module, card reading module, control module, access control module, wherein: first monitoring module is used to collect the first image dataset of target transport vehicle;Second monitoring module is used to collect first license plate image dataset;Card reading module is used to read vehicle tag dataset;Control module is used to determine target vehicle identification data according to first image dataset, first license plate image dataset and vehicle tag dataset;Obtain the target transport order data corresponding to target transport vehicle;According to target vehicle identification data and target transport order data determine target access control instruction;Access control module is used to execute corresponding access control action according to target access control instruction, to realize the access control management of transport vehicle.Adopt the application, improve the control precision of access control management system.